mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-10-07 06:47:51 +02:00
* feat(filer): option to store system metadata logs in their own collection The filer's internal /topics/.system/log chunks are assigned to the filer's default collection (-collection). In a multi-filer deployment that default is often empty, so every restart flap, full-sync, or event-buffered flush grows the default collection with system chunks that are indistinguishable from user data in collection.list. This is a large part of what makes the default collection balloon and confuses orphan analysis. This keeps the internal log in a dedicated collection when the operator asks for one, without changing where user data goes: - New optional override, filer.options.metaLog.collection (and .replication), read in NewFiler so both `weed filer` and `weed server -filer` honour it. Default "" => exactly today's behaviour (log follows the filer default), fully backward compatible. - Resolution is a small helper: override first, then the filer default, then a storage rule matched on the log path. Kept separate from the user write path so the internal log targets itself. - bucketCollection() is hardened the same way it already protects the filer's default collection: a bucket that happens to resolve to the redirected meta-log collection must not drop it on delete, because it backs internal log volumes. - Scaffold filer.toml documents the new knobs under [filer.options]. Related to the persisted deletion ledger branch (fix/persist-deletion-queue): together they cut the two sources of post-flap junk in the default collection — that PR stops orphaned user-chunk leak on filer crash, this one stops the internal log from living in default at all. They are independent: no file overlap, no functional dependency; either can merge first. They are paired only in the narrative of cleaning up default. Adds unit tests for the collection/replication resolution chain, the viper keys, and the bucket-delete guard (run green under -race). Co-Authored-By: Athena 🏛️ <hermes-agent@local> (custom / Qwen3.8-Flash-Next-ROCmFP4) * filer: collect bucket chunks when its collection survives the delete bucketCollection returning "" preserves the collection, but the bucket path still skipped per-entry chunk collection and could skip listing the children entirely, so a bucket sharing the meta-log (or any preserved) collection left its object chunks orphaned with no entry pointing at them. Only the wholesale drop of a deleted collection skips those now. Note in filer.toml that the meta-log target should stay stable: chunks written under an older collection are not migrated. * filer: exercise the metaLog override wiring through NewFiler The viper test only echoed back the keys it set, so a wrong key in NewFiler would still pass. It now asserts the fields NewFiler fills from those keys. Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * filer: tighten comments around the metaLog collection override Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Chris Lu <chris.lu@gmail.com> Co-authored-by: Chris Lu <chrislusf@users.noreply.github.com> Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
138 lines
4.4 KiB
Go
138 lines
4.4 KiB
Go
package filer
|
|
|
|
import (
|
|
"context"
|
|
"testing"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
|
|
"github.com/seaweedfs/seaweedfs/weed/util"
|
|
)
|
|
|
|
// The metadata log's collection resolution must let operators redirect the
|
|
// internal /topics/.system/log chunks into their own collection without
|
|
// touching where user data goes, and must be strictly backward compatible
|
|
// when the override is unset.
|
|
|
|
func TestMetaLogCollectionResolution(t *testing.T) {
|
|
tests := []struct {
|
|
name string
|
|
target string // filer.options.metaLog.collection override
|
|
filerDefault string // -collection flag value
|
|
ruleCollection string // storage rule matched on the log path
|
|
want string
|
|
}{
|
|
{
|
|
name: "no override: filer default wins (today's behaviour)",
|
|
target: "",
|
|
filerDefault: "mydata",
|
|
ruleCollection: "",
|
|
want: "mydata",
|
|
},
|
|
{
|
|
name: "no override anywhere: still empty (default collection)",
|
|
target: "",
|
|
filerDefault: "",
|
|
ruleCollection: "",
|
|
want: "",
|
|
},
|
|
{
|
|
name: "override wins over filer default",
|
|
target: "filer-meta",
|
|
filerDefault: "mydata",
|
|
ruleCollection: "",
|
|
want: "filer-meta",
|
|
},
|
|
{
|
|
name: "override wins over matched rule",
|
|
target: "filer-meta",
|
|
filerDefault: "",
|
|
ruleCollection: "rulecol",
|
|
want: "filer-meta",
|
|
},
|
|
{
|
|
name: "no override but rule set: rule used (unchanged fallback chain)",
|
|
target: "",
|
|
filerDefault: "",
|
|
ruleCollection: "rulecol",
|
|
want: "rulecol",
|
|
},
|
|
}
|
|
|
|
for _, tc := range tests {
|
|
t.Run(tc.name, func(t *testing.T) {
|
|
// Drive the same setter a running filer would use post-construction.
|
|
f := &Filer{}
|
|
f.metaLogTargetCollection = tc.target
|
|
f.metaLogCollection = tc.filerDefault
|
|
if got := f.metaLogCollectionFor(tc.ruleCollection); got != tc.want {
|
|
t.Errorf("metaLogCollectionFor(%q) = %q, want %q", tc.ruleCollection, got, tc.want)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestMetaLogReplicationResolution(t *testing.T) {
|
|
f := &Filer{}
|
|
f.metaLogTargetReplication = "110"
|
|
f.metaLogReplication = "010"
|
|
if got := f.metaLogReplicationFor("001"); got != "110" {
|
|
t.Errorf("override must win, got %q", got)
|
|
}
|
|
f.metaLogTargetReplication = ""
|
|
if got := f.metaLogReplicationFor("001"); got != "010" {
|
|
t.Errorf("filer replication must win when no override, got %q", got)
|
|
}
|
|
f.metaLogReplication = ""
|
|
if got := f.metaLogReplicationFor("001"); got != "001" {
|
|
t.Errorf("rule replication must be used last, got %q", got)
|
|
}
|
|
}
|
|
|
|
// TestViperReadsMetaLogOverrides proves the exact viper keys the docs promise
|
|
// are read into the fields a running filer uses.
|
|
func TestViperReadsMetaLogOverrides(t *testing.T) {
|
|
v := util.GetViper()
|
|
v.Set("filer.options.metaLog.collection", "filer-meta")
|
|
v.Set("filer.options.metaLog.replication", "100")
|
|
defer func() {
|
|
// Reset so other tests see the unset default.
|
|
v.Set("filer.options.metaLog.collection", "")
|
|
v.Set("filer.options.metaLog.replication", "")
|
|
}()
|
|
|
|
f := NewFiler(pb.ServerDiscovery{}, nil, "", "", "", "", "", 255, nil)
|
|
if got := f.metaLogTargetCollection; got != "filer-meta" {
|
|
t.Fatalf("NewFiler did not read the collection override: %q", got)
|
|
}
|
|
if got := f.metaLogTargetReplication; got != "100" {
|
|
t.Fatalf("NewFiler did not read the replication override: %q", got)
|
|
}
|
|
}
|
|
|
|
// TestBucketCollectionKeepsMetaLogTargetCollection mirrors the guarantee that
|
|
// protects the filer's default collection: when a bucket resolves to the
|
|
// collection the system metadata log was redirected to, deleting the bucket
|
|
// must not drop that collection (it backs internal log volumes).
|
|
func TestBucketCollectionKeepsMetaLogTargetCollection(t *testing.T) {
|
|
f, store, master := newFilerWithFakeMaster(t)
|
|
// Operator redirected the meta log to its own collection...
|
|
f.metaLogTargetCollection = "filer-meta"
|
|
// ...and a bucket happens to resolve to that very collection.
|
|
f.FilerConf.SetLocationConf(&filer_pb.FilerConf_PathConf{
|
|
LocationPrefix: "/buckets/a",
|
|
Collection: "filer-meta",
|
|
})
|
|
seedBucket(t, store, util.FullPath("/buckets/a"))
|
|
|
|
if err := f.DeleteEntryMetaAndData(context.Background(), "/buckets/a", true, false, true, false, nil, 0); err != nil {
|
|
t.Fatalf("DeleteEntryMetaAndData: %v", err)
|
|
}
|
|
|
|
select {
|
|
case call := <-master.calls:
|
|
t.Fatalf("the meta-log target collection was deleted by a bucket delete: %q", call.name)
|
|
default:
|
|
}
|
|
}
|