You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
test: long-running soak test at scale (millions of facts, many checkpoints, reopen cycles) #392
The nightly smoke suite has a 15-minute timeout. No test runs for hours, or at a size like a real agent-memory or audit-log deployment, for example:
10M+ facts
thousands of checkpoints
heavy retract and reassert on hot entities
many open and close cycles
Bugs like #370 appeared only after several checkpoints on a real workload.
Ask
Add a weekly soak workflow, for example 4–6 hours on one runner. It should:
grow a file-backed database to 10M+ facts, in batches of mixed sizes, with multi-valued attributes and retracts;
checkpoint on a schedule and reopen at random;
every N minutes, check a sample of entities against a reference log through EAVT, AEVT and full-scan paths;
record file size, open time, checkpoint time, peak RSS and p50/p99 query latency, and upload them as artifacts (these also feed the performance envelope issue);
fail if anything differs, or if memory grows without bound.
Activity
test: soak checks multi-valued reads by entity+attribute and AEVT (#392)
Merge pull request #519 from project-minigraf/test/392-soak
Merge pull request #520 from project-minigraf/test/392-soak-v2
adityamukho commentedon Oct 10, 2026
Done: soak test merged on v3 (#519) and main (#520).
.github/workflows/soak.ymlruns weekly (Saturday main, Sunday v3). Finding: #518.release: v2.0.5