Xray
daily rollups 1h 6h 24h 48h 3d 5d 7d 14d 30d ‹
Last 3 days▾
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 18:03:50.
› →|
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

studiosvc p95 2.0 min vs a normal 369 ms ± 242 ms for Mon 18:00 UTC (3 of the last 4 checks)

info Latency anomaly master resolved impact 15 Owner: Suresh Boddapati (backup: Madhava Mukkamala) opened 15d ago · last observed 1d ago · observed 570× · #15936 · d5c665127f60584993d7

What happened template

studiosvc's p95 is 120.0 s on master, above a normal of 369 ms ± 242 ms for this hour of the week (3 of the last 4 five-minute buckets, z = 493.5, 4 weeks of history). automated changed studiosvc 54 minutes earlier — adjacency, not proof. 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
value120,000
expected_median369.29
expected_mad242.43
z493.47
rel323.95
buckets_hit3
n36
weeks4
slotMon 18:00 UTC
bucket2026-11-16 18:55:00 UTC (1d ago)
floor_ms1,000
discriminatorapi_p95_ms
window2026-11-16 18:45:00 UTC → 2026-11-16 19:05:00 UTC

Adjacent deploys — adjacency, not proof

automatedstudiosvc · 54 min before

What is failing in studiosvc — the bad events, decomposed

“Bad events” are HTTP 5xx answers from studiosvc. In this finding's window (2026-11-16 18:45:00 UTC → 2026-11-16 19:05:00 UTC) there were 0; every line links to the grouped errors behind it.

The error shapes behind them

249× http error response returned to client since 2026-10-06 15:35:21 UTC
10× failed to fetch form summary — form 5a4d37c2-3a02-4293-bffb-9028257cc51d not found since 2026-11-04 14:46:50 UTC
3× Request completed — 500 · response set with same title and variablename already exists since 2026-11-11 03:34:02 UTC
3× response set creation failed — response set with same title and variablename already exists since 2026-11-17 06:56:38 UTC

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

History

  • 2026-11-16 08:28:23 UTCreopened x-ray · severity=info was=info title=studiosvc p95 2.0 min vs a normal 252 ms ± 232 ms for Mon 08:00 UTC (3 of the last 4 checks) level=low was_level=low finding={'id': 15936, 'fingerprint': 'd5c665127f60584993d7', 'kind': 'anomaly.latency', 'severity': 'info', 'cluster': 'master', 'subject': 'studiosvc', 'title': 'studiosvc p95 2.0 min vs a normal 252 ms ± 232 ms for Mon 08:00 UTC (3 of the last 4 checks)', 'facts': {'measure': 'api_p95_ms', 'unit': 'ms', 'value': 120000.0, 'expected_median': 252.5, 'expected_mad': 231.65625, 'z': 516.9189262107109, 'rel': 474.2475247524753, 'buckets_hit': 3, 'n': 20, 'weeks': 4, 'slot': 'Mon 08:00 UTC', 'bucket': 1794816600, 'window': [1794815700, 1794816900], 'floor_ms': 1000, 'recent_deploys': [{'who': 'automated', 'resource': 'studiosvc', 'image': None, 'revision': 'b82321d7eadde198b031a5adc017daa76cbba5e8', 'ts': 1794816347, 'minutes_before': 22}], 'discriminator': 'api_p95_ms'}, 'evidence': [{'label': 'Service', 'href': '/service/studiosvc?cluster=master&from=1794794100&to=1794816900'}, {'label': 'Fleet vs normal', 'href': '/fleet?cluster=master&from=1794794100&to=1794816900'}], 'provenance': {'source': 'rollup', 'collected_at': 1794817373, 'age_seconds': 339, 'stale': False, 'shown': None, 'total': None, 'truncated': False, 'coverage_from': None, 'retain_days': None, 'note': None}, 'impact': 14.0, 'status': 'open', 'first_seen': 1793687881, 'last_seen': 1794817703, 'resolved_at': None, 'acked_by': None, 'acked_at': None, 'snoozed_until': None, 'occurrences': 529, 'narrative': "studiosvc's p95 is 120.0 s on master, above a normal of 883 ms ± 1.0 s for this hour of the week (4 of the last 4 five-minute buckets, z = 115.9, 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': None, 'episode_at': 1794817703, 'chat_thread': None, 'kind_label': 'Latency anomaly', 'group': 'Anomalies', 'age_s': 1129831, 'stale_s': 9}
  • 2026-11-16 12:29:31 UTCresolved x-ray · reason=not observed grace_s=900 finding={'id': 15936, 'fingerprint': 'd5c665127f60584993d7', 'kind': 'anomaly.latency', 'severity': 'info', 'cluster': 'master', 'subject': 'studiosvc', 'title': 'studiosvc p95 2.0 min vs a normal 454 ms ± 131 ms for Mon 11:00 UTC (3 of the last 4 checks)', 'facts': {'measure': 'api_p95_ms', 'unit': 'ms', 'value': 120000.0, 'expected_median': 454.16666, 'expected_mad': 131.01917, 'z': 912.4300920239382, 'rel': 263.2201873647, 'buckets_hit': 3, 'n': 26, 'weeks': 5, 'slot': 'Mon 11:00 UTC', 'bucket': 1794828300, 'window': [1794827700, 1794828900], 'floor_ms': 1000, 'recent_deploys': [], 'discriminator': 'api_p95_ms'}, 'evidence': [{'label': 'Service', 'href': '/service/studiosvc?cluster=master&from=1794806100&to=1794828900'}, {'label': 'Fleet vs normal', 'href': '/fleet?cluster=master&from=1794806100&to=1794828900'}], 'provenance': {'source': 'rollup', 'collected_at': 1794829599, 'age_seconds': 1224, 'stale': False, 'shown': None, 'total': None, 'truncated': False, 'coverage_from': None, 'retain_days': None, 'note': None}, 'impact': 16.9, 'status': 'resolved', 'first_seen': 1793687881, 'last_seen': 1794830812, 'resolved_at': 1794832171, 'acked_by': None, 'acked_at': None, 'snoozed_until': None, 'occurrences': 539, 'narrative': "studiosvc's p95 is 120.0 s on master, above a normal of 454 ms ± 131 ms for this hour of the week (3 of the last 4 five-minute buckets, z = 912.4, 5 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': None, 'episode_at': 1794817703, 'chat_thread': None, 'kind_label': 'Latency anomaly', 'group': 'Anomalies', 'age_s': 1144302, 'stale_s': 1371}
  • 2026-11-16 14:38:42 UTCreopened x-ray · severity=info was=info title=studiosvc p95 1.9 min vs a normal 418 ms ± 337 ms for Mon 14:00 UTC (3 of the last 4 checks) level=low was_level=low finding={'id': 15936, 'fingerprint': 'd5c665127f60584993d7', 'kind': 'anomaly.latency', 'severity': 'info', 'cluster': 'master', 'subject': 'studiosvc', 'title': 'studiosvc p95 1.9 min vs a normal 418 ms ± 337 ms for Mon 14:00 UTC (3 of the last 4 checks)', 'facts': {'measure': 'api_p95_ms', 'unit': 'ms', 'value': 116999.99999999974, 'expected_median': 417.5, 'expected_mad': 337.2915, 'z': 345.64316029309884, 'rel': 279.23952095808323, 'buckets_hit': 3, 'n': 22, 'weeks': 4, 'slot': 'Mon 14:00 UTC', 'bucket': 1794838800, 'window': [1794837900, 1794839100], 'floor_ms': 1000, 'recent_deploys': [], 'discriminator': 'api_p95_ms'}, 'evidence': [{'label': 'Service', 'href': '/service/studiosvc?cluster=master&from=1794816300&to=1794839100'}, {'label': 'Fleet vs normal', 'href': '/fleet?cluster=master&from=1794816300&to=1794839100'}], 'provenance': {'source': 'rollup', 'collected_at': 1794839637, 'age_seconds': 295, 'stale': False, 'shown': None, 'total': None, 'truncated': False, 'coverage_from': None, 'retain_days': None, 'note': None}, 'impact': 10.4, 'status': 'open', 'first_seen': 1793687881, 'last_seen': 1794839922, 'resolved_at': None, 'acked_by': None, 'acked_at': None, 'snoozed_until': None, 'occurrences': 540, 'narrative': "studiosvc's p95 is 120.0 s on master, above a normal of 454 ms ± 131 ms for this hour of the week (3 of the last 4 five-minute buckets, z = 912.4, 5 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': None, 'episode_at': 1794839922, 'chat_thread': None, 'kind_label': 'Latency anomaly', 'group': 'Anomalies', 'age_s': 1152051, 'stale_s': 10}
  • 2026-11-16 20:29:07 UTCresolved x-ray · reason=not observed grace_s=900 finding={'id': 15936, 'fingerprint': 'd5c665127f60584993d7', 'kind': 'anomaly.latency', 'severity': 'info', 'cluster': 'master', 'subject': 'studiosvc', 'title': 'studiosvc p95 2.0 min vs a normal 369 ms ± 242 ms for Mon 18:00 UTC (3 of the last 4 checks)', 'facts': {'measure': 'api_p95_ms', 'unit': 'ms', 'value': 120000.0, 'expected_median': 369.2857, 'expected_mad': 242.42953, 'z': 493.4659333786606, 'rel': 323.951656671244, 'buckets_hit': 3, 'n': 36, 'weeks': 4, 'slot': 'Mon 18:00 UTC', 'bucket': 1794855300, 'window': [1794854700, 1794855900], 'floor_ms': 1000, 'recent_deploys': [{'who': 'automated', 'resource': 'studiosvc', 'image': None, 'revision': 'f945c27fcd6b8f50f8bca83b403e11f13d564259', 'ts': 1794853194, 'minutes_before': 54}], 'discriminator': 'api_p95_ms'}, 'evidence': [{'label': 'Service', 'href': '/service/studiosvc?cluster=master&from=1794833100&to=1794855900'}, {'label': 'Fleet vs normal', 'href': '/fleet?cluster=master&from=1794833100&to=1794855900'}], 'provenance': {'source': 'rollup', 'collected_at': 1794856251, 'age_seconds': 241, 'stale': False, 'shown': None, 'total': None, 'truncated': False, 'coverage_from': None, 'retain_days': None, 'note': None}, 'impact': 14.7, 'status': 'resolved', 'first_seen': 1793687881, 'last_seen': 1794856481, 'resolved_at': 1794860947, 'acked_by': None, 'acked_at': None, 'snoozed_until': None, 'occurrences': 570, 'narrative': "studiosvc's p95 is 120.0 s on master, above a normal of 369 ms ± 242 ms for this hour of the week (3 of the last 4 five-minute buckets, z = 493.5, 4 weeks of history). automated changed studiosvc 54 minutes earlier — adjacency, not proof. 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': None, 'episode_at': 1794839922, 'chat_thread': None, 'kind_label': 'Latency anomaly', 'group': 'Anomalies', 'age_s': 1173083, 'stale_s': 4483}

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_at1794856251
age_seconds241
staleFalse
shownNone
totalNone
truncatedFalse
coverage_fromNone
retain_daysNone
noteNone
detectorseasonal