mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-09-20 13:30:46 +02:00
Ping QiuandClaude Opus 4.6
da1b81d1c9
Durability mode implementation (sync_all, sync_quorum, best_effort): - DurabilityMode type with superblock persistence, parse/validate/string - MakeDistributedSync mode-aware barrier enforcement in dist_group_commit - blockerr sentinel package (ErrDurabilityBarrierFailed, ErrDurabilityQuorumLost) - gRPC create path: mode validation, idempotent create consistency, partial cleanup - F1: strict mode rejects partial replica provisioning with cleanup - F3: empty heartbeat does not overwrite persisted strict mode - F4: SCSI error mapping uses errors.Is sentinels (not string matching) - Proto/wire/blockapi/CLI/UI plumbing for durability_mode field - Observability dashboard: cluster health cards + per-volume columns Testrunner platform (YAML-driven integration test framework): - Engine, parser, registry, reporter (JUnit XML + HTML), metrics scraping - 52 registered actions: block, iSCSI, I/O, fault injection, assertions - Baseline regression framework with 7 hard-fail conditions - 15 YAML scenarios (smoke, crash, HA, fault, consistency, snapshot) - 49 unit tests for testrunner internals QA adversarial suite (21 tests, all PASS): - Idempotent create mode/RF mismatch detection - Heartbeat mode downgrade prevention (F3) - sync_all/sync_quorum partial replica enforcement (F1) - Concurrent create race safety - Failover/expand mode preservation - Cleanup resilience when delete fails - Master restart auto-register mode handling - Superblock roundtrip all 3 modes - Validate edge cases (mode×RF matrix) - RequiredReplicas quorum math verification - Sentinel error categorization Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
140 lines
3.1 KiB
YAML
140 lines
3.1 KiB
YAML
name: coord-dev-cycle
|
|
timeout: 5m
|
|
env:
|
|
repo_dir: "/c/work/seaweedfs"
|
|
|
|
topology:
|
|
agents:
|
|
target_agent: "192.168.1.184:9100"
|
|
client_agent: "192.168.1.181:9100"
|
|
|
|
nodes:
|
|
target_node:
|
|
host: "192.168.1.184"
|
|
agent: target_agent
|
|
client_node:
|
|
host: "192.168.1.181"
|
|
agent: client_agent
|
|
|
|
targets:
|
|
primary:
|
|
node: target_node
|
|
vol_size: 100M
|
|
iscsi_port: 3260
|
|
admin_port: 8080
|
|
iqn_suffix: dev-primary
|
|
replica:
|
|
node: target_node
|
|
vol_size: 100M
|
|
iscsi_port: 3261
|
|
admin_port: 8081
|
|
replica_data_port: 9011
|
|
replica_ctrl_port: 9012
|
|
rebuild_port: 9013
|
|
iqn_suffix: dev-replica
|
|
|
|
phases:
|
|
# Phase 0: Kill stale processes from previous runs
|
|
- name: pre_cleanup
|
|
actions:
|
|
- action: kill_stale
|
|
node: target_node
|
|
process: iscsi-target-test
|
|
ignore_error: true
|
|
- action: kill_stale
|
|
node: client_node
|
|
iscsi_cleanup: "true"
|
|
ignore_error: true
|
|
|
|
# Phase 1: Build and deploy iscsi-target binary
|
|
- name: build_deploy
|
|
actions:
|
|
- action: build_deploy
|
|
|
|
# Phase 2: Start targets, set up HA replication
|
|
- name: setup
|
|
actions:
|
|
- action: start_target
|
|
target: primary
|
|
create: "true"
|
|
- action: start_target
|
|
target: replica
|
|
create: "true"
|
|
- action: assign
|
|
target: replica
|
|
epoch: "1"
|
|
role: replica
|
|
lease_ttl: 30s
|
|
- action: assign
|
|
target: primary
|
|
epoch: "1"
|
|
role: primary
|
|
lease_ttl: 30s
|
|
- action: set_replica
|
|
target: primary
|
|
replica: replica
|
|
- action: iscsi_login
|
|
target: primary
|
|
node: client_node
|
|
save_as: device
|
|
|
|
# Phase 3: Write data, verify replication
|
|
- name: write_and_replicate
|
|
actions:
|
|
- action: dd_write
|
|
node: client_node
|
|
device: "{{ device }}"
|
|
bs: 1M
|
|
count: "1"
|
|
save_as: written_md5
|
|
- action: wait_lsn
|
|
target: replica
|
|
min_lsn: "1"
|
|
timeout: 10s
|
|
|
|
# Phase 4: Kill primary, promote replica
|
|
- name: failover
|
|
actions:
|
|
- action: kill_target
|
|
target: primary
|
|
- action: iscsi_cleanup
|
|
node: client_node
|
|
ignore_error: true
|
|
- action: assign
|
|
target: replica
|
|
epoch: "2"
|
|
role: primary
|
|
lease_ttl: 30s
|
|
- action: wait_role
|
|
target: replica
|
|
role: primary
|
|
timeout: 5s
|
|
|
|
# Phase 5: Verify data survived failover
|
|
- name: verify
|
|
actions:
|
|
- action: iscsi_login
|
|
target: replica
|
|
node: client_node
|
|
save_as: device2
|
|
- action: dd_read_md5
|
|
node: client_node
|
|
device: "{{ device2 }}"
|
|
bs: 1M
|
|
count: "1"
|
|
save_as: read_md5
|
|
- action: assert_equal
|
|
actual: "{{ read_md5 }}"
|
|
expected: "{{ written_md5 }}"
|
|
|
|
# Phase 6: Cleanup (always runs, even on failure)
|
|
- name: cleanup
|
|
always: true
|
|
actions:
|
|
- action: iscsi_cleanup
|
|
node: client_node
|
|
ignore_error: true
|
|
- action: stop_all_targets
|
|
aggressive: "true"
|
|
ignore_error: true
|