mirror of
https://github.com/hanzoai/datastore.git
synced 2026-10-30 14:48:37 +00:00
zlareb1andClaude Opus 4.7
9b6eb38dc9
Address review comment 3194583058: the date-range workflow promised
"between A and B" but only filtered ts >= '{{TS_FILTER}}', so a request
like "between 2026-04-01 and 2026-05-01" silently included every nightly
after 2026-05-01 and let cumulative deltas drift as new runs accumulated.
Add a parallel TS_FILTER_END / KEEPER_SKILL_THRESHOLD_END upper bound that
mirrors the existing lower bound at every layer:
- All 6 staging SQL queries: append `AND ts < '{{TS_FILTER_END}}'`.
- `rebuild.sh`: accept `$3` as the upper bound; sed-substitute both
placeholders; export both env vars for the Python pipeline.
- `_common.py`: parse `KEEPER_SKILL_THRESHOLD_END` (defaults to far-future
sentinel `9999-12-31`) so unbounded callers keep today's behavior.
- `build_pr_nightly_map.py` and `compute_deltas.py`: filter PRs against
the half-open `[THRESHOLD, THRESHOLD_END)` interval.
- `SKILL.md`: update Phase 2 invocation and Example 2 ("between
2026-04-01 and 2026-05-01") to pass both bounds.
- `tests/test_common.py`: 2 new cases for the `THRESHOLD_END` default
and explicit-env-var parse path. 23 -> 25 cases, all pass.
Backward-compat regression contract: invoking `rebuild.sh ... 2026-03-25`
(no upper bound) still produces `cumulative_gains.tsv` md5
e5a27e01008ef7e23597ee041f68103b and the `#99651` PR-branch isolation row
bit-identical. Bounded smoke (`... 2026-03-25 2026-04-15`) verified to
produce strictly fewer rows in `bench_summary.tsv` and `merged_metrics.tsv`,
with max `run_ended` < `2026-04-15` and all `pr_to_nightly.tsv` `merged_at`
< `2026-04-15`.
Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
66 lines
2.6 KiB
SQL
66 lines
2.6 KiB
SQL
-- Per-keeper-node prom counters → rate per sec, then aggregate across run
|
|
WITH base AS (
|
|
SELECT
|
|
scenario, backend, commit_sha, name, node,
|
|
toUnixTimestamp(ts) AS t,
|
|
max(value) AS v
|
|
FROM keeper_stress_tests.keeper_metrics_ts
|
|
WHERE source = 'prom'
|
|
AND branch = 'master'
|
|
AND ts >= '{{TS_FILTER}}'
|
|
AND ts < '{{TS_FILTER_END}}'
|
|
AND node IN ('keeper1', 'keeper2', 'keeper3')
|
|
AND name IN (
|
|
'ClickHouseProfileEvents_KeeperRequestTotal',
|
|
'ClickHouseProfileEvents_KeeperCommits',
|
|
'ClickHouseProfileEvents_KeeperPacketsSent',
|
|
'ClickHouseProfileEvents_KeeperPacketsReceived',
|
|
'ClickHouseProfileEvents_KeeperTotalElapsedMicroseconds',
|
|
'ClickHouseProfileEvents_KeeperProcessElapsedMicroseconds',
|
|
'ClickHouseProfileEvents_KeeperPreprocessElapsedMicroseconds',
|
|
'ClickHouseProfileEvents_KeeperStorageLockWaitMicroseconds',
|
|
'ClickHouseProfileEvents_FileSyncElapsedMicroseconds',
|
|
'ClickHouseProfileEvents_KeeperChangelogFileSyncMicroseconds',
|
|
'ClickHouseProfileEvents_KeeperCommitWaitElapsedMicroseconds',
|
|
'ClickHouseProfileEvents_KeeperChangelogWrittenBytes',
|
|
'ClickHouseProfileEvents_KeeperSnapshotWrittenBytes',
|
|
'ClickHouseProfileEvents_KeeperSnapshotApplys',
|
|
'ClickHouseProfileEvents_KeeperSnapshotCreations',
|
|
'ClickHouseProfileEvents_KeeperLogsEntryReadFromFile',
|
|
'ClickHouseProfileEvents_KeeperLogsPrefetchedEntries',
|
|
'ClickHouseProfileEvents_KeeperLogsEntryReadFromCommitCache',
|
|
'ClickHouseProfileEvents_KeeperLogsEntryReadFromLatestCache',
|
|
'ClickHouseProfileEvents_KeeperLatency'
|
|
)
|
|
GROUP BY scenario, backend, commit_sha, name, node, ts
|
|
),
|
|
rated AS (
|
|
SELECT
|
|
scenario, backend, commit_sha, name, node,
|
|
(v - lagInFrame(v, 1) OVER (PARTITION BY scenario, backend, commit_sha, name, node ORDER BY t))
|
|
/ nullIf(t - lagInFrame(t, 1) OVER (PARTITION BY scenario, backend, commit_sha, name, node ORDER BY t), 0) AS rate
|
|
FROM base
|
|
),
|
|
agg_per_node AS (
|
|
SELECT scenario, backend, commit_sha, name, node,
|
|
avg(rate) AS avg_rate,
|
|
quantile(0.95)(rate) AS p95_rate,
|
|
max(rate) AS max_rate
|
|
FROM rated
|
|
WHERE rate IS NOT NULL AND rate >= 0
|
|
GROUP BY scenario, backend, commit_sha, name, node
|
|
)
|
|
SELECT
|
|
scenario,
|
|
backend,
|
|
commit_sha,
|
|
name,
|
|
round(avg(avg_rate), 2) AS avg_rate_avg_node,
|
|
round(max(avg_rate), 2) AS avg_rate_max_node,
|
|
round(max(p95_rate), 2) AS p95_rate_max_node,
|
|
round(max(max_rate), 2) AS max_rate_max_node
|
|
FROM agg_per_node
|
|
GROUP BY scenario, backend, commit_sha, name
|
|
ORDER BY scenario, backend, commit_sha, name
|
|
FORMAT TSVWithNames
|