mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-11-20 19:33:41 +01:00
Compare commits
86
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
c7287f8f54 | ||
|
|
e00698a327 | ||
|
|
63a575f28f | ||
|
|
ed67f9930c | ||
|
|
dd4d06e40f | ||
|
|
64d5fb5613 | ||
|
|
e15aa250e9 | ||
|
|
c908497d56 | ||
|
|
9bc1a50b37 | ||
|
|
dc2d13a1ee | ||
|
|
af35fb158c | ||
|
|
080af98b86 | ||
|
|
4c92a00357 | ||
|
|
1d7125abf2 | ||
|
|
6018f87c25 | ||
|
|
4bbc03747f | ||
|
|
e109f91c6f | ||
|
|
817338c911 | ||
|
|
0a1e337302 | ||
|
|
374c77bcbe | ||
|
|
2382f07788 | ||
|
|
a91def90c0 | ||
|
|
2ac8db5cb4 | ||
|
|
ac7d949c61 | ||
|
|
8df716b728 | ||
|
|
2e4be5e25e | ||
|
|
f2acfb7be4 | ||
|
|
b5f23b7dbf | ||
|
|
261c534c19 | ||
|
|
5e003bae7d | ||
|
|
4ac3633f1c | ||
|
|
4a5dbe4c6f | ||
|
|
ba1bfa816c | ||
|
|
be8ebc2e04 | ||
|
|
bfbeed61a7 | ||
|
|
05427e8108 | ||
|
|
f7323f2b63 | ||
|
|
f5e091cf91 | ||
|
|
c9f3a02b94 | ||
|
|
6bdcd17ed4 | ||
|
|
729b872f01 | ||
|
|
972f85159e | ||
|
|
ed7324611c | ||
|
|
05a1463855 | ||
|
|
c1c95e127f | ||
|
|
668ca45029 | ||
|
|
dcbea0626f | ||
|
|
de4075660f | ||
|
|
652133a28a | ||
|
|
e012fca9a2 | ||
|
|
3159b8408c | ||
|
|
f88751c3ff | ||
|
|
2089abecf3 | ||
|
|
6d0a6e0935 | ||
|
|
9b94f00325 | ||
|
|
d2a0002869 | ||
|
|
c01e87689e | ||
|
|
7b4bdb77bb | ||
|
|
1fd5008d63 | ||
|
|
646549eee1 | ||
|
|
9cd183b04f | ||
|
|
23eef59417 | ||
|
|
04c7b12238 | ||
|
|
f5418845ce | ||
|
|
53bc62c773 | ||
|
|
1f5cfc7552 | ||
|
|
b1c315b837 | ||
|
|
aceb089bc8 | ||
|
|
c7d8b106d5 | ||
|
|
a3b2fd722d | ||
|
|
9f413ff2c8 | ||
|
|
e037a9c1ce | ||
|
|
3db54ee7e5 | ||
|
|
94de65b3b5 | ||
|
|
ebc77400ca | ||
|
|
ecbf7af1ca | ||
|
|
b64895ed0a | ||
|
|
72ac9e96b2 | ||
|
|
11af0e0c12 | ||
|
|
de5b3305a7 | ||
|
|
04e135c21e | ||
|
|
862913d199 | ||
|
|
8c6d09f498 | ||
|
|
eb1dca8088 | ||
|
|
deacd575ea | ||
|
|
194e6ede9f |
No files matched your search
@@ -259,6 +259,40 @@ jobs:
|
||||
grep -q "security-config" /tmp/security.yaml
|
||||
echo "Security configuration renders correctly"
|
||||
|
||||
echo "=== Testing volume server HTTPS ==="
|
||||
awk '/^ *\[https.client\]$/{f=1;next} /^ *\[/{f=0} f' /tmp/security.yaml | grep -q 'enabled = false'
|
||||
helm template test $CHART_DIR \
|
||||
--set global.seaweedfs.enableSecurity=true \
|
||||
--set global.seaweedfs.volumeHttps.enabled=true \
|
||||
--set volumes.hot.replicas=1 \
|
||||
> /tmp/volume-https.yaml
|
||||
awk '/^ *\[https.client\]$/{f=1;next} /^ *\[/{f=0} f' /tmp/volume-https.yaml > /tmp/volume-https-client.txt
|
||||
grep -q 'enabled = true' /tmp/volume-https-client.txt
|
||||
grep -q 'cert = "/usr/local/share/ca-certificates/client/tls.crt"' /tmp/volume-https-client.txt
|
||||
grep -q 'ca = "/usr/local/share/ca-certificates/ca/tls.crt"' /tmp/volume-https-client.txt
|
||||
awk '/^ *\[https.volume\]$/{f=1;next} /^ *\[/{f=0} f' /tmp/volume-https.yaml \
|
||||
| grep -q 'cert = "/usr/local/share/ca-certificates/volume/tls.crt"'
|
||||
grep -q "'\*.test-seaweedfs-volume.default'" /tmp/volume-https.yaml
|
||||
grep -q "'\*.test-seaweedfs-volume-hot.default'" /tmp/volume-https.yaml
|
||||
test "$(grep -c 'scheme: HTTPS' /tmp/volume-https.yaml)" -eq 4
|
||||
test "$(grep -c 'checksum/volume-https:' /tmp/volume-https.yaml)" -eq 4
|
||||
if grep -q 'checksum/volume-https' /tmp/security.yaml; then
|
||||
echo "FAIL: the volume HTTPS rollout annotation should only render while the option is on"
|
||||
exit 1
|
||||
fi
|
||||
if helm template test $CHART_DIR --set global.seaweedfs.volumeHttps.enabled=true > /dev/null 2>/tmp/volume-https-nosec.err; then
|
||||
echo "FAIL: volumeHttps without enableSecurity should fail to render"
|
||||
exit 1
|
||||
fi
|
||||
grep -q "requires global.seaweedfs.enableSecurity" /tmp/volume-https-nosec.err
|
||||
if helm template test $CHART_DIR --set global.seaweedfs.enableSecurity=true \
|
||||
--set global.seaweedfs.volumeHttps.enabled=true --set allInOne.enabled=true > /dev/null 2>/tmp/volume-https-aio.err; then
|
||||
echo "FAIL: volumeHttps with allInOne should fail to render"
|
||||
exit 1
|
||||
fi
|
||||
grep -q "not supported with allInOne" /tmp/volume-https-aio.err
|
||||
echo "Volume server HTTPS renders [https.volume], [https.client], certificate names, HTTPS probes and rollout annotations"
|
||||
|
||||
echo "=== Testing secure bucket-creation hook certificate mounts ==="
|
||||
helm template test $CHART_DIR \
|
||||
--show-only templates/shared/post-install-bucket-hook.yaml \
|
||||
|
||||
@@ -0,0 +1,74 @@
|
||||
name: "S3 listing study tests"
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [ master ]
|
||||
paths:
|
||||
- 'weed/s3api/**'
|
||||
- 'weed/filer/**'
|
||||
- 'weed/server/**'
|
||||
- 'test/s3/listing_study/**'
|
||||
- '.github/workflows/s3-listing-study-tests.yml'
|
||||
pull_request:
|
||||
branches: [ master ]
|
||||
paths:
|
||||
- 'weed/s3api/**'
|
||||
- 'weed/filer/**'
|
||||
- 'weed/server/**'
|
||||
- 'test/s3/listing_study/**'
|
||||
- '.github/workflows/s3-listing-study-tests.yml'
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.event.pull_request.number || github.ref }}/s3-listing-study-tests
|
||||
cancel-in-progress: true
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
listing-study:
|
||||
name: s3-listing-study tools and strategies
|
||||
runs-on: ubuntu-24.04
|
||||
timeout-minutes: 40
|
||||
defaults:
|
||||
run:
|
||||
working-directory: test/s3/listing_study
|
||||
steps:
|
||||
- name: Check out code
|
||||
uses: actions/checkout@v7
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Set up Go
|
||||
uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version-file: 'go.mod'
|
||||
cache: ${{ runner.environment == 'github-hosted' }}
|
||||
|
||||
- name: Cache pinned listing tools
|
||||
uses: actions/cache@v6
|
||||
with:
|
||||
path: test/s3/listing_study/.work/tools
|
||||
key: listing-study-tools-${{ runner.os }}-${{ hashFiles('test/s3/listing_study/Makefile', 'test/s3/listing_study/install_tools.py') }}
|
||||
|
||||
- name: Build weed and install the study's pinned tools
|
||||
run: make build-weed tools
|
||||
|
||||
- name: Run the listing study against SeaweedFS
|
||||
timeout-minutes: 15
|
||||
run: make test
|
||||
|
||||
- name: Show logs on failure
|
||||
if: failure()
|
||||
run: |
|
||||
tail -200 .work/weed.log || true
|
||||
|
||||
- name: Upload results
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v7
|
||||
with:
|
||||
name: s3-listing-study-results
|
||||
path: |
|
||||
test/s3/listing_study/.work/run/results.json
|
||||
test/s3/listing_study/.work/weed.log
|
||||
retention-days: 14
|
||||
@@ -68,7 +68,15 @@ jobs:
|
||||
with:
|
||||
java-version: '17'
|
||||
distribution: 'temurin'
|
||||
cache: ${{ runner.environment == 'github-hosted' && 'maven' || '' }}
|
||||
|
||||
- name: Cache suite Maven dependencies
|
||||
if: runner.environment == 'github-hosted'
|
||||
uses: actions/cache@v6
|
||||
with:
|
||||
path: ~/.m2/repository
|
||||
key: snowflake-s3compat-m2-${{ hashFiles('test/s3/snowflake/run.sh') }}
|
||||
restore-keys: |
|
||||
snowflake-s3compat-m2-
|
||||
|
||||
- name: Install SeaweedFS
|
||||
run: |
|
||||
@@ -78,6 +86,8 @@ jobs:
|
||||
|
||||
- name: Run Snowflake S3Compat API tests
|
||||
timeout-minutes: 20
|
||||
env:
|
||||
MAVEN_ARGS: -ntp -s ${{ github.workspace }}/test/s3/snowflake/maven-settings.xml
|
||||
run: |
|
||||
# Starts weed server, creates the buckets/objects the suite needs,
|
||||
# clones the upstream suite, and runs mvn -Dtest=S3CompatApiTest.
|
||||
|
||||
@@ -684,6 +684,12 @@ jobs:
|
||||
pull() { for i in 1 2 3; do docker pull "$1" && return 0; sleep 15; done; return 1; }
|
||||
pull apache/spark:3.5.1
|
||||
|
||||
- name: Cache Iceberg jars
|
||||
uses: actions/cache@v6
|
||||
with:
|
||||
path: ~/.cache/seaweedfs-test-jars
|
||||
key: iceberg-jars-${{ hashFiles('test/s3tables/catalog_spark/setup_test.go') }}
|
||||
|
||||
- name: Run go mod tidy
|
||||
run: go mod tidy
|
||||
|
||||
|
||||
@@ -0,0 +1,57 @@
|
||||
name: "S3 Tigris Compatibility Tests"
|
||||
|
||||
on:
|
||||
push:
|
||||
branches: [ master ]
|
||||
paths:
|
||||
- 'weed/s3api/**'
|
||||
- 'weed/server/filer_server_handlers_*.go'
|
||||
- 'test/s3/tigris_compat/**'
|
||||
- '.github/workflows/s3-tigris-compat-tests.yml'
|
||||
pull_request:
|
||||
branches: [ master ]
|
||||
paths:
|
||||
- 'weed/s3api/**'
|
||||
- 'weed/server/filer_server_handlers_*.go'
|
||||
- 'test/s3/tigris_compat/**'
|
||||
- '.github/workflows/s3-tigris-compat-tests.yml'
|
||||
|
||||
concurrency:
|
||||
group: ${{ github.workflow }}-${{ github.event.pull_request.number || (github.event_name == 'push' && github.ref) || github.run_id }}
|
||||
cancel-in-progress: ${{ github.event_name == 'pull_request' || (github.event_name == 'push' && !startsWith(github.ref, 'refs/tags/')) }}
|
||||
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
jobs:
|
||||
s3-tigris-compat-tests:
|
||||
name: s3-api-compat-tests (Tigris)
|
||||
runs-on: ubuntu-24.04
|
||||
timeout-minutes: 20
|
||||
steps:
|
||||
- name: Check out code
|
||||
uses: actions/checkout@v7
|
||||
|
||||
- name: Set up Go
|
||||
uses: actions/setup-go@v7
|
||||
with:
|
||||
go-version-file: 'go.mod'
|
||||
cache: ${{ runner.environment == 'github-hosted' }}
|
||||
|
||||
- name: Run s3-api-compat-tests
|
||||
working-directory: test/s3/tigris_compat
|
||||
run: make test
|
||||
|
||||
- name: Show server log on failure
|
||||
if: failure()
|
||||
working-directory: test/s3/tigris_compat
|
||||
run: tail -200 weed-test.log || true
|
||||
|
||||
- name: Upload report
|
||||
if: always()
|
||||
uses: actions/upload-artifact@v7
|
||||
with:
|
||||
name: s3-tigris-compat-results
|
||||
path: test/s3/tigris_compat/results.json
|
||||
if-no-files-found: ignore
|
||||
retention-days: 7
|
||||
@@ -6,12 +6,16 @@ on:
|
||||
paths:
|
||||
- 'telemetry/**'
|
||||
- 'weed/telemetry/**'
|
||||
- 'go.mod'
|
||||
- 'go.sum'
|
||||
- '.github/workflows/telemetry-integration.yml'
|
||||
pull_request:
|
||||
branches: [ master ]
|
||||
paths:
|
||||
- 'telemetry/**'
|
||||
- 'weed/telemetry/**'
|
||||
- 'go.mod'
|
||||
- 'go.sum'
|
||||
- '.github/workflows/telemetry-integration.yml'
|
||||
|
||||
concurrency:
|
||||
|
||||
@@ -569,6 +569,8 @@ s3:
|
||||
|
||||
With `rules` left empty the route sends all traffic to the component's own Service and port. A rule may set `matches`, `filters`, `timeouts` and `backendRefs`, and a rule without `backendRefs` still routes to that Service. In all-in-one mode the master, volume, filer and s3 routes target the all-in-one Service. When S3 runs only on the filer (`filer.s3.enabled` without `s3.enabled`), the s3 route uses `filer.s3.port`.
|
||||
|
||||
Outside all-in-one mode, the volume Ingress and the default volume route target the `client-volume` Service, which lists only Ready volume pods. The `volume` Service also publishes pods that are not Ready yet, so their DNS records can exist before readiness. An explicit `backendRefs` entry that names the `volume` Service can therefore reach a volume server before it is Ready. Name the `client-volume` Service instead, with `volume.port`, and copy its `metadata.name` from `helm template` because long release names are truncated.
|
||||
|
||||
## Network Policies
|
||||
|
||||
In a namespace with a default-deny policy the install hangs: the components cannot resolve each other, and the post-install bucket hook waits on the master and filer until it gives up. `networkPolicy.enabled` renders one `NetworkPolicy` per component, selecting its pods by the standard `app.kubernetes.io/{name,instance,component}` labels and admitting traffic from the other pods of the release on the ports that component listens on.
|
||||
@@ -610,6 +612,17 @@ Two things worth knowing before you turn this on:
|
||||
|
||||
The DNS selectors default to CoreDNS as kubeadm, kind and the managed offerings from AWS, Google and Azure install it. On OpenShift, override `egress.dnsNamespaceSelector` and `egress.dnsPodSelector` to match `openshift-dns`; see the comment in `values.yaml`.
|
||||
|
||||
## Volume server HTTPS
|
||||
|
||||
With `global.seaweedfs.enableSecurity`, gRPC between components uses mutual TLS, but the volume servers' HTTP port, which carries the file data, stays plaintext. Set `global.seaweedfs.volumeHttps.enabled: true` to serve it over TLS:
|
||||
|
||||
- `[https.volume]` points at the volume certificate, which then also names every volume group's service (`*.<fullname>-volume.<namespace>`), since volume servers register as `<pod>.<fullname>-volume.<namespace>`. With `certificates.externalCertificates`, the provided `<fullname>-volume-cert` needs those names.
|
||||
- `[https.client]` is enabled with the client certificate and the chart CA, so every chart pod that talks to the volume servers does it over HTTPS.
|
||||
- The volume probes use HTTPS.
|
||||
- Every pod that reads `security.toml` gets a `checksum/volume-https` annotation, so switching the option on or off restarts them together.
|
||||
|
||||
The volume servers do not require client certificates, because kubelet probes cannot present one; enable JWT signing (`securityConfig.jwtSigning`) to authorize volume reads and writes. `[https.client]` also sends the admin UI's HTTP lookups on masters and S3 over HTTPS, which their plain listeners refuse, so the UI can miss volume public URLs and refuse SSE-S3 vector buckets. A volume Ingress or HTTPRoute needs its controller's HTTPS-backend setting. `weed mount`, the CSI driver and other clients outside the chart need their own `[https.client]` with the chart CA. The option is not supported with `allInOne`, whose volume server registers by pod IP.
|
||||
|
||||
## Common labels
|
||||
|
||||
`commonLabels` adds labels to the metadata of every object the chart creates. It may be a map or a template string rendering to one. The chart's own labels cannot be overridden, and pods (see `podLabels`) and `volumeClaimTemplates` are left unchanged.
|
||||
|
||||
@@ -56,6 +56,7 @@ spec:
|
||||
{{- with .Values.admin.podAnnotations }}
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with include "seaweedfs.volumeHttpsAnnotation" $ }}{{ . | nindent 8 }}{{ end }}
|
||||
spec:
|
||||
restartPolicy: {{ default .Values.global.seaweedfs.restartPolicy .Values.admin.restartPolicy }}
|
||||
{{- if .Values.admin.affinity }}
|
||||
|
||||
@@ -1,5 +1,8 @@
|
||||
{{- include "seaweedfs.compat" . -}}
|
||||
{{- if .Values.allInOne.enabled }}
|
||||
{{- if include "seaweedfs.volumeHttps" . }}
|
||||
{{- fail "global.seaweedfs.volumeHttps is not supported with allInOne: its volume server registers by pod IP, which the volume certificate cannot name" }}
|
||||
{{- end }}
|
||||
{{- $s3PreStopSeconds := 0 }}
|
||||
{{- if .Values.allInOne.s3.enabled }}
|
||||
{{- $s3PreStopSeconds = .Values.allInOne.s3.preStopSeconds }}
|
||||
|
||||
@@ -38,6 +38,14 @@ spec:
|
||||
- '*.{{ include "seaweedfs.fullname" . }}-master.{{ include "seaweedfs.namespace" . }}'
|
||||
- '*.{{ include "seaweedfs.fullname" . }}-master.{{ include "seaweedfs.namespace" . }}.svc'
|
||||
- '*.{{ include "seaweedfs.fullname" . }}-master.{{ include "seaweedfs.namespace" . }}.svc.cluster.local'
|
||||
{{- if include "seaweedfs.volumeHttps" . }}
|
||||
{{- range $vname, $_ := deepCopy .Values.volumes | mergeOverwrite (dict "" .Values.volume) }}
|
||||
{{- $volumeService := printf "%s.%s" (include "seaweedfs.componentName" (list $ (trimSuffix "-" (printf "volume-%s" $vname)))) (include "seaweedfs.namespace" $) }}
|
||||
- '*.{{ $volumeService }}'
|
||||
- '*.{{ $volumeService }}.svc'
|
||||
- '*.{{ $volumeService }}.svc.cluster.local'
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- if .Values.certificates.ipAddresses }}
|
||||
ipAddresses:
|
||||
{{- range .Values.certificates.ipAddresses }}
|
||||
|
||||
@@ -39,6 +39,7 @@ spec:
|
||||
{{- with .Values.cosi.podAnnotations }}
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with include "seaweedfs.volumeHttpsAnnotation" $ }}{{ . | nindent 8 }}{{ end }}
|
||||
spec:
|
||||
restartPolicy: {{ default .Values.global.seaweedfs.restartPolicy .Values.cosi.restartPolicy }}
|
||||
{{- if .Values.cosi.affinity }}
|
||||
|
||||
@@ -57,6 +57,7 @@ spec:
|
||||
{{- end }}
|
||||
annotations:
|
||||
{{- toYaml $podAnnotations | nindent 8 }}
|
||||
{{- with include "seaweedfs.volumeHttpsAnnotation" $ }}{{ . | nindent 8 }}{{ end }}
|
||||
spec:
|
||||
restartPolicy: {{ default .Values.global.seaweedfs.restartPolicy .Values.filer.restartPolicy }}
|
||||
{{- if .Values.filer.affinity }}
|
||||
|
||||
@@ -48,6 +48,7 @@ spec:
|
||||
{{- $_ := set $podAnnotations "checksum/master-config" (include "seaweedfs.master.configChecksum" .) }}
|
||||
annotations:
|
||||
{{- toYaml $podAnnotations | nindent 8 }}
|
||||
{{- with include "seaweedfs.volumeHttpsAnnotation" $ }}{{ . | nindent 8 }}{{ end }}
|
||||
spec:
|
||||
restartPolicy: {{ default .Values.global.seaweedfs.restartPolicy .Values.master.restartPolicy }}
|
||||
{{- if .Values.master.affinity }}
|
||||
|
||||
@@ -54,6 +54,7 @@ spec:
|
||||
{{- end }}
|
||||
annotations:
|
||||
{{- toYaml $podAnnotations | nindent 8 }}
|
||||
{{- with include "seaweedfs.volumeHttpsAnnotation" $ }}{{ . | nindent 8 }}{{ end }}
|
||||
spec:
|
||||
restartPolicy: {{ default .Values.global.seaweedfs.restartPolicy .Values.s3.restartPolicy }}
|
||||
{{- if .Values.s3.affinity }}
|
||||
|
||||
@@ -43,6 +43,7 @@ spec:
|
||||
{{- with .Values.sftp.podAnnotations }}
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with include "seaweedfs.volumeHttpsAnnotation" $ }}{{ . | nindent 8 }}{{ end }}
|
||||
spec:
|
||||
restartPolicy: {{ default .Values.global.seaweedfs.restartPolicy .Values.sftp.restartPolicy }}
|
||||
{{- if .Values.sftp.affinity }}
|
||||
|
||||
@@ -491,6 +491,25 @@ true
|
||||
{{- end -}}
|
||||
{{- end -}}
|
||||
|
||||
{{/* True when the volume servers serve HTTPS. Their certificates come from
|
||||
enableSecurity, so the option fails without it. */}}
|
||||
{{- define "seaweedfs.volumeHttps" -}}
|
||||
{{- if ((.Values.global.seaweedfs).volumeHttps).enabled -}}
|
||||
{{- if not .Values.global.seaweedfs.enableSecurity -}}
|
||||
{{- fail "global.seaweedfs.volumeHttps.enabled requires global.seaweedfs.enableSecurity, which provides the certificates" -}}
|
||||
{{- end -}}
|
||||
true
|
||||
{{- end -}}
|
||||
{{- end -}}
|
||||
|
||||
{{/* Pod annotation that restarts the readers of security.toml when volume
|
||||
HTTPS is switched on or off. */}}
|
||||
{{- define "seaweedfs.volumeHttpsAnnotation" -}}
|
||||
{{- with include "seaweedfs.volumeHttps" . -}}
|
||||
checksum/volume-https: {{ sha256sum . | quote }}
|
||||
{{- end -}}
|
||||
{{- end -}}
|
||||
|
||||
{{/* Read a JWT key from the chart's existing security.toml without fromToml
|
||||
(which requires Helm >=3.17). Args: (list "<section>" $raw).
|
||||
Return the single-line TOML string token, including its quotes, so escapes
|
||||
|
||||
@@ -121,13 +121,25 @@ data:
|
||||
cert = "/usr/local/share/ca-certificates/client/tls.crt"
|
||||
key = "/usr/local/share/ca-certificates/client/tls.key"
|
||||
|
||||
# volume server https options
|
||||
# Note: work in progress!
|
||||
# this does not work with other clients, e.g., "weed filer|mount" etc, yet.
|
||||
{{- if include "seaweedfs.volumeHttps" . }}
|
||||
|
||||
[https.client]
|
||||
enabled = true
|
||||
cert = "/usr/local/share/ca-certificates/client/tls.crt"
|
||||
key = "/usr/local/share/ca-certificates/client/tls.key"
|
||||
ca = "/usr/local/share/ca-certificates/ca/tls.crt"
|
||||
|
||||
[https.volume]
|
||||
cert = "/usr/local/share/ca-certificates/volume/tls.crt"
|
||||
key = "/usr/local/share/ca-certificates/volume/tls.key"
|
||||
{{- else }}
|
||||
|
||||
# volume server https: set global.seaweedfs.volumeHttps.enabled
|
||||
[https.client]
|
||||
enabled = false
|
||||
[https.volume]
|
||||
cert = ""
|
||||
key = ""
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
@@ -25,6 +25,7 @@ spec:
|
||||
annotations:
|
||||
{{- with .Values.podAnnotations }}{{ toYaml . | nindent 8 }}{{ end }}
|
||||
{{- with .Values.vector.podAnnotations }}{{ toYaml . | nindent 8 }}{{ end }}
|
||||
{{- with include "seaweedfs.volumeHttpsAnnotation" $ }}{{ . | nindent 8 }}{{ end }}
|
||||
spec:
|
||||
{{- include "seaweedfs.imagePullSecrets" . | nindent 6 }}
|
||||
automountServiceAccountToken: {{ .Values.global.seaweedfs.automountServiceAccountToken }}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{{- $volumeEnabled := or .Values.volume.enabled .Values.allInOne.enabled }}
|
||||
{{- if and $volumeEnabled .Values.volume.httpRoute.enabled }}
|
||||
{{- $serviceName := ternary (include "seaweedfs.componentName" (list . "all-in-one")) (include "seaweedfs.componentName" (list . "volume")) .Values.allInOne.enabled }}
|
||||
{{- $serviceName := ternary (include "seaweedfs.componentName" (list . "all-in-one")) (include "seaweedfs.componentName" (list . "client-volume")) .Values.allInOne.enabled }}
|
||||
apiVersion: gateway.networking.k8s.io/v1
|
||||
kind: HTTPRoute
|
||||
metadata:
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
{{- $volumeEnabled := or .Values.volume.enabled .Values.allInOne.enabled }}
|
||||
{{- if and $volumeEnabled .Values.volume.ingress.enabled }}
|
||||
{{- /* Determine service name based on deployment mode */}}
|
||||
{{- $serviceName := ternary (include "seaweedfs.componentName" (list . "all-in-one")) (include "seaweedfs.componentName" (list . "volume")) .Values.allInOne.enabled }}
|
||||
{{- $serviceName := ternary (include "seaweedfs.componentName" (list . "all-in-one")) (include "seaweedfs.componentName" (list . "client-volume")) .Values.allInOne.enabled }}
|
||||
{{- if semverCompare ">=1.19-0" .Capabilities.KubeVersion.GitVersion }}
|
||||
apiVersion: networking.k8s.io/v1
|
||||
{{- else if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion }}
|
||||
|
||||
@@ -0,0 +1,42 @@
|
||||
{{- /* Ready-only backend for the volume ingress and HTTPRoute; the volume Service publishes not-ready pods for DNS.
|
||||
Not named volume-client: every volume-<key> name belongs to a group under .Values.volumes. */}}
|
||||
{{- if and .Values.volume.enabled (not .Values.allInOne.enabled) (or .Values.volume.ingress.enabled .Values.volume.httpRoute.enabled) }}
|
||||
{{- $name := include "seaweedfs.componentName" (list . "client-volume") }}
|
||||
{{- $volumes := deepCopy .Values.volumes | mergeOverwrite (dict "" .Values.volume) }}
|
||||
{{- range $vname, $volume := $volumes }}
|
||||
{{- $volumeName := trimSuffix "-" (printf "volume-%s" $vname) }}
|
||||
{{- $volume := mergeOverwrite (deepCopy $.Values.volume) (dict "enabled" true) $volume }}
|
||||
{{- if and $volume.enabled (eq (include "seaweedfs.componentName" (list $ $volumeName)) $name) }}
|
||||
{{- fail (printf "The volume Ingress/HTTPRoute Service %q has the same name as the %s Service after truncation. Shorten fullnameOverride or the release name." $name $volumeName) }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: {{ $name }}
|
||||
namespace: {{ include "seaweedfs.namespace" . | quote }}
|
||||
labels:
|
||||
app.kubernetes.io/name: {{ template "seaweedfs.name" . }}
|
||||
app.kubernetes.io/instance: {{ .Release.Name }}
|
||||
app.kubernetes.io/component: volume
|
||||
helm.sh/chart: {{ .Chart.Name }}-{{ .Chart.Version | replace "+" "_" }}
|
||||
app.kubernetes.io/managed-by: {{ .Release.Service }}
|
||||
{{- with include "seaweedfs.commonLabels" $ }}{{ . | nindent 4 }}{{ end }}
|
||||
{{- if .Values.volume.annotations }}
|
||||
annotations:
|
||||
{{- toYaml .Values.volume.annotations | nindent 4 }}
|
||||
{{- end }}
|
||||
spec:
|
||||
clusterIP: None
|
||||
internalTrafficPolicy: {{ .Values.volume.internalTrafficPolicy | default "Cluster" }}
|
||||
{{- /* No metrics port, so the volume ServiceMonitor does not scrape each pod twice */}}
|
||||
ports:
|
||||
- name: "swfs-volume"
|
||||
port: {{ .Values.volume.port }}
|
||||
targetPort: {{ .Values.volume.port }}
|
||||
protocol: TCP
|
||||
selector:
|
||||
app.kubernetes.io/name: {{ template "seaweedfs.name" . }}
|
||||
app.kubernetes.io/instance: {{ .Release.Name }}
|
||||
app.kubernetes.io/component: volume
|
||||
{{- end }}
|
||||
@@ -23,6 +23,9 @@ metadata:
|
||||
{{- end }}
|
||||
spec:
|
||||
clusterIP: None
|
||||
{{- /* The master hands out ${POD_NAME}.<this service> as soon as a volume server heartbeats, before it is Ready.
|
||||
Ingress and HTTPRoute use the client-volume Service instead, which publishes only Ready pods. */}}
|
||||
publishNotReadyAddresses: true
|
||||
internalTrafficPolicy: {{ $volume.internalTrafficPolicy | default "Cluster" }}
|
||||
ports:
|
||||
- name: "swfs-volume"
|
||||
|
||||
@@ -55,6 +55,7 @@ spec:
|
||||
{{- with $volume.podAnnotations }}
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with include "seaweedfs.volumeHttpsAnnotation" $ }}{{ . | nindent 8 }}{{ end }}
|
||||
spec:
|
||||
{{- if $volume.affinity }}
|
||||
affinity:
|
||||
@@ -281,7 +282,7 @@ spec:
|
||||
httpGet:
|
||||
path: {{ $volume.readinessProbe.httpGet.path }}
|
||||
port: {{ $volume.port }}
|
||||
scheme: {{ $volume.readinessProbe.httpGet.scheme }}
|
||||
scheme: {{ if include "seaweedfs.volumeHttps" $ }}HTTPS{{ else }}{{ $volume.readinessProbe.httpGet.scheme }}{{ end }}
|
||||
initialDelaySeconds: {{ $volume.readinessProbe.initialDelaySeconds }}
|
||||
periodSeconds: {{ $volume.readinessProbe.periodSeconds }}
|
||||
successThreshold: {{ $volume.readinessProbe.successThreshold }}
|
||||
@@ -293,7 +294,7 @@ spec:
|
||||
httpGet:
|
||||
path: {{ $volume.livenessProbe.httpGet.path }}
|
||||
port: {{ $volume.port }}
|
||||
scheme: {{ $volume.livenessProbe.httpGet.scheme }}
|
||||
scheme: {{ if include "seaweedfs.volumeHttps" $ }}HTTPS{{ else }}{{ $volume.livenessProbe.httpGet.scheme }}{{ end }}
|
||||
initialDelaySeconds: {{ $volume.livenessProbe.initialDelaySeconds }}
|
||||
periodSeconds: {{ $volume.livenessProbe.periodSeconds }}
|
||||
successThreshold: {{ $volume.livenessProbe.successThreshold }}
|
||||
|
||||
@@ -46,6 +46,7 @@ spec:
|
||||
{{- with .Values.worker.podAnnotations }}
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with include "seaweedfs.volumeHttpsAnnotation" $ }}{{ . | nindent 8 }}{{ end }}
|
||||
spec:
|
||||
restartPolicy: {{ default .Values.global.seaweedfs.restartPolicy .Values.worker.restartPolicy }}
|
||||
{{- if .Values.worker.affinity }}
|
||||
|
||||
@@ -0,0 +1,107 @@
|
||||
package tests
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"os/exec"
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func findDocument(documents []map[string]interface{}, kind, name string) map[string]interface{} {
|
||||
for _, document := range documents {
|
||||
if document["kind"] == kind && document["metadata"].(map[string]interface{})["name"] == name {
|
||||
return document
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func TestVolumeServicePublishesNotReadyPods(t *testing.T) {
|
||||
_, documents := render(t)
|
||||
service := findDocument(documents, "Service", "vector-test-seaweedfs-volume")
|
||||
if service == nil {
|
||||
t.Fatal("no volume service")
|
||||
}
|
||||
if service["spec"].(map[string]interface{})["publishNotReadyAddresses"] != true {
|
||||
t.Fatal("volume pod DNS names must resolve before the pods are Ready")
|
||||
}
|
||||
if findDocument(documents, "Service", "vector-test-seaweedfs-client-volume") != nil {
|
||||
t.Fatal("client-volume service rendered without ingress or httpRoute")
|
||||
}
|
||||
}
|
||||
|
||||
func TestVolumeIngressUsesReadyOnlyService(t *testing.T) {
|
||||
_, documents := render(t, "volume.ingress.enabled=true", "volume.httpRoute.enabled=true", "volume.metricsPort=9327")
|
||||
client := findDocument(documents, "Service", "vector-test-seaweedfs-client-volume")
|
||||
if client == nil {
|
||||
t.Fatal("no client-volume service")
|
||||
}
|
||||
spec := client["spec"].(map[string]interface{})
|
||||
if _, found := spec["publishNotReadyAddresses"]; found {
|
||||
t.Fatal("client-volume must publish only Ready pods")
|
||||
}
|
||||
for _, port := range spec["ports"].([]interface{}) {
|
||||
if port.(map[string]interface{})["name"] == "metrics" {
|
||||
t.Fatal("client-volume must not expose metrics, or the ServiceMonitor scrapes each pod twice")
|
||||
}
|
||||
}
|
||||
|
||||
ingress := findDocument(documents, "Ingress", "ingress-vector-test-seaweedfs-volume")
|
||||
if ingress == nil {
|
||||
t.Fatal("no volume ingress")
|
||||
}
|
||||
path := ingress["spec"].(map[string]interface{})["rules"].([]interface{})[0].(map[string]interface{})["http"].(map[string]interface{})["paths"].([]interface{})[0].(map[string]interface{})
|
||||
if backend := path["backend"].(map[string]interface{})["service"].(map[string]interface{})["name"]; backend != "vector-test-seaweedfs-client-volume" {
|
||||
t.Fatalf("volume ingress backend is %v", backend)
|
||||
}
|
||||
|
||||
route := findDocument(documents, "HTTPRoute", "vector-test-seaweedfs-volume")
|
||||
if route == nil {
|
||||
t.Fatal("no volume httpRoute")
|
||||
}
|
||||
rule := route["spec"].(map[string]interface{})["rules"].([]interface{})[0].(map[string]interface{})
|
||||
if backend := rule["backendRefs"].([]interface{})[0].(map[string]interface{})["name"]; backend != "vector-test-seaweedfs-client-volume" {
|
||||
t.Fatalf("volume httpRoute backend is %v", backend)
|
||||
}
|
||||
}
|
||||
|
||||
func TestVolumeRoutingServiceDoesNotCollideWithVolumeGroups(t *testing.T) {
|
||||
_, documents := render(t, "volume.ingress.enabled=true", "volume.httpRoute.enabled=true", "volumes.client.replicas=1")
|
||||
seen := map[string]bool{}
|
||||
for _, document := range documents {
|
||||
key := fmt.Sprint(document["kind"], "/", document["metadata"].(map[string]interface{})["name"])
|
||||
if seen[key] {
|
||||
t.Fatalf("%s rendered twice", key)
|
||||
}
|
||||
seen[key] = true
|
||||
}
|
||||
if !seen["Service/vector-test-seaweedfs-volume-client"] || !seen["Service/vector-test-seaweedfs-client-volume"] {
|
||||
t.Fatal("volumes.client group Service and the routing Service must both render")
|
||||
}
|
||||
}
|
||||
|
||||
func TestVolumeRoutingServiceRejectsTruncatedCollision(t *testing.T) {
|
||||
if _, err := exec.LookPath("helm"); err != nil {
|
||||
t.Skip("helm is not installed")
|
||||
}
|
||||
fullname := strings.Repeat("a", 49) + "-client"
|
||||
output, err := exec.Command("helm", "template", "test", "..", "--set", "fullnameOverride="+fullname, "--set", "volume.ingress.enabled=true").CombinedOutput()
|
||||
if err == nil || !strings.Contains(string(output), "same name as the volume Service") {
|
||||
t.Fatalf("colliding routing Service accepted: %v %s", err, output)
|
||||
}
|
||||
}
|
||||
|
||||
func TestVolumeIngressAllInOne(t *testing.T) {
|
||||
_, documents := render(t, "allInOne.enabled=true", "volume.ingress.enabled=true")
|
||||
if findDocument(documents, "Service", "vector-test-seaweedfs-client-volume") != nil {
|
||||
t.Fatal("client-volume service rendered in all-in-one mode")
|
||||
}
|
||||
ingress := findDocument(documents, "Ingress", "ingress-vector-test-seaweedfs-volume")
|
||||
if ingress == nil {
|
||||
t.Fatal("no volume ingress")
|
||||
}
|
||||
path := ingress["spec"].(map[string]interface{})["rules"].([]interface{})[0].(map[string]interface{})["http"].(map[string]interface{})["paths"].([]interface{})[0].(map[string]interface{})
|
||||
if backend := path["backend"].(map[string]interface{})["service"].(map[string]interface{})["name"]; backend != "vector-test-seaweedfs-all-in-one" {
|
||||
t.Fatalf("all-in-one volume ingress backend is %v", backend)
|
||||
}
|
||||
}
|
||||
@@ -45,6 +45,18 @@ global:
|
||||
volumeRead: 0
|
||||
filerWrite: 0
|
||||
filerRead: 0
|
||||
# Serve the volume servers' HTTP port over TLS with the chart's volume
|
||||
# certificate, and make every chart component reach them over HTTPS
|
||||
# ([https.volume] and [https.client] in security.toml). Requires
|
||||
# enableSecurity and is not supported with allInOne. Clients outside the
|
||||
# chart (weed mount, the CSI driver) need their own [https.client].
|
||||
# The volume servers do not ask for client certificates, because kubelet
|
||||
# probes cannot present one; JWT signing keeps authorizing volume access.
|
||||
# [https.client] also sends the admin UI's HTTP lookups on masters and
|
||||
# S3 over HTTPS, which their plain listeners refuse, so the UI can miss
|
||||
# volume public URLs and refuse SSE-S3 vector buckets.
|
||||
volumeHttps:
|
||||
enabled: false
|
||||
# we will use this serviceAccountName for all ClusterRoles/ClusterRoleBindings
|
||||
serviceAccountName: "seaweedfs"
|
||||
serviceAccountAnnotations: {}
|
||||
|
||||
+1055
-1067
File diff suppressed because it is too large.
Load diff
|
Before Width: | Height: | Size: 54 KiB After Width: | Height: | Size: 54 KiB |
@@ -2302,6 +2302,113 @@
|
||||
}
|
||||
],
|
||||
"pluginVersion": "10.3.1"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"title": "Writable Volumes per Disk",
|
||||
"description": "Disks holding more than one writable volume of a collection, and the most writable volumes of a collection on one disk.",
|
||||
"type": "timeseries",
|
||||
"id": 262,
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 69
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 4,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"unit": "short",
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"lastNotNull",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "count by (collection) (sum by (cluster, collection, data_center, rack, node, disk_id) (SeaweedFS_master_writable_volumes_per_disk{cluster=~\"$cluster\", state=\"writable\"}) > 1)",
|
||||
"range": true,
|
||||
"refId": "A",
|
||||
"legendFormat": "{{collection}} disks with 2+"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "max by (collection) (sum by (cluster, collection, data_center, rack, node, disk_id) (SeaweedFS_master_writable_volumes_per_disk{cluster=~\"$cluster\", state=\"writable\"}))",
|
||||
"range": true,
|
||||
"refId": "B",
|
||||
"legendFormat": "{{collection}} max on one disk"
|
||||
}
|
||||
],
|
||||
"pluginVersion": "10.3.1"
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -3335,6 +3442,102 @@
|
||||
],
|
||||
"pluginVersion": "10.3.1"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"title": "Vacuum Dropped Needles",
|
||||
"description": "Live needles vacuum dropped because their data could not be read back intact (CRC mismatch, malformed or short record), counted since the volume server started. Any non-zero value means a lost replica copy; the volume server log has each dropped key.",
|
||||
"type": "timeseries",
|
||||
"id": 267,
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 16,
|
||||
"y": 54
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 4,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"unit": "short",
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"lastNotNull",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "sum by (instance, collection) (SeaweedFS_volumeServer_vacuuming_dropped_needles{cluster=~\"$cluster\"})",
|
||||
"range": true,
|
||||
"refId": "A",
|
||||
"legendFormat": "{{instance}} {{collection}}"
|
||||
}
|
||||
],
|
||||
"pluginVersion": "10.3.1"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
@@ -6629,6 +6832,423 @@
|
||||
],
|
||||
"pluginVersion": "10.3.1"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"title": "Metadata Subscribe Delivery Lag",
|
||||
"description": "Seconds from a metadata event's mutation until the filer sends it to a subscriber, by stream scope",
|
||||
"type": "timeseries",
|
||||
"id": 263,
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 71
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 4,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"unit": "s",
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"lastNotNull",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "histogram_quantile(0.99, sum by (le, scope) (rate(SeaweedFS_filer_subscribe_delivery_lag_seconds_bucket{cluster=~\"$cluster\"}[$__rate_interval])))",
|
||||
"range": true,
|
||||
"refId": "A",
|
||||
"legendFormat": "p99 {{scope}}"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "histogram_quantile(0.5, sum by (le, scope) (rate(SeaweedFS_filer_subscribe_delivery_lag_seconds_bucket{cluster=~\"$cluster\"}[$__rate_interval])))",
|
||||
"range": true,
|
||||
"refId": "B",
|
||||
"legendFormat": "p50 {{scope}}"
|
||||
}
|
||||
],
|
||||
"pluginVersion": "10.3.1"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"title": "Metadata Watermark Hold Duration",
|
||||
"description": "How long an aggregated read stayed held at one entry until the peers' watermark released it (memory: delivery watermark, disk: flush watermark)",
|
||||
"type": "timeseries",
|
||||
"id": 264,
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 71
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 4,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"unit": "s",
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"lastNotNull",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "histogram_quantile(0.99, sum by (le, scope) (rate(SeaweedFS_filer_subscribe_hold_seconds_bucket{cluster=~\"$cluster\"}[$__rate_interval])))",
|
||||
"range": true,
|
||||
"refId": "A",
|
||||
"legendFormat": "p99 {{scope}}"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "histogram_quantile(0.5, sum by (le, scope) (rate(SeaweedFS_filer_subscribe_hold_seconds_bucket{cluster=~\"$cluster\"}[$__rate_interval])))",
|
||||
"range": true,
|
||||
"refId": "B",
|
||||
"legendFormat": "p50 {{scope}}"
|
||||
}
|
||||
],
|
||||
"pluginVersion": "10.3.1"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"title": "Metadata Delivery Claim / Peer Low-Watermark Age",
|
||||
"description": "Seconds the filer's delivery claim and the peers' delivery and flush low-watermarks trail the clock; -1 while a tracked peer has not signalled",
|
||||
"type": "timeseries",
|
||||
"id": 265,
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 79
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 4,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"unit": "s",
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"lastNotNull",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "max by (instance) (SeaweedFS_filer_meta_delivery_claim_age_seconds{cluster=~\"$cluster\"})",
|
||||
"range": true,
|
||||
"refId": "A",
|
||||
"legendFormat": "claim {{instance}}"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "max by (instance, kind) (SeaweedFS_filer_meta_peer_low_watermark_age_seconds{cluster=~\"$cluster\"})",
|
||||
"range": true,
|
||||
"refId": "B",
|
||||
"legendFormat": "peer low {{kind}} {{instance}}"
|
||||
}
|
||||
],
|
||||
"pluginVersion": "10.3.1"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"title": "Metadata Subscribers Resumed from Disk",
|
||||
"description": "Times a metadata subscriber fell off the in-memory ring and resumed from the persisted log",
|
||||
"type": "timeseries",
|
||||
"id": 266,
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 79
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 4,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "never",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"unit": "ops",
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green",
|
||||
"value": null
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"lastNotNull",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table",
|
||||
"placement": "bottom",
|
||||
"showLegend": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${DS_PROMETHEUS}"
|
||||
},
|
||||
"editorMode": "code",
|
||||
"expr": "sum by (instance, scope) (rate(SeaweedFS_filer_subscribe_resume_from_disk{cluster=~\"$cluster\"}[$__rate_interval]))",
|
||||
"range": true,
|
||||
"refId": "A",
|
||||
"legendFormat": "{{scope}} {{instance}}"
|
||||
}
|
||||
],
|
||||
"pluginVersion": "10.3.1"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
@@ -6642,7 +7262,7 @@
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 71
|
||||
"y": 87
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
@@ -6738,7 +7358,7 @@
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 71
|
||||
"y": 87
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
@@ -6834,7 +7454,7 @@
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 79
|
||||
"y": 95
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
@@ -6930,7 +7550,7 @@
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 79
|
||||
"y": 95
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
|
||||
Generated
+3
@@ -7143,6 +7143,7 @@ dependencies = [
|
||||
"aes",
|
||||
"aes-gcm",
|
||||
"anyhow",
|
||||
"arrow-array",
|
||||
"arrow-cast",
|
||||
"arrow-schema",
|
||||
"async-trait",
|
||||
@@ -7158,6 +7159,7 @@ dependencies = [
|
||||
"hmac 0.12.1",
|
||||
"http",
|
||||
"hyper-util",
|
||||
"jsonb",
|
||||
"jsonwebtoken",
|
||||
"lance",
|
||||
"lance-datafusion",
|
||||
@@ -7236,6 +7238,7 @@ dependencies = [
|
||||
"futures",
|
||||
"lance",
|
||||
"lance-arrow",
|
||||
"lance-index",
|
||||
"lance-linalg",
|
||||
"moka",
|
||||
"object_store",
|
||||
|
||||
@@ -139,6 +139,7 @@ mod tests {
|
||||
nprobes: Some(4),
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
},
|
||||
)
|
||||
.await
|
||||
@@ -167,6 +168,7 @@ mod tests {
|
||||
nprobes: Some(4),
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
};
|
||||
let filtered = ann(&dataset, &table, &query).await.unwrap();
|
||||
let exact = flat(&dataset, &table, &query).await.unwrap();
|
||||
@@ -204,6 +206,7 @@ mod tests {
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
},
|
||||
)
|
||||
.await
|
||||
|
||||
@@ -4,6 +4,7 @@
|
||||
//! compares the elements as typed JSON values: Lance's compares their text, so
|
||||
//! 1 would match "1".
|
||||
|
||||
use std::collections::HashMap;
|
||||
use std::sync::Arc;
|
||||
|
||||
use arrow_array::builder::{BooleanBuilder, StringBuilder};
|
||||
@@ -19,13 +20,21 @@ use lance::deps::datafusion::logical_expr::{
|
||||
ColumnarValue, Expr, ScalarFunctionArgs, ScalarUDF, ScalarUDFImpl, Signature, Volatility,
|
||||
};
|
||||
|
||||
/// Set `filter` on the scanner with the JSONPath functions swapped.
|
||||
pub(crate) fn apply(scanner: &mut Scanner, filter: &str) -> anyhow::Result<()> {
|
||||
/// Set `filter` on the scanner with the JSONPath functions swapped and the
|
||||
/// conjuncts on `ready` indexed keys answered by their columns. Returns the
|
||||
/// conjunction of those.
|
||||
pub(crate) fn apply(
|
||||
scanner: &mut Scanner,
|
||||
filter: &str,
|
||||
ready: &HashMap<String, String>,
|
||||
) -> anyhow::Result<Option<Expr>> {
|
||||
scanner.filter(filter)?;
|
||||
if let Some(expr) = scanner.get_expr_filter()? {
|
||||
scanner.filter_expr(swap(expr)?);
|
||||
}
|
||||
Ok(())
|
||||
let Some(expr) = scanner.get_expr_filter()? else {
|
||||
return Ok(None);
|
||||
};
|
||||
let (expr, indexed) = crate::indexed_filter::rewrite(expr, ready);
|
||||
scanner.filter_expr(swap(expr)?);
|
||||
Ok(indexed)
|
||||
}
|
||||
|
||||
fn swap(expr: Expr) -> Result<Expr> {
|
||||
@@ -268,7 +277,7 @@ mod tests {
|
||||
async fn keys(dataset: &Dataset, filter: &str, swapped: bool) -> anyhow::Result<Vec<String>> {
|
||||
let mut scanner = dataset.scan();
|
||||
if swapped {
|
||||
apply(&mut scanner, filter)?;
|
||||
apply(&mut scanner, filter, &HashMap::new())?;
|
||||
} else {
|
||||
scanner.filter(filter)?;
|
||||
}
|
||||
@@ -395,6 +404,7 @@ mod tests {
|
||||
apply(
|
||||
&mut scanner,
|
||||
r#"json_extract(`metadata`, '$["k"]') = '"v"' AND json_exists(`metadata`, '$["k"]') AND json_get_string(`metadata`, 'k') = 'v' AND json_array_contains(`metadata`, '$["k"]', '"v"') AND NOT json_array_contains(`metadata`, '$["k"]', key)"#,
|
||||
&HashMap::new(),
|
||||
)
|
||||
.unwrap();
|
||||
let mut swapped = Vec::new();
|
||||
|
||||
@@ -104,6 +104,7 @@ mod tests {
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -198,6 +199,83 @@ mod tests {
|
||||
assert_eq!(filtered.len(), 10);
|
||||
}
|
||||
|
||||
/// A filtered query through the index returns every eligible row when
|
||||
/// fewer than k match, though the probed partitions cannot hold them all:
|
||||
/// 400 of 4000 rows match, the index has 63 partitions and probes at most
|
||||
/// 32 of them.
|
||||
#[tokio::test]
|
||||
async fn filtered_ann_returns_every_match_below_k() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let rows = scattered(4000, 8, 0x9E3779B97F4A7C15);
|
||||
let tags: Vec<&str> = (0..4000)
|
||||
.map(|i| if i % 10 == 0 { "rare" } else { "common" })
|
||||
.collect();
|
||||
let mut dataset = testing::write_dataset(&dir, &rows, &tags).await;
|
||||
let table = VectorTable::resolve(&dataset, None, None).unwrap();
|
||||
build(
|
||||
&mut dataset,
|
||||
&table.vector_column,
|
||||
INDEX_NAME,
|
||||
partitions_for(4000),
|
||||
false,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(partitions_for(4000), 63);
|
||||
for vector in &scattered(3, 8, 0xD1B54A32D192ED03) {
|
||||
let q = Query {
|
||||
filter: Some("tag = 'rare'".to_string()),
|
||||
..exact(vector, 500)
|
||||
};
|
||||
let flat = query::flat(&dataset, &table, &q).await.unwrap();
|
||||
assert_eq!(flat.len(), 400);
|
||||
let ann = query::ann(&dataset, &table, &q).await.unwrap();
|
||||
assert_eq!(ann.len(), 400, "the index path dropped eligible rows");
|
||||
for (f, a) in flat.iter().zip(ann.iter()) {
|
||||
assert!((f.distance - a.distance).abs() < 1e-5);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// When no more than k rows match, every match comes back with its own
|
||||
/// distance, nearest first — not the rows the probes missed with an
|
||||
/// infinite distance. Ten fragments of 400 rows, 5 of them matching.
|
||||
#[tokio::test]
|
||||
async fn filtered_ann_scores_every_match_at_or_below_k() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let rows = scattered(4000, 8, 0x9E3779B97F4A7C15);
|
||||
let tags: Vec<&str> = (0..4000)
|
||||
.map(|i| if i % 800 == 0 { "rare" } else { "common" })
|
||||
.collect();
|
||||
let mut dataset = testing::write_dataset(&dir, &rows[..400], &tags[..400]).await;
|
||||
for chunk in 1..10 {
|
||||
let r = chunk * 400..(chunk + 1) * 400;
|
||||
testing::append_dataset(&mut dataset, &rows[r.clone()], &tags[r]).await;
|
||||
}
|
||||
let table = VectorTable::resolve(&dataset, None, None).unwrap();
|
||||
build(&mut dataset, &table.vector_column, INDEX_NAME, 63, false)
|
||||
.await
|
||||
.unwrap();
|
||||
for vector in &scattered(3, 8, 0xD1B54A32D192ED03) {
|
||||
for k in [5, 10] {
|
||||
let q = Query {
|
||||
filter: Some("tag = 'rare'".to_string()),
|
||||
..exact(vector, k)
|
||||
};
|
||||
let flat = query::flat(&dataset, &table, &q).await.unwrap();
|
||||
assert_eq!(flat.len(), 5);
|
||||
let ann = query::ann(&dataset, &table, &q).await.unwrap();
|
||||
assert_eq!(ann.len(), 5);
|
||||
for (f, a) in flat.iter().zip(ann.iter()) {
|
||||
assert!(
|
||||
(f.distance - a.distance).abs() < 1e-5,
|
||||
"k={k}: {flat:?} vs {ann:?}"
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn default_probes_take_the_largest_index() {
|
||||
use lance::index::DatasetIndexExt;
|
||||
|
||||
@@ -0,0 +1,599 @@
|
||||
//! Filters on indexed metadata keys (see `weed_lance_worker::metadata_index`).
|
||||
//!
|
||||
//! The gateway renders a string `$eq` or `$in` on a key as an OR of
|
||||
//! `json_extract(metadata, P) = '"v"'` (or `IN`) and
|
||||
//! `json_array_contains(metadata, P, '"v"')` over the same values. In the
|
||||
//! parsed filter, such a top-level conjunct on a ready key is replaced by
|
||||
//! `array_has` / `array_has_any` on the key's column, which its LABEL_LIST
|
||||
//! index answers. Everything else, including `$ne` and `$nin`, stays on the
|
||||
//! JSON path.
|
||||
|
||||
use std::collections::{BTreeMap, BTreeSet, HashMap};
|
||||
|
||||
use anyhow::Result;
|
||||
use jsonb::OwnedJsonb;
|
||||
use lance::Dataset;
|
||||
use lance::deps::datafusion::common::{Column, ScalarValue};
|
||||
use lance::deps::datafusion::functions_nested::expr_fn::{array_has, array_has_any};
|
||||
use lance::deps::datafusion::logical_expr::utils::split_conjunction_owned;
|
||||
use lance::deps::datafusion::logical_expr::{BinaryExpr, Expr, Operator};
|
||||
use lance::deps::datafusion::prelude::lit;
|
||||
use weed_lance_worker::metadata_index::{self, State};
|
||||
|
||||
const METADATA_COLUMN: &str = "metadata";
|
||||
|
||||
/// The column of each ready indexed key of `dataset`, by metadata key.
|
||||
pub(crate) fn ready_columns(dataset: &Dataset) -> HashMap<String, String> {
|
||||
let schema: arrow_schema::Schema = dataset.schema().into();
|
||||
metadata_index::indexed_keys(&schema)
|
||||
.into_iter()
|
||||
.filter(|k| k.state == Some(State::Ready))
|
||||
.map(|k| (k.key, k.column))
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// `filter` with each top-level conjunct that is a string `$eq` or `$in` on
|
||||
/// a key in `ready` answered by the key's column instead, and the
|
||||
/// conjunction of those replacements.
|
||||
pub(crate) fn rewrite(filter: Expr, ready: &HashMap<String, String>) -> (Expr, Option<Expr>) {
|
||||
if ready.is_empty() {
|
||||
return (filter, None);
|
||||
}
|
||||
let mut indexed: Option<Expr> = None;
|
||||
let mut rewritten: Option<Expr> = None;
|
||||
for conjunct in split_conjunction_owned(filter) {
|
||||
let replacement = string_membership(&conjunct).and_then(|(key, values)| {
|
||||
let column = Expr::Column(Column::from_name(ready.get(&key)?));
|
||||
Some(match values.as_slice() {
|
||||
[one] => array_has(column, lit(one.as_str())),
|
||||
_ => {
|
||||
let values: Vec<ScalarValue> = values
|
||||
.iter()
|
||||
.map(|v| ScalarValue::Utf8(Some(v.clone())))
|
||||
.collect();
|
||||
let list = ScalarValue::new_list(&values, &arrow_schema::DataType::Utf8, true);
|
||||
array_has_any(column, Expr::Literal(ScalarValue::List(list), None))
|
||||
}
|
||||
})
|
||||
});
|
||||
let part = match replacement {
|
||||
Some(expr) => {
|
||||
indexed = Some(and(indexed, expr.clone()));
|
||||
expr
|
||||
}
|
||||
None => conjunct,
|
||||
};
|
||||
rewritten = Some(and(rewritten, part));
|
||||
}
|
||||
(rewritten.unwrap_or(lit(true)), indexed)
|
||||
}
|
||||
|
||||
fn and(left: Option<Expr>, right: Expr) -> Expr {
|
||||
match left {
|
||||
Some(left) => Expr::BinaryExpr(BinaryExpr::new(
|
||||
Box::new(left),
|
||||
Operator::And,
|
||||
Box::new(right),
|
||||
)),
|
||||
None => right,
|
||||
}
|
||||
}
|
||||
|
||||
/// The key and string values of a conjunct meaning "the key holds one of
|
||||
/// these strings, or an array with one of them": the OR of scalar matches
|
||||
/// and array-member matches over the same values and key.
|
||||
fn string_membership(expr: &Expr) -> Option<(String, Vec<String>)> {
|
||||
let mut disjuncts = Vec::new();
|
||||
split_or(expr, &mut disjuncts);
|
||||
let mut path: Option<&str> = None;
|
||||
let mut scalars = BTreeSet::new();
|
||||
let mut elements = BTreeSet::new();
|
||||
for disjunct in disjuncts {
|
||||
let (p, kind) = match unwrap_false_coalesce(disjunct) {
|
||||
Expr::BinaryExpr(BinaryExpr {
|
||||
left,
|
||||
op: Operator::Eq,
|
||||
right,
|
||||
}) => (
|
||||
json_function(left, "json_extract")?,
|
||||
Member::Scalar(vec![utf8(right)?]),
|
||||
),
|
||||
Expr::InList(list) if !list.negated => (
|
||||
json_function(&list.expr, "json_extract")?,
|
||||
Member::Scalar(list.list.iter().map(utf8).collect::<Option<_>>()?),
|
||||
),
|
||||
Expr::ScalarFunction(f) if f.func.name() == "json_array_contains" => {
|
||||
let [data, p, value] = f.args.as_slice() else {
|
||||
return None;
|
||||
};
|
||||
if !is_metadata(data) {
|
||||
return None;
|
||||
}
|
||||
let element: serde_json::Value = serde_json::from_str(utf8(value)?).ok()?;
|
||||
(utf8(p)?, Member::Element(element.as_str()?.to_string()))
|
||||
}
|
||||
_ => return None,
|
||||
};
|
||||
if path.is_some_and(|q| q != p) {
|
||||
return None;
|
||||
}
|
||||
path = Some(p);
|
||||
match kind {
|
||||
Member::Scalar(values) => scalars.extend(values.into_iter().map(str::to_string)),
|
||||
Member::Element(value) => {
|
||||
elements.insert(value);
|
||||
}
|
||||
}
|
||||
}
|
||||
let key = json_path_key(path?)?;
|
||||
let rendered: BTreeSet<String> = elements
|
||||
.iter()
|
||||
.map(|s| jsonb_text(s))
|
||||
.collect::<Option<_>>()?;
|
||||
(!elements.is_empty() && rendered == scalars).then(|| (key, elements.into_iter().collect()))
|
||||
}
|
||||
|
||||
enum Member<'a> {
|
||||
Scalar(Vec<&'a str>),
|
||||
Element(String),
|
||||
}
|
||||
|
||||
fn split_or<'a>(expr: &'a Expr, out: &mut Vec<&'a Expr>) {
|
||||
match expr {
|
||||
Expr::BinaryExpr(BinaryExpr {
|
||||
left,
|
||||
op: Operator::Or,
|
||||
right,
|
||||
}) => {
|
||||
split_or(left, out);
|
||||
split_or(right, out);
|
||||
}
|
||||
Expr::Alias(alias) => split_or(&alias.expr, out),
|
||||
other => out.push(other),
|
||||
}
|
||||
}
|
||||
|
||||
/// `x` for `COALESCE(x, false)` or its simplified `x IS NOT NULL AND x`;
|
||||
/// either is false where `x` is null, which a top-level conjunct treats alike.
|
||||
fn unwrap_false_coalesce(expr: &Expr) -> &Expr {
|
||||
match expr {
|
||||
Expr::ScalarFunction(f) if f.func.name() == "coalesce" => match f.args.as_slice() {
|
||||
[x, Expr::Literal(ScalarValue::Boolean(Some(false)), _)] => x,
|
||||
_ => expr,
|
||||
},
|
||||
Expr::BinaryExpr(BinaryExpr {
|
||||
left,
|
||||
op: Operator::And,
|
||||
right,
|
||||
}) => match left.as_ref() {
|
||||
Expr::IsNotNull(x) if x == right => right,
|
||||
_ => expr,
|
||||
},
|
||||
_ => expr,
|
||||
}
|
||||
}
|
||||
|
||||
fn utf8(expr: &Expr) -> Option<&str> {
|
||||
match expr {
|
||||
Expr::Literal(ScalarValue::Utf8(Some(s)) | ScalarValue::LargeUtf8(Some(s)), _) => {
|
||||
Some(s.as_str())
|
||||
}
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
fn is_metadata(expr: &Expr) -> bool {
|
||||
matches!(expr, Expr::Column(c) if c.name == METADATA_COLUMN)
|
||||
}
|
||||
|
||||
/// The JSONPath literal of `name(metadata, path)`.
|
||||
fn json_function<'a>(expr: &'a Expr, name: &str) -> Option<&'a str> {
|
||||
match expr {
|
||||
Expr::ScalarFunction(f) if f.func.name() == name => match f.args.as_slice() {
|
||||
[data, path] if is_metadata(data) => utf8(path),
|
||||
_ => None,
|
||||
},
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
/// The key of a `$["key"]` path, with `\\` and `\"` unescaped.
|
||||
fn json_path_key(path: &str) -> Option<String> {
|
||||
let inner = path.strip_prefix("$[\"")?.strip_suffix("\"]")?;
|
||||
let mut key = String::with_capacity(inner.len());
|
||||
let mut chars = inner.chars();
|
||||
while let Some(c) = chars.next() {
|
||||
match c {
|
||||
'\\' => match chars.next()? {
|
||||
c @ ('\\' | '"') => key.push(c),
|
||||
_ => return None,
|
||||
},
|
||||
'"' => return None,
|
||||
c => key.push(c),
|
||||
}
|
||||
}
|
||||
Some(key)
|
||||
}
|
||||
|
||||
/// What json_extract returns for a stored string `s`.
|
||||
fn jsonb_text(s: &str) -> Option<String> {
|
||||
let value: OwnedJsonb = serde_json::to_string(s).ok()?.parse().ok()?;
|
||||
Some(value.to_string())
|
||||
}
|
||||
|
||||
/// How a filter compares a key.
|
||||
pub mod operand {
|
||||
pub const STRING: u8 = 1;
|
||||
pub const NUMBER: u8 = 2;
|
||||
pub const BOOL: u8 = 4;
|
||||
pub const EXISTS: u8 = 8;
|
||||
}
|
||||
|
||||
/// The metadata keys `filter` reads, each with the [`operand`] kinds it is
|
||||
/// compared with.
|
||||
pub fn filter_keys(dataset: &Dataset, filter: &str) -> Result<BTreeMap<String, u8>> {
|
||||
let mut scanner = dataset.scan();
|
||||
scanner.filter(filter)?;
|
||||
let mut keys = BTreeMap::new();
|
||||
if let Some(expr) = scanner.get_expr_filter()? {
|
||||
collect_keys(&expr, &mut keys);
|
||||
}
|
||||
Ok(keys)
|
||||
}
|
||||
|
||||
fn literal_kind(text: &str) -> u8 {
|
||||
match serde_json::from_str::<serde_json::Value>(text) {
|
||||
Ok(serde_json::Value::String(_)) => operand::STRING,
|
||||
Ok(serde_json::Value::Number(_)) => operand::NUMBER,
|
||||
Ok(serde_json::Value::Bool(_)) => operand::BOOL,
|
||||
// json_extract's text of a string with control characters is not
|
||||
// JSON, but it is quoted.
|
||||
_ if text.starts_with('"') => operand::STRING,
|
||||
_ => 0,
|
||||
}
|
||||
}
|
||||
|
||||
fn collect_keys(expr: &Expr, keys: &mut BTreeMap<String, u8>) {
|
||||
let mut note = |path: &str, kind: u8| {
|
||||
if let Some(key) = json_path_key(path) {
|
||||
*keys.entry(key).or_default() |= kind;
|
||||
}
|
||||
};
|
||||
match expr {
|
||||
Expr::TryCast(cast) if extract(&cast.expr).is_some() => {
|
||||
note(extract(&cast.expr).unwrap_or_default(), operand::NUMBER);
|
||||
return;
|
||||
}
|
||||
Expr::BinaryExpr(BinaryExpr { left, right, .. }) => {
|
||||
if let (Some(path), Some(value)) = (extract(left), utf8(right)) {
|
||||
note(path, literal_kind(value));
|
||||
return;
|
||||
}
|
||||
}
|
||||
Expr::InList(list) => {
|
||||
if let Some(path) = extract(&list.expr) {
|
||||
let kind = list
|
||||
.list
|
||||
.iter()
|
||||
.filter_map(utf8)
|
||||
.fold(0, |k, v| k | literal_kind(v));
|
||||
note(path, kind);
|
||||
return;
|
||||
}
|
||||
}
|
||||
Expr::ScalarFunction(f) if is_json_function(f.func.name()) => {
|
||||
if let [data, path, rest @ ..] = f.args.as_slice()
|
||||
&& is_metadata(data)
|
||||
&& let Some(path) = utf8(path)
|
||||
{
|
||||
let kind = match (f.func.name(), rest) {
|
||||
("json_exists", _) => operand::EXISTS,
|
||||
(_, [value]) => utf8(value).map_or(0, literal_kind),
|
||||
_ => 0,
|
||||
};
|
||||
note(path, kind);
|
||||
return;
|
||||
}
|
||||
}
|
||||
_ => {}
|
||||
}
|
||||
for child in children(expr) {
|
||||
collect_keys(child, keys);
|
||||
}
|
||||
}
|
||||
|
||||
fn extract(expr: &Expr) -> Option<&str> {
|
||||
json_function(expr, "json_extract")
|
||||
}
|
||||
|
||||
fn is_json_function(name: &str) -> bool {
|
||||
matches!(name, "json_extract" | "json_exists" | "json_array_contains")
|
||||
}
|
||||
|
||||
fn children(expr: &Expr) -> Vec<&Expr> {
|
||||
use lance::deps::datafusion::common::tree_node::TreeNode;
|
||||
let mut out = Vec::new();
|
||||
let _ = expr.apply_children(|child| {
|
||||
out.push(child);
|
||||
Ok(lance::deps::datafusion::common::tree_node::TreeNodeRecursion::Continue)
|
||||
});
|
||||
out
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use crate::query::{self, Query};
|
||||
use crate::table::VectorTable;
|
||||
use arrow_array::{FixedSizeListArray, RecordBatch, RecordBatchIterator, StringArray};
|
||||
use arrow_schema::{DataType, Field, Schema};
|
||||
use lance::index::DatasetIndexExt;
|
||||
use lance_index::IndexType;
|
||||
use lance_index::scalar::{BuiltinIndexType, ScalarIndexParams};
|
||||
use lance_linalg::distance::DistanceType;
|
||||
use std::sync::Arc;
|
||||
use tempfile::TempDir;
|
||||
|
||||
const DIM: usize = 4;
|
||||
|
||||
/// The gateway's text for `{"author": "<v>"}`.
|
||||
fn eq(field: &str, json: &str) -> String {
|
||||
let json = json.replace('\'', "''");
|
||||
format!(
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"{field}\"]') = '{json}', false) OR COALESCE(json_array_contains(`metadata`, '$[\"{field}\"]', '{json}'), false))"
|
||||
)
|
||||
}
|
||||
|
||||
/// The gateway's text for `{"author": {"$in": [<strings>]}}`.
|
||||
fn among(values: &[&str]) -> String {
|
||||
let scalars: Vec<String> = values.iter().map(|v| format!("'\"{v}\"'")).collect();
|
||||
let mut groups = vec![format!(
|
||||
"COALESCE(json_extract(`metadata`, '$[\"author\"]') in ({}), false)",
|
||||
scalars.join(", ")
|
||||
)];
|
||||
for v in values {
|
||||
groups.push(format!(
|
||||
"COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"{v}\"'), false)"
|
||||
));
|
||||
}
|
||||
format!("({})", groups.join(" OR "))
|
||||
}
|
||||
|
||||
/// Rows `u0..u<n>` by author, plus a few others, in fragments of 100,
|
||||
/// with the author column ready and indexed and a vector index.
|
||||
async fn dataset(dir: &TempDir, rows: usize) -> Dataset {
|
||||
let metadata = Field::new("metadata", DataType::Utf8, true)
|
||||
.with_metadata([("ARROW:extension:name".to_string(), "arrow.json".to_string())].into());
|
||||
let schema = Arc::new(Schema::new(vec![
|
||||
Field::new("key", DataType::Utf8, false),
|
||||
Field::new(
|
||||
"vector",
|
||||
DataType::FixedSizeList(
|
||||
Arc::new(Field::new("item", DataType::Float32, true)),
|
||||
DIM as i32,
|
||||
),
|
||||
false,
|
||||
),
|
||||
metadata,
|
||||
metadata_index::field("_mk_0", "author", State::Ready),
|
||||
]));
|
||||
let metas: Vec<serde_json::Value> = (0..rows)
|
||||
.map(|i| match i % 10 {
|
||||
0 => serde_json::json!({"author": "rare"}),
|
||||
1 => serde_json::json!({"author": ["many", "rare2"]}),
|
||||
_ => serde_json::json!({"author": "many", "n": i}),
|
||||
})
|
||||
.collect();
|
||||
let batches: Vec<RecordBatch> = (0..rows)
|
||||
.step_by(100)
|
||||
.map(|start| {
|
||||
let range = start..(start + 100).min(rows);
|
||||
RecordBatch::try_new(
|
||||
schema.clone(),
|
||||
vec![
|
||||
Arc::new(StringArray::from(
|
||||
range.clone().map(|i| format!("k{i}")).collect::<Vec<_>>(),
|
||||
)),
|
||||
Arc::new(FixedSizeListArray::from_iter_primitive::<
|
||||
arrow_array::types::Float32Type,
|
||||
_,
|
||||
_,
|
||||
>(
|
||||
range.clone().map(|i| {
|
||||
Some((0..DIM).map(move |j| Some(((i * 31 + j * 17) % 97) as f32)))
|
||||
}),
|
||||
DIM as i32,
|
||||
)),
|
||||
Arc::new(StringArray::from(
|
||||
range
|
||||
.clone()
|
||||
.map(|i| Some(metas[i].to_string()))
|
||||
.collect::<Vec<_>>(),
|
||||
)),
|
||||
metadata_index::column_from_json(range.map(|i| Some(&metas[i])), "author"),
|
||||
],
|
||||
)
|
||||
.unwrap()
|
||||
})
|
||||
.collect();
|
||||
let uri = dir.path().to_str().unwrap();
|
||||
let mut dataset = None::<Dataset>;
|
||||
for batch in batches {
|
||||
let reader = RecordBatchIterator::new(vec![Ok(batch)], schema.clone());
|
||||
dataset = Some(match dataset {
|
||||
None => Dataset::write(reader, uri, None).await.unwrap(),
|
||||
Some(mut d) => {
|
||||
d.append(reader, None).await.unwrap();
|
||||
d
|
||||
}
|
||||
});
|
||||
}
|
||||
let mut dataset = dataset.unwrap();
|
||||
dataset
|
||||
.create_index(
|
||||
&["_mk_0"],
|
||||
IndexType::LabelList,
|
||||
None,
|
||||
&ScalarIndexParams::for_builtin(BuiltinIndexType::LabelList),
|
||||
true,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
crate::index::build(&mut dataset, "vector", crate::index::INDEX_NAME, 4, false)
|
||||
.await
|
||||
.unwrap();
|
||||
dataset
|
||||
}
|
||||
|
||||
fn rewritten(dataset: &Dataset, filter: &str) -> (String, Option<String>) {
|
||||
let mut scanner = dataset.scan();
|
||||
let indexed = crate::filter::apply(&mut scanner, filter, &ready_columns(dataset)).unwrap();
|
||||
(
|
||||
scanner.get_expr_filter().unwrap().unwrap().to_string(),
|
||||
indexed.map(|e| e.to_string()),
|
||||
)
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn string_eq_and_in_on_a_ready_key_use_its_column() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let dataset = dataset(&dir, 200).await;
|
||||
assert_eq!(
|
||||
ready_columns(&dataset),
|
||||
HashMap::from([("author".to_string(), "_mk_0".to_string())])
|
||||
);
|
||||
for (filter, want) in [
|
||||
(eq("author", "\"rare\""), Some("array_has(_mk_0, Utf8(\"rare\"))")),
|
||||
(
|
||||
among(&["rare", "many"]),
|
||||
Some("array_has_any(_mk_0, List([many, rare]))"),
|
||||
),
|
||||
(
|
||||
format!("{} AND TRY_CAST(json_extract(`metadata`, '$[\"n\"]') AS DOUBLE) > 3", eq("author", "\"rare\"")),
|
||||
Some("array_has(_mk_0, Utf8(\"rare\"))"),
|
||||
),
|
||||
(eq("author", "\"o'neil \\\"q\\\"\""), Some("array_has(_mk_0, Utf8(\"o'neil \"q\"\"))")),
|
||||
(
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"c\\u0001d\\n\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"c\\u0001d\\n\"'), false))".to_string(),
|
||||
Some("array_has(_mk_0, Utf8(\"c\u{1}d\n\"))"),
|
||||
),
|
||||
// The scalar half's text is not what json_extract returns for
|
||||
// the array half's string, so the two do not agree.
|
||||
(
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"c\\u{1}d\\n\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"c\\u0001d\\n\"'), false))".to_string(),
|
||||
None,
|
||||
),
|
||||
// Not a string, not this key, or not every value on both sides.
|
||||
(eq("author", "true"), None),
|
||||
(eq("other", "\"rare\""), None),
|
||||
(format!("NOT {}", eq("author", "\"rare\"")), None),
|
||||
(format!("NOT {}", among(&["rare", "many"])), None),
|
||||
(
|
||||
"COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"rare\"', false)".to_string(),
|
||||
None,
|
||||
),
|
||||
(
|
||||
among(&["rare", "many"]).replace("'\"many\"'), false))", "'\"other\"'), false))"),
|
||||
None,
|
||||
),
|
||||
("json_exists(`metadata`, '$[\"author\"]')".to_string(), None),
|
||||
(format!("({} OR json_exists(`metadata`, '$[\"n\"]'))", eq("author", "\"rare\"")), None),
|
||||
] {
|
||||
let (expr, indexed) = rewritten(&dataset, &filter);
|
||||
assert_eq!(indexed.as_deref(), want, "{filter}");
|
||||
assert_eq!(expr.contains("json_"), want.is_none() || filter.contains(" AND "), "{filter}: {expr}");
|
||||
}
|
||||
}
|
||||
|
||||
/// The planner scores few matches exactly and leaves many to the vector
|
||||
/// index, per scope.
|
||||
#[tokio::test]
|
||||
async fn few_indexed_matches_are_scored_exactly() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let dataset = dataset(&dir, 1000).await;
|
||||
let table = VectorTable::resolve(&dataset, None, None).unwrap();
|
||||
let query = |filter: &str, fragments: Option<Vec<u64>>| Query {
|
||||
vector: vec![1.0, 2.0, 3.0, 4.0],
|
||||
k: 10,
|
||||
filter: Some(filter.to_string()),
|
||||
postfilter: false,
|
||||
distance: DistanceType::L2,
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments,
|
||||
exact_match_limit: None,
|
||||
};
|
||||
let rare = eq("author", "\"rare\"");
|
||||
let many = eq("author", "\"many\"");
|
||||
let few = |q: Query| {
|
||||
let (dataset, table) = (&dataset, &table);
|
||||
async move {
|
||||
query::few_indexed_matches(dataset, table, &q)
|
||||
.await
|
||||
.unwrap()
|
||||
}
|
||||
};
|
||||
// 100 and 900 matches, and 90 in the first two fragments.
|
||||
assert!(few(query(&rare, None)).await);
|
||||
assert!(!few(query(&many, None)).await);
|
||||
let first = Some(vec![0, 1]);
|
||||
assert!(few(query(&many, first.clone())).await);
|
||||
assert!(
|
||||
!few(Query {
|
||||
exact_match_limit: Some(0),
|
||||
..query(&rare, None)
|
||||
})
|
||||
.await
|
||||
);
|
||||
// A JSON-only filter is not counted.
|
||||
assert!(!few(query("json_exists(`metadata`, '$[\"n\"]')", None)).await);
|
||||
for (filter, fragments) in [(&rare, None), (&many, first)] {
|
||||
let q = query(filter, fragments);
|
||||
let exact = query::flat(&dataset, &table, &q).await.unwrap();
|
||||
let got = query::ann(&dataset, &table, &q).await.unwrap();
|
||||
assert_eq!(got.len(), 10);
|
||||
for (g, e) in got.iter().zip(&exact) {
|
||||
assert!(
|
||||
(g.distance - e.distance).abs() < 1e-4,
|
||||
"{got:?} vs {exact:?}"
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn the_plan_reads_the_scalar_index() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let dataset = dataset(&dir, 300).await;
|
||||
let mut scanner = dataset.scan();
|
||||
crate::filter::apply(
|
||||
&mut scanner,
|
||||
&eq("author", "\"rare\""),
|
||||
&ready_columns(&dataset),
|
||||
)
|
||||
.unwrap();
|
||||
let plan = scanner.explain_plan(true).await.unwrap();
|
||||
assert!(plan.contains("LabelList"), "{plan}");
|
||||
assert!(!plan.contains("json_"), "{plan}");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn filter_keys_note_how_each_key_is_compared() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let dataset = dataset(&dir, 100).await;
|
||||
let filter = format!(
|
||||
"{} AND TRY_CAST(json_extract(`metadata`, '$[\"n\"]') AS DOUBLE) > 3 AND NOT json_exists(`metadata`, '$[\"a.b\\\"c\"]') AND COALESCE(json_extract(`metadata`, '$[\"f\"]') = 'true', false)",
|
||||
eq("author", "\"rare\"")
|
||||
);
|
||||
let keys = filter_keys(&dataset, &filter).unwrap();
|
||||
assert_eq!(
|
||||
keys,
|
||||
BTreeMap::from([
|
||||
("a.b\"c".to_string(), operand::EXISTS),
|
||||
("author".to_string(), operand::STRING),
|
||||
("f".to_string(), operand::BOOL),
|
||||
("n".to_string(), operand::NUMBER),
|
||||
])
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -8,6 +8,7 @@
|
||||
pub mod coverage;
|
||||
mod filter;
|
||||
pub mod index;
|
||||
pub mod indexed_filter;
|
||||
pub mod maintenance;
|
||||
pub mod query;
|
||||
pub mod segments;
|
||||
|
||||
@@ -309,6 +309,7 @@ async fn main() -> Result<()> {
|
||||
nprobes,
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
};
|
||||
let hits = if flat {
|
||||
query::flat(&dataset, &vector_table, &query).await?
|
||||
|
||||
@@ -312,6 +312,7 @@ mod tests {
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
};
|
||||
let mut ids: Vec<u64> = query::flat(&pinned, &resolved, &q)
|
||||
.await
|
||||
@@ -734,6 +735,7 @@ mod tests {
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
};
|
||||
assert!(query::flat(&dataset, &resolved, &q).await.is_err());
|
||||
}
|
||||
|
||||
@@ -39,8 +39,15 @@ pub struct Query {
|
||||
/// a worker the unindexed-fragment sweep. Listed ids that no longer exist
|
||||
/// scan nothing.
|
||||
pub fragments: Option<Vec<u64>>,
|
||||
/// Score the matches exactly instead of searching the vector index when
|
||||
/// the filter's indexed metadata keys match at most this many rows of the
|
||||
/// scope; 0 never does. None takes [`DEFAULT_EXACT_MATCH_LIMIT`].
|
||||
pub exact_match_limit: Option<usize>,
|
||||
}
|
||||
|
||||
/// Up to this many matches of an indexed metadata key are scored exactly.
|
||||
pub const DEFAULT_EXACT_MATCH_LIMIT: usize = 256;
|
||||
|
||||
/// One row of a top-K answer.
|
||||
#[derive(Debug, Clone, serde::Serialize)]
|
||||
pub struct Hit {
|
||||
@@ -53,14 +60,103 @@ pub struct Hit {
|
||||
|
||||
/// Exact top-K over every fragment, ignoring any index.
|
||||
pub async fn flat(dataset: &Dataset, table: &VectorTable, query: &Query) -> Result<Vec<Hit>> {
|
||||
run(scanner(dataset, table, query, false).await?, table).await
|
||||
run(scanner(dataset, table, query, false).await?.0, table).await
|
||||
}
|
||||
|
||||
/// Top-K with the ANN index where it covers the fragment and a flat pass over
|
||||
/// the rest. Whether the index is used is Lance's decision per fragment, so
|
||||
/// rows written after the last index build are always candidates.
|
||||
///
|
||||
/// A prefiltered search sees only the probed partitions: it can come back
|
||||
/// short of k, or with unscored rows (infinite distance) when at most k rows
|
||||
/// match. Either way it is answered again by an exact scan of the same scope.
|
||||
///
|
||||
/// When the filter's indexed metadata keys match few rows of that scope,
|
||||
/// they are scored exactly to begin with. The decision is per scope, so
|
||||
/// exact answers of several scopes merge into the exact answer.
|
||||
pub async fn ann(dataset: &Dataset, table: &VectorTable, query: &Query) -> Result<Vec<Hit>> {
|
||||
run(scanner(dataset, table, query, true).await?, table).await
|
||||
if few_indexed_matches(dataset, table, query).await? {
|
||||
return exact_in_scope(dataset, table, query).await;
|
||||
}
|
||||
let (scanner, indexed) = scanner(dataset, table, query, true).await?;
|
||||
let hits = run(scanner, table).await?;
|
||||
if indexed
|
||||
&& query.filter.is_some()
|
||||
&& !query.postfilter
|
||||
&& (hits.len() < query.k || hits.iter().any(|h| !h.distance.is_finite()))
|
||||
{
|
||||
return exact_in_scope(dataset, table, query).await;
|
||||
}
|
||||
Ok(hits)
|
||||
}
|
||||
|
||||
/// [`flat`] over what [`ann`] searches for `query`: the listed fragments plus
|
||||
/// the live coverage of the listed index segments, or the whole table.
|
||||
async fn exact_in_scope(dataset: &Dataset, table: &VectorTable, query: &Query) -> Result<Vec<Hit>> {
|
||||
let exact = Query {
|
||||
index_segments: None,
|
||||
fragments: scope(dataset, table, query).await?,
|
||||
..query.clone()
|
||||
};
|
||||
run(scanner(dataset, table, &exact, false).await?.0, table).await
|
||||
}
|
||||
|
||||
/// The fragments [`ann`] searches for `query`, or None for the whole table.
|
||||
async fn scope(dataset: &Dataset, table: &VectorTable, query: &Query) -> Result<Option<Vec<u64>>> {
|
||||
Ok(match &query.index_segments {
|
||||
Some(segments) if !segments.is_empty() => {
|
||||
let mut ids = query.fragments.clone().unwrap_or_default();
|
||||
ids.extend(
|
||||
crate::segments::covered_fragments(dataset, &table.vector_column, segments).await?,
|
||||
);
|
||||
Some(ids)
|
||||
}
|
||||
_ => query.fragments.clone(),
|
||||
})
|
||||
}
|
||||
|
||||
/// Whether the rows of [`ann`]'s scope matching the filter's indexed
|
||||
/// metadata keys, counted through their scalar indexes, are at most the
|
||||
/// query's limit. Only a search through the vector index asks.
|
||||
pub(crate) async fn few_indexed_matches(
|
||||
dataset: &Dataset,
|
||||
table: &VectorTable,
|
||||
query: &Query,
|
||||
) -> Result<bool> {
|
||||
let limit = query.exact_match_limit.unwrap_or(DEFAULT_EXACT_MATCH_LIMIT);
|
||||
let Some(filter) = &query.filter else {
|
||||
return Ok(false);
|
||||
};
|
||||
if limit == 0 || query.postfilter || query.index_segments.as_ref().is_some_and(|s| s.is_empty())
|
||||
{
|
||||
return Ok(false);
|
||||
}
|
||||
let ready = crate::indexed_filter::ready_columns(dataset);
|
||||
if ready.is_empty()
|
||||
|| crate::index::index_names(dataset, &table.vector_column)
|
||||
.await?
|
||||
.is_empty()
|
||||
{
|
||||
return Ok(false);
|
||||
}
|
||||
let Some(indexed) = crate::filter::apply(&mut dataset.scan(), filter, &ready)? else {
|
||||
return Ok(false);
|
||||
};
|
||||
let mut counter = dataset.scan();
|
||||
counter.filter_expr(indexed);
|
||||
if let Some(ids) = scope(dataset, table, query).await? {
|
||||
counter.with_fragments(
|
||||
dataset
|
||||
.fragments()
|
||||
.iter()
|
||||
.filter(|f| ids.contains(&f.id))
|
||||
.cloned()
|
||||
.collect(),
|
||||
);
|
||||
}
|
||||
let matches = counter.count_rows().await?;
|
||||
tracing::debug!(matches, limit, "indexed metadata filter");
|
||||
Ok(matches <= limit as u64)
|
||||
}
|
||||
|
||||
/// Fetch rows by key, projected to `columns` (all of them when None).
|
||||
@@ -101,7 +197,7 @@ async fn scanner(
|
||||
table: &VectorTable,
|
||||
query: &Query,
|
||||
use_index: bool,
|
||||
) -> Result<Scanner> {
|
||||
) -> Result<(Scanner, bool)> {
|
||||
if query.vector.len() != table.dimension {
|
||||
bail!(
|
||||
"query dim({}) does not match the table's dim({})",
|
||||
@@ -117,18 +213,24 @@ async fn scanner(
|
||||
.use_index(use_index)
|
||||
.with_row_id();
|
||||
if let Some(filter) = &query.filter {
|
||||
crate::filter::apply(&mut scanner, filter)?;
|
||||
let ready = crate::indexed_filter::ready_columns(dataset);
|
||||
crate::filter::apply(&mut scanner, filter, &ready)?;
|
||||
scanner.prefilter(!query.postfilter);
|
||||
}
|
||||
// An explicitly empty segment list searches no index, so there is
|
||||
// nothing to size probes for.
|
||||
let no_segments = query.index_segments.as_ref().is_some_and(|s| s.is_empty());
|
||||
let mut indexed = false;
|
||||
if use_index && !no_segments {
|
||||
let probes = match query.nprobes {
|
||||
Some(n) => Some(crate::index::Probes { min: n, max: n }),
|
||||
Some(n) => crate::index::index_names(dataset, &table.vector_column)
|
||||
.await?
|
||||
.first()
|
||||
.map(|_| crate::index::Probes { min: n, max: n }),
|
||||
None => crate::index::default_probes(dataset, &table.vector_column).await?,
|
||||
};
|
||||
if let Some(probes) = probes {
|
||||
indexed = true;
|
||||
// Lance searches `min` partitions, and under a prefilter keeps
|
||||
// going up to `max` until it has k rows. An open bound would
|
||||
// make it prepare every partition for that, which costs as much
|
||||
@@ -178,7 +280,7 @@ async fn scanner(
|
||||
columns.push(DISTANCE_COLUMN.to_string());
|
||||
columns.push(ROW_ID_COLUMN.to_string());
|
||||
scanner.project(&columns)?;
|
||||
Ok(scanner)
|
||||
Ok((scanner, indexed))
|
||||
}
|
||||
|
||||
async fn run(scanner: Scanner, table: &VectorTable) -> Result<Vec<Hit>> {
|
||||
@@ -261,6 +363,7 @@ mod tests {
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
};
|
||||
let hits = flat(&dataset, &table, &query).await.unwrap();
|
||||
assert_eq!(hits.len(), 2);
|
||||
@@ -302,6 +405,7 @@ mod tests {
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
},
|
||||
)
|
||||
.await
|
||||
@@ -381,6 +485,7 @@ mod tests {
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
},
|
||||
)
|
||||
.await
|
||||
@@ -484,6 +589,7 @@ mod tests {
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
};
|
||||
assert!(flat(&dataset, &table, &query).await.is_err());
|
||||
}
|
||||
@@ -507,6 +613,7 @@ mod tests {
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
};
|
||||
let indexed = ann(&dataset, &table, &query).await.unwrap();
|
||||
let exact = flat(&dataset, &table, &query).await.unwrap();
|
||||
@@ -515,4 +622,36 @@ mod tests {
|
||||
exact.iter().map(|h| &h.key).collect::<Vec<_>>()
|
||||
);
|
||||
}
|
||||
|
||||
/// An explicit probe count does not make an unindexed table's scan count
|
||||
/// as indexed, so a short filtered answer is not scanned a second time.
|
||||
#[tokio::test]
|
||||
async fn explicit_probes_need_an_index() {
|
||||
let dir = TempDir::new().unwrap();
|
||||
let rows = crate::testing::vectors(300, DIM);
|
||||
let mut dataset = write_dataset(&dir, &rows, &["a"; 300]).await;
|
||||
let table = VectorTable::resolve(&dataset, None, None).unwrap();
|
||||
let query = Query {
|
||||
vector: rows[0].clone(),
|
||||
k: 10,
|
||||
filter: Some("tag = 'a'".to_string()),
|
||||
postfilter: false,
|
||||
distance: DistanceType::L2,
|
||||
nprobes: Some(4),
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
};
|
||||
assert!(!scanner(&dataset, &table, &query, true).await.unwrap().1);
|
||||
crate::index::build(
|
||||
&mut dataset,
|
||||
&table.vector_column,
|
||||
crate::index::INDEX_NAME,
|
||||
4,
|
||||
false,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(scanner(&dataset, &table, &query, true).await.unwrap().1);
|
||||
}
|
||||
}
|
||||
@@ -139,6 +139,7 @@ mod tests {
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
};
|
||||
let want: Vec<(u64, u32)> = query::ann(&dataset, &resolved, &base)
|
||||
.await
|
||||
@@ -239,6 +240,7 @@ mod tests {
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments: Some(vec![u64::MAX]),
|
||||
exact_match_limit: None,
|
||||
};
|
||||
assert!(
|
||||
query::ann(&dataset, &resolved, &q)
|
||||
|
||||
@@ -44,6 +44,7 @@ fn query_for(vector: Vec<f32>, k: usize) -> Query {
|
||||
nprobes: Some(4),
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -46,6 +46,7 @@ tracing.workspace = true
|
||||
tracing-subscriber.workspace = true
|
||||
|
||||
[dev-dependencies]
|
||||
lance-index = "10"
|
||||
tempfile = "3"
|
||||
|
||||
[build-dependencies]
|
||||
|
||||
@@ -0,0 +1,290 @@
|
||||
//! How often, and how slowly, each index's queries filter on each metadata
|
||||
//! key over the last hour. Keys come from the parsed filter; the number of
|
||||
//! indexes and of keys per index is bounded, so arbitrary keys cannot grow
|
||||
//! memory without limit. Not exported as metrics: a key is no label.
|
||||
|
||||
use std::collections::{BTreeMap, HashMap};
|
||||
use std::sync::Mutex;
|
||||
use std::time::{Duration, Instant};
|
||||
|
||||
use weed_vector_core::indexed_filter::operand;
|
||||
|
||||
use crate::pb::vector as pb;
|
||||
|
||||
const BUCKETS: usize = 12;
|
||||
const BUCKET: Duration = Duration::from_secs(300);
|
||||
pub const WINDOW: Duration = Duration::from_secs(BUCKET.as_secs() * BUCKETS as u64);
|
||||
pub const MAX_INDEXES: usize = 512;
|
||||
pub const MAX_KEYS_PER_INDEX: usize = 32;
|
||||
|
||||
#[derive(Default, Clone, Copy)]
|
||||
struct Bucket {
|
||||
/// The bucket's number since the stats started.
|
||||
at: u64,
|
||||
queries: u64,
|
||||
seconds: f64,
|
||||
/// The operand kinds the bucket's queries compared the key with.
|
||||
kinds: u8,
|
||||
}
|
||||
|
||||
#[derive(Default)]
|
||||
struct KeyStats {
|
||||
buckets: [Bucket; BUCKETS],
|
||||
}
|
||||
|
||||
#[derive(Default)]
|
||||
struct IndexStats {
|
||||
keys: HashMap<String, KeyStats>,
|
||||
/// The last bucket a key was left uncounted in.
|
||||
truncated: Option<u64>,
|
||||
last: u64,
|
||||
}
|
||||
|
||||
/// Whether bucket `at` is still in the window of bucket `now`.
|
||||
fn live(at: u64, now: u64) -> bool {
|
||||
at + BUCKETS as u64 > now
|
||||
}
|
||||
|
||||
pub struct FilterStats {
|
||||
start: Instant,
|
||||
indexes: Mutex<HashMap<String, IndexStats>>,
|
||||
}
|
||||
|
||||
impl Default for FilterStats {
|
||||
fn default() -> Self {
|
||||
Self::new()
|
||||
}
|
||||
}
|
||||
|
||||
impl FilterStats {
|
||||
pub fn new() -> Self {
|
||||
Self {
|
||||
start: Instant::now(),
|
||||
indexes: Mutex::new(HashMap::new()),
|
||||
}
|
||||
}
|
||||
|
||||
fn bucket(&self, now: Instant) -> u64 {
|
||||
(now.duration_since(self.start).as_secs() / BUCKET.as_secs()) + 1
|
||||
}
|
||||
|
||||
/// One query of `index` that took `elapsed` and filtered on `keys`.
|
||||
pub fn record(&self, index: &str, keys: &BTreeMap<String, u8>, elapsed: Duration) {
|
||||
self.record_at(index, keys, elapsed, Instant::now());
|
||||
}
|
||||
|
||||
fn record_at(&self, index: &str, keys: &BTreeMap<String, u8>, elapsed: Duration, now: Instant) {
|
||||
if keys.is_empty() {
|
||||
return;
|
||||
}
|
||||
let at = self.bucket(now);
|
||||
let mut indexes = self.indexes.lock().unwrap();
|
||||
if !indexes.contains_key(index) && indexes.len() >= MAX_INDEXES {
|
||||
let Some(oldest) = indexes
|
||||
.iter()
|
||||
.min_by_key(|(_, stats)| stats.last)
|
||||
.map(|(name, _)| name.clone())
|
||||
else {
|
||||
return;
|
||||
};
|
||||
indexes.remove(&oldest);
|
||||
}
|
||||
let stats = indexes.entry(index.to_string()).or_default();
|
||||
stats.last = stats.last.max(at);
|
||||
for (key, kinds) in keys {
|
||||
if !stats.keys.contains_key(key) && stats.keys.len() >= MAX_KEYS_PER_INDEX {
|
||||
// Make room only by dropping a key no query used in the window.
|
||||
let idle = stats
|
||||
.keys
|
||||
.iter()
|
||||
.find(|(_, k)| k.buckets.iter().all(|b| !live(b.at, at)))
|
||||
.map(|(name, _)| name.clone());
|
||||
match idle {
|
||||
Some(idle) => {
|
||||
stats.keys.remove(&idle);
|
||||
}
|
||||
None => {
|
||||
stats.truncated = stats.truncated.max(Some(at));
|
||||
continue;
|
||||
}
|
||||
}
|
||||
}
|
||||
let entry = stats.keys.entry(key.clone()).or_default();
|
||||
let bucket = &mut entry.buckets[(at % BUCKETS as u64) as usize];
|
||||
if bucket.at != at {
|
||||
*bucket = Bucket {
|
||||
at,
|
||||
..Default::default()
|
||||
};
|
||||
}
|
||||
bucket.queries += 1;
|
||||
bucket.seconds += elapsed.as_secs_f64();
|
||||
bucket.kinds |= kinds;
|
||||
}
|
||||
}
|
||||
|
||||
/// The stats of `index` over the window.
|
||||
pub fn snapshot(&self, index: &str) -> pb::FilterStatsResponse {
|
||||
self.snapshot_at(index, Instant::now())
|
||||
}
|
||||
|
||||
fn snapshot_at(&self, index: &str, now: Instant) -> pb::FilterStatsResponse {
|
||||
let at = self.bucket(now);
|
||||
let window_seconds = now.duration_since(self.start).min(WINDOW).as_secs() as u32;
|
||||
let indexes = self.indexes.lock().unwrap();
|
||||
let Some(stats) = indexes.get(index) else {
|
||||
return pb::FilterStatsResponse {
|
||||
window_seconds,
|
||||
..Default::default()
|
||||
};
|
||||
};
|
||||
let mut keys: Vec<pb::FilterKeyStats> = stats
|
||||
.keys
|
||||
.iter()
|
||||
.filter_map(|(key, s)| {
|
||||
let (queries, seconds, kinds) = s
|
||||
.buckets
|
||||
.iter()
|
||||
.filter(|b| live(b.at, at))
|
||||
.fold((0, 0.0, 0), |(q, t, k), b| {
|
||||
(q + b.queries, t + b.seconds, k | b.kinds)
|
||||
});
|
||||
(queries > 0).then(|| pb::FilterKeyStats {
|
||||
key: key.clone(),
|
||||
queries,
|
||||
seconds,
|
||||
string_operand: kinds & operand::STRING != 0,
|
||||
number_operand: kinds & operand::NUMBER != 0,
|
||||
bool_operand: kinds & operand::BOOL != 0,
|
||||
})
|
||||
})
|
||||
.collect();
|
||||
keys.sort_by(|a, b| b.queries.cmp(&a.queries).then(a.key.cmp(&b.key)));
|
||||
pb::FilterStatsResponse {
|
||||
keys,
|
||||
window_seconds,
|
||||
truncated: stats.truncated.is_some_and(|t| live(t, at)),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn keys(pairs: &[(&str, u8)]) -> BTreeMap<String, u8> {
|
||||
pairs.iter().map(|(k, v)| (k.to_string(), *v)).collect()
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn counts_queries_and_latency_per_key_within_the_window() {
|
||||
let stats = FilterStats::new();
|
||||
let t0 = stats.start;
|
||||
let ms = Duration::from_millis;
|
||||
stats.record_at("b/i", &keys(&[("author", operand::STRING)]), ms(10), t0);
|
||||
stats.record_at(
|
||||
"b/i",
|
||||
&keys(&[("author", operand::STRING), ("year", operand::NUMBER)]),
|
||||
ms(30),
|
||||
t0 + Duration::from_secs(600),
|
||||
);
|
||||
stats.record_at("b/j", &keys(&[("x", operand::BOOL)]), ms(5), t0);
|
||||
let got = stats.snapshot_at("b/i", t0 + Duration::from_secs(900));
|
||||
assert_eq!(got.window_seconds, 900);
|
||||
assert_eq!(got.keys.len(), 2);
|
||||
assert_eq!(got.keys[0].key, "author");
|
||||
assert_eq!(got.keys[0].queries, 2);
|
||||
assert!((got.keys[0].seconds - 0.04).abs() < 1e-9);
|
||||
assert!(got.keys[0].string_operand && !got.keys[0].number_operand);
|
||||
assert_eq!(got.keys[1].key, "year");
|
||||
assert!(got.keys[1].number_operand);
|
||||
// The first query leaves the window an hour after its bucket.
|
||||
let later = stats.snapshot_at("b/i", t0 + WINDOW + Duration::from_secs(1));
|
||||
assert_eq!(later.window_seconds, WINDOW.as_secs() as u32);
|
||||
assert_eq!(later.keys[0].queries, 1);
|
||||
let year = later.keys.iter().find(|k| k.key == "year").unwrap();
|
||||
assert!(year.number_operand);
|
||||
// A string query that left the window no longer marks the key.
|
||||
stats.record_at(
|
||||
"b/i",
|
||||
&keys(&[("author", operand::NUMBER)]),
|
||||
ms(1),
|
||||
t0 + WINDOW + Duration::from_secs(2),
|
||||
);
|
||||
let mixed = stats.snapshot_at("b/i", t0 + WINDOW + Duration::from_secs(3));
|
||||
let author = mixed.keys.iter().find(|k| k.key == "author").unwrap();
|
||||
assert!(author.string_operand && author.number_operand);
|
||||
let numeric = stats.snapshot_at("b/i", t0 + WINDOW + Duration::from_secs(700));
|
||||
let author = numeric.keys.iter().find(|k| k.key == "author").unwrap();
|
||||
assert!(!author.string_operand && author.number_operand);
|
||||
let gone = stats.snapshot_at("b/i", t0 + 2 * WINDOW + Duration::from_secs(900));
|
||||
assert!(gone.keys.is_empty());
|
||||
assert!(stats.snapshot_at("other", t0).keys.is_empty());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn indexes_and_keys_are_bounded() {
|
||||
let stats = FilterStats::new();
|
||||
let t0 = stats.start;
|
||||
for i in 0..MAX_KEYS_PER_INDEX + 5 {
|
||||
stats.record_at(
|
||||
"b/i",
|
||||
&keys(&[(&format!("k{i}"), operand::STRING)]),
|
||||
Duration::ZERO,
|
||||
t0,
|
||||
);
|
||||
}
|
||||
let got = stats.snapshot_at("b/i", t0);
|
||||
assert_eq!(got.keys.len(), MAX_KEYS_PER_INDEX);
|
||||
assert!(got.truncated);
|
||||
// A key idle for the whole window makes room for a new one.
|
||||
let later = t0 + WINDOW + BUCKET;
|
||||
stats.record_at(
|
||||
"b/i",
|
||||
&keys(&[("new", operand::STRING)]),
|
||||
Duration::ZERO,
|
||||
later,
|
||||
);
|
||||
let got = stats.snapshot_at("b/i", later);
|
||||
assert!(!got.truncated, "the uncounted keys left the window");
|
||||
assert_eq!(got.keys.len(), 1);
|
||||
assert_eq!(got.keys[0].key, "new");
|
||||
|
||||
for i in 0..MAX_INDEXES + 3 {
|
||||
stats.record_at(
|
||||
&format!("b/{i}"),
|
||||
&keys(&[("k", operand::STRING)]),
|
||||
Duration::ZERO,
|
||||
later,
|
||||
);
|
||||
}
|
||||
assert_eq!(stats.indexes.lock().unwrap().len(), MAX_INDEXES);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn a_record_from_an_earlier_bucket_keeps_the_later_truncation() {
|
||||
let stats = FilterStats::new();
|
||||
let t0 = stats.start;
|
||||
for i in 0..=MAX_KEYS_PER_INDEX {
|
||||
stats.record_at(
|
||||
"b/i",
|
||||
&keys(&[(&format!("k{i}"), operand::STRING)]),
|
||||
Duration::ZERO,
|
||||
t0 + BUCKET,
|
||||
);
|
||||
}
|
||||
// Took its time before the lock while the later bucket recorded.
|
||||
stats.record_at(
|
||||
"b/i",
|
||||
&keys(&[("late", operand::STRING)]),
|
||||
Duration::ZERO,
|
||||
t0,
|
||||
);
|
||||
let got = stats.snapshot_at("b/i", t0 + WINDOW);
|
||||
assert!(
|
||||
got.truncated,
|
||||
"the later bucket's uncounted key is in the window"
|
||||
);
|
||||
assert_eq!(stats.indexes.lock().unwrap()["b/i"].last, 2);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,627 @@
|
||||
//! Indexed metadata keys through the VectorService: PutVectors derives the
|
||||
//! columns, and a query answers the same with or without them.
|
||||
|
||||
use std::sync::Arc;
|
||||
|
||||
use arrow_array::RecordBatch;
|
||||
use arrow_schema::Schema;
|
||||
use lance::Dataset;
|
||||
use lance::dataset::{BatchUDF, NewColumnTransform};
|
||||
use lance::index::DatasetIndexExt;
|
||||
use lance_index::IndexType;
|
||||
use lance_index::scalar::{BuiltinIndexType, ScalarIndexParams};
|
||||
use tonic::Request;
|
||||
use weed_lance_worker::metadata_index::{self, STATE_FIELD_META, State};
|
||||
use weed_vector_core::query::{self, Query};
|
||||
use weed_vector_core::table::VectorTable;
|
||||
|
||||
use crate::pb::vector::{self as pb, vector_service_server::VectorService};
|
||||
use crate::service::VectorServer;
|
||||
|
||||
const DIM: usize = 8;
|
||||
const ROWS: usize = 3000;
|
||||
const COLUMN: &str = "_mk_0";
|
||||
|
||||
/// How the engine answers a filter once `author` is indexed.
|
||||
#[derive(Debug, Clone, Copy, PartialEq)]
|
||||
enum Path {
|
||||
/// Through the column, at most the exact-match limit of rows: exact.
|
||||
Exact,
|
||||
/// Through the column, more rows: the vector index with the column's
|
||||
/// prefilter.
|
||||
Ivf,
|
||||
/// Not through the column.
|
||||
Json,
|
||||
}
|
||||
|
||||
/// S3 Vectors filters, the gateway's translation of each, and its path.
|
||||
const FILTERS: [(&str, &str, Path); 22] = [
|
||||
(
|
||||
"{\"author\":\"alice\"}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"alice\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"alice\"'), false))",
|
||||
Path::Ivf,
|
||||
),
|
||||
(
|
||||
"{\"author\":{\"$eq\":\"bob\"}}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"bob\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"bob\"'), false))",
|
||||
Path::Exact,
|
||||
),
|
||||
(
|
||||
"{\"author\":\"carol\"}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"carol\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"carol\"'), false))",
|
||||
Path::Exact,
|
||||
),
|
||||
(
|
||||
"{\"author\":\"x\"}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"x\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"x\"'), false))",
|
||||
Path::Exact,
|
||||
),
|
||||
(
|
||||
"{\"author\":\"7\"}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"7\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"7\"'), false))",
|
||||
Path::Exact,
|
||||
),
|
||||
(
|
||||
"{\"author\":7}",
|
||||
"(COALESCE(TRY_CAST(json_extract(`metadata`, '$[\"author\"]') AS DOUBLE) = 7, false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '7'), false))",
|
||||
Path::Json,
|
||||
),
|
||||
(
|
||||
"{\"author\":true}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') = 'true', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', 'true'), false))",
|
||||
Path::Json,
|
||||
),
|
||||
(
|
||||
"{\"author\":{\"$in\":[\"alice\",\"bob\",\"x\"]}}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') in ('\"alice\"', '\"bob\"', '\"x\"'), false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"alice\"'), false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"bob\"'), false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"x\"'), false))",
|
||||
Path::Ivf,
|
||||
),
|
||||
(
|
||||
"{\"author\":{\"$in\":[\"alice\",7]}}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') in ('\"alice\"'), false) OR COALESCE(TRY_CAST(json_extract(`metadata`, '$[\"author\"]') AS DOUBLE) in (7), false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"alice\"'), false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '7'), false))",
|
||||
Path::Json,
|
||||
),
|
||||
(
|
||||
"{\"author\":{\"$ne\":\"alice\"}}",
|
||||
"NOT (COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"alice\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"alice\"'), false))",
|
||||
Path::Json,
|
||||
),
|
||||
(
|
||||
"{\"author\":{\"$nin\":[\"alice\",\"bob\"]}}",
|
||||
"NOT (COALESCE(json_extract(`metadata`, '$[\"author\"]') in ('\"alice\"', '\"bob\"'), false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"alice\"'), false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"bob\"'), false))",
|
||||
Path::Json,
|
||||
),
|
||||
(
|
||||
"{\"author\":{\"$exists\":false}}",
|
||||
"NOT json_exists(`metadata`, '$[\"author\"]')",
|
||||
Path::Json,
|
||||
),
|
||||
(
|
||||
"{\"$and\":[{\"author\":\"alice\"},{\"genre\":\"g1\"}]}",
|
||||
"((COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"alice\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"alice\"'), false)) AND (COALESCE(json_extract(`metadata`, '$[\"genre\"]') = '\"g1\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"genre\"]', '\"g1\"'), false)))",
|
||||
Path::Ivf,
|
||||
),
|
||||
(
|
||||
"{\"$and\":[{\"author\":\"bob\"},{\"year\":{\"$gt\":2005}}]}",
|
||||
"((COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"bob\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"bob\"'), false)) AND TRY_CAST(json_extract(`metadata`, '$[\"year\"]') AS DOUBLE) > 2005)",
|
||||
Path::Exact,
|
||||
),
|
||||
(
|
||||
"{\"$or\":[{\"author\":\"bob\"},{\"genre\":\"g2\"}]}",
|
||||
"((COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"bob\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"bob\"'), false)) OR (COALESCE(json_extract(`metadata`, '$[\"genre\"]') = '\"g2\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"genre\"]', '\"g2\"'), false)))",
|
||||
Path::Json,
|
||||
),
|
||||
(
|
||||
"{\"author\":\"o'neil \\\"q\\\" \\\\ \\n\"}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"o''neil \\\"q\\\" \\\\ \\n\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"o''neil \\\"q\\\" \\\\ \\n\"'), false))",
|
||||
Path::Exact,
|
||||
),
|
||||
(
|
||||
"{\"author\":\"nobody\"}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"nobody\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"nobody\"'), false))",
|
||||
Path::Exact,
|
||||
),
|
||||
("{\"author\":{\"$in\":[]}}", "false", Path::Json),
|
||||
(
|
||||
"{\"genre\":\"g1\"}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"genre\"]') = '\"g1\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"genre\"]', '\"g1\"'), false))",
|
||||
Path::Json,
|
||||
),
|
||||
(
|
||||
"{\"author\":\"u5\"}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"u5\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"u5\"'), false))",
|
||||
Path::Exact,
|
||||
),
|
||||
(
|
||||
"{\"author\":\"ctl\\u0001x\"}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') = '\"ctl\\u{1}x\"', false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"ctl\\u0001x\"'), false))",
|
||||
Path::Json,
|
||||
),
|
||||
(
|
||||
"{\"author\":{\"$in\":[\"u5\",\"u6\"]}}",
|
||||
"(COALESCE(json_extract(`metadata`, '$[\"author\"]') in ('\"u5\"', '\"u6\"'), false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"u5\"'), false) OR COALESCE(json_array_contains(`metadata`, '$[\"author\"]', '\"u6\"'), false))",
|
||||
Path::Exact,
|
||||
),
|
||||
];
|
||||
|
||||
fn rng(seed: &mut u64) -> f32 {
|
||||
*seed = seed
|
||||
.wrapping_mul(6364136223846793005)
|
||||
.wrapping_add(1442695040888963407);
|
||||
((*seed >> 33) as f32 / (1u64 << 31) as f32) - 0.5
|
||||
}
|
||||
|
||||
fn vector_of(i: usize) -> Vec<f32> {
|
||||
let mut centre = (i % 16) as u64 + 1;
|
||||
let mut noise = i as u64 * 7919 + 13;
|
||||
(0..DIM)
|
||||
.map(|_| rng(&mut centre) * 4.0 + rng(&mut noise))
|
||||
.collect()
|
||||
}
|
||||
|
||||
fn author(i: usize) -> Option<serde_json::Value> {
|
||||
use serde_json::json;
|
||||
Some(match i % 100 {
|
||||
0..=9 => json!("alice"),
|
||||
10 => json!("bob"),
|
||||
11 => json!(["carol", "x"]),
|
||||
12 => json!(7),
|
||||
13 => json!("7"),
|
||||
14 => serde_json::Value::Null,
|
||||
15 => return None,
|
||||
16 => json!(true),
|
||||
17 => json!("o'neil \"q\" \\ \n"),
|
||||
18 => json!("ctl\u{1}x"),
|
||||
19 => json!(["alice", 3]),
|
||||
_ => json!(format!("u{}", i % 37)),
|
||||
})
|
||||
}
|
||||
|
||||
fn row(i: usize, author: Option<serde_json::Value>) -> pb::Vector {
|
||||
let mut meta = serde_json::json!({"genre": format!("g{}", i % 3), "year": 2000 + i % 10});
|
||||
if let Some(author) = author {
|
||||
meta["author"] = author;
|
||||
}
|
||||
let serde_json::Value::Object(meta) = meta else {
|
||||
unreachable!()
|
||||
};
|
||||
pb::Vector {
|
||||
key: format!("k{i}"),
|
||||
data: vector_of(i),
|
||||
metadata: Some(crate::service::json_to_struct(meta)),
|
||||
}
|
||||
}
|
||||
|
||||
struct Fixture {
|
||||
server: VectorServer,
|
||||
exact_off: VectorServer,
|
||||
table: pb::Table,
|
||||
}
|
||||
|
||||
impl Fixture {
|
||||
async fn new() -> Self {
|
||||
let bucket = format!(
|
||||
"mk-{:x}",
|
||||
std::time::SystemTime::now()
|
||||
.duration_since(std::time::UNIX_EPOCH)
|
||||
.unwrap()
|
||||
.as_nanos()
|
||||
);
|
||||
let table = pb::Table {
|
||||
id: vec![bucket.clone(), "vector".into(), "x".into()],
|
||||
location: format!("shared-memory://{bucket}/vector/x"),
|
||||
..Default::default()
|
||||
};
|
||||
let fixture = Self {
|
||||
server: VectorServer::new().with_schemes(&["shared-memory"]),
|
||||
exact_off: VectorServer::new()
|
||||
.with_schemes(&["shared-memory"])
|
||||
.with_exact_match_limit(Some(0)),
|
||||
table,
|
||||
};
|
||||
fixture
|
||||
.server
|
||||
.create_index(Request::new(pb::CreateIndexRequest {
|
||||
table: Some(fixture.table.clone()),
|
||||
dimension: DIM as u32,
|
||||
distance_metric: pb::DistanceMetric::L2 as i32,
|
||||
..Default::default()
|
||||
}))
|
||||
.await
|
||||
.unwrap();
|
||||
fixture
|
||||
}
|
||||
|
||||
async fn put(&self, vectors: Vec<pb::Vector>) {
|
||||
self.server
|
||||
.put_vectors(Request::new(pb::PutVectorsRequest {
|
||||
table: Some(self.table.clone()),
|
||||
vectors,
|
||||
}))
|
||||
.await
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
async fn dataset(&self, version: u64) -> Dataset {
|
||||
let dataset = Dataset::open(&self.table.location).await.unwrap();
|
||||
if version == 0 {
|
||||
dataset
|
||||
} else {
|
||||
dataset.checkout_version(version).await.unwrap()
|
||||
}
|
||||
}
|
||||
|
||||
/// Adds `author`'s column, indexes it and marks it ready, returning the
|
||||
/// version before it was ready.
|
||||
async fn index_author(&self) -> u64 {
|
||||
let mut dataset = self.dataset(0).await;
|
||||
let output = Arc::new(Schema::new(vec![metadata_index::field(
|
||||
COLUMN,
|
||||
"author",
|
||||
State::Building,
|
||||
)]));
|
||||
let schema = output.clone();
|
||||
dataset
|
||||
.add_columns(
|
||||
NewColumnTransform::BatchUDF(BatchUDF {
|
||||
mapper: Box::new(move |batch: &RecordBatch| {
|
||||
let column = metadata_index::column_from_metadata(
|
||||
batch.column_by_name("metadata").unwrap().as_ref(),
|
||||
"author",
|
||||
)
|
||||
.map_err(|e| lance::Error::invalid_input(e.to_string()))?;
|
||||
Ok(RecordBatch::try_new(schema.clone(), vec![column])?)
|
||||
}),
|
||||
output_schema: output,
|
||||
result_checkpoint: None,
|
||||
}),
|
||||
Some(vec!["metadata".to_string()]),
|
||||
None,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
dataset
|
||||
.create_index(
|
||||
&[COLUMN],
|
||||
IndexType::LabelList,
|
||||
Some(format!("{COLUMN}_idx")),
|
||||
&ScalarIndexParams::for_builtin(BuiltinIndexType::LabelList),
|
||||
true,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
let building = dataset.version().version;
|
||||
self.set_state(State::Ready).await;
|
||||
building
|
||||
}
|
||||
|
||||
async fn set_state(&self, state: State) -> u64 {
|
||||
let mut dataset = self.dataset(0).await;
|
||||
dataset
|
||||
.update_field_metadata()
|
||||
.update(COLUMN, [(STATE_FIELD_META, state.as_str())])
|
||||
.unwrap()
|
||||
.await
|
||||
.unwrap();
|
||||
dataset.version().version
|
||||
}
|
||||
|
||||
async fn query(
|
||||
&self,
|
||||
server: &VectorServer,
|
||||
version: u64,
|
||||
filter: &str,
|
||||
k: u32,
|
||||
v: &[f32],
|
||||
) -> Vec<(String, f32)> {
|
||||
let mut table = self.table.clone();
|
||||
table.version = version;
|
||||
server
|
||||
.query_vectors(Request::new(pb::QueryVectorsRequest {
|
||||
table: Some(table),
|
||||
query_vector: v.to_vec(),
|
||||
top_k: k,
|
||||
filter: filter.to_string(),
|
||||
return_distance: true,
|
||||
..Default::default()
|
||||
}))
|
||||
.await
|
||||
.unwrap()
|
||||
.into_inner()
|
||||
.vectors
|
||||
.into_iter()
|
||||
.map(|r| (r.key, r.distance))
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Exact filtered top-k at `version`.
|
||||
async fn flat(&self, version: u64, filter: &str, k: u32, v: &[f32]) -> Vec<(String, f32)> {
|
||||
let dataset = self.dataset(version).await;
|
||||
let table = VectorTable::resolve(&dataset, None, Some("key")).unwrap();
|
||||
query::flat(
|
||||
&dataset,
|
||||
&table,
|
||||
&Query {
|
||||
vector: v.to_vec(),
|
||||
k: k as usize,
|
||||
filter: Some(filter.to_string()),
|
||||
postfilter: false,
|
||||
distance: lance_linalg::distance::DistanceType::L2,
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: None,
|
||||
},
|
||||
)
|
||||
.await
|
||||
.unwrap()
|
||||
.into_iter()
|
||||
.map(|h| (h.key, h.distance))
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Every filter answers through the column as through the JSON at
|
||||
/// `json` (the same rows and indexes, the column not ready), and an
|
||||
/// exact answer as the exact filtered top-k.
|
||||
async fn compare(&self, json: u64, ready: u64) {
|
||||
for q in [7, 1234] {
|
||||
let v = vector_of(q);
|
||||
for (s3, filter, path) in FILTERS {
|
||||
for k in [10, 400] {
|
||||
let what = format!("{s3} k={k} q={q}");
|
||||
let exact = self.flat(json, filter, k, &v).await;
|
||||
assert_same(&self.flat(ready, filter, k, &v).await, &exact, &what);
|
||||
let json_ann = self.query(&self.server, json, filter, k, &v).await;
|
||||
let off = self.query(&self.exact_off, ready, filter, k, &v).await;
|
||||
assert_same(&off, &json_ann, &format!("{what}: indexed prefilter"));
|
||||
let got = self.query(&self.server, ready, filter, k, &v).await;
|
||||
let want = if path == Path::Exact {
|
||||
&exact
|
||||
} else {
|
||||
&json_ann
|
||||
};
|
||||
assert_same(&got, want, &format!("{what}: {path:?}"));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fn assert_same(got: &[(String, f32)], want: &[(String, f32)], what: &str) {
|
||||
assert_eq!(got.len(), want.len(), "{what}: {got:?} vs {want:?}");
|
||||
for (g, w) in got.iter().zip(want) {
|
||||
let same = g.0 == w.0 || (g.1 - w.1).abs() < 1e-4;
|
||||
assert!(
|
||||
same && ((g.1 - w.1).abs() < 1e-4 || (g.1.is_infinite() && w.1.is_infinite())),
|
||||
"{what}: {got:?} vs {want:?}"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
/// Indexed and JSON answers agree on mixed types, missing keys, arrays,
|
||||
/// null, untouched operators, and after updates, deletes and rows no
|
||||
/// scalar or vector index covers yet.
|
||||
#[tokio::test]
|
||||
async fn indexed_answers_match_the_json_path() {
|
||||
let fixture = Fixture::new().await;
|
||||
for start in (0..ROWS).step_by(300) {
|
||||
fixture
|
||||
.put((start..start + 300).map(|i| row(i, author(i))).collect())
|
||||
.await;
|
||||
}
|
||||
let mut dataset = fixture.dataset(0).await;
|
||||
weed_lance_worker::vector_index::build(&mut dataset, "vector", "vector_idx", 16, false)
|
||||
.await
|
||||
.unwrap();
|
||||
let json = fixture.index_author().await;
|
||||
let schema: Schema = fixture.dataset(0).await.schema().into();
|
||||
assert_eq!(
|
||||
metadata_index::indexed_keys(&schema)[0].state,
|
||||
Some(State::Ready)
|
||||
);
|
||||
fixture.compare(json, 0).await;
|
||||
|
||||
// Updates move rows between values, deletes drop some, and new rows land
|
||||
// in fragments neither index covers; PutVectors fills the column.
|
||||
fixture
|
||||
.put(
|
||||
(0..60)
|
||||
.map(|i| row(i, Some(serde_json::json!(["moved", "bob"]))))
|
||||
.chain((ROWS..ROWS + 200).map(|i| row(i, author(i))))
|
||||
.collect(),
|
||||
)
|
||||
.await;
|
||||
fixture
|
||||
.server
|
||||
.delete_vectors(Request::new(pb::DeleteVectorsRequest {
|
||||
table: Some(fixture.table.clone()),
|
||||
keys: (100..130).map(|i| format!("k{i}")).collect(),
|
||||
}))
|
||||
.await
|
||||
.unwrap();
|
||||
let json = fixture.set_state(State::Building).await;
|
||||
let ready = fixture.set_state(State::Ready).await;
|
||||
fixture.compare(json, ready).await;
|
||||
let moved = r#"(COALESCE(json_extract(`metadata`, '$["author"]') = '"moved"', false) OR COALESCE(json_array_contains(`metadata`, '$["author"]', '"moved"'), false))"#;
|
||||
let hits = fixture
|
||||
.query(&fixture.server, ready, moved, 100, &vector_of(0))
|
||||
.await;
|
||||
assert_eq!(hits.len(), 60);
|
||||
}
|
||||
|
||||
/// The planner counts and scores per scope: an exact answer over a fragment
|
||||
/// subset is that subset's exact top-k.
|
||||
#[tokio::test]
|
||||
async fn a_scoped_query_is_exact_within_its_fragments() {
|
||||
let fixture = Fixture::new().await;
|
||||
for start in (0..ROWS).step_by(300) {
|
||||
fixture
|
||||
.put((start..start + 300).map(|i| row(i, author(i))).collect())
|
||||
.await;
|
||||
}
|
||||
let mut dataset = fixture.dataset(0).await;
|
||||
weed_lance_worker::vector_index::build(&mut dataset, "vector", "vector_idx", 16, false)
|
||||
.await
|
||||
.unwrap();
|
||||
let json = fixture.index_author().await;
|
||||
let ready = fixture.dataset(0).await;
|
||||
let table = VectorTable::resolve(&ready, None, Some("key")).unwrap();
|
||||
let ids: Vec<u64> = ready.fragments().iter().map(|f| f.id).take(4).collect();
|
||||
let filter = FILTERS[1].1;
|
||||
let scoped = || Query {
|
||||
vector: vector_of(5),
|
||||
k: 10,
|
||||
filter: Some(filter.to_string()),
|
||||
postfilter: false,
|
||||
distance: lance_linalg::distance::DistanceType::L2,
|
||||
nprobes: None,
|
||||
index_segments: None,
|
||||
fragments: Some(ids.clone()),
|
||||
exact_match_limit: None,
|
||||
};
|
||||
let got = query::ann(&ready, &table, &scoped()).await.unwrap();
|
||||
let old = fixture.dataset(json).await;
|
||||
let want = query::flat(&old, &table, &scoped()).await.unwrap();
|
||||
assert_eq!(want.len(), 10);
|
||||
let pairs = |hits: Vec<weed_vector_core::Hit>| {
|
||||
hits.into_iter()
|
||||
.map(|h| (h.key, h.distance))
|
||||
.collect::<Vec<_>>()
|
||||
};
|
||||
assert_same(&pairs(got), &pairs(want), "scoped bob");
|
||||
}
|
||||
|
||||
/// The engine counts each index's filtered queries by key.
|
||||
#[tokio::test]
|
||||
async fn queries_are_counted_by_filter_key() {
|
||||
let fixture = Fixture::new().await;
|
||||
fixture
|
||||
.put((0..50).map(|i| row(i, author(i))).collect())
|
||||
.await;
|
||||
for (_, filter, _) in &FILTERS[..3] {
|
||||
fixture
|
||||
.query(&fixture.server, 0, filter, 5, &vector_of(1))
|
||||
.await;
|
||||
}
|
||||
let year = FILTERS[13].1;
|
||||
fixture
|
||||
.query(&fixture.server, 0, year, 5, &vector_of(1))
|
||||
.await;
|
||||
let stats = fixture
|
||||
.server
|
||||
.filter_stats(Request::new(pb::FilterStatsRequest {
|
||||
table: Some(fixture.table.clone()),
|
||||
}))
|
||||
.await
|
||||
.unwrap()
|
||||
.into_inner();
|
||||
let author = stats.keys.iter().find(|k| k.key == "author").unwrap();
|
||||
assert_eq!(author.queries, 4);
|
||||
assert!(author.string_operand && !author.number_operand);
|
||||
let year = stats.keys.iter().find(|k| k.key == "year").unwrap();
|
||||
assert_eq!(year.queries, 1);
|
||||
assert!(year.number_operand && !year.string_operand);
|
||||
}
|
||||
|
||||
/// A PutVectors that opened the table before its key column was added and
|
||||
/// commits after: Lance rebases the write and its rows hold NULL in the new
|
||||
/// column, which the write then fills from the rows' metadata.
|
||||
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
|
||||
async fn a_write_that_raced_the_column_add_fills_the_column() {
|
||||
let fixture = Fixture::new().await;
|
||||
fixture
|
||||
.put((0..300).map(|i| row(i, author(i))).collect())
|
||||
.await;
|
||||
let unhealed = fixture.dataset(0).await;
|
||||
let healed = fixture.dataset(0).await;
|
||||
fixture.index_author().await;
|
||||
let nulls = |dataset: Dataset| async move {
|
||||
dataset
|
||||
.count_rows(Some(format!("{COLUMN} IS NULL")))
|
||||
.await
|
||||
.unwrap()
|
||||
};
|
||||
let rows: Vec<pb::Vector> = (250..400).map(|i| row(i, author(i))).collect();
|
||||
|
||||
let written = crate::service::merge_vectors(unhealed, &rows)
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(written.schema().field(COLUMN).is_some());
|
||||
assert!(nulls(written).await >= 100, "the race is reproduced");
|
||||
|
||||
let written = crate::service::write_vectors(healed, &rows).await.unwrap();
|
||||
assert_eq!(nulls(written.clone()).await, 0);
|
||||
let filter = FILTERS[1].1;
|
||||
let latest = written.version().version;
|
||||
let v = vector_of(5);
|
||||
assert_same(
|
||||
&fixture
|
||||
.query(&fixture.server, latest, filter, 400, &v)
|
||||
.await,
|
||||
&fixture.flat(latest, filter, 400, &v).await,
|
||||
"bob after the race",
|
||||
);
|
||||
assert_eq!(fixture.flat(latest, filter, 400, &v).await.len(), 4);
|
||||
}
|
||||
|
||||
/// Two writes updating the same keys raced the column add, and the first
|
||||
/// one's fill commits last: each write's rows get the values of its own
|
||||
/// metadata, not the ones derived before it or from the other write.
|
||||
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
|
||||
async fn a_write_that_raced_the_column_add_derives_its_updated_rows() {
|
||||
let fixture = Fixture::new().await;
|
||||
fixture
|
||||
.put((0..300).map(|i| row(i, author(i))).collect())
|
||||
.await;
|
||||
let first = fixture.dataset(0).await;
|
||||
let second = fixture.dataset(0).await;
|
||||
let written: Schema = first.schema().into();
|
||||
fixture.index_author().await;
|
||||
let rows = |name: &str| -> Vec<pb::Vector> {
|
||||
(250..300)
|
||||
.map(|i| row(i, Some(serde_json::json!(name))))
|
||||
.collect()
|
||||
};
|
||||
let keys: Vec<String> = (250..300).map(|i| format!("k{i}")).collect();
|
||||
|
||||
let first = crate::service::merge_vectors(first, &rows("alice"))
|
||||
.await
|
||||
.unwrap();
|
||||
let second = crate::service::merge_vectors(second, &rows("bob"))
|
||||
.await
|
||||
.unwrap();
|
||||
crate::service::heal_columns(second, &written, &keys)
|
||||
.await
|
||||
.unwrap();
|
||||
crate::service::heal_columns(first, &written, &keys)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let latest = fixture.dataset(0).await;
|
||||
let count = |filter: String| {
|
||||
let latest = latest.clone();
|
||||
async move { latest.count_rows(Some(filter)).await.unwrap() }
|
||||
};
|
||||
assert_eq!(count(format!("{COLUMN} IS NULL")).await, 0);
|
||||
for (name, filter) in [("alice", FILTERS[0].1), ("bob", FILTERS[1].1)] {
|
||||
assert_eq!(
|
||||
count(format!("array_has({COLUMN}, '{name}')")).await,
|
||||
count(filter.to_string()).await,
|
||||
"{name}"
|
||||
);
|
||||
}
|
||||
let mut got = fixture
|
||||
.server
|
||||
.get_vectors(Request::new(pb::GetVectorsRequest {
|
||||
table: Some(fixture.table.clone()),
|
||||
keys: keys.clone(),
|
||||
return_data: true,
|
||||
return_metadata: true,
|
||||
}))
|
||||
.await
|
||||
.unwrap()
|
||||
.into_inner()
|
||||
.vectors;
|
||||
got.sort_by_key(|v| v.key[1..].parse::<usize>().unwrap());
|
||||
assert_eq!(got, rows("bob"));
|
||||
}
|
||||
@@ -1,5 +1,12 @@
|
||||
//! The VectorService gRPC server the S3 gateway talks to.
|
||||
|
||||
// PutVectors awaits two Lance merge_insert futures; proving the handler
|
||||
// future Send takes deeper trait recursion than the default.
|
||||
#![recursion_limit = "256"]
|
||||
|
||||
pub mod filter_stats;
|
||||
#[cfg(test)]
|
||||
mod indexed_keys_tests;
|
||||
pub mod metrics;
|
||||
pub mod observed;
|
||||
pub mod read_cache;
|
||||
|
||||
@@ -52,6 +52,11 @@ struct Args {
|
||||
/// tenth of the index's partitions, at least 8; more under a filter.
|
||||
#[arg(long, env = "WEED_VECTOR_NPROBES")]
|
||||
nprobes: Option<std::num::NonZeroUsize>,
|
||||
/// A filtered query whose indexed metadata keys match at most this many
|
||||
/// rows scores them exactly instead of searching the vector index; 0
|
||||
/// never does.
|
||||
#[arg(long, env = "WEED_VECTOR_EXACT_MATCH_LIMIT", default_value_t = weed_vector_core::query::DEFAULT_EXACT_MATCH_LIMIT)]
|
||||
exact_match_limit: usize,
|
||||
/// The cluster's security.toml: [grpc.vector] for this server,
|
||||
/// [grpc.client] for the masters and filers, https.client for volume
|
||||
/// servers under HTTPS, jwt.signing.read.key for signed volume reads,
|
||||
@@ -170,6 +175,7 @@ async fn main() -> Result<()> {
|
||||
.then(|| ReadCache::new(args.read_cache_mb << 20).with_metrics(metrics.clone()));
|
||||
let mut service = VectorServer::new()
|
||||
.with_nprobes(args.nprobes.map(std::num::NonZeroUsize::get))
|
||||
.with_exact_match_limit(Some(args.exact_match_limit))
|
||||
.with_lance_caches(args.index_cache_mb << 20, args.metadata_cache_mb << 20)
|
||||
.with_storage(reads);
|
||||
if let Some(cache) = &cache {
|
||||
|
||||
@@ -10,6 +10,10 @@ use tonic_health::{ServingStatus, server::HealthReporter};
|
||||
|
||||
use crate::read_cache::ReadCache;
|
||||
|
||||
/// The gRPC health service an engine reports serving when its writes derive
|
||||
/// the indexed metadata key columns.
|
||||
pub const METADATA_COLUMNS_CAPABILITY: &str = "weed.vector.capability.metadata_columns";
|
||||
|
||||
#[derive(Clone)]
|
||||
pub struct Metrics {
|
||||
pub registry: Registry,
|
||||
@@ -120,6 +124,11 @@ impl Metrics {
|
||||
health
|
||||
.set_service_status("vector_pb.VectorService", status)
|
||||
.await;
|
||||
// A capability, not readiness: the admin refuses to index a
|
||||
// metadata key while an engine without it could write the table.
|
||||
health
|
||||
.set_service_status(METADATA_COLUMNS_CAPABILITY, ServingStatus::Serving)
|
||||
.await;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -78,6 +78,15 @@ impl VectorService for ObservedService {
|
||||
}
|
||||
result
|
||||
}
|
||||
async fn filter_stats(
|
||||
&self,
|
||||
request: Request<pb::FilterStatsRequest>,
|
||||
) -> Result<Response<pb::FilterStatsResponse>, Status> {
|
||||
let mut in_flight = self.metrics.start("FilterStats");
|
||||
let result = self.inner.filter_stats(request).await;
|
||||
in_flight.complete(result.as_ref().err().map(|e| e.code()));
|
||||
result
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
|
||||
@@ -19,7 +19,9 @@ use weed_lance_worker::catalog::TableDescription;
|
||||
use weed_lance_worker::dataset;
|
||||
use weed_lance_worker::direct_read::{DirectReads, Wrappers};
|
||||
use weed_lance_worker::jobs::vector_index::is_vector_table;
|
||||
use weed_lance_worker::metadata_index;
|
||||
use weed_vector_core::index;
|
||||
use weed_vector_core::indexed_filter;
|
||||
use weed_vector_core::maintenance::SharedLeases;
|
||||
use weed_vector_core::query::{self, Query};
|
||||
use weed_vector_core::table::VectorTable;
|
||||
@@ -167,14 +169,13 @@ fn batch_of(vectors: &[pb::Vector], dimension: usize, schema: Arc<Schema>) -> Re
|
||||
};
|
||||
let vectors_array =
|
||||
FixedSizeListArray::try_new(item_field.clone(), dimension as i32, values, None)?;
|
||||
let metas = vectors
|
||||
let json: Vec<Option<serde_json::Value>> = vectors
|
||||
.iter()
|
||||
.map(|v| {
|
||||
v.metadata
|
||||
.as_ref()
|
||||
.map(|m| serde_json::to_string(&struct_to_json(m)))
|
||||
.transpose()
|
||||
})
|
||||
.map(|v| v.metadata.as_ref().map(struct_to_json))
|
||||
.collect();
|
||||
let metas = json
|
||||
.iter()
|
||||
.map(|m| m.as_ref().map(serde_json::to_string).transpose())
|
||||
.collect::<Result<Vec<_>, _>>()?;
|
||||
// The stored column is lance's jsonb (LargeBinary) once the field carries
|
||||
// the arrow.json extension; encode the strings, else keep the Utf8 batch.
|
||||
@@ -187,11 +188,144 @@ fn batch_of(vectors: &[pb::Vector], dimension: usize, schema: Arc<Schema>) -> Re
|
||||
}
|
||||
_ => Arc::new(StringArray::from(metas)),
|
||||
};
|
||||
RecordBatch::try_new(
|
||||
schema,
|
||||
vec![Arc::new(keys), Arc::new(vectors_array), metadata_array],
|
||||
let (keys, vectors_array): (ArrayRef, ArrayRef) = (Arc::new(keys), Arc::new(vectors_array));
|
||||
// An indexed metadata key's column is derived from the row's metadata,
|
||||
// whatever the key's state.
|
||||
let columns = schema
|
||||
.fields()
|
||||
.iter()
|
||||
.map(|field| match field.name().as_str() {
|
||||
KEY_COLUMN => Ok(keys.clone()),
|
||||
VECTOR_COLUMN => Ok(vectors_array.clone()),
|
||||
METADATA_COLUMN => Ok(metadata_array.clone()),
|
||||
name => match metadata_index::indexed_key(field) {
|
||||
Some(indexed) => Ok(metadata_index::column_from_json(
|
||||
json.iter().map(Option::as_ref),
|
||||
&indexed.key,
|
||||
)),
|
||||
None => bail!("the table has a column {name} that PutVectors cannot fill"),
|
||||
},
|
||||
})
|
||||
.collect::<Result<Vec<_>>>()?;
|
||||
RecordBatch::try_new(schema, columns).map_err(Into::into)
|
||||
}
|
||||
|
||||
/// Upserts `vectors` by key into `dataset`, the version the request opened,
|
||||
/// then fills the indexed-key columns a concurrent column add left empty.
|
||||
pub(crate) async fn write_vectors(
|
||||
dataset: Dataset,
|
||||
vectors: &[pb::Vector],
|
||||
) -> Result<Dataset, Status> {
|
||||
let written = Arc::new(Into::<arrow_schema::Schema>::into(dataset.schema()));
|
||||
let dataset = merge_vectors(dataset, vectors).await?;
|
||||
let keys: Vec<String> = vectors.iter().map(|v| v.key.clone()).collect();
|
||||
heal_columns(dataset, &written, &keys)
|
||||
.await
|
||||
.map_err(internal)
|
||||
}
|
||||
|
||||
/// The upsert itself, in the schema of the version `dataset` is at.
|
||||
pub(crate) async fn merge_vectors(
|
||||
dataset: Dataset,
|
||||
vectors: &[pb::Vector],
|
||||
) -> Result<Dataset, Status> {
|
||||
let dimension = VectorTable::resolve(&dataset, None, Some(KEY_COLUMN))
|
||||
.map_err(invalid)?
|
||||
.dimension;
|
||||
let batch = batch_of(
|
||||
vectors,
|
||||
dimension,
|
||||
Arc::new(Into::<arrow_schema::Schema>::into(dataset.schema())),
|
||||
)
|
||||
.map_err(Into::into)
|
||||
.map_err(invalid)?;
|
||||
// Upsert by key in one merge commit: no window where the old rows are
|
||||
// already deleted, and a losing writer fails the request instead of
|
||||
// leaving duplicate keys.
|
||||
let mut builder = MergeInsertBuilder::try_new(Arc::new(dataset), vec![KEY_COLUMN.to_string()])
|
||||
.map_err(internal)?;
|
||||
builder.when_matched(WhenMatched::UpdateAll);
|
||||
builder.when_not_matched(WhenNotMatched::InsertAll);
|
||||
let (dataset, _stats) = builder
|
||||
.try_build()
|
||||
.map_err(internal)?
|
||||
.execute_batches(vec![batch])
|
||||
.await
|
||||
.map_err(internal)?;
|
||||
Ok(Arc::unwrap_or_clone(dataset))
|
||||
}
|
||||
|
||||
/// Attempts [`heal_columns`] makes against writes committing meanwhile.
|
||||
const HEAL_ATTEMPTS: usize = 10;
|
||||
|
||||
/// Lance rebases a write onto a column add committed after the write opened
|
||||
/// its version: the rows it inserted hold NULL in the new column and the
|
||||
/// rows it updated keep the value derived from their old metadata. Derive
|
||||
/// such columns again for the rows of `keys` from their stored metadata.
|
||||
pub(crate) async fn heal_columns(
|
||||
mut dataset: Dataset,
|
||||
written: &Schema,
|
||||
keys: &[String],
|
||||
) -> Result<Dataset> {
|
||||
for _ in 0..HEAL_ATTEMPTS {
|
||||
let schema: Schema = dataset.schema().into();
|
||||
let missing: Vec<metadata_index::IndexedKey> = metadata_index::indexed_keys(&schema)
|
||||
.into_iter()
|
||||
.filter(|k| written.field_with_name(&k.column).is_err())
|
||||
.collect();
|
||||
if missing.is_empty() || keys.is_empty() {
|
||||
return Ok(dataset);
|
||||
}
|
||||
let mut scanner = dataset.scan();
|
||||
scanner
|
||||
.filter(&key_list(keys))?
|
||||
.project(&[KEY_COLUMN, METADATA_COLUMN])?;
|
||||
let rows: Vec<RecordBatch> = scanner.try_into_stream().await?.try_collect().await?;
|
||||
let mut fields = vec![schema.field_with_name(KEY_COLUMN)?.clone()];
|
||||
for k in &missing {
|
||||
fields.push(schema.field_with_name(&k.column)?.clone());
|
||||
}
|
||||
let patch_schema = Arc::new(Schema::new(fields));
|
||||
let mut patches = Vec::new();
|
||||
for batch in rows.iter().filter(|b| b.num_rows() > 0) {
|
||||
let (Some(keys), Some(metadata)) = (
|
||||
batch.column_by_name(KEY_COLUMN),
|
||||
batch.column_by_name(METADATA_COLUMN),
|
||||
) else {
|
||||
bail!("the scan did not return keys and metadata");
|
||||
};
|
||||
let mut columns = vec![keys.clone()];
|
||||
for k in &missing {
|
||||
columns.push(metadata_index::column_from_metadata(
|
||||
metadata.as_ref(),
|
||||
&k.key,
|
||||
)?);
|
||||
}
|
||||
patches.push(RecordBatch::try_new(patch_schema.clone(), columns)?);
|
||||
}
|
||||
if patches.is_empty() {
|
||||
return Ok(dataset);
|
||||
}
|
||||
// Lance's own retry would join these values onto rows a later write
|
||||
// replaced; derive them again from the version that write left.
|
||||
let mut builder =
|
||||
MergeInsertBuilder::try_new(Arc::new(dataset.clone()), vec![KEY_COLUMN.to_string()])?;
|
||||
builder
|
||||
.when_matched(WhenMatched::UpdateAll)
|
||||
.when_not_matched(WhenNotMatched::DoNothing)
|
||||
.conflict_retries(0);
|
||||
match builder.try_build()?.execute_batches(patches).await {
|
||||
Ok((healed, _stats)) => {
|
||||
tracing::info!(
|
||||
rows = rows.iter().map(|b| b.num_rows()).sum::<usize>(),
|
||||
"derived indexed metadata key columns a concurrent column add left stale"
|
||||
);
|
||||
return Ok(Arc::unwrap_or_clone(healed));
|
||||
}
|
||||
Err(lance::Error::TooMuchWriteContention { .. }) => dataset.checkout_latest().await?,
|
||||
Err(e) => return Err(e.into()),
|
||||
}
|
||||
}
|
||||
bail!("writes kept replacing the rows while their indexed key columns were derived")
|
||||
}
|
||||
|
||||
fn struct_to_json(s: &Struct) -> serde_json::Value {
|
||||
@@ -230,7 +364,7 @@ fn json_to_value(v: serde_json::Value) -> Value {
|
||||
Value { kind: Some(kind) }
|
||||
}
|
||||
|
||||
fn json_to_struct(map: serde_json::Map<String, serde_json::Value>) -> Struct {
|
||||
pub(crate) fn json_to_struct(map: serde_json::Map<String, serde_json::Value>) -> Struct {
|
||||
Struct {
|
||||
fields: map
|
||||
.into_iter()
|
||||
@@ -528,6 +662,8 @@ pub struct VectorServer {
|
||||
lance_cache_bytes: (usize, usize),
|
||||
leases: SharedLeases,
|
||||
nprobes: Option<usize>,
|
||||
exact_match_limit: Option<usize>,
|
||||
filter_stats: crate::filter_stats::FilterStats,
|
||||
/// URI schemes a table's location may have.
|
||||
schemes: &'static [&'static str],
|
||||
}
|
||||
@@ -551,6 +687,8 @@ impl VectorServer {
|
||||
handles: moka::sync::Cache::new(MAX_HANDLES),
|
||||
leases: SharedLeases::default(),
|
||||
nprobes: None,
|
||||
exact_match_limit: None,
|
||||
filter_stats: Default::default(),
|
||||
schemes: &["s3"],
|
||||
}
|
||||
}
|
||||
@@ -568,6 +706,13 @@ impl VectorServer {
|
||||
self
|
||||
}
|
||||
|
||||
/// Matches of a filter's indexed metadata keys scored exactly instead of
|
||||
/// searched through the vector index, at most; None keeps the default.
|
||||
pub fn with_exact_match_limit(mut self, limit: Option<usize>) -> Self {
|
||||
self.exact_match_limit = limit;
|
||||
self
|
||||
}
|
||||
|
||||
/// Keep tables on the filers and volume servers, not through the gateway.
|
||||
/// Unset only for tests on an in-process store.
|
||||
pub fn with_storage(mut self, storage: DirectReads) -> Self {
|
||||
@@ -808,29 +953,7 @@ impl VectorService for VectorServer {
|
||||
version: dataset.version().version,
|
||||
}));
|
||||
}
|
||||
let dimension = VectorTable::resolve(&dataset, None, Some(KEY_COLUMN))
|
||||
.map_err(invalid)?
|
||||
.dimension;
|
||||
let batch = batch_of(
|
||||
&req.vectors,
|
||||
dimension,
|
||||
Arc::new(Into::<arrow_schema::Schema>::into(dataset.schema())),
|
||||
)
|
||||
.map_err(invalid)?;
|
||||
// Upsert by key in one merge commit: no window where the old rows are
|
||||
// already deleted, and a losing writer fails the request instead of
|
||||
// leaving duplicate keys.
|
||||
let mut builder =
|
||||
MergeInsertBuilder::try_new(Arc::new(dataset), vec![KEY_COLUMN.to_string()])
|
||||
.map_err(internal)?;
|
||||
builder.when_matched(WhenMatched::UpdateAll);
|
||||
builder.when_not_matched(WhenNotMatched::InsertAll);
|
||||
let (dataset, _stats) = builder
|
||||
.try_build()
|
||||
.map_err(internal)?
|
||||
.execute_batches(vec![batch])
|
||||
.await
|
||||
.map_err(internal)?;
|
||||
let dataset = write_vectors(dataset, &req.vectors).await?;
|
||||
Ok(Response::new(pb::PutVectorsResponse {
|
||||
version: dataset.version().version,
|
||||
}))
|
||||
@@ -908,14 +1031,9 @@ impl VectorService for VectorServer {
|
||||
0 => DEFAULT_PAGE,
|
||||
n => n.min(MAX_PAGE),
|
||||
};
|
||||
// A purge keeps only the latest version, so lease the one this page reads.
|
||||
let _lease = self.leases.try_pin(&dataset).await.map_err(internal)?;
|
||||
if segments > 1 {
|
||||
// Data and metadata come from a second read of this version, so
|
||||
// lease it as get_vectors does.
|
||||
let _lease = if columns.len() > 1 {
|
||||
self.leases.try_pin(&dataset).await.map_err(internal)?
|
||||
} else {
|
||||
None
|
||||
};
|
||||
let (vectors, next) = list_segment(
|
||||
&dataset,
|
||||
&columns,
|
||||
@@ -953,6 +1071,7 @@ impl VectorService for VectorServer {
|
||||
&self,
|
||||
request: Request<pb::QueryVectorsRequest>,
|
||||
) -> Result<Response<pb::QueryVectorsResponse>, Status> {
|
||||
let started = std::time::Instant::now();
|
||||
let req = request.into_inner();
|
||||
let table = req
|
||||
.table
|
||||
@@ -962,6 +1081,11 @@ impl VectorService for VectorServer {
|
||||
// while this query runs against it.
|
||||
let _lease = self.leases.try_pin(&dataset).await.map_err(internal)?;
|
||||
let resolved = VectorTable::resolve(&dataset, None, Some(KEY_COLUMN)).map_err(invalid)?;
|
||||
let filter_keys = if req.filter.is_empty() {
|
||||
Default::default()
|
||||
} else {
|
||||
indexed_filter::filter_keys(&dataset, &req.filter).unwrap_or_default()
|
||||
};
|
||||
if req.query_vector.len() != resolved.dimension {
|
||||
return Err(Status::invalid_argument(format!(
|
||||
"query vector carries {} floats, the index dimension is {}",
|
||||
@@ -986,6 +1110,7 @@ impl VectorService for VectorServer {
|
||||
nprobes: self.nprobes,
|
||||
index_segments: None,
|
||||
fragments: None,
|
||||
exact_match_limit: self.exact_match_limit,
|
||||
};
|
||||
let hits = query::ann(&dataset, &resolved, &query)
|
||||
.await
|
||||
@@ -1061,8 +1186,23 @@ impl VectorService for VectorServer {
|
||||
data: data_map.remove(&hit.key).unwrap_or_default(),
|
||||
});
|
||||
}
|
||||
self.filter_stats
|
||||
.record(&table.id.join("/"), &filter_keys, started.elapsed());
|
||||
Ok(Response::new(pb::QueryVectorsResponse { vectors }))
|
||||
}
|
||||
|
||||
async fn filter_stats(
|
||||
&self,
|
||||
request: Request<pb::FilterStatsRequest>,
|
||||
) -> Result<Response<pb::FilterStatsResponse>, Status> {
|
||||
let table = request
|
||||
.into_inner()
|
||||
.table
|
||||
.ok_or_else(|| Status::invalid_argument("missing table"))?;
|
||||
Ok(Response::new(
|
||||
self.filter_stats.snapshot(&table.id.join("/")),
|
||||
))
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
|
||||
@@ -147,6 +147,7 @@ service VolumeServer {
|
||||
message BatchDeleteRequest {
|
||||
repeated string file_ids = 1;
|
||||
bool skip_cookie_check = 2;
|
||||
bool fsync = 3;
|
||||
}
|
||||
|
||||
message BatchDeleteResponse {
|
||||
|
||||
@@ -416,6 +416,7 @@ async fn run(
|
||||
.to_string_lossy()
|
||||
.into_owned()
|
||||
},
|
||||
ec_lifecycle_locks: std::sync::Mutex::new(std::collections::HashMap::new()),
|
||||
ec_decodes_in_flight: std::sync::Mutex::new(std::collections::HashSet::new()),
|
||||
volume_copies_in_flight,
|
||||
ec_decode_tail: std::sync::Mutex::new(std::collections::HashSet::new()),
|
||||
|
||||
@@ -85,6 +85,19 @@ pub static VACUUMING_COMMIT_COUNTER: LazyLock<IntCounterVec> = LazyLock::new(||
|
||||
.expect("metric can be created")
|
||||
});
|
||||
|
||||
/// Live needles vacuum dropped because their data could not be read back
|
||||
/// intact, with label `collection`.
|
||||
pub static VACUUMING_DROPPED_NEEDLES_COUNTER: LazyLock<IntCounterVec> = LazyLock::new(|| {
|
||||
IntCounterVec::new(
|
||||
Opts::new(
|
||||
"SeaweedFS_volumeServer_vacuuming_dropped_needles",
|
||||
"Counter of live needles dropped by vacuum because their data could not be read back intact.",
|
||||
),
|
||||
&["collection"],
|
||||
)
|
||||
.expect("metric can be created")
|
||||
});
|
||||
|
||||
/// Vacuuming duration histogram with label `type` (compact/commit).
|
||||
pub static VACUUMING_HISTOGRAM: LazyLock<HistogramVec> = LazyLock::new(|| {
|
||||
HistogramVec::new(
|
||||
@@ -402,6 +415,7 @@ pub fn register_metrics() {
|
||||
Box::new(VACUUMING_COMPACT_COUNTER.clone()),
|
||||
Box::new(VACUUMING_COMMIT_COUNTER.clone()),
|
||||
Box::new(VACUUMING_HISTOGRAM.clone()),
|
||||
Box::new(VACUUMING_DROPPED_NEEDLES_COUNTER.clone()),
|
||||
Box::new(VOLUME_GAUGE.clone()),
|
||||
Box::new(READ_ONLY_VOLUME_GAUGE.clone()),
|
||||
Box::new(MAX_VOLUMES.clone()),
|
||||
|
||||
@@ -106,6 +106,39 @@ pub fn decode_jwt(signing_key: &SigningKey, token: &str) -> Result<FileIdClaims,
|
||||
Ok(data.claims)
|
||||
}
|
||||
|
||||
/// Reports a signed, fid-bound write token whose only failure is expiry. It
|
||||
/// never authorizes a request. Mirrors Go's `security.IsExpiredVolumeJwt`.
|
||||
pub fn is_expired_volume_jwt(signing_key: &SigningKey, token: &str, expected_fid: &str) -> bool {
|
||||
match decode_jwt(signing_key, token) {
|
||||
Err(JwtError::Jwt(e))
|
||||
if matches!(e.kind(), jsonwebtoken::errors::ErrorKind::ExpiredSignature) => {}
|
||||
_ => return false,
|
||||
}
|
||||
|
||||
#[derive(Deserialize)]
|
||||
struct ExpiredClaims {
|
||||
fid: Option<String>,
|
||||
iat: Option<u64>,
|
||||
}
|
||||
let mut validation = Validation::new(Algorithm::HS256);
|
||||
validation.required_spec_claims.clear();
|
||||
validation.validate_exp = false;
|
||||
validation.validate_nbf = true;
|
||||
validation.leeway = 0;
|
||||
let Ok(data) = decode::<ExpiredClaims>(
|
||||
token,
|
||||
&DecodingKey::from_secret(&signing_key.0),
|
||||
&validation,
|
||||
) else {
|
||||
return false;
|
||||
};
|
||||
let now = SystemTime::now()
|
||||
.duration_since(UNIX_EPOCH)
|
||||
.unwrap_or_default()
|
||||
.as_secs();
|
||||
data.claims.fid.as_deref() == Some(expected_fid) && data.claims.iat.is_none_or(|iat| iat <= now)
|
||||
}
|
||||
|
||||
// ============================================================================
|
||||
// Guard
|
||||
// ============================================================================
|
||||
@@ -410,6 +443,53 @@ mod tests {
|
||||
assert!(decode_jwt(&key2, &token).is_err());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_is_expired_volume_jwt_classifies_expiry_only() {
|
||||
let key = SigningKey::from_string("write-key");
|
||||
let fid = "3,01637037d6";
|
||||
let now = SystemTime::now()
|
||||
.duration_since(UNIX_EPOCH)
|
||||
.unwrap()
|
||||
.as_secs();
|
||||
let sign = |claims: serde_json::Value, key: &SigningKey| {
|
||||
encode(
|
||||
&Header::new(Algorithm::HS256),
|
||||
&claims,
|
||||
&EncodingKey::from_secret(&key.0),
|
||||
)
|
||||
.unwrap()
|
||||
};
|
||||
let expired = sign(serde_json::json!({"fid": fid, "exp": now - 10}), &key);
|
||||
assert!(is_expired_volume_jwt(&key, &expired, fid));
|
||||
assert!(!is_expired_volume_jwt(&key, &expired, "3,01637037d7"));
|
||||
assert!(!is_expired_volume_jwt(
|
||||
&SigningKey::from_string("other-key"),
|
||||
&expired,
|
||||
fid
|
||||
));
|
||||
assert!(!is_expired_volume_jwt(&SigningKey(vec![]), &expired, fid));
|
||||
let immature = sign(
|
||||
serde_json::json!({"fid": fid, "exp": now - 10, "nbf": now + 60}),
|
||||
&key,
|
||||
);
|
||||
assert!(!is_expired_volume_jwt(&key, &immature, fid));
|
||||
let future_issued = sign(
|
||||
serde_json::json!({"fid": fid, "exp": now - 10, "iat": now + 60}),
|
||||
&key,
|
||||
);
|
||||
assert!(!is_expired_volume_jwt(&key, &future_issued, fid));
|
||||
let live = sign(serde_json::json!({"fid": fid, "exp": now + 60}), &key);
|
||||
assert!(!is_expired_volume_jwt(&key, &live, fid));
|
||||
let unsigned = format!(
|
||||
"eyJhbGciOiJub25lIiwidHlwIjoiSldUIn0.{}.",
|
||||
base64::Engine::encode(
|
||||
&base64::engine::general_purpose::URL_SAFE_NO_PAD,
|
||||
serde_json::json!({"fid": fid, "exp": now - 10}).to_string()
|
||||
)
|
||||
);
|
||||
assert!(!is_expired_volume_jwt(&key, &unsigned, fid));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_guard_empty_whitelist() {
|
||||
let guard = Guard::new(&[], SigningKey(vec![]), 0, SigningKey(vec![]), 0);
|
||||
|
||||
File diff suppressed because it is too large.
Load diff
@@ -165,8 +165,10 @@ impl SourceReadRequest {
|
||||
fn served_from_source(&self, n: &Needle) -> bool {
|
||||
if self.is_head {
|
||||
// HEAD is meta-only unless the payload is needed to expand a
|
||||
// manifest or to answer an image transform's length.
|
||||
return !self.has_image_ops && !(n.is_chunk_manifest() && !self.bypass_cm);
|
||||
// manifest or to answer a decoded or transformed length.
|
||||
return !self.has_image_ops
|
||||
&& !n.is_compressed()
|
||||
&& !(n.is_chunk_manifest() && !self.bypass_cm);
|
||||
}
|
||||
self.direct(n) && (self.has_range || n.data_size > STREAMING_THRESHOLD)
|
||||
}
|
||||
@@ -483,6 +485,18 @@ fn extract_file_id(path: &str) -> String {
|
||||
format!("{},{}", parsed.vid, fid)
|
||||
}
|
||||
|
||||
fn is_multipart_form_data(headers: &HeaderMap) -> bool {
|
||||
headers
|
||||
.get(header::CONTENT_TYPE)
|
||||
.and_then(|value| value.to_str().ok())
|
||||
.and_then(|value| value.split(';').next())
|
||||
.is_some_and(|media_type| {
|
||||
media_type
|
||||
.trim()
|
||||
.eq_ignore_ascii_case("multipart/form-data")
|
||||
})
|
||||
}
|
||||
|
||||
fn streaming_chunk_size(read_buffer_size_bytes: usize, data_size: usize) -> usize {
|
||||
std::cmp::min(
|
||||
read_buffer_size_bytes.max(DEFAULT_STREAMING_CHUNK_SIZE),
|
||||
@@ -671,6 +685,7 @@ async fn batch_delete_file_ids(
|
||||
.batch_delete(volume_server_pb::BatchDeleteRequest {
|
||||
file_ids: batch.clone(),
|
||||
skip_cookie_check: true,
|
||||
fsync: false,
|
||||
})
|
||||
.await
|
||||
.map_err(|e| format!("batch delete {}: {}", grpc_addr, e))?
|
||||
@@ -846,7 +861,12 @@ async fn do_replicated_request(
|
||||
|
||||
futures.push(async move {
|
||||
match req_builder.send().await {
|
||||
Ok(r) if r.status().is_success() => Ok(()),
|
||||
Ok(r)
|
||||
if r.status().is_success()
|
||||
|| (allow_delete && r.status() == StatusCode::NOT_FOUND) =>
|
||||
{
|
||||
Ok(())
|
||||
}
|
||||
Ok(r) => {
|
||||
crate::metrics::UPLOAD_ERROR_COUNTER
|
||||
.with_label_values(&[&r.status().as_u16().to_string()])
|
||||
@@ -1329,6 +1349,7 @@ async fn get_or_head_handler_inner(
|
||||
&query,
|
||||
&ext,
|
||||
request_kind.has_image_ops,
|
||||
request_kind.has_range,
|
||||
&mut response_headers,
|
||||
) {
|
||||
ControlFlow::Continue(data) => data,
|
||||
@@ -1630,8 +1651,8 @@ async fn read_volume_needle(
|
||||
|
||||
let can_stream =
|
||||
can_direct_source_read && n.data_size > STREAMING_THRESHOLD && !has_range && !is_head;
|
||||
// HEAD is meta-only when served_from_source loaded no payload. A chunk
|
||||
// manifest without cm=false is read in full so expansion can run.
|
||||
// HEAD is meta-only when served_from_source loaded no payload. A compressed
|
||||
// needle, or a chunk manifest without cm=false, is read in full.
|
||||
let can_handle_head_from_meta = stream_info.is_some() && is_head;
|
||||
let can_handle_range_from_source = can_direct_source_read && has_range;
|
||||
|
||||
@@ -2026,6 +2047,7 @@ fn buffered_payload(
|
||||
query: &ReadQueryParams,
|
||||
ext: &str,
|
||||
needs_image_ops: bool,
|
||||
has_range: bool,
|
||||
response_headers: &mut HeaderMap,
|
||||
) -> ControlFlow<Response, Vec<u8>> {
|
||||
// Handle compressed data: if needle is compressed, either pass through or decompress
|
||||
@@ -2054,7 +2076,9 @@ fn buffered_payload(
|
||||
.get(header::ACCEPT_ENCODING)
|
||||
.and_then(|v| v.to_str().ok())
|
||||
.unwrap_or("");
|
||||
if accept_encoding.contains("gzip")
|
||||
// A range is over the decoded bytes, so only a whole read passes gzip through.
|
||||
if !has_range
|
||||
&& accept_encoding.contains("gzip")
|
||||
&& data.len() >= 2
|
||||
&& data[0] == 0x1f
|
||||
&& data[1] == 0x8b
|
||||
@@ -2777,14 +2801,28 @@ pub async fn post_handler(
|
||||
// JWT check for writes
|
||||
let file_id = extract_file_id(&path);
|
||||
let token = extract_jwt(&headers, request.uri());
|
||||
if state
|
||||
.guard
|
||||
.read()
|
||||
.unwrap()
|
||||
.check_jwt_for_file(token.as_deref(), &file_id, true)
|
||||
.is_err()
|
||||
{
|
||||
return json_error_with_query(StatusCode::UNAUTHORIZED, "wrong jwt", Some(&query));
|
||||
let expired_jwt = {
|
||||
let guard = state.guard.read().unwrap();
|
||||
match guard.check_jwt_for_file(token.as_deref(), &file_id, true) {
|
||||
Ok(()) => None,
|
||||
Err(_) => Some(
|
||||
is_multipart_form_data(&headers)
|
||||
&& token.as_deref().is_some_and(|token| {
|
||||
crate::security::is_expired_volume_jwt(&guard.signing_key, token, &file_id)
|
||||
}),
|
||||
),
|
||||
}
|
||||
};
|
||||
if let Some(expired_jwt) = expired_jwt {
|
||||
let mut response =
|
||||
json_error_with_query(StatusCode::UNAUTHORIZED, "wrong jwt", Some(&query));
|
||||
if expired_jwt {
|
||||
response.headers_mut().insert(
|
||||
"x-seaweed-write-outcome",
|
||||
header::HeaderValue::from_static("expired-jwt-before-append"),
|
||||
);
|
||||
}
|
||||
return response;
|
||||
}
|
||||
|
||||
// Upload throttling: check inflight bytes against limit
|
||||
@@ -3654,22 +3692,30 @@ pub async fn delete_handler(
|
||||
|
||||
// Read needle first to validate cookie (matching Go behavior)
|
||||
let original_cookie = cookie;
|
||||
let is_replicate = serde_urlencoded::from_str::<Vec<(String, String)>>(&del_query)
|
||||
.unwrap_or_default()
|
||||
.into_iter()
|
||||
.find(|(name, _)| name == "type")
|
||||
.is_some_and(|(_, value)| value == "replicate");
|
||||
let del_fields =
|
||||
serde_urlencoded::from_str::<Vec<(String, String)>>(&del_query).unwrap_or_default();
|
||||
let del_field = |key: &str| {
|
||||
del_fields
|
||||
.iter()
|
||||
.find(|(name, _)| name == key)
|
||||
.map(|(_, value)| value.as_str())
|
||||
};
|
||||
let is_replicate = del_field("type") == Some("replicate");
|
||||
let fsync = del_field("fsync") == Some("true");
|
||||
{
|
||||
let vol = {
|
||||
let store = state.store.read().unwrap();
|
||||
store.find_volume(vid).map(|(_, vol)| vol)
|
||||
};
|
||||
let replicated = vol
|
||||
.as_ref()
|
||||
.is_some_and(|v| v.super_block().replica_placement.get_copy_count() > 1);
|
||||
let mut found = vol
|
||||
.as_ref()
|
||||
.ok_or(crate::storage::volume::VolumeError::NotFound)
|
||||
.and_then(|vol| vol.read_needle_with_option(&mut n, &mut delete_read_option()));
|
||||
if found.is_err()
|
||||
&& is_replicate
|
||||
&& (is_replicate || replicated)
|
||||
&& let Some(vol) = &vol
|
||||
{
|
||||
// the write this delete undoes can still be queued here
|
||||
@@ -3678,7 +3724,42 @@ pub async fn delete_handler(
|
||||
}
|
||||
match found {
|
||||
Ok(_) => {}
|
||||
Err(_) => {
|
||||
Err(e) => {
|
||||
// 404 tells the forwarding replica the needle is gone here, so a
|
||||
// read that failed for any other reason must not answer it
|
||||
if !matches!(
|
||||
e,
|
||||
crate::storage::volume::VolumeError::NotFound
|
||||
| crate::storage::volume::VolumeError::Deleted
|
||||
) {
|
||||
return json_error_with_query(
|
||||
StatusCode::INTERNAL_SERVER_ERROR,
|
||||
format!("Deletion Failed: {}", e),
|
||||
Some(&del_query),
|
||||
);
|
||||
}
|
||||
// a retry of a delete whose replica fan-out failed finds nothing
|
||||
// here, but the other replicas may still hold the needle
|
||||
if !is_replicate
|
||||
&& replicated
|
||||
&& let Err(e) = do_replicated_request(
|
||||
&state,
|
||||
vid.0,
|
||||
Method::DELETE,
|
||||
&path,
|
||||
&del_query,
|
||||
&headers,
|
||||
None,
|
||||
)
|
||||
.await
|
||||
{
|
||||
tracing::error!("replicated delete failed: {}", e);
|
||||
return json_error_with_query(
|
||||
StatusCode::INTERNAL_SERVER_ERROR,
|
||||
format!("replication failed: {}", e),
|
||||
Some(&del_query),
|
||||
);
|
||||
}
|
||||
let result = DeleteResult { size: 0 };
|
||||
return json_response_with_params(
|
||||
StatusCode::NOT_FOUND,
|
||||
@@ -3760,7 +3841,16 @@ pub async fn delete_handler(
|
||||
Ok(vol) if vol.is_no_write_or_delete() => {
|
||||
Err(crate::storage::volume::VolumeError::ReadOnly(vid))
|
||||
}
|
||||
Ok(vol) => vol.delete_needle(&mut n),
|
||||
Ok(vol) if fsync => {
|
||||
tokio::task::spawn_blocking(move || vol.delete_needle(&mut n, true))
|
||||
.await
|
||||
.unwrap_or_else(|e| {
|
||||
Err(crate::storage::volume::VolumeError::Io(
|
||||
std::io::Error::other(e),
|
||||
))
|
||||
})
|
||||
}
|
||||
Ok(vol) => vol.delete_needle(&mut n, false),
|
||||
}
|
||||
};
|
||||
|
||||
@@ -4969,13 +5059,13 @@ fn try_gzip_data(data: &[u8]) -> Option<Vec<u8>> {
|
||||
}
|
||||
|
||||
fn maybe_decompress_gzip(data: &[u8]) -> Result<Vec<u8>, GunzipError> {
|
||||
use flate2::read::GzDecoder;
|
||||
use flate2::read::MultiGzDecoder;
|
||||
use std::io::Read;
|
||||
// Cap the output so a crafted, highly-compressible (gzip-bomb) needle cannot
|
||||
// OOM the server when decompressed on read or upload. take(limit+1) lets us
|
||||
// tell "exactly at the limit" apart from "over it", which we reject as
|
||||
// TooLarge so callers fail the request instead of silently using raw bytes.
|
||||
let mut decoder = GzDecoder::new(data).take(MAX_EXPANSION_BYTES + 1);
|
||||
let mut decoder = MultiGzDecoder::new(data).take(MAX_EXPANSION_BYTES + 1);
|
||||
let mut decompressed = Vec::new();
|
||||
decoder
|
||||
.read_to_end(&mut decompressed)
|
||||
@@ -5064,6 +5154,34 @@ mod tests {
|
||||
(addr, receipts)
|
||||
}
|
||||
|
||||
/// A replica that no longer holds the needle answers a forwarded delete
|
||||
/// with 404, which means it is gone there too.
|
||||
#[tokio::test]
|
||||
async fn test_replicated_delete_takes_a_replica_404_as_done() {
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let app = axum::Router::new().fallback(|| async { StatusCode::NOT_FOUND });
|
||||
let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
|
||||
let peer = listener.local_addr().unwrap();
|
||||
tokio::spawn(async move { axum::serve(listener, app).await.unwrap() });
|
||||
let state = remote_manifest_state(&tmp, spawn_lookup(peer).await);
|
||||
for (method, done) in [
|
||||
(axum::http::Method::DELETE, true),
|
||||
(axum::http::Method::POST, false),
|
||||
] {
|
||||
let sent = do_replicated_request(
|
||||
&state,
|
||||
1,
|
||||
method.clone(),
|
||||
"/1,01ab",
|
||||
"",
|
||||
&axum::http::HeaderMap::new(),
|
||||
None,
|
||||
)
|
||||
.await;
|
||||
assert_eq!(sent.is_ok(), done, "{method}: {sent:?}");
|
||||
}
|
||||
}
|
||||
|
||||
/// The whole replicated write path, not only the request builder: the
|
||||
/// replica receives the forward, never answers, and the write fails at
|
||||
/// the bound for its body with an error naming that replica.
|
||||
@@ -5465,6 +5583,83 @@ mod tests {
|
||||
assert_eq!(extract_jwt(&headers, &uri), None);
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn http_expired_write_jwt_is_marked_before_append() {
|
||||
use crate::security::SigningKey;
|
||||
use jsonwebtoken::{Algorithm, EncodingKey, Header, encode};
|
||||
use tower::ServiceExt;
|
||||
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let state = volume_test_state(&tmp);
|
||||
let key = SigningKey(b"write-secret".to_vec());
|
||||
state.guard.write().unwrap().signing_key = key.clone();
|
||||
let volume = state
|
||||
.store
|
||||
.read()
|
||||
.unwrap()
|
||||
.find_volume(VolumeId(1))
|
||||
.unwrap()
|
||||
.1;
|
||||
let before = volume.dat_file_size().unwrap();
|
||||
let fid = format!("1,{:x}{TEST_COOKIE:08x}", 0x6e7a_0c09u64);
|
||||
let now = std::time::SystemTime::now()
|
||||
.duration_since(std::time::UNIX_EPOCH)
|
||||
.unwrap()
|
||||
.as_secs();
|
||||
let sign = |key: &[u8]| {
|
||||
encode(
|
||||
&Header::new(Algorithm::HS256),
|
||||
&serde_json::json!({"fid": fid, "exp": now - 10}),
|
||||
&EncodingKey::from_secret(key),
|
||||
)
|
||||
.unwrap()
|
||||
};
|
||||
let boundary = "expiredjwtboundary";
|
||||
let body = format!(
|
||||
"--{boundary}\r\nContent-Disposition: form-data; name=\"file\"; filename=\"a\"\r\n\r\nexpired-bytes\r\n--{boundary}--\r\n"
|
||||
);
|
||||
for (token, content_type, marked) in [
|
||||
(
|
||||
sign(&key.0),
|
||||
format!("multipart/form-data; boundary={boundary}"),
|
||||
true,
|
||||
),
|
||||
(
|
||||
sign(b"other-secret"),
|
||||
format!("multipart/form-data; boundary={boundary}"),
|
||||
false,
|
||||
),
|
||||
(sign(&key.0), "application/octet-stream".to_string(), false),
|
||||
] {
|
||||
let response = super::super::volume_server::build_admin_router(state.clone())
|
||||
.oneshot(
|
||||
Request::builder()
|
||||
.method(Method::POST)
|
||||
.uri(format!("/{fid}"))
|
||||
.header(header::AUTHORIZATION, format!("Bearer {token}"))
|
||||
.header(header::CONTENT_TYPE, &content_type)
|
||||
.body(Body::from(body.clone()))
|
||||
.unwrap(),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(
|
||||
response.status(),
|
||||
StatusCode::UNAUTHORIZED,
|
||||
"{content_type}"
|
||||
);
|
||||
assert_eq!(
|
||||
response
|
||||
.headers()
|
||||
.get("x-seaweed-write-outcome")
|
||||
.map(|value| value.to_str().unwrap()),
|
||||
marked.then_some("expired-jwt-before-append"),
|
||||
"{content_type}"
|
||||
);
|
||||
}
|
||||
assert_eq!(volume.dat_file_size().unwrap(), before);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_handle_range_single() {
|
||||
let data = b"hello world";
|
||||
@@ -6278,6 +6473,7 @@ mod tests {
|
||||
security_file: String::new(),
|
||||
cli_white_list: vec![],
|
||||
state_file_path: String::new(),
|
||||
ec_lifecycle_locks: std::sync::Mutex::new(std::collections::HashMap::new()),
|
||||
ec_decodes_in_flight: std::sync::Mutex::new(std::collections::HashSet::new()),
|
||||
volume_copies_in_flight: std::sync::Arc::new(std::sync::Mutex::new(std::collections::HashSet::new())),
|
||||
ec_decode_tail: std::sync::Mutex::new(std::collections::HashSet::new()),
|
||||
@@ -7310,6 +7506,28 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
/// A needle of concatenated gzip members decodes to all of them, as Go's
|
||||
/// gzip reader does, so a range spans the whole decoded content.
|
||||
#[tokio::test]
|
||||
async fn test_get_range_over_multi_member_gzip_needle() {
|
||||
const ID: u64 = 0x6e7a_0503;
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let state = volume_test_state(&tmp);
|
||||
let mut gz = try_gzip_data(b"hello").unwrap();
|
||||
gz.extend(try_gzip_data(b"world").unwrap());
|
||||
let path = put_test_needle_with(&state, ID, &gz, |n| n.set_is_compressed());
|
||||
|
||||
let (status, headers, body) =
|
||||
send_read(&state, Method::GET, &path, Some(b"bytes=3-7")).await;
|
||||
assert_eq!(status, StatusCode::PARTIAL_CONTENT);
|
||||
assert_eq!(body, b"lowor");
|
||||
assert_eq!(headers["Content-Range"], "bytes 3-7/10");
|
||||
|
||||
let (status, _, body) = send_read(&state, Method::GET, &path, None).await;
|
||||
assert_eq!(status, StatusCode::OK);
|
||||
assert_eq!(body, b"helloworld");
|
||||
}
|
||||
|
||||
/// An EC needle is served from memory: its GET parses Range like any
|
||||
/// other, and its HEAD ignores it as Go's writeResponseContent does.
|
||||
#[tokio::test]
|
||||
@@ -8656,7 +8874,7 @@ mod tests {
|
||||
.store
|
||||
.write()
|
||||
.unwrap()
|
||||
.delete_volume_needle(VolumeId(1), &mut filler)
|
||||
.delete_volume_needle(VolumeId(1), &mut filler, false)
|
||||
.unwrap();
|
||||
let data_offset = || {
|
||||
let mut plan = crate::storage::store::Store::needle_read_plan(
|
||||
@@ -8847,6 +9065,119 @@ mod tests {
|
||||
}
|
||||
}
|
||||
|
||||
/// A delete whose fan-out failed was already applied here, so the
|
||||
/// client's retry finds nothing locally; it must still reach the replica
|
||||
/// that kept the needle, or the replicas stay different.
|
||||
#[tokio::test]
|
||||
async fn test_delete_retry_reaches_the_replica_after_a_failed_fan_out() {
|
||||
use crate::storage::super_block::ReplicaPlacement;
|
||||
use axum::response::IntoResponse;
|
||||
use axum::{Json, Router, middleware, routing::get};
|
||||
|
||||
let replicated = |state: &Arc<VolumeServerState>| {
|
||||
let vol = state
|
||||
.store
|
||||
.read()
|
||||
.unwrap()
|
||||
.find_volume(VolumeId(1))
|
||||
.unwrap()
|
||||
.1;
|
||||
vol.set_replica_placement(ReplicaPlacement::from_string("001").unwrap())
|
||||
.unwrap();
|
||||
vol
|
||||
};
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let mut state = volume_test_state(&tmp);
|
||||
Arc::get_mut(&mut state).unwrap().self_url = "127.0.0.1:8080".to_string();
|
||||
let volume = replicated(&state);
|
||||
let peer_tmp = tempfile::TempDir::new().unwrap();
|
||||
let peer = volume_test_state(&peer_tmp);
|
||||
let peer_volume = replicated(&peer);
|
||||
|
||||
let id = 0x6e7a_0c06u64;
|
||||
let path = put_test_needle(&state, id, b"replicated delete");
|
||||
put_test_needle(&peer, id, b"replicated delete");
|
||||
let live = |vol: &Arc<crate::storage::volume::Volume>| {
|
||||
vol.read_needle(&mut Needle {
|
||||
id: NeedleId(id),
|
||||
..Needle::default()
|
||||
})
|
||||
.is_ok()
|
||||
};
|
||||
|
||||
let fail_next = Arc::new(std::sync::atomic::AtomicBool::new(true));
|
||||
let app = super::super::volume_server::build_admin_router(peer).layer(middleware::from_fn(
|
||||
move |request: Request<Body>, next: middleware::Next| {
|
||||
let fail = fail_next.swap(false, Ordering::SeqCst);
|
||||
async move {
|
||||
if fail {
|
||||
return StatusCode::INTERNAL_SERVER_ERROR.into_response();
|
||||
}
|
||||
next.run(request).await
|
||||
}
|
||||
},
|
||||
));
|
||||
let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
|
||||
let peer_addr = listener.local_addr().unwrap();
|
||||
let peer_server = tokio::spawn(async move { axum::serve(listener, app).await.unwrap() });
|
||||
let master = Router::new().route(
|
||||
"/dir/lookup",
|
||||
get(move || async move {
|
||||
Json(serde_json::json!({"locations": [
|
||||
{"url": "127.0.0.1:8080"},
|
||||
{"url": peer_addr.to_string()}
|
||||
]}))
|
||||
}),
|
||||
);
|
||||
let listener = tokio::net::TcpListener::bind("127.0.0.1:0").await.unwrap();
|
||||
*state.current_master_url.write().await = listener.local_addr().unwrap().to_string();
|
||||
let master_server =
|
||||
tokio::spawn(async move { axum::serve(listener, master).await.unwrap() });
|
||||
|
||||
assert_eq!(
|
||||
send_delete(&state, &path).await,
|
||||
StatusCode::INTERNAL_SERVER_ERROR
|
||||
);
|
||||
assert!(!live(&volume));
|
||||
assert!(live(&peer_volume));
|
||||
|
||||
assert_eq!(send_delete(&state, &path).await, StatusCode::NOT_FOUND);
|
||||
assert!(!live(&peer_volume));
|
||||
master_server.abort();
|
||||
peer_server.abort();
|
||||
}
|
||||
|
||||
/// A forwarding replica takes a 404 as the needle being gone here, so a
|
||||
/// delete whose read fails for another reason answers 500.
|
||||
#[tokio::test]
|
||||
async fn test_delete_whose_read_fails_is_not_a_404() {
|
||||
use std::io::{Seek, SeekFrom, Write};
|
||||
let tmp = tempfile::TempDir::new().unwrap();
|
||||
let state = volume_test_state(&tmp);
|
||||
let id = 0x6e7a_0c07u64;
|
||||
let path = put_test_needle(&state, id, b"unreadable");
|
||||
let dat = state
|
||||
.store
|
||||
.read()
|
||||
.unwrap()
|
||||
.find_volume(VolumeId(1))
|
||||
.unwrap()
|
||||
.1
|
||||
.dat_path();
|
||||
let mut file = std::fs::OpenOptions::new().write(true).open(dat).unwrap();
|
||||
// the needle's size field, right after the superblock, cookie and id
|
||||
file.seek(SeekFrom::Start(8 + 4 + 8)).unwrap();
|
||||
file.write_all(&u32::MAX.to_be_bytes()).unwrap();
|
||||
file.sync_all().unwrap();
|
||||
for query in ["", "?type=replicate"] {
|
||||
assert_eq!(
|
||||
send_delete(&state, &format!("{path}{query}")).await,
|
||||
StatusCode::INTERNAL_SERVER_ERROR,
|
||||
"{query}"
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn http_replication_preserves_query_authentication() {
|
||||
use crate::security::{SigningKey, gen_jwt};
|
||||
@@ -9320,8 +9651,8 @@ mod tests {
|
||||
/// replicate delete of it finds nothing. The delete cancels the write, so
|
||||
/// it is taken back when it lands instead of reviving the needle on this
|
||||
/// copy alone, even when its handler was dropped while it waited in the
|
||||
/// durable queue. A plain delete that finds nothing is not sent on to the
|
||||
/// replicas, so it leaves the write alone.
|
||||
/// durable queue. A plain delete on an unreplicated volume that finds
|
||||
/// nothing leaves the write alone.
|
||||
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
||||
#[allow(clippy::await_holding_lock)]
|
||||
async fn test_replicate_delete_cancels_a_queued_write() {
|
||||
|
||||
@@ -1698,6 +1698,7 @@ mod tests {
|
||||
security_file: String::new(),
|
||||
cli_white_list: vec![],
|
||||
state_file_path: String::new(),
|
||||
ec_lifecycle_locks: std::sync::Mutex::new(std::collections::HashMap::new()),
|
||||
ec_decodes_in_flight: std::sync::Mutex::new(std::collections::HashSet::new()),
|
||||
volume_copies_in_flight: std::sync::Arc::new(std::sync::Mutex::new(std::collections::HashSet::new())),
|
||||
ec_decode_tail: std::sync::Mutex::new(std::collections::HashSet::new()),
|
||||
|
||||
@@ -2384,23 +2384,45 @@ pub(crate) async fn recover_missing_ec_indexes(
|
||||
"cannot look up peers to recover missing .ecx: {}",
|
||||
e
|
||||
);
|
||||
continue;
|
||||
Vec::new()
|
||||
}
|
||||
};
|
||||
if peers.is_empty() {
|
||||
tracing::warn!(
|
||||
volume_id = m.vid.0,
|
||||
"shards present locally but .ecx missing and no peer holds it; leaving shards unloaded"
|
||||
);
|
||||
continue;
|
||||
// Under the volume's lifecycle lock, so an in-flight VolumeEcShardsCopy
|
||||
// of it, which may unlink the shards it renamed in, never has them
|
||||
// mounted from under it.
|
||||
let _lifecycle = state.ec_lifecycle_lock(m.vid).lock_owned().await;
|
||||
let current = state
|
||||
.store
|
||||
.read()
|
||||
.unwrap()
|
||||
.collect_ec_volumes_missing_index_only(Some(m.vid))
|
||||
.into_iter()
|
||||
.find(|x| x.vid == m.vid && x.collection == m.collection);
|
||||
// A copy holding the lock may have installed the index meanwhile: skip
|
||||
// the fetch, but its shards still need the mount.
|
||||
if let Some(current) = ¤t {
|
||||
if peers.is_empty() {
|
||||
tracing::warn!(
|
||||
volume_id = m.vid.0,
|
||||
"shards present locally but .ecx missing and no peer holds it; leaving shards unloaded"
|
||||
);
|
||||
continue;
|
||||
}
|
||||
if !fetch_ec_index_from_peers(state, current, &peers).await {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
if fetch_ec_index_from_peers(state, m, &peers).await {
|
||||
state
|
||||
.store
|
||||
.write()
|
||||
.unwrap()
|
||||
.mount_recovered_ec_shards_only(Some(m.vid));
|
||||
if current.is_some() {
|
||||
recovered += 1;
|
||||
}
|
||||
}
|
||||
|
||||
if recovered > 0 {
|
||||
state.store.write().unwrap().mount_recovered_ec_shards();
|
||||
tracing::info!(
|
||||
"recovered missing EC index for {} volume(s) from peers and mounted their shards",
|
||||
recovered
|
||||
|
||||
@@ -125,6 +125,11 @@ pub struct VolumeServerState {
|
||||
pub cli_white_list: Vec<String>,
|
||||
/// Path to state.pb file for persisting VolumeServerState across restarts.
|
||||
pub state_file_path: String,
|
||||
/// Per-vid EC lifecycle lock, serializing EC ops that install or remove a
|
||||
/// vid's files. A tokio Mutex so the guard survives the copy's `.await` IO.
|
||||
pub ec_lifecycle_locks: std::sync::Mutex<
|
||||
std::collections::HashMap<crate::storage::types::VolumeId, Arc<tokio::sync::Mutex<()>>>,
|
||||
>,
|
||||
/// Volumes with an EC decode in flight. A dropped request leaves the
|
||||
/// blocking job running; this keeps a retry from racing it on the
|
||||
/// same volume files.
|
||||
@@ -151,6 +156,20 @@ pub struct VolumeServerState {
|
||||
}
|
||||
|
||||
impl VolumeServerState {
|
||||
/// Return the per-vid EC lifecycle lock, creating it on first use. Entries
|
||||
/// are never reaped.
|
||||
pub fn ec_lifecycle_lock(
|
||||
&self,
|
||||
vid: crate::storage::types::VolumeId,
|
||||
) -> Arc<tokio::sync::Mutex<()>> {
|
||||
self.ec_lifecycle_locks
|
||||
.lock()
|
||||
.unwrap()
|
||||
.entry(vid)
|
||||
.or_insert_with(|| Arc::new(tokio::sync::Mutex::new(())))
|
||||
.clone()
|
||||
}
|
||||
|
||||
/// The master lookups should go to: the leader the heartbeat confirmed,
|
||||
/// or empty while none is known, in its announced `host:port[.grpcPort]`
|
||||
/// form. Mirrors Go's `vs.getCurrentMaster()`.
|
||||
|
||||
@@ -467,6 +467,7 @@ mod tests {
|
||||
security_file: String::new(),
|
||||
cli_white_list: vec![],
|
||||
state_file_path: String::new(),
|
||||
ec_lifecycle_locks: std::sync::Mutex::new(std::collections::HashMap::new()),
|
||||
ec_decodes_in_flight: std::sync::Mutex::new(std::collections::HashSet::new()),
|
||||
volume_copies_in_flight: std::sync::Arc::new(std::sync::Mutex::new(std::collections::HashSet::new())),
|
||||
ec_decode_tail: std::sync::Mutex::new(std::collections::HashSet::new()),
|
||||
|
||||
@@ -829,6 +829,24 @@ impl DiskLocation {
|
||||
self.volumes.len()
|
||||
}
|
||||
|
||||
/// Number of local volumes of `collection` that still take writes: not
|
||||
/// read-only and, when `volume_size_limit` is known (non zero), with a .dat
|
||||
/// below it. The .dat size is what the master compares with the limit to
|
||||
/// stop writes. Mirrors Go's WritableCollectionVolumesLen.
|
||||
pub fn writable_collection_volumes_len(
|
||||
&self,
|
||||
collection: &str,
|
||||
volume_size_limit: u64,
|
||||
) -> usize {
|
||||
self.volumes
|
||||
.values()
|
||||
.filter(|v| v.collection == collection && !v.has_remote_file() && !v.is_read_only())
|
||||
.filter(|v| {
|
||||
volume_size_limit == 0 || v.dat_file_size().unwrap_or(0) < volume_size_limit
|
||||
})
|
||||
.count()
|
||||
}
|
||||
|
||||
/// Get all volume IDs, sorted.
|
||||
pub fn volume_ids(&self) -> Vec<VolumeId> {
|
||||
let mut ids: Vec<VolumeId> = self.volumes.keys().copied().collect();
|
||||
|
||||
@@ -292,12 +292,20 @@ impl Store {
|
||||
|
||||
// ---- Volume lifecycle ----
|
||||
|
||||
/// Find the location with fewest volumes (load-balance) of the given disk type.
|
||||
/// Matches Go's FindFreeLocation: accounts for EC shards when computing free slots.
|
||||
fn find_free_location(&self, disk_type: &DiskType, preallocate: u64) -> Option<usize> {
|
||||
/// Find the location with the fewest writable volumes of `collection`, so
|
||||
/// they do not share one disk's write bandwidth, then the most free slots
|
||||
/// (load-balance) of the given disk type. Matches Go's FindFreeLocation:
|
||||
/// accounts for EC shards when computing free slots.
|
||||
fn find_free_location(
|
||||
&self,
|
||||
disk_type: &DiskType,
|
||||
collection: &str,
|
||||
preallocate: u64,
|
||||
) -> Option<usize> {
|
||||
use crate::storage::erasure_coding::ec_shard::DATA_SHARDS_COUNT;
|
||||
|
||||
let mut best: Option<(usize, i64)> = None; // (index, effective_free)
|
||||
let volume_size_limit = self.volume_size_limit.load(Ordering::Relaxed);
|
||||
let mut best: Option<(usize, usize, i64)> = None; // (index, writable, effective_free)
|
||||
for (i, loc) in self.locations.iter().enumerate() {
|
||||
if &loc.disk_type != disk_type {
|
||||
continue;
|
||||
@@ -327,11 +335,14 @@ impl Store {
|
||||
) {
|
||||
continue;
|
||||
}
|
||||
if best.is_none() || effective_free > best.unwrap().1 {
|
||||
best = Some((i, effective_free));
|
||||
let writable = loc.writable_collection_volumes_len(collection, volume_size_limit);
|
||||
if best.is_none_or(|(_, min_writable, max_free)| {
|
||||
writable < min_writable || (writable == min_writable && effective_free > max_free)
|
||||
}) {
|
||||
best = Some((i, writable, effective_free));
|
||||
}
|
||||
}
|
||||
best.map(|(i, _)| i)
|
||||
best.map(|(i, _, _)| i)
|
||||
}
|
||||
|
||||
/// Find a free location matching a predicate.
|
||||
@@ -601,7 +612,7 @@ impl Store {
|
||||
return Err(VolumeError::AlreadyExists);
|
||||
}
|
||||
let loc_idx = self
|
||||
.find_free_location(&disk_type, spec.preallocate)
|
||||
.find_free_location(&disk_type, spec.collection, spec.preallocate)
|
||||
.ok_or_else(|| {
|
||||
VolumeError::Io(io::Error::other(format!(
|
||||
"no free location for disk type {:?}",
|
||||
@@ -1042,13 +1053,18 @@ impl Store {
|
||||
}
|
||||
|
||||
/// Delete a needle from a volume.
|
||||
pub fn delete_volume_needle(&self, vid: VolumeId, n: &mut Needle) -> Result<Size, VolumeError> {
|
||||
pub fn delete_volume_needle(
|
||||
&self,
|
||||
vid: VolumeId,
|
||||
n: &mut Needle,
|
||||
fsync: bool,
|
||||
) -> Result<Size, VolumeError> {
|
||||
// Match Go's DeleteVolumeNeedle: check noWriteOrDelete before proceeding.
|
||||
let (_, vol) = self.find_volume(vid).ok_or(VolumeError::NotFound)?;
|
||||
if vol.is_no_write_or_delete() {
|
||||
return Err(VolumeError::ReadOnly(vid));
|
||||
}
|
||||
vol.delete_needle(n)
|
||||
vol.delete_needle(n, fsync)
|
||||
}
|
||||
|
||||
// ---- Collection operations ----
|
||||
@@ -2923,7 +2939,9 @@ mod tests {
|
||||
cookie: Cookie(0xaa),
|
||||
..Needle::default()
|
||||
};
|
||||
let deleted = store.delete_volume_needle(VolumeId(1), &mut del_n).unwrap();
|
||||
let deleted = store
|
||||
.delete_volume_needle(VolumeId(1), &mut del_n, false)
|
||||
.unwrap();
|
||||
assert!(deleted.0 > 0);
|
||||
}
|
||||
|
||||
@@ -3032,6 +3050,87 @@ mod tests {
|
||||
assert_eq!(store.locations[1].volumes_len(), 1);
|
||||
}
|
||||
|
||||
fn add_spread_test_volume(store: &mut Store, vid: u32, collection: &str) {
|
||||
let spec = VolumeSpec {
|
||||
collection,
|
||||
..VolumeSpec::default()
|
||||
};
|
||||
store
|
||||
.add_volume(VolumeId(vid), DiskType::HardDrive, &spec)
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
fn location_of(store: &Store, vid: u32) -> Option<usize> {
|
||||
store
|
||||
.locations
|
||||
.iter()
|
||||
.position(|loc| loc.find_volume(VolumeId(vid)).is_some())
|
||||
}
|
||||
|
||||
// Mirrors Go's TestAddVolumeSpreadsCollectionOverDisks.
|
||||
#[test]
|
||||
fn test_add_volume_spreads_collection_over_disks() {
|
||||
let tmp1 = TempDir::new().unwrap();
|
||||
let tmp2 = TempDir::new().unwrap();
|
||||
let mut store =
|
||||
make_test_store(&[tmp1.path().to_str().unwrap(), tmp2.path().to_str().unwrap()]);
|
||||
|
||||
add_spread_test_volume(&mut store, 1, "other");
|
||||
add_spread_test_volume(&mut store, 2, "other");
|
||||
add_spread_test_volume(&mut store, 3, "spread");
|
||||
let first = location_of(&store, 3);
|
||||
// Leave the disk with the "spread" volume holding fewer volumes overall.
|
||||
let other_on_first = if first == Some(1) { 2 } else { 1 };
|
||||
store
|
||||
.delete_volume(VolumeId(other_on_first), false, false, false)
|
||||
.unwrap();
|
||||
|
||||
add_spread_test_volume(&mut store, 4, "spread");
|
||||
assert_ne!(location_of(&store, 4), first);
|
||||
}
|
||||
|
||||
// Mirrors Go's TestAddVolumeIgnoresFullVolumesOfCollection.
|
||||
#[test]
|
||||
fn test_add_volume_ignores_full_volumes_of_collection() {
|
||||
let tmp1 = TempDir::new().unwrap();
|
||||
let tmp2 = TempDir::new().unwrap();
|
||||
let mut store =
|
||||
make_test_store(&[tmp1.path().to_str().unwrap(), tmp2.path().to_str().unwrap()]);
|
||||
// Every .dat holds at least its superblock, so all volumes are full.
|
||||
store.volume_size_limit.store(1, Ordering::Relaxed);
|
||||
|
||||
add_spread_test_volume(&mut store, 1, "spread");
|
||||
let full_disk = location_of(&store, 1);
|
||||
add_spread_test_volume(&mut store, 2, "other");
|
||||
add_spread_test_volume(&mut store, 3, "spread");
|
||||
assert_eq!(location_of(&store, 3), full_disk);
|
||||
}
|
||||
|
||||
// Mirrors Go's TestAddVolumeIgnoresReadOnlyVolumesOfCollection.
|
||||
#[test]
|
||||
fn test_add_volume_ignores_read_only_volumes_of_collection() {
|
||||
let tmp1 = TempDir::new().unwrap();
|
||||
let tmp2 = TempDir::new().unwrap();
|
||||
let mut store =
|
||||
make_test_store(&[tmp1.path().to_str().unwrap(), tmp2.path().to_str().unwrap()]);
|
||||
|
||||
add_spread_test_volume(&mut store, 1, "spread");
|
||||
let writable_disk = location_of(&store, 1);
|
||||
add_spread_test_volume(&mut store, 2, "other");
|
||||
add_spread_test_volume(&mut store, 3, "spread");
|
||||
assert_ne!(location_of(&store, 3), writable_disk);
|
||||
store
|
||||
.find_volume(VolumeId(3))
|
||||
.unwrap()
|
||||
.1
|
||||
.set_read_only()
|
||||
.unwrap();
|
||||
|
||||
// The other disk holds more volumes, but its "spread" volume is read-only.
|
||||
add_spread_test_volume(&mut store, 4, "spread");
|
||||
assert_ne!(location_of(&store, 4), writable_disk);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_store_delete_collection() {
|
||||
let tmp = TempDir::new().unwrap();
|
||||
@@ -3400,7 +3499,7 @@ mod tests {
|
||||
cookie: Cookie(2),
|
||||
..Needle::default()
|
||||
};
|
||||
store.delete_volume_needle(vid, &mut del).unwrap();
|
||||
store.delete_volume_needle(vid, &mut del, false).unwrap();
|
||||
|
||||
let size_before = store.find_volume(vid).unwrap().1.dat_file_size().unwrap();
|
||||
|
||||
@@ -3724,7 +3823,7 @@ mod tests {
|
||||
cookie: Cookie(2),
|
||||
..Needle::default()
|
||||
};
|
||||
store.delete_volume_needle(vid, &mut del).unwrap();
|
||||
store.delete_volume_needle(vid, &mut del, false).unwrap();
|
||||
let revision = {
|
||||
let (_, v) = store.find_volume(vid).unwrap();
|
||||
v.super_block().compaction_revision
|
||||
@@ -3749,7 +3848,7 @@ mod tests {
|
||||
cookie: Cookie(4),
|
||||
..Needle::default()
|
||||
};
|
||||
store.delete_volume_needle(vid, &mut del).unwrap();
|
||||
store.delete_volume_needle(vid, &mut del, false).unwrap();
|
||||
|
||||
drop(release_tx);
|
||||
copy.join().unwrap().unwrap();
|
||||
|
||||
@@ -36,10 +36,14 @@ impl Store {
|
||||
/// `reconcile_ec_shards_across_disks` so the orphan pass can
|
||||
/// prefer the local idx_directory.
|
||||
pub fn mirror_ec_metadata_to_shard_disks(&mut self) {
|
||||
self.mirror_ec_metadata_to_shard_disks_only(None)
|
||||
}
|
||||
|
||||
pub(crate) fn mirror_ec_metadata_to_shard_disks_only(&mut self, only: Option<VolumeId>) {
|
||||
if self.locations.len() < 2 {
|
||||
return;
|
||||
}
|
||||
let owners = self.index_ecx_owners_for_mirror();
|
||||
let owners = self.index_ecx_owners_for_mirror(only);
|
||||
if owners.is_empty() {
|
||||
return;
|
||||
}
|
||||
@@ -54,7 +58,7 @@ impl Store {
|
||||
}
|
||||
let mut mirrors: Vec<Mirror> = Vec::new();
|
||||
for (loc_idx, loc) in self.locations.iter().enumerate() {
|
||||
let orphans = collect_shard_disk_volumes(loc);
|
||||
let orphans = collect_shard_disk_volumes(loc, only);
|
||||
for (key, _shards) in orphans {
|
||||
let Some(owner) = owners.get(&key) else {
|
||||
continue;
|
||||
@@ -113,7 +117,7 @@ impl Store {
|
||||
// Records both idx_dir (where .ecx was found) and data_dir, so
|
||||
// the mirror can resolve .vif from data_dir even when .ecx lives
|
||||
// in idx_directory.
|
||||
fn index_ecx_owners_for_mirror(&self) -> HashMap<EcKey, EcxOwner> {
|
||||
fn index_ecx_owners_for_mirror(&self, only: Option<VolumeId>) -> HashMap<EcKey, EcxOwner> {
|
||||
let mut owners: HashMap<EcKey, EcxOwner> = HashMap::new();
|
||||
for (loc_idx, loc) in self.locations.iter().enumerate() {
|
||||
let mut seen: Vec<&str> = Vec::with_capacity(2);
|
||||
@@ -133,15 +137,18 @@ impl Store {
|
||||
let Some(base) = name.strip_suffix(".ecx") else {
|
||||
continue;
|
||||
};
|
||||
let Some((collection, vid)) = parse_collection_volume_id_pub(base) else {
|
||||
continue;
|
||||
};
|
||||
if only.is_some_and(|o| o != vid) {
|
||||
continue;
|
||||
}
|
||||
// A 0-byte .ecx is a corrupt stub from a failed copy, not a
|
||||
// credible owner — skip it so the scan keeps looking for a
|
||||
// real index on a sibling disk (Go's indexEcxOwners).
|
||||
if !ent.metadata().is_ok_and(|m| m.len() > 0) {
|
||||
continue;
|
||||
}
|
||||
let Some((collection, vid)) = parse_collection_volume_id_pub(base) else {
|
||||
continue;
|
||||
};
|
||||
owners
|
||||
.entry(EcKey { collection, vid })
|
||||
.or_insert_with(|| EcxOwner {
|
||||
@@ -297,7 +304,10 @@ fn copy_sidecar_atomic(src: &Path, dst: &Path) -> io::Result<()> {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn collect_shard_disk_volumes(loc: &DiskLocation) -> HashMap<EcKey, Vec<String>> {
|
||||
fn collect_shard_disk_volumes(
|
||||
loc: &DiskLocation,
|
||||
only: Option<VolumeId>,
|
||||
) -> HashMap<EcKey, Vec<String>> {
|
||||
let mut out: HashMap<EcKey, Vec<String>> = HashMap::new();
|
||||
let Ok(read) = fs::read_dir(&loc.directory) else {
|
||||
return out;
|
||||
@@ -314,13 +324,16 @@ fn collect_shard_disk_volumes(loc: &DiskLocation) -> HashMap<EcKey, Vec<String>>
|
||||
if crate::storage::disk_location::is_ec_shard_extension(ext).is_none() {
|
||||
continue;
|
||||
}
|
||||
let Some((collection, vid)) = parse_collection_volume_id_pub(base) else {
|
||||
continue;
|
||||
};
|
||||
if only.is_some_and(|o| o != vid) {
|
||||
continue;
|
||||
}
|
||||
match ent.metadata() {
|
||||
Ok(meta) if meta.len() > 0 => {}
|
||||
_ => continue,
|
||||
}
|
||||
let Some((collection, vid)) = parse_collection_volume_id_pub(base) else {
|
||||
continue;
|
||||
};
|
||||
out.entry(EcKey { collection, vid }).or_default().push(name);
|
||||
}
|
||||
out
|
||||
@@ -688,7 +701,7 @@ mod tests {
|
||||
add_loc(&mut store, &dir0);
|
||||
add_loc(&mut store, &dir1);
|
||||
|
||||
let owners = store.index_ecx_owners_for_mirror();
|
||||
let owners = store.index_ecx_owners_for_mirror(None);
|
||||
let owner = owners
|
||||
.get(&EcKey {
|
||||
collection: collection.to_string(),
|
||||
|
||||
@@ -92,11 +92,15 @@ impl Store {
|
||||
///
|
||||
/// Mirrors `Store.reconcileEcShardsAcrossDisks` in Go.
|
||||
pub fn reconcile_ec_shards_across_disks(&mut self) {
|
||||
self.reconcile_ec_shards_across_disks_only(None)
|
||||
}
|
||||
|
||||
pub(crate) fn reconcile_ec_shards_across_disks_only(&mut self, only: Option<VolumeId>) {
|
||||
if self.locations.len() < 2 {
|
||||
return;
|
||||
}
|
||||
|
||||
let owners = self.index_ecx_owners();
|
||||
let owners = self.index_ecx_owners(only);
|
||||
if owners.is_empty() {
|
||||
return;
|
||||
}
|
||||
@@ -106,7 +110,7 @@ impl Store {
|
||||
// loc.idx_directory instead of the owner disk.
|
||||
let mut to_load: Vec<OrphanShardLoad> = Vec::new();
|
||||
for (loc_idx, loc) in self.locations.iter().enumerate() {
|
||||
let orphans = collect_orphan_ec_shards(loc, loc_idx);
|
||||
let orphans = collect_orphan_ec_shards(loc, loc_idx, only);
|
||||
for (key, shards) in orphans {
|
||||
let Some(owner) = owners.get(&key) else {
|
||||
warn!(
|
||||
@@ -402,7 +406,7 @@ impl Store {
|
||||
/// matched so downstream loaders point `EcVolume::new` at the
|
||||
/// directory that really has the file. The first owner found wins;
|
||||
/// duplicates across disks are unusual but tolerated.
|
||||
fn index_ecx_owners(&self) -> HashMap<EcKey, EcxOwnerInfo> {
|
||||
fn index_ecx_owners(&self, only: Option<VolumeId>) -> HashMap<EcKey, EcxOwnerInfo> {
|
||||
let mut owners: HashMap<EcKey, EcxOwnerInfo> = HashMap::new();
|
||||
for (loc_idx, loc) in self.locations.iter().enumerate() {
|
||||
let mut seen: Vec<&str> = Vec::with_capacity(2);
|
||||
@@ -422,15 +426,18 @@ impl Store {
|
||||
let Some(base) = name.strip_suffix(".ecx") else {
|
||||
continue;
|
||||
};
|
||||
let Some((collection, vid)) = parse_collection_volume_id_pub(base) else {
|
||||
continue;
|
||||
};
|
||||
if only.is_some_and(|o| o != vid) {
|
||||
continue;
|
||||
}
|
||||
// A 0-byte .ecx is a corrupt stub from a failed copy, not a
|
||||
// credible owner — skip it so the scan keeps looking for a
|
||||
// real index on a sibling disk (Go's indexEcxOwners).
|
||||
if !ent.metadata().is_ok_and(|m| m.len() > 0) {
|
||||
continue;
|
||||
}
|
||||
let Some((collection, vid)) = parse_collection_volume_id_pub(base) else {
|
||||
continue;
|
||||
};
|
||||
let key = EcKey { collection, vid };
|
||||
owners.entry(key).or_insert(EcxOwnerInfo {
|
||||
location: loc_idx,
|
||||
@@ -450,11 +457,18 @@ impl Store {
|
||||
///
|
||||
/// Mirrors `Store.CollectEcVolumesMissingIndex` in Go.
|
||||
pub(crate) fn collect_ec_volumes_missing_index(&self) -> Vec<EcVolumeMissingIndex> {
|
||||
let owners = self.index_ecx_owners();
|
||||
self.collect_ec_volumes_missing_index_only(None)
|
||||
}
|
||||
|
||||
pub(crate) fn collect_ec_volumes_missing_index_only(
|
||||
&self,
|
||||
only: Option<VolumeId>,
|
||||
) -> Vec<EcVolumeMissingIndex> {
|
||||
let owners = self.index_ecx_owners(only);
|
||||
let mut seen: HashSet<EcKey> = HashSet::new();
|
||||
let mut missing = Vec::new();
|
||||
for (loc_idx, loc) in self.locations.iter().enumerate() {
|
||||
for (key, _shards) in collect_orphan_ec_shards(loc, loc_idx) {
|
||||
for (key, _shards) in collect_orphan_ec_shards(loc, loc_idx, only) {
|
||||
if owners.contains_key(&key) || !seen.insert(key.clone()) {
|
||||
continue;
|
||||
}
|
||||
@@ -474,18 +488,24 @@ impl Store {
|
||||
/// the disks that now have a local index, then fall back to the cross-disk
|
||||
/// virtual mount. Mirrors `Store.MountRecoveredEcShards` in Go.
|
||||
pub(crate) fn mount_recovered_ec_shards(&mut self) {
|
||||
self.mirror_ec_metadata_to_shard_disks();
|
||||
self.load_orphan_ec_shards_with_local_index();
|
||||
self.reconcile_ec_shards_across_disks();
|
||||
self.mount_recovered_ec_shards_only(None)
|
||||
}
|
||||
|
||||
/// `mount_recovered_ec_shards` restricted to one volume's shards when
|
||||
/// `only` names it.
|
||||
pub(crate) fn mount_recovered_ec_shards_only(&mut self, only: Option<VolumeId>) {
|
||||
self.mirror_ec_metadata_to_shard_disks_only(only);
|
||||
self.load_orphan_ec_shards_with_local_index(only);
|
||||
self.reconcile_ec_shards_across_disks_only(only);
|
||||
}
|
||||
|
||||
/// Mount on-disk EC shards whose `.ecx` index is now present on the same disk.
|
||||
/// Unlike `reconcile_ec_shards_across_disks` it needs no sibling disk, so a
|
||||
/// single-disk store recovers once its index has been fetched from a peer.
|
||||
fn load_orphan_ec_shards_with_local_index(&mut self) {
|
||||
fn load_orphan_ec_shards_with_local_index(&mut self, only: Option<VolumeId>) {
|
||||
let mut work: Vec<(usize, EcKey, Vec<ShardId>)> = Vec::new();
|
||||
for (loc_idx, loc) in self.locations.iter().enumerate() {
|
||||
for (key, shards) in collect_orphan_ec_shards(loc, loc_idx) {
|
||||
for (key, shards) in collect_orphan_ec_shards(loc, loc_idx, only) {
|
||||
if !loc.has_ecx_file_on_disk(&key.collection, key.vid) {
|
||||
continue;
|
||||
}
|
||||
@@ -516,6 +536,7 @@ impl Store {
|
||||
fn collect_orphan_ec_shards(
|
||||
loc: &crate::storage::disk_location::DiskLocation,
|
||||
_loc_idx: usize,
|
||||
only: Option<VolumeId>,
|
||||
) -> HashMap<EcKey, Vec<(String, ShardId)>> {
|
||||
let mut orphans: HashMap<EcKey, Vec<(String, ShardId)>> = HashMap::new();
|
||||
let Ok(read) = fs::read_dir(&loc.directory) else {
|
||||
@@ -533,6 +554,12 @@ fn collect_orphan_ec_shards(
|
||||
let Some(shard_id) = is_ec_shard_extension(ext) else {
|
||||
continue;
|
||||
};
|
||||
let Some((collection, vid)) = parse_collection_volume_id_pub(base) else {
|
||||
continue;
|
||||
};
|
||||
if only.is_some_and(|o| o != vid) {
|
||||
continue;
|
||||
}
|
||||
// Ignore zero-byte shards. Use the DirEntry's metadata so we
|
||||
// don't pay a second stat syscall per file beyond what
|
||||
// read_dir already returned.
|
||||
@@ -540,9 +567,6 @@ fn collect_orphan_ec_shards(
|
||||
Ok(meta) if meta.len() > 0 => {}
|
||||
_ => continue,
|
||||
}
|
||||
let Some((collection, vid)) = parse_collection_volume_id_pub(base) else {
|
||||
continue;
|
||||
};
|
||||
// Skip shards that are already registered to an EcVolume.
|
||||
if let Some(ecv) = loc.find_ec_volume(vid)
|
||||
&& ecv.has_shard(shard_id)
|
||||
@@ -655,7 +679,7 @@ mod tests {
|
||||
std::fs::write(ec_local_ecx_path(&d0, "pics", VolumeId(7)), b"").unwrap();
|
||||
write_index_files(&d1, "pics", 7, 10, 4);
|
||||
|
||||
let owners = store.index_ecx_owners();
|
||||
let owners = store.index_ecx_owners(None);
|
||||
let owner = owners
|
||||
.get(&EcKey {
|
||||
collection: "pics".to_string(),
|
||||
@@ -667,7 +691,7 @@ mod tests {
|
||||
|
||||
// A stub with no real index anywhere owns nothing.
|
||||
std::fs::write(ec_local_ecx_path(&d0, "pics", VolumeId(8)), b"").unwrap();
|
||||
assert!(!store.index_ecx_owners().contains_key(&EcKey {
|
||||
assert!(!store.index_ecx_owners(None).contains_key(&EcKey {
|
||||
collection: "pics".to_string(),
|
||||
vid: VolumeId(8),
|
||||
}));
|
||||
@@ -1240,6 +1264,79 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_mount_recovered_ec_shards_only_named_volume() {
|
||||
// Recovering one volume mounts only its shards. Another volume's orphan
|
||||
// shards, such as ones an in-flight copy just renamed in, stay unmounted
|
||||
// even when an index for them is already on disk. Mirrors Go
|
||||
// TestMountRecoveredEcShards_OnlyNamedVolume.
|
||||
let tmp = TempDir::new().unwrap();
|
||||
let dir0 = tmp.path().join("data0");
|
||||
let dir1 = tmp.path().join("data1");
|
||||
std::fs::create_dir_all(&dir0).unwrap();
|
||||
std::fs::create_dir_all(&dir1).unwrap();
|
||||
|
||||
let collection = "col";
|
||||
let (recovered_vid, other_vid) = (71u32, 72u32);
|
||||
let mut store = Store::new(NeedleMapKind::InMemory);
|
||||
for d in [&dir0, &dir1] {
|
||||
store
|
||||
.add_location(
|
||||
d.to_str().unwrap(),
|
||||
d.to_str().unwrap(),
|
||||
100,
|
||||
DiskType::HardDrive,
|
||||
MinFreeSpace::Percent(0.0),
|
||||
Vec::new(),
|
||||
)
|
||||
.unwrap();
|
||||
}
|
||||
for vid in [recovered_vid, other_vid] {
|
||||
write_shard(dir0.to_str().unwrap(), collection, vid, 0);
|
||||
write_shard(dir1.to_str().unwrap(), collection, vid, 1);
|
||||
}
|
||||
write_index_files(dir0.to_str().unwrap(), collection, other_vid, 10, 4);
|
||||
let missing = store.collect_ec_volumes_missing_index();
|
||||
let m = missing
|
||||
.iter()
|
||||
.find(|m| m.vid == VolumeId(recovered_vid))
|
||||
.expect("recovered volume not reported as missing its index");
|
||||
write_index_files(&m.idx_dir, collection, recovered_vid, 10, 4);
|
||||
|
||||
store.mount_recovered_ec_shards_only(Some(VolumeId(recovered_vid)));
|
||||
|
||||
for (i, loc) in store.locations.iter().enumerate() {
|
||||
let ev = loc
|
||||
.find_ec_volume(VolumeId(recovered_vid))
|
||||
.unwrap_or_else(|| panic!("volume {} not mounted on disk{}", recovered_vid, i));
|
||||
assert!(
|
||||
ev.has_shard(i as u8),
|
||||
"shard {}.{} not mounted",
|
||||
recovered_vid,
|
||||
i
|
||||
);
|
||||
assert!(
|
||||
loc.find_ec_volume(VolumeId(other_vid)).is_none(),
|
||||
"volume {} mounted on disk{} by the recovery of volume {}",
|
||||
other_vid,
|
||||
i,
|
||||
recovered_vid,
|
||||
);
|
||||
}
|
||||
let mirrored = format!(
|
||||
"{}/{}_{}.ecx",
|
||||
dir1.to_str().unwrap(),
|
||||
collection,
|
||||
other_vid
|
||||
);
|
||||
assert!(
|
||||
!std::path::Path::new(&mirrored).exists(),
|
||||
"volume {} index mirrored to disk1 by the recovery of volume {}",
|
||||
other_vid,
|
||||
recovered_vid,
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_collect_missing_index_excludes_cross_disk_orphan() {
|
||||
// A .ecx merely on a sibling disk is the same-server case the reconcile
|
||||
|
||||
File diff suppressed because it is too large.
Load diff
@@ -188,7 +188,7 @@ mod tests {
|
||||
for id in 1..=3 {
|
||||
v.write_needle(&mut needle(id), true, false).unwrap();
|
||||
}
|
||||
v.delete_needle(&mut needle(2)).unwrap();
|
||||
v.delete_needle(&mut needle(2), false).unwrap();
|
||||
v.sync_to_disk().unwrap();
|
||||
let (want_count, want_deleted) = (v.file_count(), v.deleted_count());
|
||||
drop(v);
|
||||
|
||||
@@ -382,10 +382,13 @@ pub(crate) mod tests {
|
||||
|
||||
write_test_volume(dir, 6);
|
||||
let v = open_volume(dir);
|
||||
v.delete_needle(&mut Needle {
|
||||
id: NeedleId(3),
|
||||
..Needle::default()
|
||||
})
|
||||
v.delete_needle(
|
||||
&mut Needle {
|
||||
id: NeedleId(3),
|
||||
..Needle::default()
|
||||
},
|
||||
false,
|
||||
)
|
||||
.unwrap();
|
||||
drop(v);
|
||||
|
||||
@@ -417,10 +420,13 @@ pub(crate) mod tests {
|
||||
|
||||
write_test_volume(dir, 8);
|
||||
let v = open_volume(dir);
|
||||
v.delete_needle(&mut Needle {
|
||||
id: NeedleId(2),
|
||||
..Needle::default()
|
||||
})
|
||||
v.delete_needle(
|
||||
&mut Needle {
|
||||
id: NeedleId(2),
|
||||
..Needle::default()
|
||||
},
|
||||
false,
|
||||
)
|
||||
.unwrap();
|
||||
drop(v);
|
||||
|
||||
|
||||
@@ -505,10 +505,13 @@ mod tests {
|
||||
f.written.insert(*id, n.data.clone());
|
||||
}
|
||||
Op::Del(id) => {
|
||||
v.delete_needle(&mut Needle {
|
||||
id: NeedleId(*id),
|
||||
..Needle::default()
|
||||
})
|
||||
v.delete_needle(
|
||||
&mut Needle {
|
||||
id: NeedleId(*id),
|
||||
..Needle::default()
|
||||
},
|
||||
false,
|
||||
)
|
||||
.unwrap();
|
||||
}
|
||||
Op::Empty(id) => {
|
||||
|
||||
@@ -110,6 +110,7 @@ fn build_test_state(
|
||||
vacuum_commit_slots: None,
|
||||
vacuum_commits_waiting: std::sync::atomic::AtomicU32::new(0),
|
||||
is_heartbeating: std::sync::atomic::AtomicBool::new(true),
|
||||
ec_lifecycle_locks: std::sync::Mutex::new(std::collections::HashMap::new()),
|
||||
ec_decodes_in_flight: std::sync::Mutex::new(std::collections::HashSet::new()),
|
||||
volume_copies_in_flight: std::sync::Arc::new(std::sync::Mutex::new(std::collections::HashSet::new())),
|
||||
ec_decode_tail: std::sync::Mutex::new(std::collections::HashSet::new()),
|
||||
@@ -1435,3 +1436,120 @@ async fn write_queue_upload_returns_same_etag_as_direct_write() {
|
||||
}
|
||||
assert_eq!(etags[1], etags[0], "unchanged upload ETag differs");
|
||||
}
|
||||
|
||||
// ============================================================================
|
||||
// A Range over a compressed needle is answered from the decoded bytes
|
||||
// ============================================================================
|
||||
|
||||
#[tokio::test]
|
||||
async fn range_with_accept_gzip_on_compressed_needle_serves_decoded_bytes() {
|
||||
let (state, _tmp) = test_state();
|
||||
let uri = "/1/03637037d6/notes.txt";
|
||||
let plain: Vec<u8> = (0..400)
|
||||
.flat_map(|i| format!("line {i:06}: the quick brown fox\n").into_bytes())
|
||||
.collect();
|
||||
|
||||
let app = build_admin_router(state.clone());
|
||||
let response = app
|
||||
.oneshot(
|
||||
Request::builder()
|
||||
.method("POST")
|
||||
.uri(uri)
|
||||
.body(Body::from(plain.clone()))
|
||||
.unwrap(),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(response.status(), StatusCode::CREATED);
|
||||
|
||||
let read = |range: Option<&str>| {
|
||||
let mut request = Request::builder()
|
||||
.uri(uri)
|
||||
.header("Accept-Encoding", "gzip");
|
||||
if let Some(range) = range {
|
||||
request = request.header("Range", range);
|
||||
}
|
||||
build_admin_router(state.clone()).oneshot(request.body(Body::empty()).unwrap())
|
||||
};
|
||||
|
||||
// The whole read passes the stored gzip through, so its length is the compressed size.
|
||||
let response = read(None).await.unwrap();
|
||||
assert_eq!(response.status(), StatusCode::OK);
|
||||
assert_eq!(response.headers()["Content-Encoding"], "gzip");
|
||||
let compressed_len = body_bytes(response).await.len();
|
||||
assert!(compressed_len < plain.len() / 4);
|
||||
|
||||
for (start, end) in [(10, 69), (compressed_len + 10, compressed_len + 69)] {
|
||||
let response = read(Some(&format!("bytes={start}-{end}"))).await.unwrap();
|
||||
assert_eq!(response.status(), StatusCode::PARTIAL_CONTENT);
|
||||
assert!(response.headers().get("Content-Encoding").is_none());
|
||||
assert_eq!(
|
||||
response.headers()["Content-Range"],
|
||||
format!("bytes {start}-{end}/{}", plain.len()).as_str()
|
||||
);
|
||||
assert_eq!(body_bytes(response).await, &plain[start..=end]);
|
||||
}
|
||||
}
|
||||
|
||||
// ============================================================================
|
||||
// HEAD of a compressed needle reports the length the matching GET would send
|
||||
// ============================================================================
|
||||
|
||||
#[tokio::test]
|
||||
async fn head_on_compressed_needle_reports_served_length() {
|
||||
let (state, _tmp) = test_state();
|
||||
let uri = "/1/04637037d6/notes.txt";
|
||||
let plain: Vec<u8> = (0..400)
|
||||
.flat_map(|i| format!("line {i:06}: the quick brown fox\n").into_bytes())
|
||||
.collect();
|
||||
|
||||
let app = build_admin_router(state.clone());
|
||||
let response = app
|
||||
.oneshot(
|
||||
Request::builder()
|
||||
.method("POST")
|
||||
.uri(uri)
|
||||
.body(Body::from(plain.clone()))
|
||||
.unwrap(),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(response.status(), StatusCode::CREATED);
|
||||
|
||||
let send = |method: &str, accept_gzip: bool, range: Option<&str>| {
|
||||
let mut request = Request::builder().method(method).uri(uri);
|
||||
if accept_gzip {
|
||||
request = request.header("Accept-Encoding", "gzip");
|
||||
}
|
||||
if let Some(range) = range {
|
||||
request = request.header("Range", range);
|
||||
}
|
||||
build_admin_router(state.clone()).oneshot(request.body(Body::empty()).unwrap())
|
||||
};
|
||||
|
||||
let response = send("GET", true, None).await.unwrap();
|
||||
let compressed_len = body_bytes(response).await.len();
|
||||
assert!(compressed_len < plain.len() / 4);
|
||||
|
||||
for (accept_gzip, range, encoding, length) in [
|
||||
(false, None, None, plain.len()),
|
||||
(true, None, Some("gzip"), compressed_len),
|
||||
(true, Some("bytes=0-9"), None, plain.len()),
|
||||
] {
|
||||
let response = send("HEAD", accept_gzip, range).await.unwrap();
|
||||
assert_eq!(response.status(), StatusCode::OK);
|
||||
assert_eq!(
|
||||
response
|
||||
.headers()
|
||||
.get("Content-Encoding")
|
||||
.map(|v| v.to_str().unwrap()),
|
||||
encoding,
|
||||
"accept_gzip={accept_gzip} range={range:?}"
|
||||
);
|
||||
assert_eq!(
|
||||
response.headers()["Content-Length"],
|
||||
length.to_string().as_str(),
|
||||
"accept_gzip={accept_gzip} range={range:?}"
|
||||
);
|
||||
}
|
||||
}
|
||||
Generated
+2
@@ -7170,8 +7170,10 @@ dependencies = [
|
||||
"hmac 0.12.1",
|
||||
"http 1.5.0",
|
||||
"hyper-util",
|
||||
"jsonb",
|
||||
"jsonwebtoken",
|
||||
"lance",
|
||||
"lance-arrow",
|
||||
"lance-datafusion",
|
||||
"lance-index",
|
||||
"lance-linalg",
|
||||
|
||||
@@ -35,8 +35,12 @@ lance-table = "10"
|
||||
# For the execution options the sort needs; the scanner's own stream helper
|
||||
# takes the default, which has spilling off.
|
||||
lance-datafusion = "10"
|
||||
arrow-array = "58"
|
||||
arrow-schema = "58"
|
||||
arrow-cast = "58"
|
||||
# Lance's stored form of the metadata JSON, read when deriving the
|
||||
# indexed-key columns.
|
||||
jsonb = { version = "0.5", default-features = false }
|
||||
chrono = "0.4"
|
||||
futures = "0.3"
|
||||
anyhow.workspace = true
|
||||
@@ -88,7 +92,7 @@ protoc-bin-vendored = "3"
|
||||
[dev-dependencies]
|
||||
tokio = { workspace = true, features = ["test-util"] }
|
||||
tonic.workspace = true
|
||||
arrow-array = "58"
|
||||
lance-arrow = "10"
|
||||
arrow-schema = "58"
|
||||
arrow-cast = "58"
|
||||
lance-linalg = "10"
|
||||
|
||||
@@ -3,11 +3,12 @@ use std::collections::HashMap;
|
||||
use anyhow::{Context, Result, anyhow};
|
||||
use async_trait::async_trait;
|
||||
use chrono::{Duration, Utc};
|
||||
use lance::Dataset;
|
||||
use lance::dataset::cleanup::{CleanupPolicy, cleanup_old_versions};
|
||||
use seaweed_worker_core::config_form::{form, int_or, int_value, number_field};
|
||||
use seaweed_worker_core::pb::{
|
||||
ConfigValue, DetectionComplete, DetectionProposals, ExecuteJobRequest, JobCompleted,
|
||||
JobProgressUpdate, JobProposal, JobResult, JobTypeCapability, JobTypeDescriptor,
|
||||
AdminRuntimeDefaults, ConfigValue, DetectionComplete, DetectionProposals, ExecuteJobRequest,
|
||||
JobCompleted, JobProgressUpdate, JobProposal, JobResult, JobTypeCapability, JobTypeDescriptor,
|
||||
RunDetectionRequest,
|
||||
};
|
||||
use seaweed_worker_core::{DetectionSender, ExecutionSender, JobHandler};
|
||||
@@ -15,6 +16,7 @@ use tracing::warn;
|
||||
|
||||
use crate::catalog::{NamespaceClient, SigningKey, parse_id};
|
||||
use crate::dataset;
|
||||
use crate::jobs::purge::{self, Retention};
|
||||
use crate::jobs::{clamp, string_list, table_id};
|
||||
|
||||
pub const JOB_TYPE: &str = "lance_cleanup_versions";
|
||||
@@ -28,7 +30,9 @@ const MAX_MIN_VERSIONS: i64 = 1000;
|
||||
|
||||
/// Lance keeps every version until something removes it. Lance can also do this
|
||||
/// itself through auto-cleanup, so this job is for deployments that would rather
|
||||
/// the cluster owned the policy than each writer.
|
||||
/// the cluster owned the policy than each writer. A table may override the
|
||||
/// retention in its own config, and may ask for a purge (see [`purge`]), which
|
||||
/// this job carries out ahead of the retention window.
|
||||
pub struct CleanupVersionsHandler {
|
||||
namespace_url: String,
|
||||
storage: dataset::Storage,
|
||||
@@ -68,9 +72,8 @@ impl CleanupVersionsHandler {
|
||||
|
||||
/// The oldest version that may be removed while still leaving `min_versions`
|
||||
/// behind, or None when the table has no more than the floor.
|
||||
async fn version_floor(table: &dataset::OpenTable, min_versions: usize) -> Result<Option<u64>> {
|
||||
let mut versions: Vec<u64> = table
|
||||
.dataset
|
||||
async fn version_floor(dataset: &Dataset, min_versions: usize) -> Result<Option<u64>> {
|
||||
let mut versions: Vec<u64> = dataset
|
||||
.versions()
|
||||
.await?
|
||||
.iter()
|
||||
@@ -83,6 +86,33 @@ async fn version_floor(table: &dataset::OpenTable, min_versions: usize) -> Resul
|
||||
Ok(Some(versions[versions.len() - min_versions]))
|
||||
}
|
||||
|
||||
/// The cleanup that keeps `min_versions` and every version younger than
|
||||
/// `retain_hours`, or None when the floor leaves nothing to remove. A purge
|
||||
/// cleans up through it too.
|
||||
pub async fn retention_policy(
|
||||
dataset: &Dataset,
|
||||
retain_hours: i64,
|
||||
min_versions: usize,
|
||||
) -> Result<Option<CleanupPolicy>> {
|
||||
let Some(floor) = version_floor(dataset, min_versions).await? else {
|
||||
return Ok(None);
|
||||
};
|
||||
Ok(Some(CleanupPolicy {
|
||||
before_timestamp: Some(Utc::now() - Duration::hours(retain_hours)),
|
||||
// should_clean() ANDs its clauses, so a version has to be both older
|
||||
// than the window and below the floor to go.
|
||||
before_version: Some(floor),
|
||||
// Files this dataset cannot account for are left alone: they may
|
||||
// belong to a writer that has not committed yet, and deleting them
|
||||
// would corrupt a commit in flight.
|
||||
delete_unverified: false,
|
||||
// A tagged version is pinned on purpose, so refuse rather than
|
||||
// silently dropping what someone named.
|
||||
error_if_tagged_old_versions: true,
|
||||
..Default::default()
|
||||
}))
|
||||
}
|
||||
|
||||
#[async_trait]
|
||||
impl JobHandler for CleanupVersionsHandler {
|
||||
fn capability(&self) -> JobTypeCapability {
|
||||
@@ -134,6 +164,12 @@ impl JobHandler for CleanupVersionsHandler {
|
||||
defaults.clone(),
|
||||
)),
|
||||
worker_default_values: defaults,
|
||||
// A purge compacts and retrains, so it gets a build's time.
|
||||
admin_runtime_defaults: Some(AdminRuntimeDefaults {
|
||||
job_type_max_runtime_seconds: super::vector_index::EXECUTION_TIMEOUT_SECONDS,
|
||||
execution_timeout_seconds: super::vector_index::EXECUTION_TIMEOUT_SECONDS,
|
||||
..Default::default()
|
||||
}),
|
||||
..Default::default()
|
||||
}
|
||||
}
|
||||
@@ -181,10 +217,23 @@ impl JobHandler for CleanupVersionsHandler {
|
||||
continue;
|
||||
}
|
||||
};
|
||||
let config = table.dataset.config();
|
||||
let pending_purge = purge::pending(config);
|
||||
let floor = Retention::for_table(
|
||||
config,
|
||||
Retention {
|
||||
retain_hours: DEFAULT_RETAIN_HOURS,
|
||||
min_versions,
|
||||
},
|
||||
MAX_RETAIN_HOURS,
|
||||
MAX_MIN_VERSIONS,
|
||||
)
|
||||
.min_versions;
|
||||
// Age is decided at execution against the retention window; a table
|
||||
// at or under the floor cannot lose a version whatever its age, so
|
||||
// proposing one would only produce a job with nothing to do.
|
||||
if stats.total_versions <= min_versions {
|
||||
// proposing one would only produce a job with nothing to do. A
|
||||
// requested purge ignores the floor: it keeps only the latest.
|
||||
if pending_purge.is_none() && stats.total_versions <= floor {
|
||||
continue;
|
||||
}
|
||||
let mut parameters: HashMap<String, ConfigValue> = HashMap::new();
|
||||
@@ -193,12 +242,21 @@ impl JobHandler for CleanupVersionsHandler {
|
||||
proposal_id: format!("{JOB_TYPE}:{encoded}"),
|
||||
dedupe_key: format!("{JOB_TYPE}:{encoded}"),
|
||||
job_type: JOB_TYPE.to_string(),
|
||||
summary: format!("Clean up {encoded} ({} versions)", stats.total_versions),
|
||||
detail: format!(
|
||||
"{} versions retained, above the {min_versions} floor; \
|
||||
those outside the retention window can go",
|
||||
stats.total_versions
|
||||
),
|
||||
summary: match &pending_purge {
|
||||
Some(_) => format!("Purge {encoded} ({} versions)", stats.total_versions),
|
||||
None => format!("Clean up {encoded} ({} versions)", stats.total_versions),
|
||||
},
|
||||
detail: match &pending_purge {
|
||||
Some(token) => format!(
|
||||
"purge requested at {token}: rewrite fragments with deletions \
|
||||
and keep only the latest version"
|
||||
),
|
||||
None => format!(
|
||||
"{} versions retained, above the {floor} floor; \
|
||||
those outside the retention window can go",
|
||||
stats.total_versions
|
||||
),
|
||||
},
|
||||
parameters,
|
||||
..Default::default()
|
||||
});
|
||||
@@ -254,14 +312,33 @@ impl JobHandler for CleanupVersionsHandler {
|
||||
) as usize;
|
||||
|
||||
let client = self.client();
|
||||
let table = dataset::open(&client, &id, &self.storage).await?;
|
||||
let mut table = dataset::open(&client, &id, &self.storage).await?;
|
||||
let before = table.stats().await?;
|
||||
|
||||
if let Some(token) = purge::pending(table.dataset.config()) {
|
||||
return self
|
||||
.execute_purge(request, sender, &job.job_id, &mut table, &token)
|
||||
.await;
|
||||
}
|
||||
let Retention {
|
||||
retain_hours,
|
||||
min_versions,
|
||||
} = Retention::for_table(
|
||||
table.dataset.config(),
|
||||
Retention {
|
||||
retain_hours,
|
||||
min_versions,
|
||||
},
|
||||
MAX_RETAIN_HOURS,
|
||||
MAX_MIN_VERSIONS,
|
||||
);
|
||||
|
||||
// The floor is a promise about how much history survives, so it has to
|
||||
// be applied here and not only when the job was proposed: by the time it
|
||||
// runs, versions may have aged past the retention window, and age alone
|
||||
// would take the table below what the operator asked to keep.
|
||||
let Some(floor) = version_floor(&table, min_versions).await? else {
|
||||
let Some(policy) = retention_policy(&table.dataset, retain_hours, min_versions).await?
|
||||
else {
|
||||
sender.send_completed(JobCompleted {
|
||||
request_id: request.request_id.clone(),
|
||||
job_id: job.job_id.clone(),
|
||||
@@ -288,20 +365,6 @@ impl JobHandler for CleanupVersionsHandler {
|
||||
..Default::default()
|
||||
})?;
|
||||
|
||||
let policy = CleanupPolicy {
|
||||
before_timestamp: Some(Utc::now() - Duration::hours(retain_hours)),
|
||||
// should_clean() ANDs its clauses, so a version has to be both older
|
||||
// than the window and below the floor to go.
|
||||
before_version: Some(floor),
|
||||
// Files this dataset cannot account for are left alone: they may
|
||||
// belong to a writer that has not committed yet, and deleting them
|
||||
// would corrupt a commit in flight.
|
||||
delete_unverified: false,
|
||||
// A tagged version is pinned on purpose, so refuse rather than
|
||||
// silently dropping what someone named.
|
||||
error_if_tagged_old_versions: true,
|
||||
..Default::default()
|
||||
};
|
||||
let stats = cleanup_old_versions(&table.dataset, policy)
|
||||
.await
|
||||
.with_context(|| format!("clean up versions of {}", table.location))?;
|
||||
@@ -343,3 +406,73 @@ impl JobHandler for CleanupVersionsHandler {
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
impl CleanupVersionsHandler {
|
||||
async fn execute_purge(
|
||||
&self,
|
||||
request: &ExecuteJobRequest,
|
||||
sender: &dyn ExecutionSender,
|
||||
job_id: &str,
|
||||
table: &mut dataset::OpenTable,
|
||||
token: &str,
|
||||
) -> Result<()> {
|
||||
let stats = purge::purge(&mut table.dataset, token)
|
||||
.await
|
||||
.with_context(|| format!("purge {}", table.location))?;
|
||||
if let Some(counters) = &self.metrics {
|
||||
counters.versions_removed.inc_by(stats.old_versions);
|
||||
counters.bytes_reclaimed.inc_by(stats.bytes_removed);
|
||||
}
|
||||
let mut output: HashMap<String, ConfigValue> = HashMap::new();
|
||||
output.insert(
|
||||
"fragments_rewritten".to_string(),
|
||||
int_value(stats.fragments_rewritten as i64),
|
||||
);
|
||||
output.insert(
|
||||
"old_versions_removed".to_string(),
|
||||
int_value(stats.old_versions as i64),
|
||||
);
|
||||
output.insert(
|
||||
"bytes_removed".to_string(),
|
||||
int_value(stats.bytes_removed as i64),
|
||||
);
|
||||
sender.send_completed(JobCompleted {
|
||||
request_id: request.request_id.clone(),
|
||||
job_id: job_id.to_string(),
|
||||
job_type: JOB_TYPE.to_string(),
|
||||
success: true,
|
||||
result: Some(JobResult {
|
||||
output_values: output,
|
||||
summary: if stats.served {
|
||||
format!(
|
||||
"purged: rewrote {} fragments, removed {} versions and {} bytes",
|
||||
stats.fragments_rewritten, stats.old_versions, stats.bytes_removed
|
||||
)
|
||||
} else {
|
||||
format!(
|
||||
"purge pending: rewrote {} fragments, removed {} versions and {} bytes; \
|
||||
versions from before the rebuild are still retained",
|
||||
stats.fragments_rewritten, stats.old_versions, stats.bytes_removed
|
||||
)
|
||||
},
|
||||
..Default::default()
|
||||
}),
|
||||
..Default::default()
|
||||
})?;
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn a_purge_gets_a_builds_execution_timeout() {
|
||||
let descriptor = CleanupVersionsHandler::new(String::new()).descriptor();
|
||||
let defaults = descriptor.admin_runtime_defaults.unwrap();
|
||||
assert_eq!(defaults.execution_timeout_seconds, 3600);
|
||||
assert_eq!(defaults.job_type_max_runtime_seconds, 3600);
|
||||
assert!(!defaults.enabled);
|
||||
}
|
||||
}
|
||||
@@ -9,6 +9,7 @@
|
||||
pub mod cleanup;
|
||||
pub mod compact;
|
||||
pub mod indices;
|
||||
pub mod purge;
|
||||
pub mod sort;
|
||||
pub mod vector_index;
|
||||
|
||||
|
||||
@@ -0,0 +1,328 @@
|
||||
//! Per-table retention for version cleanup, and purges: compaction that
|
||||
//! rewrites every fragment with deletions followed by a cleanup that keeps
|
||||
//! only the latest version, so the bytes of deleted rows leave storage now
|
||||
//! rather than after the retention window.
|
||||
//!
|
||||
//! Both are set in the table's own Lance config, so any client that can write
|
||||
//! the table can set them and they travel with it:
|
||||
//!
|
||||
//! - `seaweedfs.cleanup.retain_hours` and `seaweedfs.cleanup.min_versions`
|
||||
//! override the worker's retention for this table.
|
||||
//! - `seaweedfs.purge.requested` holds a request token ([`request_purge`]
|
||||
//! writes the current time); a purge is pending while it differs from
|
||||
//! `seaweedfs.purge.completed`, which the purge sets to the token it served.
|
||||
//! `seaweedfs.purge.rebuilt` records the token whose rebuild is done.
|
||||
|
||||
use std::collections::{BTreeMap, BTreeSet, HashMap};
|
||||
|
||||
use anyhow::{Context, Result, bail};
|
||||
use chrono::Utc;
|
||||
use lance::Dataset;
|
||||
use lance::dataset::cleanup::{RemovalStats, cleanup_old_versions};
|
||||
use lance::dataset::optimize::{CompactionOptions, compact_files};
|
||||
use lance::index::{DatasetIndexExt, DatasetIndexInternalExt};
|
||||
use lance_index::metrics::NoOpMetricsCollector;
|
||||
use lance_index::optimize::OptimizeOptions;
|
||||
use lance_index::{IndexType, is_system_index};
|
||||
use lance_table::format::IndexMetadata;
|
||||
use tracing::warn;
|
||||
|
||||
use crate::jobs::cleanup::retention_policy;
|
||||
|
||||
pub const RETAIN_HOURS_KEY: &str = "seaweedfs.cleanup.retain_hours";
|
||||
pub const MIN_VERSIONS_KEY: &str = "seaweedfs.cleanup.min_versions";
|
||||
pub const PURGE_REQUESTED_KEY: &str = "seaweedfs.purge.requested";
|
||||
pub const PURGE_COMPLETED_KEY: &str = "seaweedfs.purge.completed";
|
||||
pub const PURGE_REBUILT_KEY: &str = "seaweedfs.purge.rebuilt";
|
||||
|
||||
/// The retention cleanup applies to one table: the worker's, unless the
|
||||
/// table's config overrides a value with one inside the worker's range.
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub struct Retention {
|
||||
pub retain_hours: i64,
|
||||
pub min_versions: usize,
|
||||
}
|
||||
|
||||
impl Retention {
|
||||
pub fn for_table(
|
||||
config: &HashMap<String, String>,
|
||||
worker: Retention,
|
||||
max_retain_hours: i64,
|
||||
max_min_versions: i64,
|
||||
) -> Retention {
|
||||
let read = |key: &str, min: i64, max: i64| -> Option<i64> {
|
||||
let raw = config.get(key)?;
|
||||
match raw.trim().parse::<i64>() {
|
||||
Ok(value) if (min..=max).contains(&value) => Some(value),
|
||||
_ => {
|
||||
warn!("ignoring table config {key}={raw:?}: not an integer in {min}..={max}");
|
||||
None
|
||||
}
|
||||
}
|
||||
};
|
||||
Retention {
|
||||
retain_hours: read(RETAIN_HOURS_KEY, 0, max_retain_hours)
|
||||
.unwrap_or(worker.retain_hours),
|
||||
min_versions: read(MIN_VERSIONS_KEY, 1, max_min_versions)
|
||||
.map(|v| v as usize)
|
||||
.unwrap_or(worker.min_versions),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// The request token of a purge the table is waiting for, if any.
|
||||
pub fn pending(config: &HashMap<String, String>) -> Option<String> {
|
||||
let requested = config.get(PURGE_REQUESTED_KEY).map(|s| s.trim())?;
|
||||
if requested.is_empty() {
|
||||
return None;
|
||||
}
|
||||
match config.get(PURGE_COMPLETED_KEY) {
|
||||
Some(completed) if completed.trim() == requested => None,
|
||||
_ => Some(requested.to_string()),
|
||||
}
|
||||
}
|
||||
|
||||
/// Records a purge request on the table and returns its token. The next
|
||||
/// cleanup detection proposes the purge.
|
||||
pub async fn request_purge(dataset: &mut Dataset) -> Result<String> {
|
||||
let token = Utc::now().to_rfc3339_opts(chrono::SecondsFormat::Nanos, true);
|
||||
dataset
|
||||
.update_config([(PURGE_REQUESTED_KEY, token.as_str())])
|
||||
.await
|
||||
.context("record purge request")?;
|
||||
Ok(token)
|
||||
}
|
||||
|
||||
#[derive(Debug, Default, Clone, PartialEq, Eq)]
|
||||
pub struct PurgeStats {
|
||||
pub fragments_rewritten: usize,
|
||||
pub old_versions: u64,
|
||||
pub bytes_removed: u64,
|
||||
/// False while versions from before the rebuild remain.
|
||||
pub served: bool,
|
||||
}
|
||||
|
||||
/// Rewrites every fragment that has deleted rows and rebuilds the indices from
|
||||
/// the rows that remain, then removes the versions from before that through
|
||||
/// the cleanup job's retention policy with only the latest version kept, and
|
||||
/// marks `token` served once none of them is left. The rebuild is needed
|
||||
/// because compaction only remaps an index: an IVF_FLAT index keeps the
|
||||
/// deleted vector's values in its partitions under a remapped row address. It
|
||||
/// runs once per request, so a purge that has to wait for its cleanup (a
|
||||
/// version pinned by a tag, a query lease or one someone named, fails it)
|
||||
/// retries only the cleanup. Files no version references stay while Lance
|
||||
/// cannot tell them from a writer's uncommitted ones, which is up to seven
|
||||
/// days for an abandoned write.
|
||||
pub async fn purge(dataset: &mut Dataset, token: &str) -> Result<PurgeStats> {
|
||||
let fragments_rewritten = rebuild(dataset, token).await?;
|
||||
let cleanup = match retention_policy(dataset, 0, 1).await? {
|
||||
Some(policy) => cleanup_old_versions(dataset, policy)
|
||||
.await
|
||||
.context("remove versions older than the purge")?,
|
||||
None => RemovalStats::default(),
|
||||
};
|
||||
let served = finish(dataset, token).await?;
|
||||
Ok(PurgeStats {
|
||||
fragments_rewritten,
|
||||
old_versions: cleanup.old_versions,
|
||||
bytes_removed: cleanup.bytes_removed,
|
||||
served,
|
||||
})
|
||||
}
|
||||
|
||||
/// Rewrites the fragments with deletions and rebuilds the indices for
|
||||
/// `token`, unless that was done already, and returns how many fragments it
|
||||
/// rewrote.
|
||||
pub async fn rebuild(dataset: &mut Dataset, token: &str) -> Result<usize> {
|
||||
if dataset.config().get(PURGE_REBUILT_KEY).map(|s| s.trim()) == Some(token) {
|
||||
return Ok(0);
|
||||
}
|
||||
let vector_indices = vector_index_names(dataset).await?;
|
||||
let options = CompactionOptions {
|
||||
materialize_deletions: true,
|
||||
// Zero materializes every fragment with any deletion.
|
||||
materialize_deletions_threshold: 0.0,
|
||||
..Default::default()
|
||||
};
|
||||
let compaction = compact_files(dataset, options, None)
|
||||
.await
|
||||
.context("rewrite fragments with deletions")?;
|
||||
dataset.checkout_latest().await?;
|
||||
if !vector_indices.is_empty() {
|
||||
let mut options = OptimizeOptions::retrain();
|
||||
options.index_names = Some(vector_indices);
|
||||
dataset
|
||||
.optimize_indices(&options)
|
||||
.await
|
||||
.context("rebuild indices without the deleted rows")?;
|
||||
}
|
||||
rebuild_scalar_indices(dataset).await?;
|
||||
dataset.checkout_latest().await?;
|
||||
dataset
|
||||
.update_config([(PURGE_REBUILT_KEY, token)])
|
||||
.await
|
||||
.context("record purge rebuild")?;
|
||||
Ok(compaction.fragments_removed)
|
||||
}
|
||||
|
||||
/// Marks `token` served when the oldest version left is one the rebuild for
|
||||
/// it wrote, so no version from before the rebuild remains.
|
||||
pub async fn finish(dataset: &mut Dataset, token: &str) -> Result<bool> {
|
||||
let oldest = dataset
|
||||
.versions()
|
||||
.await?
|
||||
.iter()
|
||||
.map(|v| v.version)
|
||||
.min()
|
||||
.context("the table has no versions")?;
|
||||
let oldest = dataset.checkout_version(oldest).await?;
|
||||
if oldest.config().get(PURGE_REBUILT_KEY).map(|s| s.trim()) != Some(token) {
|
||||
return Ok(false);
|
||||
}
|
||||
dataset
|
||||
.update_config([(PURGE_COMPLETED_KEY, token)])
|
||||
.await
|
||||
.context("record purge completion")?;
|
||||
Ok(true)
|
||||
}
|
||||
|
||||
/// Names of the vector indices. A retrain builds each name over the whole
|
||||
/// table, so a column whose index is sharded over several names is refused:
|
||||
/// its shards would overlap.
|
||||
async fn vector_index_names(dataset: &Dataset) -> Result<Vec<String>> {
|
||||
let mut by_column: BTreeMap<Vec<i32>, BTreeSet<String>> = BTreeMap::new();
|
||||
for index in dataset
|
||||
.load_indices()
|
||||
.await?
|
||||
.iter()
|
||||
.filter(|i| is_vector(i))
|
||||
{
|
||||
by_column
|
||||
.entry(index.fields.clone())
|
||||
.or_default()
|
||||
.insert(index.name.clone());
|
||||
}
|
||||
let mut names = Vec::new();
|
||||
for shards in by_column.into_values() {
|
||||
if shards.len() > 1 {
|
||||
bail!(
|
||||
"the vector index is sharded over {shards:?}; a purge would rebuild each over the whole table"
|
||||
);
|
||||
}
|
||||
names.extend(shards);
|
||||
}
|
||||
Ok(names)
|
||||
}
|
||||
|
||||
/// Builds every scalar index again from the rows that remain. Compaction only
|
||||
/// remaps them: a bitmap index keeps a deleted key, and under stable row ids
|
||||
/// no scalar index is rewritten at all.
|
||||
async fn rebuild_scalar_indices(dataset: &mut Dataset) -> Result<()> {
|
||||
let indices = dataset.load_indices().await?;
|
||||
let mut rebuilt = BTreeSet::new();
|
||||
for index in indices.iter() {
|
||||
if is_system_index(index) || is_vector(index) || !rebuilt.insert(index.name.clone()) {
|
||||
continue;
|
||||
}
|
||||
let [field] = index.fields[..] else {
|
||||
bail!("index {} covers {} columns", index.name, index.fields.len());
|
||||
};
|
||||
let column = dataset.schema().field_path(field)?;
|
||||
let params = dataset
|
||||
.open_scalar_index(&column, &index.uuid, &NoOpMetricsCollector)
|
||||
.await?
|
||||
.derive_index_params()?;
|
||||
dataset
|
||||
.create_index(
|
||||
&[column.as_str()],
|
||||
IndexType::Scalar,
|
||||
Some(index.name.clone()),
|
||||
¶ms,
|
||||
true,
|
||||
)
|
||||
.await
|
||||
.with_context(|| format!("rebuild index {}", index.name))?;
|
||||
}
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn is_vector(index: &IndexMetadata) -> bool {
|
||||
index
|
||||
.index_details
|
||||
.as_ref()
|
||||
.is_some_and(|details| details.type_url.ends_with("VectorIndexDetails"))
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
fn config(pairs: &[(&str, &str)]) -> HashMap<String, String> {
|
||||
pairs
|
||||
.iter()
|
||||
.map(|(k, v)| (k.to_string(), v.to_string()))
|
||||
.collect()
|
||||
}
|
||||
|
||||
const WORKER: Retention = Retention {
|
||||
retain_hours: 168,
|
||||
min_versions: 5,
|
||||
};
|
||||
|
||||
#[test]
|
||||
fn table_retention_overrides_within_range() {
|
||||
assert_eq!(
|
||||
Retention::for_table(&config(&[]), WORKER, 8760, 1000),
|
||||
WORKER
|
||||
);
|
||||
assert_eq!(
|
||||
Retention::for_table(
|
||||
&config(&[(RETAIN_HOURS_KEY, "0"), (MIN_VERSIONS_KEY, "1")]),
|
||||
WORKER,
|
||||
8760,
|
||||
1000
|
||||
),
|
||||
Retention {
|
||||
retain_hours: 0,
|
||||
min_versions: 1
|
||||
}
|
||||
);
|
||||
for bad in ["-1", "8761", "x", ""] {
|
||||
assert_eq!(
|
||||
Retention::for_table(&config(&[(RETAIN_HOURS_KEY, bad)]), WORKER, 8760, 1000)
|
||||
.retain_hours,
|
||||
168,
|
||||
"{bad:?}"
|
||||
);
|
||||
}
|
||||
assert_eq!(
|
||||
Retention::for_table(&config(&[(MIN_VERSIONS_KEY, "0")]), WORKER, 8760, 1000)
|
||||
.min_versions,
|
||||
5
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn purge_is_pending_until_its_token_is_served() {
|
||||
assert_eq!(pending(&config(&[])), None);
|
||||
assert_eq!(pending(&config(&[(PURGE_REQUESTED_KEY, "")])), None);
|
||||
assert_eq!(
|
||||
pending(&config(&[(PURGE_REQUESTED_KEY, "t1")])),
|
||||
Some("t1".to_string())
|
||||
);
|
||||
assert_eq!(
|
||||
pending(&config(&[
|
||||
(PURGE_REQUESTED_KEY, "t2"),
|
||||
(PURGE_COMPLETED_KEY, "t1")
|
||||
])),
|
||||
Some("t2".to_string())
|
||||
);
|
||||
assert_eq!(
|
||||
pending(&config(&[
|
||||
(PURGE_REQUESTED_KEY, "t2"),
|
||||
(PURGE_COMPLETED_KEY, "t2")
|
||||
])),
|
||||
None
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -11,6 +11,7 @@ pub mod dataset;
|
||||
pub mod direct_read;
|
||||
pub mod grpc_tls;
|
||||
pub mod jobs;
|
||||
pub mod metadata_index;
|
||||
pub mod metrics;
|
||||
pub mod preview;
|
||||
pub mod security;
|
||||
|
||||
@@ -0,0 +1,285 @@
|
||||
//! Metadata keys an S3 Vectors index keeps a scalar index for.
|
||||
//!
|
||||
//! Each indexed key is a hidden `_mk_<n>` column of `List<Utf8>`: the strings
|
||||
//! an S3 `$eq` on a string matches, that is the value when it is a string or
|
||||
//! the string elements of an array, and nothing for any other type or a
|
||||
//! missing key. The field metadata names the key and its state. The
|
||||
//! `metadata` JSON column stays the source of truth: every writer derives the
|
||||
//! columns from it, and queries use one only once its state is `ready`.
|
||||
|
||||
use std::sync::Arc;
|
||||
|
||||
use anyhow::{Result, bail};
|
||||
use arrow_array::builder::{ListBuilder, StringBuilder};
|
||||
use arrow_array::{Array, ArrayRef, LargeBinaryArray, StringArray};
|
||||
use arrow_schema::{DataType, Field, Schema};
|
||||
|
||||
pub const COLUMN_PREFIX: &str = "_mk_";
|
||||
/// Field metadata naming the metadata key a column holds.
|
||||
pub const KEY_FIELD_META: &str = "weed:metadata_key";
|
||||
/// Field metadata holding the column's [`State`].
|
||||
pub const STATE_FIELD_META: &str = "weed:metadata_key_state";
|
||||
/// Indexed keys an index may have.
|
||||
pub const MAX_KEYS: usize = 8;
|
||||
|
||||
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
|
||||
pub enum State {
|
||||
/// The column exists; its scalar index may not.
|
||||
Building,
|
||||
/// The column and its scalar index exist; queries may use them.
|
||||
Ready,
|
||||
}
|
||||
|
||||
impl State {
|
||||
pub fn as_str(self) -> &'static str {
|
||||
match self {
|
||||
State::Building => "building",
|
||||
State::Ready => "ready",
|
||||
}
|
||||
}
|
||||
|
||||
pub fn parse(s: &str) -> Option<Self> {
|
||||
match s {
|
||||
"building" => Some(State::Building),
|
||||
"ready" => Some(State::Ready),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// One indexed key, as the table's schema records it.
|
||||
#[derive(Debug, Clone, PartialEq, Eq)]
|
||||
pub struct IndexedKey {
|
||||
pub column: String,
|
||||
pub key: String,
|
||||
/// None for a state this version does not know, which no query uses.
|
||||
pub state: Option<State>,
|
||||
}
|
||||
|
||||
/// The type of every indexed-key column.
|
||||
pub fn column_type() -> DataType {
|
||||
DataType::List(Arc::new(Field::new("item", DataType::Utf8, true)))
|
||||
}
|
||||
|
||||
/// The field of the column holding `key`.
|
||||
pub fn field(column: &str, key: &str, state: State) -> Field {
|
||||
Field::new(column, column_type(), true).with_metadata(
|
||||
[
|
||||
(KEY_FIELD_META.to_string(), key.to_string()),
|
||||
(STATE_FIELD_META.to_string(), state.as_str().to_string()),
|
||||
]
|
||||
.into_iter()
|
||||
.collect(),
|
||||
)
|
||||
}
|
||||
|
||||
/// The indexed-key columns of `schema`, in schema order.
|
||||
pub fn indexed_keys(schema: &Schema) -> Vec<IndexedKey> {
|
||||
schema
|
||||
.fields()
|
||||
.iter()
|
||||
.filter_map(|f| indexed_key(f))
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// The key `field` holds, when it is an indexed-key column.
|
||||
pub fn indexed_key(field: &Field) -> Option<IndexedKey> {
|
||||
if !field.name().starts_with(COLUMN_PREFIX) {
|
||||
return None;
|
||||
}
|
||||
let key = field.metadata().get(KEY_FIELD_META)?;
|
||||
Some(IndexedKey {
|
||||
column: field.name().clone(),
|
||||
key: key.clone(),
|
||||
state: field
|
||||
.metadata()
|
||||
.get(STATE_FIELD_META)
|
||||
.and_then(|s| State::parse(s)),
|
||||
})
|
||||
}
|
||||
|
||||
/// The strings an S3 `$eq` on a string matches for this stored value.
|
||||
pub fn json_strings(value: Option<&serde_json::Value>) -> Vec<&str> {
|
||||
match value {
|
||||
Some(serde_json::Value::String(s)) => vec![s.as_str()],
|
||||
Some(serde_json::Value::Array(items)) => items.iter().filter_map(|v| v.as_str()).collect(),
|
||||
_ => Vec::new(),
|
||||
}
|
||||
}
|
||||
|
||||
/// [`json_strings`] for `key` of one row's metadata as Lance stores it (jsonb).
|
||||
pub fn jsonb_strings(metadata: &[u8], key: &str) -> Result<Vec<String>> {
|
||||
let raw = jsonb::RawJsonb::new(metadata);
|
||||
let Some(value) = raw.get_by_name(key, false)? else {
|
||||
return Ok(Vec::new());
|
||||
};
|
||||
let value = value.as_raw();
|
||||
if let Some(s) = value.as_str()? {
|
||||
return Ok(vec![s.into_owned()]);
|
||||
}
|
||||
let Some(items) = value.array_values()? else {
|
||||
return Ok(Vec::new());
|
||||
};
|
||||
let mut out = Vec::new();
|
||||
for item in items {
|
||||
if let Some(s) = item.as_raw().as_str()? {
|
||||
out.push(s.into_owned());
|
||||
}
|
||||
}
|
||||
Ok(out)
|
||||
}
|
||||
|
||||
/// The column for `key` over rows whose metadata is given as JSON objects.
|
||||
pub fn column_from_json<'a>(
|
||||
rows: impl IntoIterator<Item = Option<&'a serde_json::Value>>,
|
||||
key: &str,
|
||||
) -> ArrayRef {
|
||||
let mut builder = ListBuilder::new(StringBuilder::new());
|
||||
for row in rows {
|
||||
for s in json_strings(row.and_then(|m| m.get(key))) {
|
||||
builder.values().append_value(s);
|
||||
}
|
||||
builder.append(true);
|
||||
}
|
||||
Arc::new(builder.finish())
|
||||
}
|
||||
|
||||
/// The column for `key` over a stored `metadata` column: jsonb (LargeBinary)
|
||||
/// or JSON text (Utf8).
|
||||
pub fn column_from_metadata(metadata: &dyn Array, key: &str) -> Result<ArrayRef> {
|
||||
let mut builder = ListBuilder::new(StringBuilder::new());
|
||||
if let Some(jsonb) = metadata.as_any().downcast_ref::<LargeBinaryArray>() {
|
||||
for i in 0..jsonb.len() {
|
||||
if !jsonb.is_null(i) {
|
||||
for s in jsonb_strings(jsonb.value(i), key)? {
|
||||
builder.values().append_value(s);
|
||||
}
|
||||
}
|
||||
builder.append(true);
|
||||
}
|
||||
} else if let Some(text) = metadata.as_any().downcast_ref::<StringArray>() {
|
||||
for i in 0..text.len() {
|
||||
if !text.is_null(i) {
|
||||
let row: serde_json::Value = serde_json::from_str(text.value(i))?;
|
||||
for s in json_strings(row.get(key)) {
|
||||
builder.values().append_value(s);
|
||||
}
|
||||
}
|
||||
builder.append(true);
|
||||
}
|
||||
} else {
|
||||
bail!("metadata column is {}", metadata.data_type());
|
||||
}
|
||||
Ok(Arc::new(builder.finish()))
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use arrow_array::ListArray;
|
||||
|
||||
fn lists(array: &ArrayRef) -> Vec<Vec<String>> {
|
||||
let list = array.as_any().downcast_ref::<ListArray>().unwrap();
|
||||
(0..list.len())
|
||||
.map(|i| {
|
||||
assert!(!list.is_null(i));
|
||||
let values = list.value(i);
|
||||
let values = values.as_any().downcast_ref::<StringArray>().unwrap();
|
||||
values.iter().map(|v| v.unwrap().to_string()).collect()
|
||||
})
|
||||
.collect()
|
||||
}
|
||||
|
||||
const ROWS: [Option<&str>; 12] = [
|
||||
Some(r#"{"k": "a"}"#),
|
||||
Some(r#"{"k": 7}"#),
|
||||
Some(r#"{"k": "7"}"#),
|
||||
Some(r#"{"k": ["a", "b", 7, true, null, ["c"], {"d": "e"}]}"#),
|
||||
Some(r#"{"x": "a"}"#),
|
||||
Some(r#"{"k": null}"#),
|
||||
Some(r#"{"k": true}"#),
|
||||
Some(r#"{"k": {"a": "b"}}"#),
|
||||
Some(r#"{"k": "line\nbreak\u0001"}"#),
|
||||
Some(r#"{"k": []}"#),
|
||||
Some(r#"{"K": "upper"}"#),
|
||||
None,
|
||||
];
|
||||
|
||||
fn want() -> Vec<Vec<String>> {
|
||||
let s = |v: &[&str]| v.iter().map(|s| s.to_string()).collect::<Vec<_>>();
|
||||
vec![
|
||||
s(&["a"]),
|
||||
s(&[]),
|
||||
s(&["7"]),
|
||||
s(&["a", "b"]),
|
||||
s(&[]),
|
||||
s(&[]),
|
||||
s(&[]),
|
||||
s(&[]),
|
||||
s(&["line\nbreak\u{1}"]),
|
||||
s(&[]),
|
||||
s(&[]),
|
||||
s(&[]),
|
||||
]
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn json_and_jsonb_rows_derive_the_same_strings() {
|
||||
let values: Vec<Option<serde_json::Value>> = ROWS
|
||||
.iter()
|
||||
.map(|r| r.map(|r| serde_json::from_str(r).unwrap()))
|
||||
.collect();
|
||||
assert_eq!(
|
||||
lists(&column_from_json(values.iter().map(|v| v.as_ref()), "k")),
|
||||
want()
|
||||
);
|
||||
|
||||
let text = StringArray::from(ROWS.to_vec());
|
||||
assert_eq!(lists(&column_from_metadata(&text, "k").unwrap()), want());
|
||||
|
||||
let jsonb = lance_arrow::json::JsonArray::try_from_iter(ROWS.iter().copied())
|
||||
.unwrap()
|
||||
.into_inner();
|
||||
assert_eq!(lists(&column_from_metadata(&jsonb, "k").unwrap()), want());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn indexed_keys_come_from_the_field_metadata() {
|
||||
let mut unknown = field("_mk_2", "c", State::Ready);
|
||||
unknown.set_metadata(
|
||||
[
|
||||
(KEY_FIELD_META.to_string(), "c".to_string()),
|
||||
(STATE_FIELD_META.to_string(), "later".to_string()),
|
||||
]
|
||||
.into_iter()
|
||||
.collect(),
|
||||
);
|
||||
let schema = Schema::new(vec![
|
||||
Field::new("key", DataType::Utf8, false),
|
||||
field("_mk_0", "a.b", State::Ready),
|
||||
Field::new("_mk_1", column_type(), true),
|
||||
field("_mk_3", "d", State::Building),
|
||||
unknown,
|
||||
]);
|
||||
assert_eq!(
|
||||
indexed_keys(&schema),
|
||||
vec![
|
||||
IndexedKey {
|
||||
column: "_mk_0".into(),
|
||||
key: "a.b".into(),
|
||||
state: Some(State::Ready),
|
||||
},
|
||||
IndexedKey {
|
||||
column: "_mk_3".into(),
|
||||
key: "d".into(),
|
||||
state: Some(State::Building),
|
||||
},
|
||||
IndexedKey {
|
||||
column: "_mk_2".into(),
|
||||
key: "c".into(),
|
||||
state: None,
|
||||
},
|
||||
]
|
||||
);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,394 @@
|
||||
//! A purge removes a deleted vector's bytes from storage: after it, no file
|
||||
//! under the table holds the vector, its key or its metadata. Runs on a local
|
||||
//! table, so it needs no cluster.
|
||||
|
||||
use std::path::Path;
|
||||
use std::sync::Arc;
|
||||
|
||||
use arrow_array::types::Float32Type;
|
||||
use arrow_array::{FixedSizeListArray, RecordBatch, RecordBatchIterator, StringArray};
|
||||
use arrow_schema::{DataType, Field, Schema};
|
||||
use lance::Dataset;
|
||||
use lance::dataset::cleanup::{CleanupPolicy, RemovalStats, cleanup_old_versions};
|
||||
use lance::index::DatasetIndexExt;
|
||||
use lance::index::vector::VectorIndexParams;
|
||||
use lance_index::IndexType;
|
||||
use lance_linalg::distance::DistanceType;
|
||||
use weed_lance_worker::jobs::purge;
|
||||
|
||||
const DIM: i32 = 8;
|
||||
const ROWS: usize = 300;
|
||||
const MARKER_ROW: usize = 137;
|
||||
const KEY_MARKER: &str = "purge-key-5f0c2e9a7d41b3c8";
|
||||
const METADATA_MARKER: &str = "purge-metadata-a93e1d5b77c2f046";
|
||||
|
||||
fn marker_vector() -> Vec<f32> {
|
||||
// Values no other row has, so their bytes identify the row.
|
||||
(0..DIM).map(|i| 31_337.125 + i as f32 * 0.5).collect()
|
||||
}
|
||||
|
||||
fn batch() -> (Arc<Schema>, RecordBatch) {
|
||||
let schema = Arc::new(Schema::new(vec![
|
||||
Field::new("key", DataType::Utf8, false),
|
||||
Field::new(
|
||||
"vector",
|
||||
DataType::FixedSizeList(Arc::new(Field::new("item", DataType::Float32, true)), DIM),
|
||||
false,
|
||||
),
|
||||
Field::new("metadata", DataType::Utf8, true),
|
||||
]));
|
||||
let keys: Vec<String> = (0..ROWS)
|
||||
.map(|i| {
|
||||
if i == MARKER_ROW {
|
||||
KEY_MARKER.to_string()
|
||||
} else {
|
||||
format!("k{i}")
|
||||
}
|
||||
})
|
||||
.collect();
|
||||
let metadata: Vec<String> = (0..ROWS)
|
||||
.map(|i| {
|
||||
if i == MARKER_ROW {
|
||||
format!("{{\"note\":\"{METADATA_MARKER}\"}}")
|
||||
} else {
|
||||
format!("{{\"n\":{i}}}")
|
||||
}
|
||||
})
|
||||
.collect();
|
||||
let vectors = FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(
|
||||
(0..ROWS).map(|i| {
|
||||
let values: Vec<f32> = if i == MARKER_ROW {
|
||||
marker_vector()
|
||||
} else {
|
||||
(0..DIM)
|
||||
.map(|d| ((i * 7 + d as usize) % 97) as f32)
|
||||
.collect()
|
||||
};
|
||||
Some(values.into_iter().map(Some).collect::<Vec<_>>())
|
||||
}),
|
||||
DIM,
|
||||
);
|
||||
let batch = RecordBatch::try_new(
|
||||
schema.clone(),
|
||||
vec![
|
||||
Arc::new(StringArray::from(keys)),
|
||||
Arc::new(vectors),
|
||||
Arc::new(StringArray::from(metadata)),
|
||||
],
|
||||
)
|
||||
.unwrap();
|
||||
(schema, batch)
|
||||
}
|
||||
|
||||
fn vector_bytes() -> Vec<u8> {
|
||||
marker_vector()
|
||||
.iter()
|
||||
.flat_map(|v| v.to_le_bytes())
|
||||
.collect()
|
||||
}
|
||||
|
||||
/// Each marker found under `dir`, as "<marker> in <file>".
|
||||
fn markers_in(dir: &Path) -> Vec<String> {
|
||||
let vector = vector_bytes();
|
||||
let mut found = Vec::new();
|
||||
let mut stack = vec![dir.to_path_buf()];
|
||||
while let Some(path) = stack.pop() {
|
||||
for entry in std::fs::read_dir(&path).unwrap() {
|
||||
let entry = entry.unwrap();
|
||||
if entry.file_type().unwrap().is_dir() {
|
||||
stack.push(entry.path());
|
||||
continue;
|
||||
}
|
||||
let bytes = std::fs::read(entry.path()).unwrap();
|
||||
let has = |needle: &[u8]| bytes.windows(needle.len()).any(|w| w == needle);
|
||||
for (name, needle) in [
|
||||
("vector", vector.as_slice()),
|
||||
("key", KEY_MARKER.as_bytes()),
|
||||
("metadata", METADATA_MARKER.as_bytes()),
|
||||
] {
|
||||
if has(needle) {
|
||||
let file = entry.path();
|
||||
let file = file.strip_prefix(dir).unwrap_or(&file);
|
||||
found.push(format!("{name} in {}", file.display()));
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
found.sort_unstable();
|
||||
found
|
||||
}
|
||||
|
||||
/// A purge whose cleanup nothing holds back, so only the latest version
|
||||
/// stays. [`purge::purge`] cleans up through the cleanup job's retention
|
||||
/// policy, which a deployment may have keep more.
|
||||
async fn purge_to_latest(
|
||||
dataset: &mut Dataset,
|
||||
token: &str,
|
||||
) -> anyhow::Result<(usize, RemovalStats, bool)> {
|
||||
let rewritten = purge::rebuild(dataset, token).await?;
|
||||
let policy = CleanupPolicy {
|
||||
before_timestamp: Some(chrono::Utc::now()),
|
||||
before_version: Some(dataset.latest_version_id().await?),
|
||||
error_if_tagged_old_versions: true,
|
||||
..Default::default()
|
||||
};
|
||||
let removed = cleanup_old_versions(dataset, policy).await?;
|
||||
Ok((rewritten, removed, purge::finish(dataset, token).await?))
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn purge_removes_a_deleted_vectors_bytes() {
|
||||
purge_leaves_no_trace(false).await;
|
||||
}
|
||||
|
||||
/// Under stable row ids compaction leaves scalar indices as they are, so only
|
||||
/// a rebuild takes the key out of them.
|
||||
#[tokio::test]
|
||||
async fn purge_removes_a_deleted_vectors_bytes_under_stable_row_ids() {
|
||||
purge_leaves_no_trace(true).await;
|
||||
}
|
||||
|
||||
async fn purge_leaves_no_trace(stable_row_ids: bool) {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let uri = dir.path().join("index.lance");
|
||||
let uri = uri.to_str().unwrap();
|
||||
let (schema, batch) = batch();
|
||||
let params = lance::dataset::WriteParams {
|
||||
enable_stable_row_ids: stable_row_ids,
|
||||
..Default::default()
|
||||
};
|
||||
let mut dataset = Dataset::write(
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
uri,
|
||||
Some(params),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
dataset
|
||||
.create_index(
|
||||
&["vector"],
|
||||
IndexType::Vector,
|
||||
Some("vector_idx".to_string()),
|
||||
&VectorIndexParams::ivf_flat(2, DistanceType::L2),
|
||||
false,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
dataset
|
||||
.create_index(
|
||||
&["key"],
|
||||
IndexType::BTree,
|
||||
Some("key_idx".to_string()),
|
||||
&lance_index::scalar::ScalarIndexParams::default(),
|
||||
false,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
// A remapped bitmap index still lists the deleted row's value.
|
||||
dataset
|
||||
.create_index(
|
||||
&["metadata"],
|
||||
IndexType::Bitmap,
|
||||
Some("metadata_idx".to_string()),
|
||||
&lance_index::scalar::ScalarIndexParams::for_builtin(
|
||||
lance_index::scalar::BuiltinIndexType::Bitmap,
|
||||
),
|
||||
false,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
dataset.checkout_latest().await.unwrap();
|
||||
|
||||
let before = markers_in(dir.path());
|
||||
assert!(
|
||||
before.iter().any(|m| m.starts_with("vector ")),
|
||||
"the vector's bytes should be found before deletion, found {before:?}"
|
||||
);
|
||||
|
||||
dataset
|
||||
.delete(&format!("key = '{KEY_MARKER}'"))
|
||||
.await
|
||||
.unwrap();
|
||||
assert_eq!(dataset.count_rows(None).await.unwrap(), ROWS - 1);
|
||||
|
||||
// A deletion alone, and the default retention cleanup, leave the bytes:
|
||||
// the fragment still holds the row and older versions still reference it.
|
||||
cleanup_old_versions(
|
||||
&dataset,
|
||||
CleanupPolicy {
|
||||
before_timestamp: Some(chrono::Utc::now() - chrono::Duration::hours(168)),
|
||||
..Default::default()
|
||||
},
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(
|
||||
markers_in(dir.path())
|
||||
.iter()
|
||||
.any(|m| m.starts_with("vector ")),
|
||||
"a deleted vector is expected to stay until purged"
|
||||
);
|
||||
|
||||
let token = purge::request_purge(&mut dataset).await.unwrap();
|
||||
assert_eq!(purge::pending(dataset.config()), Some(token.clone()));
|
||||
let (rewritten, removed, served) = purge_to_latest(&mut dataset, &token).await.unwrap();
|
||||
assert!(served);
|
||||
assert!(rewritten >= 1);
|
||||
assert!(removed.old_versions >= 1, "{removed:?}");
|
||||
|
||||
assert_eq!(
|
||||
markers_in(dir.path()),
|
||||
Vec::<String>::new(),
|
||||
"deleted vector's bytes remain in storage after the purge"
|
||||
);
|
||||
assert_eq!(purge::pending(dataset.config()), None);
|
||||
|
||||
// The table is intact: every other row, and the index, still serve.
|
||||
let reopened = Dataset::open(uri).await.unwrap();
|
||||
assert_eq!(reopened.count_rows(None).await.unwrap(), ROWS - 1);
|
||||
assert_eq!(purge::pending(reopened.config()), None);
|
||||
assert_eq!(reopened.load_indices().await.unwrap().len(), 3);
|
||||
}
|
||||
|
||||
/// A version a query lease (a tag) pins still holds the deleted row, so the
|
||||
/// purge must fail and leave the request pending rather than report success.
|
||||
/// Once the tag goes, the next purge only cleans up: the rebuild is not done
|
||||
/// again.
|
||||
#[tokio::test]
|
||||
async fn purge_refuses_while_a_tag_pins_old_data() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let uri = dir.path().join("index.lance");
|
||||
let uri = uri.to_str().unwrap();
|
||||
let (schema, batch) = batch();
|
||||
let mut dataset = Dataset::write(RecordBatchIterator::new(vec![Ok(batch)], schema), uri, None)
|
||||
.await
|
||||
.unwrap();
|
||||
dataset
|
||||
.create_index(
|
||||
&["vector"],
|
||||
IndexType::Vector,
|
||||
Some("vector_idx".to_string()),
|
||||
&VectorIndexParams::ivf_flat(2, DistanceType::L2),
|
||||
false,
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
let pinned = dataset.version().version;
|
||||
dataset
|
||||
.tags()
|
||||
.create(
|
||||
"weed-vector-query-lease",
|
||||
lance::dataset::refs::Ref::Version(None, Some(pinned)),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
dataset
|
||||
.delete(&format!("key = '{KEY_MARKER}'"))
|
||||
.await
|
||||
.unwrap();
|
||||
let token = purge::request_purge(&mut dataset).await.unwrap();
|
||||
assert!(purge_to_latest(&mut dataset, &token).await.is_err());
|
||||
dataset.checkout_latest().await.unwrap();
|
||||
assert_eq!(purge::pending(dataset.config()), Some(token.clone()));
|
||||
|
||||
let index = |dataset: &Dataset| {
|
||||
let dataset = dataset.clone();
|
||||
async move { dataset.load_indices().await.unwrap()[0].uuid }
|
||||
};
|
||||
let rebuilt = index(&dataset).await;
|
||||
dataset
|
||||
.tags()
|
||||
.delete("weed-vector-query-lease")
|
||||
.await
|
||||
.unwrap();
|
||||
let (rewritten, _, served) = purge_to_latest(&mut dataset, &token).await.unwrap();
|
||||
assert!(served);
|
||||
assert_eq!(rewritten, 0);
|
||||
assert_eq!(
|
||||
index(&dataset).await,
|
||||
rebuilt,
|
||||
"the index was rebuilt again"
|
||||
);
|
||||
assert_eq!(purge::pending(dataset.config()), None);
|
||||
assert_eq!(markers_in(dir.path()), Vec::<String>::new());
|
||||
}
|
||||
|
||||
/// The request is served only once no version from before the rebuild is
|
||||
/// left, whatever kept one.
|
||||
#[tokio::test]
|
||||
async fn purge_is_served_once_older_versions_are_gone() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let uri = dir.path().join("index.lance");
|
||||
let uri = uri.to_str().unwrap();
|
||||
let (schema, batch) = batch();
|
||||
let mut dataset = Dataset::write(RecordBatchIterator::new(vec![Ok(batch)], schema), uri, None)
|
||||
.await
|
||||
.unwrap();
|
||||
dataset
|
||||
.delete(&format!("key = '{KEY_MARKER}'"))
|
||||
.await
|
||||
.unwrap();
|
||||
let token = purge::request_purge(&mut dataset).await.unwrap();
|
||||
assert_eq!(purge::rebuild(&mut dataset, &token).await.unwrap(), 1);
|
||||
assert!(!purge::finish(&mut dataset, &token).await.unwrap());
|
||||
assert_eq!(purge::pending(dataset.config()), Some(token.clone()));
|
||||
|
||||
let (rewritten, removed, served) = purge_to_latest(&mut dataset, &token).await.unwrap();
|
||||
assert!(served);
|
||||
assert_eq!(rewritten, 0);
|
||||
assert!(removed.old_versions >= 1, "{removed:?}");
|
||||
assert_eq!(purge::pending(dataset.config()), None);
|
||||
}
|
||||
|
||||
/// A retrain builds every index name over the whole table, so shards of one
|
||||
/// vector index would end up overlapping: the purge refuses before touching
|
||||
/// the table and leaves the request pending.
|
||||
#[tokio::test]
|
||||
async fn purge_refuses_a_sharded_vector_index() {
|
||||
let dir = tempfile::tempdir().unwrap();
|
||||
let uri = dir.path().join("index.lance");
|
||||
let uri = uri.to_str().unwrap();
|
||||
let (schema, batch) = batch();
|
||||
let params = lance::dataset::WriteParams {
|
||||
max_rows_per_file: ROWS / 2,
|
||||
..Default::default()
|
||||
};
|
||||
let mut dataset = Dataset::write(
|
||||
RecordBatchIterator::new(vec![Ok(batch)], schema),
|
||||
uri,
|
||||
Some(params),
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
let fragments: Vec<u32> = dataset
|
||||
.get_fragments()
|
||||
.iter()
|
||||
.map(|f| f.id() as u32)
|
||||
.collect();
|
||||
assert_eq!(fragments.len(), 2);
|
||||
for (shard, fragment) in fragments.iter().enumerate() {
|
||||
dataset
|
||||
.create_index_builder(
|
||||
&["vector"],
|
||||
IndexType::Vector,
|
||||
&VectorIndexParams::ivf_flat(2, DistanceType::L2),
|
||||
)
|
||||
.name(format!("shard-{shard}"))
|
||||
.fragments(vec![*fragment])
|
||||
.await
|
||||
.unwrap();
|
||||
dataset.checkout_latest().await.unwrap();
|
||||
}
|
||||
dataset
|
||||
.delete(&format!("key = '{KEY_MARKER}'"))
|
||||
.await
|
||||
.unwrap();
|
||||
let token = purge::request_purge(&mut dataset).await.unwrap();
|
||||
let version = dataset.version().version;
|
||||
|
||||
let err = purge::purge(&mut dataset, &token).await.unwrap_err();
|
||||
assert!(format!("{err:#}").contains("sharded"), "{err:#}");
|
||||
dataset.checkout_latest().await.unwrap();
|
||||
assert_eq!(dataset.version().version, version, "the table was changed");
|
||||
assert_eq!(purge::pending(dataset.config()), Some(token));
|
||||
}
|
||||
@@ -13,9 +13,9 @@ require (
|
||||
github.com/beorn7/perks v1.0.1 // indirect
|
||||
github.com/cespare/xxhash/v2 v2.3.0 // indirect
|
||||
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
|
||||
github.com/prometheus/common v0.70.1 // indirect
|
||||
github.com/prometheus/procfs v0.22.0 // indirect
|
||||
golang.org/x/sys v0.48.0 // indirect
|
||||
github.com/prometheus/common v0.71.0 // indirect
|
||||
github.com/prometheus/procfs v0.23.0 // indirect
|
||||
golang.org/x/sys v0.49.0 // indirect
|
||||
)
|
||||
|
||||
replace github.com/seaweedfs/seaweedfs => ../..
|
||||
+12
-16
@@ -2,35 +2,31 @@ github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
|
||||
github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
|
||||
github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
|
||||
github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
|
||||
github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
|
||||
github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
|
||||
github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
|
||||
github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
|
||||
github.com/klauspost/compress v1.19.2 h1:hMRETovs/pu/dVWN7zIT1PGG8t509MwT6bO7XSi26R8=
|
||||
github.com/klauspost/compress v1.19.2/go.mod h1:cwPg85FWrGar70rWktvGQj8/hthj3wpl0PGDogxkrSQ=
|
||||
github.com/klauspost/compress v1.20.3 h1:zWNoFqq/lSuYQRim3dUXlXeA0IqwuZGicdG5ZTfY5j4=
|
||||
github.com/klauspost/compress v1.20.3/go.mod h1:LUdAzn7YLVvxLpc7y3V1m40wESHTgc1422pwwBSKYuI=
|
||||
github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
|
||||
github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
|
||||
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
|
||||
github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
|
||||
github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
|
||||
github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
|
||||
github.com/prometheus/client_golang v1.24.1 h1:JnJkREXzWxUdCuPFpIWZiPispT9xVV59uiuyR2bPlnU=
|
||||
github.com/prometheus/client_golang v1.24.1/go.mod h1:F+oSRECHg4sse5ucfYpYDeIv/hu68Zo0uoHKetWnzcE=
|
||||
github.com/prometheus/client_model v0.6.3 h1:O0jaTVAYNxTHYInEPFJt5I3+sN8zqBtVMPTB1qyxiEo=
|
||||
github.com/prometheus/client_model v0.6.3/go.mod h1:gpN5P9S7Rr6Yr92PiQ+Ixvhf6JZEkF1dnxsYL2aPBEM=
|
||||
github.com/prometheus/common v0.70.1 h1:1HvjP4D5oL3t8RsPlwxA9onvvStjtIHYE5XuuwOi/PY=
|
||||
github.com/prometheus/common v0.70.1/go.mod h1:VdFUQDMZK3VLkurFUVhia6uys/0suUp86TJz5qbJRhc=
|
||||
github.com/prometheus/procfs v0.22.0 h1:6q9+/JL9IKAPbCmBrv9n5O5Ty3NKnciV5X7YGw0oics=
|
||||
github.com/prometheus/procfs v0.22.0/go.mod h1:CvmFr/GVhIjIvWJZW3tgkODBQMRIf0EyWMQLHCHab58=
|
||||
github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
|
||||
github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
|
||||
github.com/prometheus/common v0.71.0 h1:9KDAKb7Mj3HEVKyFCK6Dc/HIwlBzZIN2l7/lrHl3KK8=
|
||||
github.com/prometheus/common v0.71.0/go.mod h1:CLJ5H8TEsGX8bl31BdMkfhIZ+QmZ9tBPPotUxUbfcmk=
|
||||
github.com/prometheus/procfs v0.23.0 h1:ad+S6FTkzwaMgacKLM5h6bNKExS+DMH0YiUwXItH/o4=
|
||||
github.com/prometheus/procfs v0.23.0/go.mod h1:3AVXO0FqLafyYFU/V/IQRZlC8Rgqz8Dm/x6pKLK+RIk=
|
||||
github.com/stretchr/testify v1.12.1 h1:EuwCh5fleGS7H32xRwO3wRGT7DxrDhLAT6FF8MpWDWE=
|
||||
github.com/stretchr/testify v1.12.1/go.mod h1:MDEgiDPPsNp5cuIrHPPCyornHKgEVbtFUmoNlxoYthg=
|
||||
go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
|
||||
go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
|
||||
go.yaml.in/yaml/v2 v2.4.4 h1:tuyd0P+2Ont/d6e2rl3be67goVK4R6deVxCUX5vyPaQ=
|
||||
go.yaml.in/yaml/v2 v2.4.4/go.mod h1:gMZqIpDtDqOfM0uNfy0SkpRhvUryYH0Z6wdMYcacYXQ=
|
||||
golang.org/x/sys v0.48.0 h1:bbX/i/6MgT9BVLM9RT1thmxL04yeTAhbEz4SyadbXoo=
|
||||
golang.org/x/sys v0.48.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og=
|
||||
go.yaml.in/yaml/v3 v3.0.6 h1:zcDfvjXEqTQmpjniUBLc91xYJMB2c4QOFxEF/LCEckM=
|
||||
go.yaml.in/yaml/v3 v3.0.6/go.mod h1:HVTZu1O7/Vkt2N+BFy8Zza+lnLsABggaTM2ZpNIGuKg=
|
||||
golang.org/x/sys v0.49.0 h1:XbzkgYJHdqh/8m2Uu0W/dQv8nktxx4BFHp1M0gROTXA=
|
||||
golang.org/x/sys v0.49.0/go.mod h1:hNLxWAXmnKAxqDtdwIYC4bM9oQPEecfsnNMuSxOs3og=
|
||||
google.golang.org/protobuf v1.36.12 h1:pJOKDDOyeXErUroCihFAd5LQuwXBSpVnKGrj5o/fwxc=
|
||||
google.golang.org/protobuf v1.36.12/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=
|
||||
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
|
||||
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
|
||||
@@ -74,9 +74,15 @@ func (s *PrometheusStorage) GetVersionSeries(days, limit int) VersionSeries {
|
||||
|
||||
if limit > 0 && len(series.Versions) > limit {
|
||||
// Old releases are a long tail of one-cluster bands; keep the versions
|
||||
// most of the fleet is on now and sum the rest into one band.
|
||||
// most of the fleet is on now and sum the rest into one band. The
|
||||
// newest release is kept too, while it is still too small to rank, or
|
||||
// clusters upgrading to it look like they left the named versions.
|
||||
newest := newestRelease(series.Versions, last)
|
||||
ranked := append([]VersionCounts(nil), series.Versions...)
|
||||
sort.Slice(ranked, func(i, j int) bool {
|
||||
if (ranked[i].Version == newest) != (ranked[j].Version == newest) {
|
||||
return ranked[i].Version == newest
|
||||
}
|
||||
if ranked[i].Clusters[last] != ranked[j].Clusters[last] {
|
||||
return ranked[i].Clusters[last] > ranked[j].Clusters[last]
|
||||
}
|
||||
@@ -104,6 +110,21 @@ func (s *PrometheusStorage) GetVersionSeries(days, limit int) VersionSeries {
|
||||
return series
|
||||
}
|
||||
|
||||
// newestRelease is the newest plain release, without a build suffix, that
|
||||
// clusters run on the last day.
|
||||
func newestRelease(versions []VersionCounts, last int) string {
|
||||
newest := ""
|
||||
for _, v := range versions {
|
||||
if _, suffix, ok := versionParts(v.Version); !ok || suffix != "" || v.Clusters[last] == 0 {
|
||||
continue
|
||||
}
|
||||
if newest == "" || versionLess(newest, v.Version) {
|
||||
newest = v.Version
|
||||
}
|
||||
}
|
||||
return newest
|
||||
}
|
||||
|
||||
// versionedHistories drops the samples recorded before the reported version was
|
||||
// kept in history, so the version series spans the days it actually knows a
|
||||
// version for instead of climbing out of a run of blank days.
|
||||
|
||||
@@ -93,6 +93,32 @@ func TestVersionSeriesHoldsForwardAndLimits(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
func TestVersionSeriesKeepsNewestRelease(t *testing.T) {
|
||||
s := newPrometheusStorage(prometheus.NewRegistry())
|
||||
|
||||
seedSamples(s, "a", HistorySample{Version: "4.40"}, -2, -1, 0)
|
||||
seedSamples(s, "b", HistorySample{Version: "4.40"}, -2, -1, 0)
|
||||
seedSamples(s, "c", HistorySample{Version: "4.41"}, -2, -1, 0)
|
||||
seedSamples(s, "d", HistorySample{Version: "4.41"}, -2, -1, 0)
|
||||
// Upgraded to the newest release, which is still the smallest band.
|
||||
seedSamples(s, "e", HistorySample{Version: "4.41"}, -2)
|
||||
seedSamples(s, "e", HistorySample{Version: "4.42"}, -1, 0)
|
||||
// A suffixed build newer than every release does not take its place.
|
||||
seedSamples(s, "f", HistorySample{Version: "4.43-dev"}, -2, -1, 0)
|
||||
|
||||
series := s.GetVersionSeries(3, 2)
|
||||
var kept []string
|
||||
for _, v := range series.Versions {
|
||||
kept = append(kept, v.Version)
|
||||
}
|
||||
if len(kept) != 2 || kept[0] != "4.41" || kept[1] != "4.42" {
|
||||
t.Fatalf("kept = %v, want 4.41 and the newest release 4.42", kept)
|
||||
}
|
||||
if series.Other == nil || series.Other.Count != 2 {
|
||||
t.Fatalf("other = %+v, want 4.40 and 4.43-dev", series.Other)
|
||||
}
|
||||
}
|
||||
|
||||
func TestVersionLess(t *testing.T) {
|
||||
// Ordered oldest to newest; every pair must compare in this order.
|
||||
ordered := []string{"unknown", "3.97", "4.02", "4.30", "4.30-enterprise", "9.99", "10.02"}
|
||||
|
||||
@@ -29,6 +29,7 @@ type FuseTestFramework struct {
|
||||
mountProcess *managedProcess
|
||||
filerAddr string
|
||||
filerPort int
|
||||
masterPort int
|
||||
weedBinary string
|
||||
isSetup bool
|
||||
config *TestConfig
|
||||
@@ -74,6 +75,10 @@ func NewFuseTestFramework(t *testing.T, config *TestConfig) *FuseTestFramework {
|
||||
require.NoError(t, err)
|
||||
|
||||
filerPort := freePort(t)
|
||||
masterPort := freePort(t)
|
||||
for masterPort == filerPort {
|
||||
masterPort = freePort(t)
|
||||
}
|
||||
|
||||
return &FuseTestFramework{
|
||||
t: t,
|
||||
@@ -83,6 +88,7 @@ func NewFuseTestFramework(t *testing.T, config *TestConfig) *FuseTestFramework {
|
||||
logDir: filepath.Join(tempDir, "logs"),
|
||||
filerPort: filerPort,
|
||||
filerAddr: fmt.Sprintf("127.0.0.1:%d", filerPort),
|
||||
masterPort: masterPort,
|
||||
weedBinary: findWeedBinary(),
|
||||
isSetup: false,
|
||||
config: config,
|
||||
@@ -218,6 +224,11 @@ func (f *FuseTestFramework) GetFilerAddr() string {
|
||||
return f.filerAddr
|
||||
}
|
||||
|
||||
// GetMasterAddr returns the master HTTP address of the mini cluster.
|
||||
func (f *FuseTestFramework) GetMasterAddr() string {
|
||||
return fmt.Sprintf("127.0.0.1:%d", f.masterPort)
|
||||
}
|
||||
|
||||
// managedProcess is a started weed sub-command whose exit is watched, so a wait
|
||||
// for it to come up ends the moment it dies instead of burning its full timeout.
|
||||
type managedProcess struct {
|
||||
@@ -321,7 +332,7 @@ func (f *FuseTestFramework) startMini(config *TestConfig) error {
|
||||
args = append(args, "-v=4")
|
||||
}
|
||||
adminPort := freePort(f.t)
|
||||
for adminPort == f.filerPort {
|
||||
for adminPort == f.filerPort || adminPort == f.masterPort {
|
||||
adminPort = freePort(f.t)
|
||||
}
|
||||
args = append(args,
|
||||
@@ -330,6 +341,8 @@ func (f *FuseTestFramework) startMini(config *TestConfig) error {
|
||||
"-ip=127.0.0.1",
|
||||
"-ip.bind=127.0.0.1",
|
||||
"-filer.port="+strconv.Itoa(f.filerPort),
|
||||
"-master.port="+strconv.Itoa(f.masterPort),
|
||||
"-master.port.grpc="+strconv.Itoa(f.masterPort+grpcPortOffset),
|
||||
"-s3=false",
|
||||
"-webdav=false",
|
||||
"-admin.ui=false",
|
||||
|
||||
@@ -0,0 +1,214 @@
|
||||
//go:build linux
|
||||
|
||||
package fuse_test
|
||||
|
||||
import (
|
||||
"encoding/binary"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
"golang.org/x/sys/unix"
|
||||
)
|
||||
|
||||
const (
|
||||
mergePageSize = 8192
|
||||
mergePages = 32
|
||||
)
|
||||
|
||||
// mergeHTTP bounds every HTTP call the test makes to the cluster.
|
||||
var mergeHTTP = &http.Client{Timeout: 30 * time.Second}
|
||||
|
||||
// mergeVacuumHTTP outlasts a master vacuum, which waits up to 30 s per volume
|
||||
// for writes assigned to it to drain before compacting it.
|
||||
var mergeVacuumHTTP = &http.Client{Timeout: 3 * time.Minute}
|
||||
|
||||
// TestReadOpenHandleAfterChunkMerge covers a file a flush merged while a
|
||||
// descriptor kept it open. The merge rewrites the file into new chunks and the
|
||||
// filer deletes the chunks it replaced, so after a vacuum only the new chunks
|
||||
// exist. Reads through the open handle must find them at once, whether or not
|
||||
// the handle has a write it has not flushed yet.
|
||||
func TestReadOpenHandleAfterChunkMerge(t *testing.T) {
|
||||
config := DefaultTestConfig()
|
||||
// The client chunk cache could still hold a replaced chunk; the reads
|
||||
// below have to reach the volume server.
|
||||
config.CacheSizeMB = 0
|
||||
config.MountOptions = append(config.MountOptions, "-cacheCapacityMB=0")
|
||||
framework := NewFuseTestFramework(t, config)
|
||||
defer framework.Cleanup()
|
||||
require.NoError(t, framework.Setup(config))
|
||||
|
||||
t.Run("CleanHandle", func(t *testing.T) {
|
||||
testReadOpenHandleAfterChunkMerge(t, framework, "merged_clean.dat", false)
|
||||
})
|
||||
t.Run("HandleWithUnflushedWrite", func(t *testing.T) {
|
||||
testReadOpenHandleAfterChunkMerge(t, framework, "merged_dirty.dat", true)
|
||||
})
|
||||
}
|
||||
|
||||
func testReadOpenHandleAfterChunkMerge(t *testing.T, framework *FuseTestFramework, name string, unflushedWrite bool) {
|
||||
path := filepath.Join(framework.GetMountPoint(), name)
|
||||
held, err := os.OpenFile(path, os.O_CREATE|os.O_RDWR|os.O_TRUNC, 0644)
|
||||
require.NoError(t, err)
|
||||
defer held.Close()
|
||||
|
||||
version := make([]int, mergePages)
|
||||
whole := make([]byte, 0, mergePages*mergePageSize)
|
||||
for p := 0; p < mergePages; p++ {
|
||||
whole = append(whole, mergePagePattern(p, 0)...)
|
||||
}
|
||||
_, err = held.WriteAt(whole, 0)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, held.Sync())
|
||||
|
||||
// Overlapping 16-page windows: each leaves part of every older window
|
||||
// visible, so the stored chunks soon add up to more than twice the file
|
||||
// size and the next flush merges them.
|
||||
var replaced []mergeChunk
|
||||
for i, start := range []int{0, 3, 6, 9, 12, 15} {
|
||||
before := mergeEntryChunks(t, framework, name)
|
||||
window := make([]byte, 0, 16*mergePageSize)
|
||||
for p := start; p < start+16; p++ {
|
||||
window = append(window, mergePagePattern(p, i+1)...)
|
||||
version[p] = i + 1
|
||||
}
|
||||
_, err = held.WriteAt(window, int64(start*mergePageSize))
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, held.Sync())
|
||||
if after := mergeEntryChunks(t, framework, name); len(after) == 1 && after[0].ModifiedTsNs == 0 {
|
||||
replaced = before
|
||||
break
|
||||
}
|
||||
}
|
||||
require.NotEmpty(t, replaced, "the overlapping writes never made a flush merge the chunks")
|
||||
|
||||
// The filer deletes the replaced chunks after the merge commits; vacuum
|
||||
// once they are deleted so that only the merged chunk is left on disk.
|
||||
master := framework.GetMasterAddr()
|
||||
require.Eventually(t, func() bool {
|
||||
for _, c := range replaced {
|
||||
if mergeChunkStatus(master, c, false) != http.StatusNotFound {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}, 30*time.Second, 200*time.Millisecond, "the replaced chunks were never deleted")
|
||||
require.Eventually(t, func() bool {
|
||||
resp, err := mergeVacuumHTTP.Get(fmt.Sprintf("http://%s/vol/vacuum?garbageThreshold=0.0001", master))
|
||||
if err != nil {
|
||||
return false
|
||||
}
|
||||
resp.Body.Close()
|
||||
if resp.StatusCode != http.StatusOK {
|
||||
return false
|
||||
}
|
||||
for _, c := range replaced {
|
||||
if mergeChunkStatus(master, c, true) != http.StatusNotFound {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}, 4*time.Minute, time.Second, "vacuum left the replaced chunks on disk")
|
||||
|
||||
if unflushedWrite {
|
||||
_, err = held.WriteAt(mergePagePattern(mergePages-1, 99), int64((mergePages-1)*mergePageSize))
|
||||
require.NoError(t, err)
|
||||
version[mergePages-1] = 99
|
||||
}
|
||||
|
||||
// A second descriptor shares the handle the first one keeps open. Drop its
|
||||
// pages from the kernel cache so every read goes to the mount.
|
||||
reader, err := os.Open(path)
|
||||
require.NoError(t, err)
|
||||
defer reader.Close()
|
||||
require.NoError(t, unix.Fadvise(int(reader.Fd()), 0, 0, unix.FADV_DONTNEED))
|
||||
started := time.Now()
|
||||
buf := make([]byte, mergePageSize)
|
||||
for p := 0; p < mergePages; p++ {
|
||||
n, err := reader.ReadAt(buf, int64(p*mergePageSize))
|
||||
require.NoError(t, err, "read page %d through the open handle after the merge", p)
|
||||
require.Equal(t, mergePageSize, n, "page %d", p)
|
||||
require.Equal(t, mergePagePattern(p, version[p]), buf, "page %d", p)
|
||||
}
|
||||
assert.Less(t, time.Since(started), 5*time.Second, "reads through the open handle waited on chunks the merge replaced")
|
||||
}
|
||||
|
||||
func mergePagePattern(page, version int) []byte {
|
||||
b := make([]byte, mergePageSize)
|
||||
for i := 0; i < len(b); i += 8 {
|
||||
binary.LittleEndian.PutUint32(b[i:], uint32(page))
|
||||
binary.LittleEndian.PutUint32(b[i+4:], uint32(version))
|
||||
}
|
||||
return b
|
||||
}
|
||||
|
||||
type mergeChunk struct {
|
||||
FileId string `json:"file_id"`
|
||||
ModifiedTsNs int64 `json:"modified_ts_ns"`
|
||||
Fid *struct {
|
||||
VolumeId uint32 `json:"volume_id"`
|
||||
FileKey uint64 `json:"file_key"`
|
||||
Cookie uint32 `json:"cookie"`
|
||||
} `json:"fid"`
|
||||
}
|
||||
|
||||
func (c mergeChunk) fileId() string {
|
||||
if c.FileId != "" || c.Fid == nil {
|
||||
return c.FileId
|
||||
}
|
||||
return fmt.Sprintf("%d,%x%08x", c.Fid.VolumeId, c.Fid.FileKey, c.Fid.Cookie)
|
||||
}
|
||||
|
||||
// mergeEntryChunks returns the chunks the filer stores for the file.
|
||||
func mergeEntryChunks(t *testing.T, framework *FuseTestFramework, name string) []mergeChunk {
|
||||
t.Helper()
|
||||
resp, err := mergeHTTP.Get(fmt.Sprintf("http://%s/%s?metadata=true", framework.GetFilerAddr(), url.PathEscape(name)))
|
||||
require.NoError(t, err)
|
||||
defer resp.Body.Close()
|
||||
require.Equal(t, http.StatusOK, resp.StatusCode, "filer metadata of %s", name)
|
||||
var entry struct {
|
||||
Chunks []mergeChunk `json:"chunks"`
|
||||
}
|
||||
require.NoError(t, json.NewDecoder(resp.Body).Decode(&entry))
|
||||
return entry.Chunks
|
||||
}
|
||||
|
||||
// mergeChunkStatus HEADs a chunk on the volume server holding it, and returns
|
||||
// 0 when it cannot ask. With readDeleted, a deleted needle still answers until
|
||||
// a vacuum removes it.
|
||||
func mergeChunkStatus(master string, c mergeChunk, readDeleted bool) int {
|
||||
fid := c.fileId()
|
||||
volumeId := strings.SplitN(fid, ",", 2)[0]
|
||||
resp, err := mergeHTTP.Get(fmt.Sprintf("http://%s/dir/lookup?volumeId=%s", master, volumeId))
|
||||
if err != nil {
|
||||
return 0
|
||||
}
|
||||
var lookup struct {
|
||||
Locations []struct {
|
||||
Url string `json:"url"`
|
||||
} `json:"locations"`
|
||||
}
|
||||
err = json.NewDecoder(resp.Body).Decode(&lookup)
|
||||
resp.Body.Close()
|
||||
if err != nil || len(lookup.Locations) == 0 {
|
||||
return 0
|
||||
}
|
||||
target := fmt.Sprintf("http://%s/%s", lookup.Locations[0].Url, fid)
|
||||
if readDeleted {
|
||||
target += "?readDeleted=true"
|
||||
}
|
||||
head, err := mergeHTTP.Head(target)
|
||||
if err != nil {
|
||||
return 0
|
||||
}
|
||||
head.Body.Close()
|
||||
return head.StatusCode
|
||||
}
|
||||
@@ -0,0 +1,116 @@
|
||||
//go:build !windows
|
||||
|
||||
package metadata_subscribe
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strconv"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/stretchr/testify/require"
|
||||
|
||||
"github.com/seaweedfs/seaweedfs/test/testutil"
|
||||
"github.com/seaweedfs/seaweedfs/weed/pb"
|
||||
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
||||
)
|
||||
|
||||
// A peer removal is broadcast only to the filers connected to the master that
|
||||
// saw the peer go. A peer that dies while no master is up (or across a leader
|
||||
// change) is never removed: the filer keeps retrying its address, the peer's
|
||||
// delivery watermark stays at zero, and every aggregated subscriber of that
|
||||
// filer is held at the settled horizon (2 x LogFlushInterval) for good.
|
||||
func TestAggregatedSubscriberNotHeldByPeerThatDiedUnnoticed(t *testing.T) {
|
||||
if testing.Short() {
|
||||
t.Skip("skipping integration test in short mode")
|
||||
}
|
||||
|
||||
weedBinary := findWeedBinary()
|
||||
require.NotEmpty(t, weedBinary, "weed binary not found")
|
||||
|
||||
testDir, err := os.MkdirTemp("", "seaweedfs_peer_unreachable_")
|
||||
require.NoError(t, err)
|
||||
t.Cleanup(func() {
|
||||
if t.Failed() {
|
||||
t.Logf("logs kept at %s", testDir)
|
||||
return
|
||||
}
|
||||
os.RemoveAll(testDir)
|
||||
})
|
||||
|
||||
ports, err := testutil.AllocateMiniPorts(3)
|
||||
require.NoError(t, err)
|
||||
masterPort, filer1Port, filer2Port := ports[0], ports[1], ports[2]
|
||||
master := pb.ServerAddress(fmt.Sprintf("127.0.0.1:%d", masterPort))
|
||||
filer1Address := fmt.Sprintf("127.0.0.1:%d", filer1Port)
|
||||
|
||||
masterArgs := []string{"master",
|
||||
"-ip=127.0.0.1",
|
||||
"-port=" + strconv.Itoa(masterPort),
|
||||
"-mdir=" + mkdir(t, testDir, "master"),
|
||||
"-peers=none"}
|
||||
masterProcess := startProcess(t, weedBinary, filepath.Join(testDir, "master.log"), masterArgs...)
|
||||
require.NoError(t, waitForLeader(masterPort, 60*time.Second))
|
||||
startFiler(t, weedBinary, testDir, "filer1", filer1Port, masterPort)
|
||||
require.NoError(t, waitForHTTPServer(fmt.Sprintf("http://127.0.0.1:%d/", filer1Port), 30*time.Second))
|
||||
filer2 := startFiler(t, weedBinary, testDir, "filer2", filer2Port, masterPort)
|
||||
require.NoError(t, waitForHTTPServer(fmt.Sprintf("http://127.0.0.1:%d/", filer2Port), 30*time.Second))
|
||||
filer2Address := fmt.Sprintf("127.0.0.1:%d", filer2Port)
|
||||
|
||||
// filer1 follows filer2: an entry created on filer2 reaches filer1
|
||||
createPeerEntry(t, filer2Address, "from-filer2")
|
||||
require.NoError(t, waitForPeerEntry(filer1Address, "from-filer2", 60*time.Second),
|
||||
"filer1 never followed filer2")
|
||||
|
||||
ctx, cancel := context.WithCancel(context.Background())
|
||||
defer cancel()
|
||||
events := make(chan *filer_pb.SubscribeMetadataResponse, 1000)
|
||||
sinceNs := time.Now().UnixNano()
|
||||
go subscribeToMetadataWithOptions(ctx, filer1Address, peerEntryDir, sinceNs, events)
|
||||
arrived := make(map[string]time.Time)
|
||||
waitArrival := func(name string, within time.Duration) bool {
|
||||
deadline := time.After(within)
|
||||
for {
|
||||
if _, ok := arrived[name]; ok {
|
||||
return true
|
||||
}
|
||||
select {
|
||||
case ev := <-events:
|
||||
if n := ev.GetEventNotification().GetNewEntry(); n != nil {
|
||||
arrived[n.Name] = time.Now()
|
||||
}
|
||||
case <-deadline:
|
||||
return false
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
createPeerEntry(t, filer1Address, "baseline")
|
||||
require.True(t, waitArrival("baseline", 20*time.Second), "the baseline event never reached the subscriber")
|
||||
|
||||
// filer2 dies while no master is up, so no removal is ever broadcast
|
||||
stopProcess(masterProcess)
|
||||
stopProcess(filer2)
|
||||
startProcess(t, weedBinary, filepath.Join(testDir, "master.log"), masterArgs...)
|
||||
require.NoError(t, waitForLeader(masterPort, 60*time.Second))
|
||||
require.NoError(t, waitForClusterNode(master, filer1Address, 60*time.Second))
|
||||
diedAt := time.Now()
|
||||
|
||||
// Unpatched, every event from here on arrives 2 x LogFlushInterval late.
|
||||
// The dead peer may hold reads for its unreachable bound plus the removal
|
||||
// grace (2 x LogFlushInterval each); after that delivery must be prompt.
|
||||
for i := 0; ; i++ {
|
||||
name := fmt.Sprintf("probe-%d", i)
|
||||
createPeerEntry(t, filer1Address, name)
|
||||
if waitArrival(name, 10*time.Second) {
|
||||
t.Logf("%s delivered promptly %v after the peer died", name, time.Since(diedAt).Round(time.Second))
|
||||
return
|
||||
}
|
||||
if time.Since(diedAt) > 6*time.Minute {
|
||||
t.Fatalf("aggregated delivery still held %v after the peer died unnoticed", time.Since(diedAt).Round(time.Second))
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -2,13 +2,16 @@ package acl
|
||||
|
||||
import (
|
||||
"context"
|
||||
"net/http"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/aws/aws-sdk-go-v2/aws"
|
||||
awsmiddleware "github.com/aws/aws-sdk-go-v2/aws/middleware"
|
||||
"github.com/aws/aws-sdk-go-v2/service/s3"
|
||||
"github.com/aws/aws-sdk-go-v2/service/s3/types"
|
||||
smithyhttp "github.com/aws/smithy-go/transport/http"
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
)
|
||||
@@ -63,12 +66,22 @@ func TestBucketOwnershipControlsLifecycle(t *testing.T) {
|
||||
putObjectOwnership(t, client, bucketName, types.ObjectOwnershipBucketOwnerEnforced)
|
||||
assert.Equal(t, types.ObjectOwnershipBucketOwnerEnforced, getObjectOwnership(t, client, bucketName))
|
||||
|
||||
_, err := client.DeleteBucketOwnershipControls(context.TODO(), &s3.DeleteBucketOwnershipControlsInput{
|
||||
deleted, err := client.DeleteBucketOwnershipControls(context.TODO(), &s3.DeleteBucketOwnershipControlsInput{
|
||||
Bucket: aws.String(bucketName),
|
||||
})
|
||||
require.NoError(t, err)
|
||||
raw, ok := awsmiddleware.GetRawResponse(deleted.ResultMetadata).(*smithyhttp.Response)
|
||||
require.True(t, ok)
|
||||
assert.Equal(t, http.StatusNoContent, raw.StatusCode)
|
||||
|
||||
assert.Equal(t, types.ObjectOwnershipBucketOwnerEnforced, getObjectOwnership(t, client, bucketName))
|
||||
_, err = client.GetBucketOwnershipControls(context.TODO(), &s3.GetBucketOwnershipControlsInput{
|
||||
Bucket: aws.String(bucketName),
|
||||
})
|
||||
require.Error(t, err)
|
||||
assert.Contains(t, err.Error(), "OwnershipControlsNotFoundError")
|
||||
|
||||
putObjectOwnership(t, client, bucketName, types.ObjectOwnershipBucketOwnerPreferred)
|
||||
assert.Equal(t, types.ObjectOwnershipBucketOwnerPreferred, getObjectOwnership(t, client, bucketName))
|
||||
}
|
||||
|
||||
// A bucket with nothing stored already reports BucketOwnerEnforced, so this put has
|
||||
|
||||
@@ -0,0 +1 @@
|
||||
.work
|
||||
@@ -0,0 +1,87 @@
|
||||
# Runs the listing tools and listing strategies of
|
||||
# https://github.com/varveio/s3-listing-study against a local SeaweedFS.
|
||||
#
|
||||
# make test build weed, fetch the study and its pinned tools, start
|
||||
# weed server on free ports, run, stop
|
||||
# make run ENDPOINT=... run against an already running endpoint
|
||||
#
|
||||
# Needs: go, python3, node/npm, cargo, docker (swath image), curl.
|
||||
#
|
||||
# The server runs with -s3.allowBackslashInKey, the AWS-compatible key mode: by
|
||||
# default SeaweedFS rewrites '\' in object keys to '/', and the edge key set
|
||||
# holds a key with a backslash.
|
||||
|
||||
STUDY_REPO ?= https://github.com/varveio/s3-listing-study.git
|
||||
STUDY_REV ?= 666ec620d245e16baaaa0cf53461382f42c35917
|
||||
WORK_DIR ?= $(CURDIR)/.work
|
||||
STUDY_DIR ?= $(WORK_DIR)/s3-listing-study
|
||||
TOOLS_DIR ?= $(WORK_DIR)/tools
|
||||
VENV ?= $(WORK_DIR)/venv
|
||||
WEED_BINARY ?= $(WORK_DIR)/weed
|
||||
TOOLS ?= aws-cli,minio-mc,ps3,rclone,s3-fast-list,s3kor,s3p,s4cmd,s5cmd,s7cmd,swath
|
||||
ACCESS_KEY ?= listing_study_access
|
||||
SECRET_KEY ?= listing_study_secret
|
||||
JOBS ?= 4
|
||||
ONLY ?=
|
||||
|
||||
.PHONY: test run build-weed study venv tools start-server stop-server clean
|
||||
|
||||
test: build-weed tools
|
||||
@$(MAKE) --no-print-directory start-server; status=$$?; \
|
||||
if [ $$status -eq 0 ]; then \
|
||||
$(MAKE) --no-print-directory run ENDPOINT=http://127.0.0.1:$$(cat $(WORK_DIR)/s3.port); status=$$?; \
|
||||
fi; \
|
||||
$(MAKE) --no-print-directory stop-server; exit $$status
|
||||
|
||||
build-weed:
|
||||
mkdir -p $(WORK_DIR)
|
||||
cd ../../../weed && go build -buildvcs=false -o $(WEED_BINARY) .
|
||||
|
||||
study:
|
||||
@if [ "$$(git -C $(STUDY_DIR) rev-parse HEAD 2>/dev/null)" != "$(STUDY_REV)" ]; then \
|
||||
git init -q $(STUDY_DIR) && \
|
||||
git -C $(STUDY_DIR) fetch -q --depth 1 $(STUDY_REPO) $(STUDY_REV) && \
|
||||
git -C $(STUDY_DIR) checkout -q --force FETCH_HEAD; \
|
||||
fi
|
||||
|
||||
venv:
|
||||
@test -x $(VENV)/bin/python || python3 -m venv $(VENV)
|
||||
$(VENV)/bin/pip install -q -r requirements.txt
|
||||
|
||||
tools: study venv
|
||||
$(VENV)/bin/python install_tools.py --study $(STUDY_DIR) --tools-dir $(TOOLS_DIR) --tools $(TOOLS)
|
||||
|
||||
start-server:
|
||||
@mkdir -p $(WORK_DIR)
|
||||
@set -e; data=$$(mktemp -d $(WORK_DIR)/data.XXXXXX); ports=$$(python3 free_ports.py 5); \
|
||||
set -- $$ports; \
|
||||
$(WEED_BINARY) server -filer -s3 -ip 127.0.0.1 -ip.bind 127.0.0.1 -dir=$$data \
|
||||
-master.peers=none -master.raftHashicorp -master.electionTimeout 1s -master.volumeSizeLimitMB=1024 \
|
||||
-volume.max=50 -volume.preStopSeconds=1 \
|
||||
-master.port=$$1 -volume.port=$$2 -filer.port=$$3 -s3.port=$$4 -metricsPort=$$5 \
|
||||
-s3.port.iceberg=0 -s3.port.lance=0 -s3.allowBackslashInKey -s3.config=$(CURDIR)/s3.json \
|
||||
> $(WORK_DIR)/weed.log 2>&1 & echo $$! > $(WORK_DIR)/weed.pid; \
|
||||
echo $$4 > $(WORK_DIR)/s3.port; \
|
||||
for i in $$(seq 1 90); do \
|
||||
if curl -sf -o /dev/null http://127.0.0.1:$$3/ && curl -s -o /dev/null http://127.0.0.1:$$4/; then \
|
||||
echo "SeaweedFS S3 ready on port $$4"; exit 0; fi; \
|
||||
kill -0 $$(cat $(WORK_DIR)/weed.pid) || { tail -50 $(WORK_DIR)/weed.log; exit 1; }; \
|
||||
sleep 1; \
|
||||
done; tail -50 $(WORK_DIR)/weed.log; exit 1
|
||||
|
||||
stop-server:
|
||||
@if [ -f $(WORK_DIR)/weed.pid ]; then \
|
||||
pid=$$(cat $(WORK_DIR)/weed.pid); kill $$pid 2>/dev/null || true; \
|
||||
for i in $$(seq 1 20); do kill -0 $$pid 2>/dev/null || break; sleep 0.5; done; \
|
||||
rm -f $(WORK_DIR)/weed.pid; \
|
||||
fi
|
||||
|
||||
run: study
|
||||
$(VENV)/bin/python run_study.py --endpoint $(ENDPOINT) \
|
||||
--access-key $(ACCESS_KEY) --secret-key $(SECRET_KEY) \
|
||||
--study $(STUDY_DIR) --tools-dir $(TOOLS_DIR) --work-dir $(WORK_DIR)/run \
|
||||
--tools $(TOOLS) --jobs $(JOBS) --expected-failures expected_failures.txt \
|
||||
$(if $(ONLY),--only '$(ONLY)')
|
||||
|
||||
clean: stop-server
|
||||
rm -rf .work
|
||||
@@ -0,0 +1,29 @@
|
||||
# Cases that fail for reasons outside SeaweedFS. A listed case that passes is
|
||||
# reported as XPASS and fails the run, so this list has to shrink with fixes.
|
||||
# Format: <case name> # reason
|
||||
|
||||
# aws-cli prints "None" for a --query over a page with no Contents (the canary
|
||||
# has no root-level keys); the capsule normalizer reads it as a malformed row.
|
||||
aws-cli:s3api-v2-remainder:canary:/ # capsule normalizer cannot parse aws-cli's "None"
|
||||
|
||||
# The edge bucket holds zero-byte directory markers (markers/dir/, markers/empty/).
|
||||
# These modes list them as directories, not objects: rclone's --files-only and
|
||||
# lsf --files-only drop them, s5cmd types any key ending in "/" as DIR and the
|
||||
# capsule normalizer drops DIR rows from its recursive modes. The reference
|
||||
# probes check that SeaweedFS returns both markers as Contents.
|
||||
rclone:recursive-fastlist:edge:/ # tool hides directory marker objects
|
||||
rclone:recursive-hierarchical:edge:/ # tool hides directory marker objects
|
||||
rclone:recursive-walk:edge:/ # tool hides directory marker objects
|
||||
rclone:listv1:edge:/ # tool hides directory marker objects
|
||||
rclone:lsf:edge:/ # tool hides directory marker objects
|
||||
s5cmd:recursive:edge:/ # tool hides directory marker objects
|
||||
s5cmd:listv1:edge:/ # tool hides directory marker objects
|
||||
s5cmd:allversions:edge:/ # tool hides directory marker objects
|
||||
|
||||
# Deleting the last key under a prefix leaves its filer directory behind, and an
|
||||
# empty directory is still listed as a CommonPrefix until the filer's empty-folder
|
||||
# cleanup removes it (2 minutes by default). This is deliberate: directories made
|
||||
# through mount or the filer stay visible to S3 clients (dirHoldsOnlyHiddenEntries
|
||||
# in weed/s3api/s3api_object_handlers_list.go). AWS derives CommonPrefixes from
|
||||
# keys only, so prefix-discovery tools briefly see the deleted prefix.
|
||||
reference:study-churn:deleted-prefixes # empty directories are listed until cleanup
|
||||
@@ -0,0 +1,27 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Print N free TCP ports whose +10000 gRPC companions are free too, all below
|
||||
the Linux ephemeral range (32768+) that outgoing connections draw from."""
|
||||
|
||||
import random
|
||||
import socket
|
||||
import sys
|
||||
|
||||
|
||||
def free(port: int) -> bool:
|
||||
with socket.socket() as s:
|
||||
try:
|
||||
s.bind(("127.0.0.1", port))
|
||||
return True
|
||||
except OSError:
|
||||
return False
|
||||
|
||||
|
||||
picked: list[int] = []
|
||||
taken: list[int] = []
|
||||
while len(picked) < int(sys.argv[1]):
|
||||
port = random.randrange(10000, 22000)
|
||||
pair = (port, port + 10000)
|
||||
if all(abs(p - t) > 20 for p in pair for t in taken) and all(free(p) for p in pair):
|
||||
picked.append(port)
|
||||
taken += pair
|
||||
print(*picked)
|
||||
@@ -0,0 +1,247 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Install the listing tools pinned by the s3-listing-study checkout.
|
||||
|
||||
Every artifact locator and sha256 comes from the study's own
|
||||
tools/<tool>/build/image.json, so bumping STUDY_REV bumps the tools with it.
|
||||
Tools land under TOOLS_DIR at the paths listed in run_study.PATH_MAP.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import shutil
|
||||
import stat
|
||||
import subprocess
|
||||
import sys
|
||||
import tarfile
|
||||
import urllib.request
|
||||
import zipfile
|
||||
from pathlib import Path
|
||||
|
||||
ALL_TOOLS = (
|
||||
"aws-cli",
|
||||
"minio-mc",
|
||||
"ps3",
|
||||
"rclone",
|
||||
"s3-fast-list",
|
||||
"s3kor",
|
||||
"s3p",
|
||||
"s4cmd",
|
||||
"s5cmd",
|
||||
"s7cmd",
|
||||
"swath",
|
||||
)
|
||||
|
||||
MC_COMMIT = "d6541ea280b73a834b64d4097e21f2be77676104"
|
||||
"""github.com/minio/mc tag RELEASE.2025-08-13T08-35-41Z."""
|
||||
|
||||
SOURCE_PATCHES = {
|
||||
"s3-fast-list": (
|
||||
"s3-fast-list/src/data_map.rs",
|
||||
(
|
||||
(
|
||||
" match ctx.data_map_channel.try_recv() {",
|
||||
" let list_tasks_running = ctx.all_list_tasks_is_running();\n"
|
||||
" match ctx.data_map_channel.try_recv() {",
|
||||
),
|
||||
(
|
||||
"!ctx.all_list_tasks_is_running() && !has_more_in_queue",
|
||||
"!list_tasks_running && !has_more_in_queue",
|
||||
),
|
||||
),
|
||||
),
|
||||
}
|
||||
"""Source fixes applied before a build. s3-fast-list's data map reads the channel
|
||||
and then the list-task state, so a last page sent and completed between the two
|
||||
reads is dropped and the run exits 0 with a short or empty listing. Reading the
|
||||
state first means a finished task's pages are already in the channel."""
|
||||
|
||||
|
||||
def patch_source(tool: str, work: Path) -> None:
|
||||
rel, edits = SOURCE_PATCHES[tool]
|
||||
path = work / rel
|
||||
text = path.read_text()
|
||||
for old, new in edits:
|
||||
if text.count(old) != 1:
|
||||
raise SystemExit(f"{tool}: {rel} no longer matches its source patch: {old!r}")
|
||||
text = text.replace(old, new)
|
||||
path.write_text(text)
|
||||
|
||||
|
||||
def fetch(url: str, sha256: str, dest: Path) -> Path:
|
||||
if dest.exists() and hashlib.sha256(dest.read_bytes()).hexdigest() == sha256:
|
||||
return dest
|
||||
dest.parent.mkdir(parents=True, exist_ok=True)
|
||||
tmp = dest.with_suffix(dest.suffix + ".part")
|
||||
request = urllib.request.Request(url, headers={"User-Agent": "curl/8"})
|
||||
with urllib.request.urlopen(request, timeout=300) as response, tmp.open("wb") as out:
|
||||
shutil.copyfileobj(response, out)
|
||||
digest = hashlib.sha256(tmp.read_bytes()).hexdigest()
|
||||
if digest != sha256:
|
||||
tmp.unlink()
|
||||
raise SystemExit(f"{url}: sha256 {digest} != pinned {sha256}")
|
||||
tmp.rename(dest)
|
||||
return dest
|
||||
|
||||
|
||||
def executable(path: Path) -> None:
|
||||
path.chmod(path.stat().st_mode | stat.S_IXUSR | stat.S_IXGRP | stat.S_IXOTH)
|
||||
|
||||
|
||||
def wrapper(path: Path, body: str) -> None:
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
path.write_text(f"#!/bin/sh\n{body}\n")
|
||||
executable(path)
|
||||
|
||||
|
||||
def tar_member(archive: Path, member: str, dest: Path) -> None:
|
||||
with tarfile.open(archive) as tar:
|
||||
source = tar.extractfile(member)
|
||||
if source is None:
|
||||
raise SystemExit(f"{archive}: no member {member}")
|
||||
dest.parent.mkdir(parents=True, exist_ok=True)
|
||||
dest.write_bytes(source.read())
|
||||
executable(dest)
|
||||
|
||||
|
||||
def install(tool: str, study: Path, tools_dir: Path) -> None:
|
||||
image = json.loads((study / "tools" / tool / "build" / "image.json").read_text())
|
||||
artifact = image["tool_artifact"]
|
||||
url, sha = artifact["locator"], artifact["sha256"]
|
||||
dl = tools_dir / "downloads"
|
||||
bin_dir = tools_dir / "bin"
|
||||
bin_dir.mkdir(parents=True, exist_ok=True)
|
||||
name = url.rsplit("/", 1)[-1]
|
||||
stamp = tools_dir / "installed" / tool
|
||||
installed = sha + ("+patched" if tool in SOURCE_PATCHES else "")
|
||||
if stamp.exists() and stamp.read_text() == installed:
|
||||
print(f"{tool} {image.get('tool_version', '')} already installed")
|
||||
return
|
||||
|
||||
if tool == "aws-cli":
|
||||
archive = fetch(url, sha, dl / name)
|
||||
work = tools_dir / "aws-cli-src"
|
||||
shutil.rmtree(work, ignore_errors=True)
|
||||
with zipfile.ZipFile(archive) as zf:
|
||||
zf.extractall(work)
|
||||
for rel in ("aws/install", "aws/dist/aws", "aws/dist/aws_completer"):
|
||||
executable(work / rel)
|
||||
subprocess.run(
|
||||
[
|
||||
str(work / "aws" / "install"),
|
||||
"--install-dir",
|
||||
str(tools_dir / "aws-cli"),
|
||||
"--bin-dir",
|
||||
str(tools_dir / "aws-cli-bin"),
|
||||
"--update",
|
||||
],
|
||||
check=True,
|
||||
)
|
||||
shutil.rmtree(work)
|
||||
elif tool == "minio-mc":
|
||||
# dl.min.io answers 410 Gone for every archived mc release, so build the
|
||||
# same release tag from source instead.
|
||||
if image["tool_version"] != "RELEASE.2025-08-13T08-35-41Z":
|
||||
raise SystemExit(f"minio-mc: no source commit pinned for {image['tool_version']}")
|
||||
subprocess.run(
|
||||
["go", "install", f"github.com/minio/mc@{MC_COMMIT}"],
|
||||
env={**os.environ, "GOBIN": str(bin_dir)},
|
||||
check=True,
|
||||
)
|
||||
elif tool == "ps3":
|
||||
shutil.copyfile(fetch(url, sha, dl / name), bin_dir / "pS3")
|
||||
executable(bin_dir / "pS3")
|
||||
elif tool == "rclone":
|
||||
archive = fetch(url, sha, dl / name)
|
||||
with zipfile.ZipFile(archive) as zf:
|
||||
member = f"{name.removesuffix('.zip')}/rclone"
|
||||
(bin_dir / "rclone").write_bytes(zf.read(member))
|
||||
executable(bin_dir / "rclone")
|
||||
elif tool == "s3kor":
|
||||
tar_member(fetch(url, sha, dl / name), "s3kor", bin_dir / "s3kor")
|
||||
elif tool == "s5cmd":
|
||||
tar_member(fetch(url, sha, dl / name), "s5cmd", bin_dir / "s5cmd")
|
||||
elif tool == "s7cmd":
|
||||
tar_member(fetch(url, sha, dl / name), "s7cmd", bin_dir / "s7cmd")
|
||||
elif tool == "s3p":
|
||||
work = tools_dir / "s3p"
|
||||
work.mkdir(parents=True, exist_ok=True)
|
||||
for f in ("package.json", "package-lock.json"):
|
||||
shutil.copyfile(study / "tools/s3p/build" / f, work / f)
|
||||
subprocess.run(["npm", "ci", "--ignore-scripts", "--no-audit", "--no-fund"], cwd=work, check=True)
|
||||
wrapper(bin_dir / "s3p", f'exec node "{work}/node_modules/s3p/bin/s3p" "$@"')
|
||||
elif tool == "s4cmd":
|
||||
archive = fetch(url, sha, dl / name)
|
||||
venv = tools_dir / "s4cmd-venv"
|
||||
subprocess.run([sys.executable, "-m", "venv", "--clear", str(venv)], check=True)
|
||||
subprocess.run(
|
||||
[
|
||||
str(venv / "bin" / "python"),
|
||||
"-m",
|
||||
"pip",
|
||||
"install",
|
||||
"--quiet",
|
||||
"--require-hashes",
|
||||
"--no-deps",
|
||||
"-r",
|
||||
str(study / "tools/s4cmd/build/requirements.txt"),
|
||||
],
|
||||
check=True,
|
||||
)
|
||||
script = tools_dir / "s4cmd" / "s4cmd.py"
|
||||
with tarfile.open(archive) as tar:
|
||||
source = tar.extractfile("s4cmd-2.1.0/s4cmd.py")
|
||||
assert source is not None
|
||||
script.parent.mkdir(parents=True, exist_ok=True)
|
||||
script.write_bytes(source.read())
|
||||
wrapper(bin_dir / "s4cmd", f'exec "{venv}/bin/python" "{script}" "$@"')
|
||||
elif tool == "s3-fast-list":
|
||||
archive = fetch(url, sha, dl / name)
|
||||
work = tools_dir / "s3-fast-list-src"
|
||||
shutil.rmtree(work, ignore_errors=True)
|
||||
work.mkdir(parents=True)
|
||||
subprocess.run(["tar", "xzf", str(archive), "--strip-components=1", "-C", str(work)], check=True)
|
||||
shutil.copyfile(study / "tools/s3-fast-list/build/Cargo.lock", work / "Cargo.lock")
|
||||
patch_source(tool, work)
|
||||
subprocess.run(["cargo", "build", "--release", "--locked", "--quiet"], cwd=work, check=True)
|
||||
for exe in ("s3-fast-list", "ks-tool"):
|
||||
shutil.copyfile(work / "target/release" / exe, bin_dir / exe)
|
||||
executable(bin_dir / exe)
|
||||
elif tool == "swath":
|
||||
ref = f"{url}@sha256:{sha}"
|
||||
subprocess.run(["docker", "pull", "--quiet", ref], check=True, stdout=subprocess.DEVNULL)
|
||||
cid = subprocess.run(
|
||||
["docker", "create", ref], check=True, capture_output=True, text=True
|
||||
).stdout.strip()
|
||||
try:
|
||||
dest = tools_dir / "swath"
|
||||
shutil.rmtree(dest, ignore_errors=True)
|
||||
dest.mkdir(parents=True)
|
||||
subprocess.run(["docker", "cp", f"{cid}:/opt/java/openjdk", str(dest / "openjdk")], check=True)
|
||||
subprocess.run(["docker", "cp", f"{cid}:/opt/swath/swath.jar", str(dest / "swath.jar")], check=True)
|
||||
finally:
|
||||
subprocess.run(["docker", "rm", cid], check=True, stdout=subprocess.DEVNULL)
|
||||
else:
|
||||
raise SystemExit(f"unknown tool {tool}")
|
||||
stamp.parent.mkdir(parents=True, exist_ok=True)
|
||||
stamp.write_text(installed)
|
||||
print(f"installed {tool} {image.get('tool_version', '')}")
|
||||
|
||||
|
||||
def main() -> int:
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("--study", required=True, type=Path)
|
||||
parser.add_argument("--tools-dir", required=True, type=Path)
|
||||
parser.add_argument("--tools", default=",".join(ALL_TOOLS))
|
||||
args = parser.parse_args()
|
||||
for tool in filter(None, args.tools.split(",")):
|
||||
install(tool, args.study.resolve(), args.tools_dir.resolve())
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
os.umask(0o022)
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,6 @@
|
||||
# Versions the pinned s3-listing-study uv.lock resolves for the capsule normalizers.
|
||||
duckdb==1.5.5
|
||||
ijson==3.5.1
|
||||
pyyaml==6.0.3
|
||||
zstandard==0.25.0
|
||||
botocore==1.44.5
|
||||
@@ -0,0 +1,922 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Run the s3-listing-study tool capsules and ListObjects reference probes against SeaweedFS.
|
||||
|
||||
Tool cases: every mode of every capsule under the study's tools/ is compiled by
|
||||
the capsule's own command.py (benchmark.adapters.compile_command, with the
|
||||
custom-endpoint wiring the study's replay-endpoint pilot established), run
|
||||
against SeaweedFS with the pinned tool build, normalized by the capsule's own
|
||||
normalize.py, and the normalized listing is compared exactly against the keys
|
||||
that were written.
|
||||
|
||||
Reference probes: raw, signed ListObjectsV2/ListObjects requests implementing
|
||||
the strategies the study classifies tools by (serial pagination, delimiter
|
||||
prefix discovery, start-after range splitting) plus the request semantics in
|
||||
docs/s3-reference.md, checked against the byte-ordered key set.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import concurrent.futures
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import shutil
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
import traceback
|
||||
import urllib.error
|
||||
import urllib.parse
|
||||
import urllib.request
|
||||
import xml.etree.ElementTree as ET
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
|
||||
REGION = "us-east-1"
|
||||
S3NS = "{http://s3.amazonaws.com/doc/2006-03-01/}"
|
||||
|
||||
|
||||
def canary_keys() -> dict[str, int]:
|
||||
"""benchmark/fixtures/replay-canary/generate.sql: 2,048 keys in 16 prefixes."""
|
||||
return {f"group-{i // 128:02d}/object-{i:06d}.dat": 1024 + i for i in range(2048)}
|
||||
|
||||
|
||||
EDGE_KEYS = [
|
||||
# docs/smoke-bucket.md: a root key beside the prefixes, for delimiter checks.
|
||||
"index.html",
|
||||
# docs/s3-reference.md examples.
|
||||
"test_file(3).png",
|
||||
"photos/2006/February/sample.jpg",
|
||||
"photos/2006/January/sample.jpg",
|
||||
"photos/2007/sample.jpg",
|
||||
"notes/summer/july",
|
||||
"notes/summer/august",
|
||||
"notes/winter",
|
||||
# Byte order around the '/' (0x2f) delimiter.
|
||||
"order/a",
|
||||
"order/a b",
|
||||
"order/a!b",
|
||||
"order/a-b",
|
||||
"order/a.b",
|
||||
"order/a/b",
|
||||
"order/a/c/d",
|
||||
"order/a0",
|
||||
"order/aa",
|
||||
"order/a~",
|
||||
"order/A",
|
||||
"order/b",
|
||||
# Zero-byte directory markers.
|
||||
"markers/dir/",
|
||||
"markers/dir/child",
|
||||
"markers/empty/",
|
||||
# Characters that need XML or URL escaping.
|
||||
"chars/space key",
|
||||
"chars/plus+key",
|
||||
"chars/percent%20key",
|
||||
"chars/amp&key",
|
||||
"chars/lt<gt>key",
|
||||
'chars/quote"key',
|
||||
"chars/apos'key",
|
||||
"chars/hash#key",
|
||||
"chars/question?key",
|
||||
"chars/equals=key",
|
||||
"chars/semicolon;key",
|
||||
"chars/colon:key",
|
||||
"chars/at@key",
|
||||
"chars/comma,key",
|
||||
"chars/star*key",
|
||||
"chars/bang!key",
|
||||
"chars/dollar$key",
|
||||
"chars/caret^key",
|
||||
"chars/backslash\\key",
|
||||
"chars/brace{key}",
|
||||
"chars/pipe|key",
|
||||
"chars/backtick`key",
|
||||
"chars/tilde~key",
|
||||
# UTF-8 byte order, which differs from UTF-16 order above U+FFFF.
|
||||
"unicode/café-nfc",
|
||||
"unicode/café-nfd",
|
||||
"unicode/日本語.txt",
|
||||
"unicode/。-halfwidth",
|
||||
"unicode/\U0001f600-emoji",
|
||||
"unicode/z-ascii",
|
||||
"deep/a/b/c/d/e/f/g/h/i/j/k.txt",
|
||||
"long/" + "/".join(["y" * 200] * 4),
|
||||
]
|
||||
|
||||
|
||||
def edge_keys() -> dict[str, int]:
|
||||
return {k: (0 if k.endswith("/") else 100 + i) for i, k in enumerate(EDGE_KEYS)}
|
||||
|
||||
|
||||
def body_for(key: str, size: int) -> bytes:
|
||||
seed = hashlib.sha256(key.encode()).digest()
|
||||
return (seed * (size // len(seed) + 1))[:size]
|
||||
|
||||
|
||||
def utf8_sorted(keys) -> list[str]:
|
||||
return sorted(keys, key=lambda k: k.encode("utf-8"))
|
||||
|
||||
|
||||
# ---------------------------------------------------------------- signed HTTP
|
||||
|
||||
|
||||
class S3:
|
||||
def __init__(self, endpoint: str, access: str, secret: str) -> None:
|
||||
from botocore.auth import S3SigV4Auth
|
||||
from botocore.credentials import Credentials
|
||||
|
||||
self.endpoint = endpoint.rstrip("/")
|
||||
self.auth = S3SigV4Auth(Credentials(access, secret), "s3", REGION)
|
||||
|
||||
def request(
|
||||
self, method: str, path: str, params: list[tuple[str, str]] | None = None, body: bytes = b""
|
||||
) -> tuple[int, bytes]:
|
||||
from botocore.awsrequest import AWSRequest
|
||||
|
||||
query = "&".join(
|
||||
f"{urllib.parse.quote(k, safe='-_.~')}={urllib.parse.quote(v, safe='-_.~')}"
|
||||
for k, v in (params or [])
|
||||
)
|
||||
url = self.endpoint + urllib.parse.quote(path, safe="/-_.~") + (f"?{query}" if query else "")
|
||||
req = AWSRequest(method=method, url=url, data=body)
|
||||
req.headers["x-amz-content-sha256"] = hashlib.sha256(body).hexdigest()
|
||||
self.auth.add_auth(req)
|
||||
prepared = req.prepare()
|
||||
http = urllib.request.Request(prepared.url, data=body or None, method=method)
|
||||
for k, v in prepared.headers.items():
|
||||
http.add_header(k, v)
|
||||
try:
|
||||
with urllib.request.urlopen(http, timeout=60) as resp:
|
||||
return resp.status, resp.read()
|
||||
except urllib.error.HTTPError as err:
|
||||
return err.code, err.read()
|
||||
|
||||
def put_object(self, bucket: str, key: str, body: bytes) -> None:
|
||||
# The first writes to a new bucket can get a retryable 500 while its
|
||||
# volumes grow; SDK clients retry those the same way.
|
||||
for attempt in range(10):
|
||||
status, out = self.request("PUT", f"/{bucket}/{key}", body=body)
|
||||
if status < 500:
|
||||
break
|
||||
time.sleep(0.5 * (attempt + 1))
|
||||
if status != 200:
|
||||
raise RuntimeError(f"PUT {bucket}/{key!r}: {status} {out[:300]!r}")
|
||||
|
||||
def delete_object(self, bucket: str, key: str) -> None:
|
||||
status, out = self.request("DELETE", f"/{bucket}/{key}")
|
||||
if status != 204:
|
||||
raise RuntimeError(f"DELETE {bucket}/{key!r}: {status} {out[:300]!r}")
|
||||
|
||||
def create_bucket(self, bucket: str) -> None:
|
||||
status, out = self.request("PUT", f"/{bucket}")
|
||||
if status not in (200, 409):
|
||||
raise RuntimeError(f"create bucket {bucket}: {status} {out[:300]!r}")
|
||||
|
||||
def list_page(self, bucket: str, params: list[tuple[str, str]]) -> ET.Element:
|
||||
status, out = self.request("GET", f"/{bucket}", params)
|
||||
if status != 200:
|
||||
raise AssertionError(f"list {params}: HTTP {status} {out[:300]!r}")
|
||||
return ET.fromstring(out)
|
||||
|
||||
|
||||
def text(el: ET.Element, name: str) -> str | None:
|
||||
child = el.find(S3NS + name)
|
||||
return None if child is None else (child.text or "")
|
||||
|
||||
|
||||
@dataclass
|
||||
class Page:
|
||||
entries: list[tuple[str, str]] # ("key"|"prefix", value) in response order
|
||||
truncated: bool
|
||||
token: str | None
|
||||
next_marker: str | None
|
||||
key_count: str | None
|
||||
raw: ET.Element
|
||||
|
||||
|
||||
def check_byte_order(values: list[str], what: str) -> None:
|
||||
for a, b in zip(values, values[1:]):
|
||||
assert a.encode() <= b.encode(), f"{what} out of byte order: {a!r} before {b!r}"
|
||||
|
||||
|
||||
def parse_page(root: ET.Element, url_encoded: bool) -> Page:
|
||||
dec = urllib.parse.unquote_plus if url_encoded else (lambda s: s)
|
||||
entries: list[tuple[str, str]] = []
|
||||
for child in root:
|
||||
if child.tag == S3NS + "Contents":
|
||||
entries.append(("key", dec(text(child, "Key") or "")))
|
||||
elif child.tag == S3NS + "CommonPrefixes":
|
||||
entries.append(("prefix", dec(text(child, "Prefix") or "")))
|
||||
nm = text(root, "NextMarker")
|
||||
# XML carries Contents and CommonPrefixes as two lists, each in byte order;
|
||||
# their merged byte order is what pagination has to respect.
|
||||
for kind in ("key", "prefix"):
|
||||
check_byte_order([v for k, v in entries if k == kind], f"{kind} list")
|
||||
entries.sort(key=lambda e: e[1].encode())
|
||||
return Page(
|
||||
entries,
|
||||
text(root, "IsTruncated") == "true",
|
||||
text(root, "NextContinuationToken"),
|
||||
dec(nm) if nm is not None else None,
|
||||
text(root, "KeyCount"),
|
||||
root,
|
||||
)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------- expectations
|
||||
|
||||
|
||||
def direct_view(keys: list[str], prefix: str, delimiter: str) -> list[tuple[str, str]]:
|
||||
"""What a delimiter listing of prefix returns, in byte order."""
|
||||
out: dict[str, str] = {}
|
||||
for k in keys:
|
||||
if not k.startswith(prefix):
|
||||
continue
|
||||
rest = k[len(prefix) :]
|
||||
idx = rest.find(delimiter) if delimiter else -1
|
||||
if idx >= 0:
|
||||
out[prefix + rest[: idx + len(delimiter)]] = "prefix"
|
||||
else:
|
||||
out[k] = "key"
|
||||
return [(out[k], k) for k in utf8_sorted(out)]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------- reference probes
|
||||
|
||||
|
||||
class Probe:
|
||||
def __init__(self, s3: S3, bucket: str, keys: list[str]) -> None:
|
||||
self.s3, self.bucket, self.keys = s3, bucket, utf8_sorted(keys)
|
||||
|
||||
def v2_all(self, base: list[tuple[str, str]], max_keys: int, url: bool = False) -> list[Page]:
|
||||
pages: list[Page] = []
|
||||
token = None
|
||||
while True:
|
||||
params = [("list-type", "2"), ("max-keys", str(max_keys)), *base]
|
||||
if url:
|
||||
params.append(("encoding-type", "url"))
|
||||
if token:
|
||||
params.append(("continuation-token", token))
|
||||
page = parse_page(self.s3.list_page(self.bucket, params), url)
|
||||
pages.append(page)
|
||||
n = len(page.entries)
|
||||
assert n <= max_keys, f"page holds {n} > max-keys {max_keys}"
|
||||
assert page.key_count == str(n), f"KeyCount {page.key_count} != {n} entries"
|
||||
if not page.truncated:
|
||||
assert not page.token, "NextContinuationToken on an untruncated page"
|
||||
return pages
|
||||
assert page.token, "IsTruncated without NextContinuationToken"
|
||||
assert len(pages) < 10000, "pagination does not terminate"
|
||||
token = page.token
|
||||
|
||||
def v1_all(self, base: list[tuple[str, str]], max_keys: int, delimiter: str) -> list[Page]:
|
||||
pages: list[Page] = []
|
||||
marker = None
|
||||
while True:
|
||||
params = [("max-keys", str(max_keys)), *base]
|
||||
if delimiter:
|
||||
params.append(("delimiter", delimiter))
|
||||
if marker is not None:
|
||||
params.append(("marker", marker))
|
||||
page = parse_page(self.s3.list_page(self.bucket, params), False)
|
||||
pages.append(page)
|
||||
assert len(page.entries) <= max_keys
|
||||
if not page.truncated:
|
||||
return pages
|
||||
if delimiter:
|
||||
assert page.next_marker, "truncated delimiter page without NextMarker"
|
||||
marker = page.next_marker
|
||||
else:
|
||||
marker = page.next_marker or page.entries[-1][1]
|
||||
assert len(pages) < 10000, "pagination does not terminate"
|
||||
|
||||
@staticmethod
|
||||
def flat(pages: list[Page]) -> list[tuple[str, str]]:
|
||||
return [e for p in pages for e in p.entries]
|
||||
|
||||
def expect_eq(self, got, want, what: str) -> None:
|
||||
if got != want:
|
||||
gs, ws = set(got), set(want)
|
||||
missing = [w for w in want if w not in gs][:5]
|
||||
extra = [g for g in got if g not in ws][:5]
|
||||
first = next((i for i, (a, b) in enumerate(zip(got, want)) if a != b), min(len(got), len(want)))
|
||||
raise AssertionError(
|
||||
f"{what}: got {len(got)} want {len(want)}; missing {missing} extra {extra}; "
|
||||
f"first difference at {first}: got {got[first:first + 3]} want {want[first:first + 3]}"
|
||||
)
|
||||
|
||||
# Serial pagination (aws-cli, mc, s3kor, s5cmd ls).
|
||||
def serial(self, prefix: str, max_keys: int) -> None:
|
||||
want = [("key", k) for k in self.keys if k.startswith(prefix)]
|
||||
got = self.flat(self.v2_all([("prefix", prefix)], max_keys))
|
||||
self.expect_eq(got, want, f"serial prefix={prefix!r} max-keys={max_keys}")
|
||||
|
||||
# Delimiter view and page boundaries inside it.
|
||||
def delimiter(self, prefix: str, delimiter: str, max_keys: int, v1: bool = False) -> None:
|
||||
want = direct_view(self.keys, prefix, delimiter)
|
||||
if v1:
|
||||
got = self.flat(self.v1_all([("prefix", prefix)], max_keys, delimiter))
|
||||
else:
|
||||
got = self.flat(self.v2_all([("prefix", prefix), ("delimiter", delimiter)], max_keys))
|
||||
self.expect_eq(got, want, f"{'v1' if v1 else 'v2'} delimiter={delimiter!r} prefix={prefix!r} max-keys={max_keys}")
|
||||
|
||||
# Prefix discovery (rclone walk, s7cmd, s4cmd): recurse through CommonPrefixes.
|
||||
def walk(self, max_keys: int, v1: bool = False) -> None:
|
||||
found: list[str] = []
|
||||
queue = [""]
|
||||
while queue:
|
||||
prefix = queue.pop()
|
||||
if v1:
|
||||
entries = self.flat(self.v1_all([("prefix", prefix)], max_keys, "/"))
|
||||
else:
|
||||
entries = self.flat(self.v2_all([("prefix", prefix), ("delimiter", "/")], max_keys))
|
||||
for kind, value in entries:
|
||||
(queue.append if kind == "prefix" else found.append)(value)
|
||||
self.expect_eq(utf8_sorted(found), self.keys, f"{'v1' if v1 else 'v2'} delimiter walk max-keys={max_keys}")
|
||||
assert len(found) == len(set(found)), "walk returned a key twice"
|
||||
|
||||
# Range splitting (S3P, s3-fast-list, Swath): start-after cut points.
|
||||
def ranges(self, cuts: list[str], max_keys: int) -> None:
|
||||
cuts = sorted(set(cuts), key=lambda c: c.encode())
|
||||
bounds = [None, *cuts, None]
|
||||
found: list[str] = []
|
||||
for lo, hi in zip(bounds, bounds[1:]):
|
||||
token = None
|
||||
done = False
|
||||
while not done:
|
||||
params = [("list-type", "2"), ("max-keys", str(max_keys))]
|
||||
if token:
|
||||
params.append(("continuation-token", token))
|
||||
elif lo is not None:
|
||||
params.append(("start-after", lo))
|
||||
page = parse_page(self.s3.list_page(self.bucket, params), False)
|
||||
for _, key in page.entries:
|
||||
if lo is not None:
|
||||
assert key.encode() > lo.encode(), f"start-after {lo!r} returned {key!r}"
|
||||
if hi is not None and key.encode() > hi.encode():
|
||||
done = True
|
||||
break
|
||||
found.append(key)
|
||||
if not page.truncated:
|
||||
break
|
||||
token = page.token
|
||||
self.expect_eq(found, self.keys, f"start-after ranges ({len(cuts)} cuts, max-keys={max_keys})")
|
||||
|
||||
def start_after_with_delimiter(self, prefix: str, start_after: str) -> None:
|
||||
want = [
|
||||
e
|
||||
for e in direct_view(self.keys, prefix, "/")
|
||||
if e[1].encode() > start_after.encode()
|
||||
]
|
||||
got = self.flat(
|
||||
self.v2_all([("prefix", prefix), ("delimiter", "/"), ("start-after", start_after)], 1000)
|
||||
)
|
||||
self.expect_eq(got, want, f"start-after={start_after!r} delimiter=/ prefix={prefix!r}")
|
||||
|
||||
def token_overrides_start_after(self) -> None:
|
||||
first = parse_page(self.s3.list_page(self.bucket, [("list-type", "2"), ("max-keys", "5")]), False)
|
||||
assert first.truncated and first.token
|
||||
params = [("list-type", "2"), ("max-keys", "5"), ("continuation-token", first.token)]
|
||||
plain = parse_page(self.s3.list_page(self.bucket, params), False)
|
||||
mixed = parse_page(
|
||||
self.s3.list_page(self.bucket, [*params, ("start-after", self.keys[len(self.keys) // 2])]),
|
||||
False,
|
||||
)
|
||||
self.expect_eq(mixed.entries, plain.entries, "continuation-token with a later start-after")
|
||||
|
||||
def versions(self, prefix: str, delimiter: str, max_keys: int, url: bool) -> None:
|
||||
"""ListObjectVersions paging (key-marker/version-id-marker) over unversioned keys."""
|
||||
want = direct_view(self.keys, prefix, delimiter) if delimiter else [("key", k) for k in self.keys if k.startswith(prefix)]
|
||||
got: list[tuple[str, str]] = []
|
||||
key_marker = version_marker = None
|
||||
dec = urllib.parse.unquote_plus if url else (lambda v: v)
|
||||
for _ in range(10000):
|
||||
params = [("versions", ""), ("max-keys", str(max_keys)), ("prefix", prefix)]
|
||||
if delimiter:
|
||||
params.append(("delimiter", delimiter))
|
||||
if url:
|
||||
params.append(("encoding-type", "url"))
|
||||
if key_marker is not None:
|
||||
params += [("key-marker", key_marker), ("version-id-marker", version_marker or "")]
|
||||
root = self.s3.list_page(self.bucket, params)
|
||||
page: list[tuple[str, str]] = []
|
||||
for child in root:
|
||||
if child.tag in (S3NS + "Version", S3NS + "DeleteMarker"):
|
||||
page.append(("key", dec(text(child, "Key") or "")))
|
||||
elif child.tag == S3NS + "CommonPrefixes":
|
||||
page.append(("prefix", dec(text(child, "Prefix") or "")))
|
||||
assert len(page) <= max_keys, f"{len(page)} entries > max-keys {max_keys}"
|
||||
for kind in ("key", "prefix"):
|
||||
check_byte_order([v for k, v in page if k == kind], f"version {kind} list")
|
||||
got += sorted(page, key=lambda e: e[1].encode())
|
||||
if text(root, "IsTruncated") != "true":
|
||||
break
|
||||
nk = text(root, "NextKeyMarker")
|
||||
assert nk, "truncated versions page without NextKeyMarker"
|
||||
key_marker, version_marker = dec(nk), text(root, "NextVersionIdMarker")
|
||||
self.expect_eq(got, want, f"versions prefix={prefix!r} delimiter={delimiter!r} max-keys={max_keys} url={url}")
|
||||
|
||||
def url_encoding(self, prefix: str) -> None:
|
||||
want = [("key", k) for k in self.keys if k.startswith(prefix)]
|
||||
got = self.flat(self.v2_all([("prefix", prefix)], 7, url=True))
|
||||
self.expect_eq(got, want, f"encoding-type=url prefix={prefix!r}")
|
||||
root = self.s3.list_page(
|
||||
self.bucket,
|
||||
[("list-type", "2"), ("encoding-type", "url"), ("prefix", prefix), ("delimiter", "/"), ("start-after", prefix + "a b")],
|
||||
)
|
||||
for name, value in (("Prefix", prefix), ("Delimiter", "/"), ("StartAfter", prefix + "a b")):
|
||||
raw = text(root, name)
|
||||
assert raw is not None and urllib.parse.unquote_plus(raw) == value, f"encoded {name} {raw!r} != {value!r}"
|
||||
assert text(root, "EncodingType") == "url", "EncodingType not echoed"
|
||||
|
||||
|
||||
def deleted_prefixes(s3: S3, bucket: str) -> None:
|
||||
"""A prefix whose last key was deleted is no longer a CommonPrefix."""
|
||||
s3.create_bucket(bucket)
|
||||
keys = ["keep", "gone/a/b", "gone/c", "half/x", "half/y/z"]
|
||||
for k in keys:
|
||||
s3.put_object(bucket, k, b"x")
|
||||
for k in ("gone/a/b", "gone/c", "half/y/z"):
|
||||
s3.delete_object(bucket, k)
|
||||
p = Probe(s3, bucket, ["keep", "half/x"])
|
||||
p.delimiter("", "/", 1000)
|
||||
p.delimiter("half/", "/", 1000)
|
||||
p.delimiter("gone/", "/", 1000)
|
||||
|
||||
|
||||
def run_probes(
|
||||
s3: S3, buckets: dict[str, dict[str, int]], churn_bucket: str, only: re.Pattern | None
|
||||
) -> list[tuple[str, str | None]]:
|
||||
results: list[tuple[str, str | None]] = []
|
||||
|
||||
def check(name: str, fn, *a) -> None:
|
||||
if only and not only.search(name):
|
||||
return
|
||||
try:
|
||||
fn(*a)
|
||||
results.append((name, None))
|
||||
except Exception as exc: # noqa: BLE001
|
||||
results.append((name, f"{type(exc).__name__}: {exc}"))
|
||||
|
||||
check(f"reference:{churn_bucket}:deleted-prefixes", deleted_prefixes, s3, churn_bucket)
|
||||
for bucket, keymap in buckets.items():
|
||||
p = Probe(s3, bucket, list(keymap))
|
||||
keys = p.keys
|
||||
tag = f"reference:{bucket}"
|
||||
for mk in (1, 7, 100, 1000):
|
||||
check(f"{tag}:serial:max-keys={mk}", p.serial, "", mk)
|
||||
check(f"{tag}:url-encoding", p.url_encoding, "")
|
||||
check(f"{tag}:token-overrides-start-after", p.token_overrides_start_after)
|
||||
for mk in (2, 1000):
|
||||
check(f"{tag}:walk-v2:max-keys={mk}", p.walk, mk)
|
||||
check(f"{tag}:walk-v1:max-keys={mk}", p.walk, mk, True)
|
||||
prefixes = sorted({k[: k.index("/") + 1] for k in keys if "/" in k})
|
||||
scopes = ["", *prefixes[:: max(1, len(prefixes) // 4)]]
|
||||
if bucket.endswith("edge"):
|
||||
scopes += ["order/", "order/a", "chars/", "unicode/", "markers/", "markers/dir/", "photos/2006/", "o"]
|
||||
for prefix in scopes:
|
||||
for mk in (1, 3, 1000):
|
||||
check(f"{tag}:delimiter-v2:prefix={prefix}:max-keys={mk}", p.delimiter, prefix, "/", mk)
|
||||
check(f"{tag}:delimiter-v1:prefix={prefix}:max-keys={mk}", p.delimiter, prefix, "/", mk, True)
|
||||
for prefix in ("", scopes[-1]):
|
||||
for delim in ("", "/"):
|
||||
for mk in (2, 1000):
|
||||
check(f"{tag}:versions:prefix={prefix}:delimiter={delim}:max-keys={mk}", p.versions, prefix, delim, mk, False)
|
||||
check(f"{tag}:versions-url:prefix={prefix}", p.versions, prefix, "/", 3, True)
|
||||
for d in ("-", "a", "ou"):
|
||||
check(f"{tag}:delimiter={d}", p.delimiter, "", d, 1000)
|
||||
check(f"{tag}:serial:prefix-no-slash", p.serial, keys[len(keys) // 3][:4], 5)
|
||||
# Cut points that are existing keys, absent keys between keys, prefixes,
|
||||
# and a common prefix with and without its trailing delimiter.
|
||||
step = max(1, len(keys) // 9)
|
||||
existing = keys[step::step]
|
||||
absent = [k + "\x7f" for k in existing[::2]] + [k[:-1] for k in existing[1::2] if len(k) > 1]
|
||||
dirs = [k[: k.rfind("/") + 1] for k in existing if "/" in k]
|
||||
dirs += [d.rstrip("/") for d in dirs]
|
||||
for name, cuts in (("existing", existing), ("absent", absent), ("dirs", dirs), ("mixed", existing + absent + dirs)):
|
||||
for mk in (3, 1000):
|
||||
check(f"{tag}:ranges-{name}:max-keys={mk}", p.ranges, cuts, mk)
|
||||
for sa in (keys[len(keys) // 2], prefixes[len(prefixes) // 2], prefixes[len(prefixes) // 2].rstrip("/")):
|
||||
check(f"{tag}:start-after-delimiter:{sa}", p.start_after_with_delimiter, "", sa)
|
||||
if bucket.endswith("edge"):
|
||||
for sa in ("order/a", "order/a/", "order/a/b", "order/a.b", "order/a0"):
|
||||
check(f"{tag}:start-after-delimiter:{sa}", p.start_after_with_delimiter, "order/", sa)
|
||||
check(f"{tag}:url-encoding:chars/", p.url_encoding, "chars/")
|
||||
return results
|
||||
|
||||
|
||||
# ---------------------------------------------------------------- tool capsules
|
||||
|
||||
|
||||
@dataclass
|
||||
class Case:
|
||||
tool: str
|
||||
mode: str
|
||||
bucket: str
|
||||
prefix: str
|
||||
status: str = ""
|
||||
detail: str = ""
|
||||
argv: list[str] = field(default_factory=list)
|
||||
|
||||
|
||||
class ToolRunner:
|
||||
def __init__(self, args, study: Path, work: Path, endpoint: str) -> None:
|
||||
sys.path.insert(0, str(study / "benchmark" / "src"))
|
||||
from benchmark import adapters # noqa: PLC0415
|
||||
from benchmark.runtime.command_adapter import CommandAdapterError, Stated # noqa: PLC0415
|
||||
|
||||
self.adapters, self.refusal, self.stated = adapters, CommandAdapterError, Stated
|
||||
self.study, self.work, self.endpoint = study, work, endpoint
|
||||
tools = Path(args.tools_dir).resolve()
|
||||
self.fixture_dir = work / "fixtures"
|
||||
self.path_map = {
|
||||
"/usr/local/bin/aws": str(tools / "aws-cli-bin" / "aws"),
|
||||
"/usr/bin/mc": str(tools / "bin" / "mc"),
|
||||
"/usr/local/bin/pS3": str(tools / "bin" / "pS3"),
|
||||
"/usr/local/bin/rclone": str(tools / "bin" / "rclone"),
|
||||
"/usr/bin/s3-fast-list": str(tools / "bin" / "s3-fast-list"),
|
||||
"/usr/bin/ks-tool": str(tools / "bin" / "ks-tool"),
|
||||
"/usr/local/bin/s3kor": str(tools / "bin" / "s3kor"),
|
||||
"/usr/local/bin/s3p": str(tools / "bin" / "s3p"),
|
||||
"/usr/local/bin/s4cmd": str(tools / "bin" / "s4cmd"),
|
||||
"/s5cmd": str(tools / "bin" / "s5cmd"),
|
||||
"/usr/local/bin/s7cmd": str(tools / "bin" / "s7cmd"),
|
||||
"/opt/java/openjdk/bin/java": str(tools / "swath" / "openjdk" / "bin" / "java"),
|
||||
"/opt/swath/swath.jar": str(tools / "swath" / "swath.jar"),
|
||||
"/usr/bin/python3": sys.executable,
|
||||
"/opt/benchmark/tools/": str(study / "tools") + "/",
|
||||
}
|
||||
os.environ["PYTHONPATH"] = str(study / "benchmark" / "src")
|
||||
self.env = {
|
||||
"PATH": os.environ.get("PATH", "/usr/bin:/bin"),
|
||||
"AWS_ACCESS_KEY_ID": args.access_key,
|
||||
"AWS_SECRET_ACCESS_KEY": args.secret_key,
|
||||
"AWS_REGION": REGION,
|
||||
"AWS_DEFAULT_REGION": REGION,
|
||||
"AWS_EC2_METADATA_DISABLED": "true",
|
||||
"TZ": "UTC",
|
||||
"LC_ALL": "C.UTF-8",
|
||||
"PYTHONPATH": str(study / "benchmark" / "src"),
|
||||
}
|
||||
|
||||
def localize(self, argv, bucket: str) -> list[str]:
|
||||
out = []
|
||||
path_map = {**self.path_map, "/fixtures/source/": f"{self.fixture_dir / bucket}/"}
|
||||
for token in argv:
|
||||
for src, dst in path_map.items():
|
||||
if token == src or (src.endswith("/") and token.startswith(src)):
|
||||
token = dst + token[len(src) :]
|
||||
break
|
||||
out.append(token)
|
||||
return out
|
||||
|
||||
def adapter_dir(self, tool: str) -> Path:
|
||||
return self.study / "tools" / tool / "adapter"
|
||||
|
||||
def write_fixture_companions(self, bucket: str, keys: list[str]) -> None:
|
||||
"""The staged-fixture companions, built the way fixture_bundle.py builds them."""
|
||||
import duckdb # noqa: PLC0415
|
||||
|
||||
out = self.fixture_dir / bucket
|
||||
shutil.rmtree(out, ignore_errors=True)
|
||||
out.mkdir(parents=True)
|
||||
shards = sorted({k.split("/", 1)[0] for k in keys})
|
||||
if all(re.fullmatch(r"[A-Za-z0-9._/-]+", s) for s in shards):
|
||||
(out / "s5cmd-shards.input").write_text("".join(f"{s}\n" for s in shards))
|
||||
parts = out / "parquet"
|
||||
parts.mkdir()
|
||||
with duckdb.connect() as con:
|
||||
con.execute("CREATE TABLE f (key BLOB, row_type VARCHAR)")
|
||||
con.executemany("INSERT INTO f VALUES (?, 'OBJECT')", [(k.encode(),) for k in keys])
|
||||
con.execute(f"COPY f TO '{parts / 'part-00000.parquet'}' (FORMAT parquet)")
|
||||
sys.path.insert(0, str(self.study / "tools" / "s3-fast-list" / "adapter"))
|
||||
from fixture_hints import FixtureHintsError, generate_hints # noqa: PLC0415
|
||||
|
||||
try:
|
||||
generate_hints(parts, out / "s3-fast-list-hints.input", segments=4)
|
||||
except FixtureHintsError as exc:
|
||||
print(f"{bucket}: no s3-fast-list fixture hints: {exc}", flush=True)
|
||||
|
||||
def inject_endpoint(self, tool: str, argv: list[str], env: dict) -> tuple[list[str], dict]:
|
||||
"""Add the endpoint the way the replay-endpoint pilot (run.sh) did, for modes
|
||||
the capsule refuses only because the replay server lacks the API."""
|
||||
ep = self.endpoint
|
||||
if tool == "rclone":
|
||||
return [a.replace(f"region={REGION}", f'region={REGION},endpoint="{ep}",force_path_style=true') for a in argv], env
|
||||
if tool == "minio-mc":
|
||||
return argv, {**env, "MC_HOST_s3": ep, "MC_REGION": REGION}
|
||||
if tool == "s3kor":
|
||||
return [argv[0], argv[1], "--custom-endpoint-url", ep, *argv[2:]], env
|
||||
if tool == "s7cmd":
|
||||
return [*argv[:-1], "--target-endpoint-url", ep, "--target-force-path-style", argv[-1]], env
|
||||
if tool == "s5cmd":
|
||||
return [argv[0], "--endpoint-url", ep, *argv[1:]], env
|
||||
return [*argv, "--endpoint-url", ep], env
|
||||
|
||||
def config_for(self, adapter, case: Case, mode: str, keys: list[str]) -> dict[str, object]:
|
||||
config: dict[str, object] = {}
|
||||
for name, axis in adapter.modes[mode].axes.items():
|
||||
if isinstance(axis, self.stated):
|
||||
config[name] = 4
|
||||
if adapter.tool == "s5cmd" and mode == "fanout-with-dirs":
|
||||
initials = sorted({k[len(case.prefix)] for k in keys if k.startswith(case.prefix) and len(k) > len(case.prefix)})
|
||||
if not all(re.fullmatch(r"[A-Za-z0-9._-]", c) for c in initials):
|
||||
raise NotApplicable(f"key initials {initials} are outside the capsule's safe shard set")
|
||||
config["shard_initials"] = "".join(initials)
|
||||
return config
|
||||
|
||||
def execute(self, adapter, case: Case, mode: str, sink: Path, keys: list[str], artifact_path: str = "") -> tuple[Path | None, dict]:
|
||||
signed = adapter.supports_signed
|
||||
inject = case.tool in INJECT_ENDPOINT and mode in INJECT_ENDPOINT[case.tool]
|
||||
config = self.config_for(adapter, case, mode, keys)
|
||||
argv, env = self.adapters.compile_command(
|
||||
self.adapter_dir(case.tool),
|
||||
case.tool,
|
||||
mode=mode,
|
||||
bucket=case.bucket,
|
||||
region=REGION,
|
||||
prefix=case.prefix,
|
||||
signed=signed,
|
||||
config=config,
|
||||
sink_dir=str(sink),
|
||||
artifact_path=artifact_path,
|
||||
visible_memory_gb=2.0,
|
||||
endpoint_url="" if inject else self.endpoint,
|
||||
)
|
||||
if inject:
|
||||
argv, env = self.inject_endpoint(case.tool, list(argv), env)
|
||||
case.detail = "endpoint injected; "
|
||||
argv = self.localize(argv, case.bucket)
|
||||
case.argv = argv
|
||||
sink.mkdir(parents=True, exist_ok=True)
|
||||
home = sink / "home"
|
||||
home.mkdir(exist_ok=True)
|
||||
manifest = adapter.modes[mode]
|
||||
stdout_path = sink / (manifest.product_file if manifest.product_channel == "stdout" and manifest.product_artifact else "stdout")
|
||||
with stdout_path.open("wb") as out, (sink / "stderr").open("wb") as err:
|
||||
proc = subprocess.run(
|
||||
argv,
|
||||
stdout=out,
|
||||
stderr=err,
|
||||
env={**self.env, **env, "HOME": str(home)},
|
||||
cwd=sink,
|
||||
timeout=300,
|
||||
check=False,
|
||||
)
|
||||
if proc.returncode != 0:
|
||||
tail = (sink / "stderr").read_bytes()[-600:].decode(errors="replace")
|
||||
raise RuntimeError(f"exit {proc.returncode}: {tail}")
|
||||
product = sink / manifest.product_file if manifest.product_artifact else None
|
||||
return product, config
|
||||
|
||||
def run_case(self, case: Case, expected: dict[str, tuple[int, str]]) -> None:
|
||||
adapter = self.adapters.load_adapter(self.adapter_dir(case.tool), case.tool)
|
||||
manifest = adapter.modes[case.mode]
|
||||
if manifest.purpose_ceiling == "preparation" or not manifest.product_artifact or (case.tool, case.mode) in NOT_A_LISTING:
|
||||
case.status = "skip"
|
||||
case.detail = f"{manifest.purpose_ceiling} mode, not a compared listing"
|
||||
return
|
||||
if (case.tool, case.mode) in ROOT_ONLY and case.prefix:
|
||||
case.status, case.detail = "skip", "mode lists the bucket root whatever the prefix"
|
||||
return
|
||||
fixture = self.fixture_dir / case.bucket
|
||||
needs = {"fanout-fixture-with-dirs": "s5cmd-shards.input", "list-hinted-fixture": "s3-fast-list-hints.input"}.get(case.mode)
|
||||
if needs and not (fixture / needs).exists():
|
||||
case.status, case.detail = "skip", f"fixture_bundle.py would not build {needs} for this key set"
|
||||
return
|
||||
keys = list(expected)
|
||||
sink = self.work / "cases" / case.tool / case.mode / (case.bucket + "~" + (case.prefix.replace("/", "_") or "root"))
|
||||
shutil.rmtree(sink, ignore_errors=True)
|
||||
try:
|
||||
artifact_path = ""
|
||||
for step in adapter.requires.get(case.mode, ()):
|
||||
producer_sink = sink / f"requires-{step.mode}"
|
||||
self.execute(adapter, case, step.mode, producer_sink, keys)
|
||||
artifact_path = str(producer_sink / adapter.modes[step.mode].artifacts[step.artifact])
|
||||
if manifest.inline:
|
||||
inline_sink = sink / f"inline-{manifest.inline}"
|
||||
self.execute(adapter, case, manifest.inline, inline_sink, keys, artifact_path)
|
||||
inline_manifest = adapter.modes[manifest.inline]
|
||||
artifact_path = str(inline_sink / next(iter(inline_manifest.artifacts.values())))
|
||||
product, config = self.execute(adapter, case, case.mode, sink, keys, artifact_path)
|
||||
except NotApplicable as exc:
|
||||
case.status, case.detail = "skip", str(exc)
|
||||
return
|
||||
except self.adapters.AdapterError as exc:
|
||||
if "custom endpoint" in str(exc) or "replay endpoint" in str(exc) or "no --prefix" in str(exc) or "requires HeadBucket" in str(exc):
|
||||
case.status, case.detail = "skip", f"capsule refuses: {str(exc).split(': ', 2)[-1][:160]}"
|
||||
return
|
||||
raise
|
||||
normalized = sink / "normalized.tsv"
|
||||
self.adapters.normalize_to_path(
|
||||
self.adapter_dir(case.tool),
|
||||
case.tool,
|
||||
case.mode,
|
||||
case.prefix,
|
||||
normalized,
|
||||
input_path=None if manifest.product_channel == "dataset" else product,
|
||||
dataset=product if manifest.product_channel == "dataset" else None,
|
||||
config=config,
|
||||
)
|
||||
compare(case, normalized.read_bytes(), expected, manifest.fields)
|
||||
|
||||
|
||||
INJECT_ENDPOINT = {
|
||||
"aws-cli": {"s3api-v1-text", "s3api-versions-text"},
|
||||
"minio-mc": {"versions-json", "find", "find-json"},
|
||||
"rclone": {"listv1"},
|
||||
"s3kor": {"list-versions"},
|
||||
"s4cmd": {"recursive", "shallow", "show-directory", "du"},
|
||||
"s5cmd": {"listv1", "allversions"},
|
||||
"s7cmd": {"all-versions"},
|
||||
}
|
||||
"""Capsule modes refused only because the study's replay server serves
|
||||
ListObjectsV2 alone; SeaweedFS serves ListObjects, ListObjectVersions and
|
||||
HeadBucket too."""
|
||||
|
||||
NOT_A_LISTING = {
|
||||
("rclone", "debug"),
|
||||
("rclone", "walk-debug"),
|
||||
("s3p", "summarize"),
|
||||
("s4cmd", "du"),
|
||||
("s4cmd", "show-directory"),
|
||||
}
|
||||
"""Modes with no per-key listing: rclone's normalizer has no debug modes, summarize
|
||||
and du print one aggregate, and `ls -d` prints the directory itself."""
|
||||
|
||||
|
||||
class NotApplicable(Exception):
|
||||
pass
|
||||
|
||||
|
||||
ROOT_ONLY = {
|
||||
("aws-cli", "s3api-v2-remainder"),
|
||||
("s5cmd", "fanout-fixture-with-dirs"),
|
||||
("s3-fast-list", "list-hinted-fixture"),
|
||||
}
|
||||
"""Modes whose capsule lists the root (remainder) or a staged root-scope fixture."""
|
||||
|
||||
SHALLOW = re.compile(r"shallow|delimiter|rootkeys|remainder|max-depth")
|
||||
KEYS_ONLY = re.compile(r"rootkeys|remainder")
|
||||
"""Shallow modes whose normalizer keeps only the keys, dropping CommonPrefixes."""
|
||||
|
||||
|
||||
def compare(case: Case, normalized: bytes, expected: dict[str, tuple[int, str]], fields) -> None:
|
||||
rows = []
|
||||
for line in normalized.split(b"\n"):
|
||||
if not line:
|
||||
continue
|
||||
f = line.split(b"\t")
|
||||
rows.append((f[0].decode("utf-8", "surrogateescape"), f[1].decode(), f[2].decode()))
|
||||
scope = {k: v for k, v in expected.items() if k.startswith(case.prefix)}
|
||||
keys = utf8_sorted(scope)
|
||||
shallow = bool(SHALLOW.search(case.mode))
|
||||
if shallow:
|
||||
view = direct_view(keys, case.prefix, "/")
|
||||
want_objects = [k for kind, k in view if kind == "key"]
|
||||
allowed_dirs = {k for kind, k in view if kind == "prefix"}
|
||||
else:
|
||||
want_objects = keys
|
||||
allowed_dirs = {k[: i + 1] for k in keys for i, c in enumerate(k) if c == "/" and i >= len(case.prefix)}
|
||||
problems: list[str] = []
|
||||
objects, dirs = [], []
|
||||
for key, size, etag in rows:
|
||||
is_dir = key.endswith("/") and size == "-" and etag == "-" and key not in scope
|
||||
(dirs if is_dir else objects).append((key, size, etag))
|
||||
got_keys = [k for k, _, _ in objects]
|
||||
dup = {k for k in got_keys if got_keys.count(k) > 1} if len(got_keys) != len(set(got_keys)) else set()
|
||||
if dup:
|
||||
problems.append(f"duplicate keys {sorted(dup)[:5]}")
|
||||
missing = [k for k in want_objects if k not in set(got_keys)]
|
||||
extra = [k for k in set(got_keys) if k not in set(want_objects)]
|
||||
if missing:
|
||||
problems.append(f"missing {len(missing)}: {missing[:5]}")
|
||||
if extra:
|
||||
problems.append(f"unexpected {len(extra)}: {sorted(extra)[:5]}")
|
||||
bad_dirs = [d for d, _, _ in dirs if d not in allowed_dirs]
|
||||
if bad_dirs:
|
||||
problems.append(f"unexpected directory rows {bad_dirs[:5]}")
|
||||
if shallow and not KEYS_ONLY.search(case.mode) and {d for d, _, _ in dirs} != allowed_dirs:
|
||||
problems.append(f"common prefixes {sorted(d for d, _, _ in dirs)[:8]} != {sorted(allowed_dirs)[:8]}")
|
||||
for key, size, etag in objects:
|
||||
if key not in scope:
|
||||
continue
|
||||
want_size, want_etag = scope[key]
|
||||
if size != "-" and size != str(want_size):
|
||||
problems.append(f"{key!r} size {size} != {want_size}")
|
||||
if etag != "-" and etag != want_etag:
|
||||
problems.append(f"{key!r} etag {etag} != {want_etag}")
|
||||
case.status = "fail" if problems else "pass"
|
||||
case.detail += "; ".join(problems)[:1500] if problems else f"{len(objects)} objects, {len(dirs)} prefixes"
|
||||
|
||||
|
||||
# ---------------------------------------------------------------- main
|
||||
|
||||
|
||||
def load_expected_failures(path: Path | None) -> dict[str, str]:
|
||||
out: dict[str, str] = {}
|
||||
if path and path.exists():
|
||||
for line in path.read_text().splitlines():
|
||||
line = line.strip()
|
||||
if line and not line.startswith("#"):
|
||||
name, _, reason = line.partition("#")
|
||||
out[name.strip()] = reason.strip()
|
||||
return out
|
||||
|
||||
|
||||
def main() -> int:
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument("--endpoint", required=True)
|
||||
ap.add_argument("--access-key", required=True)
|
||||
ap.add_argument("--secret-key", required=True)
|
||||
ap.add_argument("--study", required=True)
|
||||
ap.add_argument("--tools-dir", required=True)
|
||||
ap.add_argument("--work-dir", required=True)
|
||||
ap.add_argument("--tools", default="aws-cli,minio-mc,ps3,rclone,s3-fast-list,s3kor,s3p,s4cmd,s5cmd,s7cmd,swath")
|
||||
ap.add_argument("--bucket-prefix", default="study")
|
||||
ap.add_argument("--expected-failures", type=Path)
|
||||
ap.add_argument("--skip-upload", action="store_true")
|
||||
ap.add_argument("--only", default="", help="regex over case names")
|
||||
ap.add_argument("--jobs", type=int, default=4)
|
||||
args = ap.parse_args()
|
||||
|
||||
study = Path(args.study).resolve()
|
||||
work = Path(args.work_dir).resolve()
|
||||
work.mkdir(parents=True, exist_ok=True)
|
||||
s3 = S3(args.endpoint, args.access_key, args.secret_key)
|
||||
buckets = {f"{args.bucket_prefix}-canary": canary_keys(), f"{args.bucket_prefix}-edge": edge_keys()}
|
||||
expected: dict[str, dict[str, tuple[int, str]]] = {}
|
||||
for bucket, keymap in buckets.items():
|
||||
expected[bucket] = {k: (size, hashlib.md5(body_for(k, size)).hexdigest()) for k, size in keymap.items()}
|
||||
if args.skip_upload:
|
||||
continue
|
||||
s3.create_bucket(bucket)
|
||||
start = time.time()
|
||||
with concurrent.futures.ThreadPoolExecutor(16) as pool:
|
||||
list(pool.map(lambda k: s3.put_object(bucket, k, body_for(k, keymap[k])), keymap))
|
||||
print(f"uploaded {len(keymap)} objects to {bucket} in {time.time() - start:.1f}s", flush=True)
|
||||
|
||||
only = re.compile(args.only) if args.only else None
|
||||
results: list[tuple[str, str, str]] = []
|
||||
for name, err in run_probes(s3, buckets, f"{args.bucket_prefix}-churn", only):
|
||||
results.append((name, "fail" if err else "pass", err or ""))
|
||||
|
||||
runner = ToolRunner(args, study, work, args.endpoint)
|
||||
cases: list[Case] = []
|
||||
for bucket in buckets:
|
||||
runner.write_fixture_companions(bucket, list(buckets[bucket]))
|
||||
scopes = ["", "group-07/"] if bucket.endswith("canary") else ["", "order/", "chars/"]
|
||||
for tool in filter(None, args.tools.split(",")):
|
||||
adapter = runner.adapters.load_adapter(runner.adapter_dir(tool), tool)
|
||||
for mode in adapter.modes:
|
||||
for prefix in scopes:
|
||||
case = Case(tool, mode, bucket, prefix)
|
||||
if only and not only.search(case_name(case)):
|
||||
continue
|
||||
cases.append(case)
|
||||
|
||||
def run(case: Case) -> Case:
|
||||
start = time.time()
|
||||
try:
|
||||
runner.run_case(case, expected[case.bucket])
|
||||
except Exception as exc: # noqa: BLE001
|
||||
case.status = "fail"
|
||||
case.detail = f"{type(exc).__name__}: {exc}"[:1500]
|
||||
if os.environ.get("STUDY_DEBUG"):
|
||||
traceback.print_exc()
|
||||
print(f"{case.status:5} {case_name(case)} ({time.time() - start:.1f}s) {case.detail[:300]}", flush=True)
|
||||
return case
|
||||
|
||||
with concurrent.futures.ThreadPoolExecutor(args.jobs) as pool:
|
||||
for case in pool.map(run, cases):
|
||||
results.append((case_name(case), case.status, case.detail))
|
||||
|
||||
xfail = load_expected_failures(args.expected_failures)
|
||||
regressions, fixed = [], []
|
||||
counts: dict[str, int] = {}
|
||||
for name, status, detail in results:
|
||||
if status == "fail" and name in xfail:
|
||||
status = "xfail"
|
||||
elif status == "pass" and name in xfail:
|
||||
fixed.append(name)
|
||||
elif status == "fail":
|
||||
regressions.append((name, detail))
|
||||
counts[status] = counts.get(status, 0) + 1
|
||||
(work / "results.json").write_text(json.dumps(results, indent=1, ensure_ascii=False))
|
||||
print("\n== summary:", ", ".join(f"{k}={v}" for k, v in sorted(counts.items())))
|
||||
for name in fixed:
|
||||
print(f"XPASS (remove from expected failures): {name}")
|
||||
for name, detail in regressions:
|
||||
print(f"FAIL {name}: {detail}")
|
||||
return 1 if regressions or fixed else 0
|
||||
|
||||
|
||||
def case_name(case: Case) -> str:
|
||||
return f"{case.tool}:{case.mode}:{case.bucket.rsplit('-', 1)[-1]}:{case.prefix or '/'}"
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
raise SystemExit(main())
|
||||
@@ -0,0 +1,18 @@
|
||||
{
|
||||
"identities": [
|
||||
{
|
||||
"name": "listing_study_admin",
|
||||
"credentials": [
|
||||
{
|
||||
"accessKey": "listing_study_access",
|
||||
"secretKey": "listing_study_secret"
|
||||
}
|
||||
],
|
||||
"actions": ["Admin", "Read", "List", "Tagging", "Write"]
|
||||
},
|
||||
{
|
||||
"name": "anonymous",
|
||||
"actions": ["Read", "List"]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -31,3 +31,7 @@ already-running server, and see the top of `run.sh` for the other overrides.
|
||||
to path-style access with a `sed` patch.
|
||||
- `NOT_ACCESSIBLE_BUCKET` is a real bucket carrying a deny-all bucket policy,
|
||||
which is how the suite's `AccessDenied` negative tests are satisfied.
|
||||
- CI runs Maven with `maven-settings.xml`, which adds Google's Maven Central
|
||||
mirror in front of Central, so a 429 from one falls through to the other.
|
||||
Locally, pass it with
|
||||
`MAVEN_ARGS="-s $PWD/test/s3/snowflake/maven-settings.xml"`.
|
||||
@@ -0,0 +1,28 @@
|
||||
<settings>
|
||||
<profiles>
|
||||
<profile>
|
||||
<id>central-fallback</id>
|
||||
<repositories>
|
||||
<repository>
|
||||
<id>google-maven-central</id>
|
||||
<url>https://maven-central.storage-download.googleapis.com/maven2/</url>
|
||||
<snapshots>
|
||||
<enabled>false</enabled>
|
||||
</snapshots>
|
||||
</repository>
|
||||
</repositories>
|
||||
<pluginRepositories>
|
||||
<pluginRepository>
|
||||
<id>google-maven-central</id>
|
||||
<url>https://maven-central.storage-download.googleapis.com/maven2/</url>
|
||||
<snapshots>
|
||||
<enabled>false</enabled>
|
||||
</snapshots>
|
||||
</pluginRepository>
|
||||
</pluginRepositories>
|
||||
</profile>
|
||||
</profiles>
|
||||
<activeProfiles>
|
||||
<activeProfile>central-fallback</activeProfile>
|
||||
</activeProfiles>
|
||||
</settings>
|
||||
@@ -432,3 +432,100 @@ func createVersionedTestBucket(t *testing.T, client *s3.Client) string {
|
||||
|
||||
return bucketName
|
||||
}
|
||||
|
||||
// TestTaggingReportsVersionId checks that tagging requests on a versioned
|
||||
// bucket answer with the version they acted on.
|
||||
func TestTaggingReportsVersionId(t *testing.T) {
|
||||
client := getS3Client(t)
|
||||
bucketName := createVersionedTestBucket(t, client)
|
||||
defer cleanupTestBucket(t, client, bucketName)
|
||||
|
||||
objectKey := "tagging-version-id"
|
||||
put := func(body string) string {
|
||||
resp, err := client.PutObject(context.TODO(), &s3.PutObjectInput{
|
||||
Bucket: aws.String(bucketName),
|
||||
Key: aws.String(objectKey),
|
||||
Body: strings.NewReader(body),
|
||||
})
|
||||
require.NoError(t, err)
|
||||
return aws.ToString(resp.VersionId)
|
||||
}
|
||||
versionId1 := put("v1")
|
||||
versionId2 := put("v2")
|
||||
require.NotEmpty(t, versionId1)
|
||||
require.NotEmpty(t, versionId2)
|
||||
require.NotEqual(t, versionId1, versionId2)
|
||||
tagging := &types.Tagging{TagSet: []types.Tag{{Key: aws.String("k"), Value: aws.String("v")}}}
|
||||
|
||||
putResp, err := client.PutObjectTagging(context.TODO(), &s3.PutObjectTaggingInput{
|
||||
Bucket: aws.String(bucketName), Key: aws.String(objectKey), VersionId: aws.String(versionId1), Tagging: tagging,
|
||||
})
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, versionId1, aws.ToString(putResp.VersionId))
|
||||
|
||||
putResp, err = client.PutObjectTagging(context.TODO(), &s3.PutObjectTaggingInput{
|
||||
Bucket: aws.String(bucketName), Key: aws.String(objectKey), Tagging: tagging,
|
||||
})
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, versionId2, aws.ToString(putResp.VersionId))
|
||||
|
||||
getResp, err := client.GetObjectTagging(context.TODO(), &s3.GetObjectTaggingInput{
|
||||
Bucket: aws.String(bucketName), Key: aws.String(objectKey), VersionId: aws.String(versionId1),
|
||||
})
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, versionId1, aws.ToString(getResp.VersionId))
|
||||
|
||||
getResp, err = client.GetObjectTagging(context.TODO(), &s3.GetObjectTaggingInput{
|
||||
Bucket: aws.String(bucketName), Key: aws.String(objectKey),
|
||||
})
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, versionId2, aws.ToString(getResp.VersionId))
|
||||
|
||||
delResp, err := client.DeleteObjectTagging(context.TODO(), &s3.DeleteObjectTaggingInput{
|
||||
Bucket: aws.String(bucketName), Key: aws.String(objectKey), VersionId: aws.String(versionId1),
|
||||
})
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, versionId1, aws.ToString(delResp.VersionId))
|
||||
}
|
||||
|
||||
// TestTaggingReportsNullVersionId checks that tagging an object written before
|
||||
// versioning was enabled reports the "null" version.
|
||||
func TestTaggingReportsNullVersionId(t *testing.T) {
|
||||
client := getS3Client(t)
|
||||
bucketName := createTestBucket(t, client)
|
||||
defer cleanupTestBucket(t, client, bucketName)
|
||||
|
||||
objectKey := "tagging-null-version-id"
|
||||
_, err := client.PutObject(context.TODO(), &s3.PutObjectInput{
|
||||
Bucket: aws.String(bucketName),
|
||||
Key: aws.String(objectKey),
|
||||
Body: strings.NewReader("before versioning"),
|
||||
})
|
||||
require.NoError(t, err)
|
||||
_, err = client.PutBucketVersioning(context.TODO(), &s3.PutBucketVersioningInput{
|
||||
Bucket: aws.String(bucketName),
|
||||
VersioningConfiguration: &types.VersioningConfiguration{Status: types.BucketVersioningStatusEnabled},
|
||||
})
|
||||
require.NoError(t, err)
|
||||
tagging := &types.Tagging{TagSet: []types.Tag{{Key: aws.String("k"), Value: aws.String("v")}}}
|
||||
|
||||
for _, versionId := range []*string{nil, aws.String("null")} {
|
||||
putResp, err := client.PutObjectTagging(context.TODO(), &s3.PutObjectTaggingInput{
|
||||
Bucket: aws.String(bucketName), Key: aws.String(objectKey), VersionId: versionId, Tagging: tagging,
|
||||
})
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, "null", aws.ToString(putResp.VersionId))
|
||||
|
||||
getResp, err := client.GetObjectTagging(context.TODO(), &s3.GetObjectTaggingInput{
|
||||
Bucket: aws.String(bucketName), Key: aws.String(objectKey), VersionId: versionId,
|
||||
})
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, "null", aws.ToString(getResp.VersionId))
|
||||
|
||||
delResp, err := client.DeleteObjectTagging(context.TODO(), &s3.DeleteObjectTaggingInput{
|
||||
Bucket: aws.String(bucketName), Key: aws.String(objectKey), VersionId: versionId,
|
||||
})
|
||||
require.NoError(t, err)
|
||||
assert.Equal(t, "null", aws.ToString(delResp.VersionId))
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,7 @@
|
||||
s3-api-compat-tests/
|
||||
test-volume-data/
|
||||
compat-runner
|
||||
results.json
|
||||
weed-test.log
|
||||
weed-server.pid
|
||||
weed-server.started
|
||||
@@ -0,0 +1,132 @@
|
||||
# Runs https://github.com/tigrisdata-community/s3-api-compat-tests against a
|
||||
# local SeaweedFS S3 gateway and compares the report with expected_failures.txt.
|
||||
|
||||
.PHONY: all test help build-weed build-suite start-server stop-server run-suite test-with-server logs clean
|
||||
|
||||
SUITE_REPO := https://github.com/tigrisdata-community/s3-api-compat-tests.git
|
||||
SUITE_COMMIT := e846275e489ec30b324344d462e698252c3a1f67
|
||||
SUITE_DIR := s3-api-compat-tests
|
||||
SUITE_STAMP := $(SUITE_DIR)/.seaweedfs-prepared
|
||||
|
||||
WEED_BINARY := ../../../weed/weed_binary
|
||||
S3_PORT ?= 8335
|
||||
MASTER_PORT ?= 9335
|
||||
VOLUME_PORT ?= 8085
|
||||
FILER_PORT ?= 8889
|
||||
WEBDAV_PORT ?= 7335
|
||||
ADMIN_PORT ?= 23647
|
||||
SERVER_DIR := ./test-volume-data
|
||||
S3_CONFIG := ./test_s3.json
|
||||
# Succeeds while weed-server.pid names the server start-server launched: the
|
||||
# process at that pid must have the start time recorded with it, so a process
|
||||
# that reused the pid is left alone.
|
||||
OWN_SERVER_RUNNING = [ -f weed-server.pid ] && [ -s weed-server.started ] && \
|
||||
[ "$$(ps -p "$$(cat weed-server.pid)" -o lstart= 2>/dev/null)" = "$$(cat weed-server.started)" ]
|
||||
|
||||
.DEFAULT_GOAL := help
|
||||
|
||||
all: test
|
||||
|
||||
test: test-with-server
|
||||
|
||||
help:
|
||||
@echo "s3-api-compat-tests (Tigris) against SeaweedFS"
|
||||
@echo ""
|
||||
@echo " build-weed - Build the SeaweedFS binary"
|
||||
@echo " build-suite - Fetch the suite at $(SUITE_COMMIT) and build it"
|
||||
@echo " start-server - Start weed mini with S3 on port $(S3_PORT)"
|
||||
@echo " run-suite - Run the suite and check expected_failures.txt"
|
||||
@echo " stop-server - Stop the test server"
|
||||
@echo " test-with-server - Start server, run suite, stop server"
|
||||
@echo " logs - Show server logs"
|
||||
@echo " clean - Remove test artifacts"
|
||||
|
||||
build-weed:
|
||||
@cd ../../../weed && go build -o weed_binary .
|
||||
|
||||
build-suite:
|
||||
@want="$(SUITE_COMMIT) $$(git hash-object seaweedfs-provider.patch)"; \
|
||||
if [ "$$(cat $(SUITE_STAMP) 2>/dev/null)" != "$$want" ]; then \
|
||||
rm -rf $(SUITE_DIR) && mkdir -p $(SUITE_DIR) && \
|
||||
git -C $(SUITE_DIR) init -q && \
|
||||
git -C $(SUITE_DIR) fetch -q --depth 1 $(SUITE_REPO) $(SUITE_COMMIT) && \
|
||||
git -C $(SUITE_DIR) checkout -q FETCH_HEAD && \
|
||||
git -C $(SUITE_DIR) apply ../seaweedfs-provider.patch && \
|
||||
echo "$$want" > $(SUITE_STAMP); \
|
||||
fi
|
||||
@cd $(SUITE_DIR) && go build -o ../compat-runner .
|
||||
|
||||
start-server: build-weed
|
||||
@if curl -sS --max-time 2 -o /dev/null http://127.0.0.1:$(S3_PORT)/ >/dev/null 2>&1; then \
|
||||
echo "port $(S3_PORT) is already served by another process; refusing to test against it"; \
|
||||
exit 1; \
|
||||
fi
|
||||
@if $(OWN_SERVER_RUNNING); then \
|
||||
echo "the server this Makefile started (pid $$(cat weed-server.pid)) is still running; run make stop-server first"; \
|
||||
exit 1; \
|
||||
fi
|
||||
@rm -rf weed-server.pid weed-server.started $(SERVER_DIR)
|
||||
@mkdir -p $(SERVER_DIR)
|
||||
@$(WEED_BINARY) mini \
|
||||
-dir=$(SERVER_DIR) \
|
||||
-ip=127.0.0.1 \
|
||||
-ip.bind=127.0.0.1 \
|
||||
-master.port=$(MASTER_PORT) \
|
||||
-volume.port=$(VOLUME_PORT) \
|
||||
-filer.port=$(FILER_PORT) \
|
||||
-webdav.port=$(WEBDAV_PORT) \
|
||||
-admin.port=$(ADMIN_PORT) \
|
||||
-admin.port.legacy=0 \
|
||||
-s3.port=$(S3_PORT) \
|
||||
-s3.config=$(S3_CONFIG) \
|
||||
-master.peers=none \
|
||||
> weed-test.log 2>&1 & echo $$! > weed-server.pid; \
|
||||
ps -p $$! -o lstart= > weed-server.started
|
||||
@for i in $$(seq 1 60); do \
|
||||
kill -0 $$(cat weed-server.pid) 2>/dev/null || { \
|
||||
echo "SeaweedFS server exited during startup"; \
|
||||
cat weed-test.log; \
|
||||
exit 1; \
|
||||
}; \
|
||||
if curl -sS --max-time 2 -o /dev/null http://127.0.0.1:$(S3_PORT)/ >/dev/null 2>&1; then \
|
||||
echo "SeaweedFS S3 server is ready on port $(S3_PORT)"; \
|
||||
exit 0; \
|
||||
fi; \
|
||||
sleep 1; \
|
||||
done; \
|
||||
echo "SeaweedFS S3 server failed to start"; \
|
||||
cat weed-test.log; \
|
||||
$(MAKE) --no-print-directory stop-server; \
|
||||
exit 1
|
||||
|
||||
stop-server:
|
||||
@if [ -f weed-server.pid ]; then \
|
||||
if $(OWN_SERVER_RUNNING); then \
|
||||
kill $$(cat weed-server.pid) 2>/dev/null || true; \
|
||||
for i in $$(seq 1 30); do $(OWN_SERVER_RUNNING) || break; sleep 1; done; \
|
||||
if $(OWN_SERVER_RUNNING); then \
|
||||
echo "the server this Makefile started (pid $$(cat weed-server.pid)) is still running after 30s; keeping weed-server.pid"; \
|
||||
exit 1; \
|
||||
fi; \
|
||||
fi; \
|
||||
rm -f weed-server.pid weed-server.started; \
|
||||
fi
|
||||
|
||||
run-suite: build-suite
|
||||
SEAWEEDFS_S3_ENDPOINT=http://127.0.0.1:$(S3_PORT) \
|
||||
SEAWEEDFS_S3_ACCESS_KEY_ID=admin \
|
||||
SEAWEEDFS_S3_SECRET_ACCESS_KEY=admin \
|
||||
./compat-runner --providers=seaweedfs --output=results.json
|
||||
python3 check_results.py results.json expected_failures.txt
|
||||
|
||||
test-with-server:
|
||||
@$(MAKE) start-server || exit $$?; \
|
||||
$(MAKE) run-suite; TEST_RESULT=$$?; \
|
||||
$(MAKE) stop-server; STOP_RESULT=$$?; \
|
||||
if [ $$TEST_RESULT -ne 0 ]; then exit $$TEST_RESULT; fi; exit $$STOP_RESULT
|
||||
|
||||
logs:
|
||||
@test -f weed-test.log && tail -100 weed-test.log || echo "No log file found"
|
||||
|
||||
clean: stop-server
|
||||
@rm -rf $(SERVER_DIR) $(SUITE_DIR) compat-runner results.json weed-test.log weed-server.pid weed-server.started
|
||||
@@ -0,0 +1,64 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Compare an s3-api-compat-tests JSON report with expected_failures.txt.
|
||||
|
||||
Fails on any test that did not pass and is not listed with the status it
|
||||
ended with, and on any listed test that now passes or did not run, so the list
|
||||
only ever shrinks.
|
||||
"""
|
||||
import json
|
||||
import sys
|
||||
|
||||
|
||||
def load_expected(path):
|
||||
expected = {}
|
||||
with open(path) as f:
|
||||
for line in f:
|
||||
fields = line.split("#", 1)[0].split()
|
||||
if fields:
|
||||
expected[fields[0]] = fields[1] if len(fields) > 1 else "fail"
|
||||
return expected
|
||||
|
||||
|
||||
def main():
|
||||
if len(sys.argv) != 3:
|
||||
sys.exit("usage: check_results.py <results.json> <expected_failures.txt>")
|
||||
with open(sys.argv[1]) as f:
|
||||
report = json.load(f)
|
||||
expected = load_expected(sys.argv[2])
|
||||
|
||||
providers = report.get("providers") or []
|
||||
results = providers[0].get("results") if providers else None
|
||||
if not results:
|
||||
sys.exit("no test results in the report: the suite could not start against the server")
|
||||
|
||||
seen = set()
|
||||
regressions, fixed = [], []
|
||||
for r in results:
|
||||
name, status = r["operation"], r["status"]
|
||||
seen.add(name)
|
||||
detail = r.get("error") or r.get("notes") or ""
|
||||
if status == "pass":
|
||||
if name in expected:
|
||||
fixed.append(name)
|
||||
elif name not in expected:
|
||||
regressions.append(f"{name} [{status}]: {detail}")
|
||||
elif status != expected[name]:
|
||||
regressions.append(f"{name} [{status}, listed as {expected[name]}]: {detail}")
|
||||
else:
|
||||
print(f"expected failure: {name} [{status}]")
|
||||
|
||||
missing = sorted(set(expected) - seen)
|
||||
print(f"{len(results)} tests, {len(regressions)} unexpected failures, "
|
||||
f"{len(fixed)} unexpected passes, {len(missing)} listed but not run")
|
||||
for line in regressions:
|
||||
print(f"UNEXPECTED FAILURE: {line}")
|
||||
for name in fixed:
|
||||
print(f"UNEXPECTED PASS: {name} (remove it from expected_failures.txt)")
|
||||
for name in missing:
|
||||
print(f"NOT RUN: {name} (remove it from expected_failures.txt)")
|
||||
if regressions or fixed or missing:
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
@@ -0,0 +1,18 @@
|
||||
# Tests from s3-api-compat-tests that SeaweedFS is expected to fail.
|
||||
# check_results.py fails CI on any other failure, and on any test listed here
|
||||
# that passes, so remove an entry together with the fix that makes it pass.
|
||||
# An entry expects the test to fail; "<name> error" expects its setup to fail
|
||||
# before the call it checks, and any other status is a regression.
|
||||
|
||||
# AWS answers GetBucketPolicyStatus on a bucket without a policy with
|
||||
# NoSuchBucketPolicy, and so does SeaweedFS; the suite expects a status.
|
||||
GetBucketPolicyStatus
|
||||
|
||||
# Glacier restore: SeaweedFS has no archive storage class to restore from, and
|
||||
# AWS also refuses RestoreObject on a STANDARD object (InvalidObjectState).
|
||||
RestoreObject
|
||||
|
||||
# SeaweedFS reads x-amz-rename-source as a literal key first and then, when it
|
||||
# starts with the request's bucket, as bucket/key, because AWS documents both
|
||||
# spellings. A leading slash is dropped since filer paths cannot hold it.
|
||||
RenameObject_SourceIsLiteralKey
|
||||
@@ -0,0 +1,19 @@
|
||||
diff --git a/providers.go b/providers.go
|
||||
index 149f94c..bc7aeeb 100644
|
||||
--- a/providers.go
|
||||
+++ b/providers.go
|
||||
@@ -180,6 +180,14 @@ func (p *Provider) CreateVersionedBucket(ctx context.Context, client *s3.Client,
|
||||
// If names is non-empty, only those named providers are returned.
|
||||
func LoadProviders(names []string) []Provider {
|
||||
all := []Provider{
|
||||
+ {
|
||||
+ Name: "seaweedfs",
|
||||
+ Endpoint: os.Getenv("SEAWEEDFS_S3_ENDPOINT"),
|
||||
+ Region: envOr("SEAWEEDFS_S3_REGION", "us-east-1"),
|
||||
+ PathStyle: true,
|
||||
+ AccessKey: os.Getenv("SEAWEEDFS_S3_ACCESS_KEY_ID"),
|
||||
+ SecretKey: os.Getenv("SEAWEEDFS_S3_SECRET_ACCESS_KEY"),
|
||||
+ },
|
||||
{
|
||||
Name: "tigris",
|
||||
Endpoint: "https://t3.storage.dev",
|
||||
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"identities": [
|
||||
{
|
||||
"name": "admin",
|
||||
"credentials": [
|
||||
{
|
||||
"accessKey": "admin",
|
||||
"secretKey": "admin"
|
||||
}
|
||||
],
|
||||
"actions": [
|
||||
"Admin",
|
||||
"Read",
|
||||
"List",
|
||||
"Tagging",
|
||||
"Write"
|
||||
]
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -187,18 +187,34 @@ catalog.s3.path-style-access = "true"
|
||||
return configDir
|
||||
}
|
||||
|
||||
var icebergJars = []struct{ artifact, sha256 string }{
|
||||
{"iceberg-spark-runtime-3.5_2.12", "2aec4b78d806cc81d4e50325b351f6349c90de641544e644c6032f000938618b"},
|
||||
{"iceberg-aws-bundle", "f4398dcdfefc0b186b899d500651e6e5ac62abe26e25d5cbe28403eaaec24c20"},
|
||||
}
|
||||
|
||||
const (
|
||||
icebergVersion = "1.5.2"
|
||||
sparkJarsDir = "/opt/iceberg-jars"
|
||||
sparkJarsConfig = sparkJarsDir + "/iceberg-spark-runtime-3.5_2.12-" + icebergVersion + ".jar," +
|
||||
sparkJarsDir + "/iceberg-aws-bundle-" + icebergVersion + ".jar"
|
||||
)
|
||||
|
||||
func (env *TestEnvironment) startSparkContainer(t *testing.T, configDir string) {
|
||||
t.Helper()
|
||||
|
||||
mounts := testcontainers.Mounts(testcontainers.BindMount(configDir, "/config"))
|
||||
for _, jar := range icebergJars {
|
||||
path := testutil.MavenJar(t, "org.apache.iceberg", jar.artifact, icebergVersion, jar.sha256)
|
||||
mounts = append(mounts, testcontainers.BindMount(path, testcontainers.ContainerMountTarget(sparkJarsDir+"/"+filepath.Base(path))))
|
||||
}
|
||||
|
||||
ctx, cancel := context.WithTimeout(context.Background(), 2*time.Minute)
|
||||
defer cancel()
|
||||
|
||||
req := testcontainers.ContainerRequest{
|
||||
Image: "apache/spark:3.5.1",
|
||||
ExposedPorts: []string{"4040/tcp"},
|
||||
Mounts: testcontainers.Mounts(
|
||||
testcontainers.BindMount(configDir, "/config"),
|
||||
),
|
||||
Mounts: mounts,
|
||||
Env: map[string]string{
|
||||
"SPARK_LOCAL_IP": "localhost",
|
||||
},
|
||||
@@ -266,8 +282,6 @@ import sys
|
||||
spark_home = os.environ.get("SPARK_HOME", "/opt/spark")
|
||||
python_path = os.path.join(spark_home, "python")
|
||||
py4j_glob = glob.glob(os.path.join(python_path, "lib", "py4j-*.zip"))
|
||||
ivy_dir = "/tmp/ivy"
|
||||
os.makedirs(ivy_dir, exist_ok=True)
|
||||
os.environ["AWS_REGION"] = "us-west-2"
|
||||
os.environ["AWS_DEFAULT_REGION"] = "us-west-2"
|
||||
os.environ["AWS_ACCESS_KEY_ID"] = "test"
|
||||
@@ -281,8 +295,7 @@ from pyspark.sql import SparkSession
|
||||
|
||||
spark = (SparkSession.builder
|
||||
.appName("SeaweedFS Iceberg Test")
|
||||
.config("spark.jars.ivy", ivy_dir)
|
||||
.config("spark.jars.packages", "org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.5.2,org.apache.iceberg:iceberg-aws-bundle:1.5.2")
|
||||
.config("spark.jars", "%s")
|
||||
.config("spark.sql.extensions", "org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions")
|
||||
.config("spark.sql.catalog.iceberg", "org.apache.iceberg.spark.SparkCatalog")
|
||||
.config("spark.sql.catalog.iceberg.type", "rest")
|
||||
@@ -303,7 +316,7 @@ spark = (SparkSession.builder
|
||||
.getOrCreate())
|
||||
|
||||
%s
|
||||
`, icebergPort, s3Port, sql)
|
||||
`, sparkJarsConfig, icebergPort, s3Port, sql)
|
||||
|
||||
code, out, err := container.Exec(ctx, []string{"python3", "-c", pythonScript})
|
||||
var output string
|
||||
|
||||
Loaded 100 of 348 files, more files were not shown because too many files have changed in this diff.
Show more
Reference in new issue
Block a user