Xray
1h 6h 24h 48h 3d 5d 7d 14d 30d ‹
Last 1 hour▾
Ends now. Anything up to this cluster's 30-day retention.
Start and end times
Cancel
Interpreted in UTC (change it at the right of this bar). Earliest available: 2026-10-19 14:14:26.
› →|
updated 1d ago
Sample data. This database was generated by scripts/seed_dev_db.py — every service, deploy, person and figure on this page is synthetic. Names are sample.*@seed.invalid and image tags are prefixed SEED-. Nothing here happened.
← findings

execsvc p95 4.15 s vs a normal 462 ms ± 398 ms for Mon 20:00 UTC (3 of the last 4 checks)

info Latency anomaly production resolved impact 17 Owner: Madhava Mukkamala (backup: Shashank Agrawal) opened 70d ago · last observed 1d ago · observed 44× · #1329 · de5361d971015bf5d662

What happened template

execsvc's p95 is 4.2 s on production, above a normal of 462 ms ± 398 ms for this hour of the week (3 of the last 4 five-minute buckets, z = 9.3, 4 weeks of history). Whether users noticed depends on which endpoints carried it — the service page shows the split. A p95 that stays under a second is never reported — below that nobody notices, whatever the deviation.

p95 far above its hour-of-week normal — and at least 1 s; under a second is noise.

The facts

measureapi_p95_ms
unitms
value4,152
expected_median462.50
expected_mad398.45
z9.26
rel7.98
buckets_hit3
n24
weeks4
slotMon 20:00 UTC
bucket2026-11-16 20:40:00 UTC (1d ago)
floor_ms1,000
discriminatorapi_p95_ms
window2026-11-16 20:30:00 UTC → 2026-11-16 20:50:00 UTC

What is failing in execsvc — the bad events, decomposed

“Bad events” are HTTP 5xx answers from execsvc. In this finding's window (2026-11-16 20:30:00 UTC → 2026-11-16 20:50:00 UTC) there were 1; every line links to the grouped errors behind it.

POST /api/trialexec/careplan/:id/visit/:id/preVisitTodo 1 bad of 1 calls · 100% of the service's 5xx

The error shapes behind them

473× no result from branch evaluation since 2026-11-11 14:55:54 UTC
473× failed to evaluate and raise auto query for participant question — no result from branch evaluation for branch, protocol… since 2026-11-16 16:26:25 UTC
78× failed to evaluate and raise auto query for participant question — evalResult is not a bool since 2026-11-16 16:26:23 UTC
78× evalResult is not a bool since 2026-11-16 16:26:23 UTC
23× message was never published because transaction was never committed since 2026-11-11 20:50:40 UTC

All execsvc errors, grouped → · service page · its logs

History

  • 2026-11-16 06:13:57 UTCresolved x-ray · reason=not observed grace_s=900 finding={'id': 1329, 'fingerprint': 'de5361d971015bf5d662', 'kind': 'anomaly.latency', 'severity': 'info', 'cluster': 'production', 'subject': 'execsvc', 'title': 'execsvc p95 3.88 s vs a normal <1 ms ± 100 ms for Fri 21:00 UTC (3 of the last 4 checks)', 'facts': {'measure': 'api_p95_ms', 'unit': 'ms', 'value': 3875.0, 'expected_median': 0.95, 'expected_mad': 100.0, 'z': 38.740500000000004, 'rel': 4077.947368421053, 'buckets_hit': 3, 'n': 25, 'weeks': 3, 'slot': 'Fri 21:00 UTC', 'bucket': 1794604200, 'window': [1794603600, 1794604800], 'floor_ms': 1000, 'recent_deploys': [], 'discriminator': 'api_p95_ms'}, 'evidence': [{'label': 'Service', 'href': '/service/execsvc?cluster=production&from=1794582000&to=1794604800'}, {'label': 'Fleet vs normal', 'href': '/fleet?cluster=production&from=1794582000&to=1794604800'}], 'provenance': {'source': 'rollup', 'collected_at': 1794605179, 'age_seconds': 61, 'stale': False, 'shown': None, 'total': None, 'truncated': False, 'coverage_from': None, 'retain_days': None, 'note': None}, 'impact': 17.4, 'status': 'resolved', 'first_seen': 1788956811, 'last_seen': 1794605231, 'resolved_at': 1794809637, 'acked_by': None, 'acked_at': None, 'snoozed_until': None, 'occurrences': 42, 'narrative': "execsvc's p95 is 3.9 s on production, above a normal of 1 ms ± 100 ms for this hour of the week (3 of the last 4 five-minute buckets, z = 38.7, 3 weeks of history). Whether users noticed depends on which endpoints carried it — the service page shows the split. A p95 that stays under a second is never reported — below that nobody notices, whatever the deviation.", 'narrative_kind': 'template', 'discriminator': 'api_p95_ms', 'level': 'low', 'told_level': 'low', 'episode_at': 1794603258, 'chat_thread': 'xray-alert-11-748fd5a928-g-1791896750', 'kind_label': 'Latency anomaly', 'group': 'Anomalies', 'age_s': 5852838, 'stale_s': 204418}
  • 2026-11-16 20:53:56 UTCreopened x-ray · severity=info was=info title=execsvc p95 4.15 s vs a normal 462 ms ± 398 ms for Mon 20:00 UTC (3 of the last 4 checks) level=low was_level=low finding={'id': 1329, 'fingerprint': 'de5361d971015bf5d662', 'kind': 'anomaly.latency', 'severity': 'info', 'cluster': 'production', 'subject': 'execsvc', 'title': 'execsvc p95 4.15 s vs a normal 462 ms ± 398 ms for Mon 20:00 UTC (3 of the last 4 checks)', 'facts': {'measure': 'api_p95_ms', 'unit': 'ms', 'value': 4152.173913043478, 'expected_median': 462.5, 'expected_mad': 398.44876, 'z': 9.260096362311375, 'rel': 7.977673325499412, 'buckets_hit': 3, 'n': 24, 'weeks': 4, 'slot': 'Mon 20:00 UTC', 'bucket': 1794861600, 'window': [1794860700, 1794861900], 'floor_ms': 1000, 'recent_deploys': [], 'discriminator': 'api_p95_ms'}, 'evidence': [{'label': 'Service', 'href': '/service/execsvc?cluster=production&from=1794839100&to=1794861900'}, {'label': 'Fleet vs normal', 'href': '/fleet?cluster=production&from=1794839100&to=1794861900'}], 'provenance': {'source': 'rollup', 'collected_at': 1794862402, 'age_seconds': 45, 'stale': False, 'shown': None, 'total': None, 'truncated': False, 'coverage_from': None, 'retain_days': None, 'note': None}, 'impact': 11.6, 'status': 'open', 'first_seen': 1788956811, 'last_seen': 1794862436, 'resolved_at': None, 'acked_by': None, 'acked_at': None, 'snoozed_until': None, 'occurrences': 43, 'narrative': "execsvc's p95 is 3.9 s on production, above a normal of 1 ms ± 100 ms for this hour of the week (3 of the last 4 five-minute buckets, z = 38.7, 3 weeks of history). Whether users noticed depends on which endpoints carried it — the service page shows the split. A p95 that stays under a second is never reported — below that nobody notices, whatever the deviation.", 'narrative_kind': 'template', 'discriminator': 'api_p95_ms', 'level': 'low', 'told_level': 'low', 'episode_at': 1794862436, 'chat_thread': 'xray-alert-11-748fd5a928-g-1791896750', 'kind_label': 'Latency anomaly', 'group': 'Anomalies', 'age_s': 5905636, 'stale_s': 11}
  • 2026-11-16 23:14:34 UTCresolved x-ray · reason=not observed grace_s=900 finding={'id': 1329, 'fingerprint': 'de5361d971015bf5d662', 'kind': 'anomaly.latency', 'severity': 'info', 'cluster': 'production', 'subject': 'execsvc', 'title': 'execsvc p95 4.15 s vs a normal 462 ms ± 398 ms for Mon 20:00 UTC (3 of the last 4 checks)', 'facts': {'measure': 'api_p95_ms', 'unit': 'ms', 'value': 4152.173913043478, 'expected_median': 462.5, 'expected_mad': 398.44876, 'z': 9.260096362311375, 'rel': 7.977673325499412, 'buckets_hit': 3, 'n': 24, 'weeks': 4, 'slot': 'Mon 20:00 UTC', 'bucket': 1794861600, 'window': [1794861000, 1794862200], 'floor_ms': 1000, 'recent_deploys': [], 'discriminator': 'api_p95_ms'}, 'evidence': [{'label': 'Service', 'href': '/service/execsvc?cluster=production&from=1794839400&to=1794862200'}, {'label': 'Fleet vs normal', 'href': '/fleet?cluster=production&from=1794839400&to=1794862200'}], 'provenance': {'source': 'rollup', 'collected_at': 1794862816, 'age_seconds': 80, 'stale': False, 'shown': None, 'total': None, 'truncated': False, 'coverage_from': None, 'retain_days': None, 'note': None}, 'impact': 16.6, 'status': 'resolved', 'first_seen': 1788956811, 'last_seen': 1794862882, 'resolved_at': 1794870874, 'acked_by': None, 'acked_at': None, 'snoozed_until': None, 'occurrences': 44, 'narrative': "execsvc's p95 is 4.2 s on production, above a normal of 462 ms ± 398 ms for this hour of the week (3 of the last 4 five-minute buckets, z = 9.3, 4 weeks of history). Whether users noticed depends on which endpoints carried it — the service page shows the split. A p95 that stays under a second is never reported — below that nobody notices, whatever the deviation.", 'narrative_kind': 'template', 'discriminator': 'api_p95_ms', 'level': 'low', 'told_level': 'low', 'episode_at': 1794862436, 'chat_thread': 'xray-alert-11-748fd5a928-g-1791896750', 'kind_label': 'Latency anomaly', 'group': 'Anomalies', 'age_s': 5914075, 'stale_s': 8004}

Notifications

  • 2026-11-16 23:15:29 UTCdigest-itemin-app,prod-notifications · sent
  • 2026-11-16 06:14:19 UTCdigest-itemin-app,prod-notifications · sent

Check it yourself

Every link carries the finding's own time window, so it shows tomorrow what it shows now.

Actions

Sign in (IAP) to acknowledge, snooze or resolve.

Where the numbers come from

sourcerollup
collected_at1794862816
age_seconds80
staleFalse
shownNone
totalNone
truncatedFalse
coverage_fromNone
retain_daysNone
noteNone
detectorseasonal