mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-05-21 09:11:29 +00:00
d7cd415714
One named workload validation package for RF=2 sync_all: - Scenario: cp13-8-real-workload-validation.yaml (6 phases) - ext4 proof: write 200 files → failover → fsck + file count + md5sum diff - pgbench proof: TPC-B on promoted replica (database durability) - Disturbance: one bounded failover (kill primary, promote replica) Workload envelope doc: phase-13-cp8-workload-validation.md - Named topology, transport, workloads, disturbance, exclusions - Pass criteria: fsck passes, 200 files, checksums match, pgbench TPS > 0 - Maps each pass criterion to accepted CP13-1..7 semantics - Explicit non-claims: not rollout approval, not NVMe, not soak, not CP13-9 Reuses existing infrastructure: - cp85-db-ext4-fsck.yaml pattern (extended with checksums + pgbench) - benchmark-pgbench.yaml actions (pgbench_init/pgbench_run) Must run on real hardware (m01/M02). Cannot run in unit test harness. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
sw-block
Private WAL V2 and standalone block-service workspace.
Purpose:
- keep WAL V2 design/prototype work isolated from WAL V1 production code in
weed/storage/blockvol - allow private design notes and experiments to evolve without polluting V1 delivery paths
- keep the future standalone
sw-blockproduct structure clean enough to split into a separate repo later if needed
Suggested layout:
design/: shared V2 design docsprototype/: code prototypes and experiments.private/: private notes, phase development, roadmap, and non-public working material
Repository direction:
- current state:
sw-block/is an isolated workspace insideseaweedfs - likely future state:
sw-blockbecomes a standalone sibling repo/product - design and prototype structure should therefore stay product-oriented and not depend on SeaweedFS-specific paths