snapshot of https://github.com/tldraw/tldraw.git (main, 2026-09-23; blobs > 131072B omitted)
Some checks failed
Deploy analytics worker / Deploy analytics worker to ${{ (github.ref == 'refs/heads/production' && 'production') || (github.ref == 'refs/heads/main' && 'staging') || 'preview' }} (push) Failing after 1s
i18n upload strings / Upload latest strings (push) Failing after 1s
Deploy bemo / Deploy bemo to ${{ (github.ref == 'refs/heads/bemo-production' && 'production') || (github.ref == 'refs/heads/main' && 'staging') || 'preview' }} (push) Failing after 1s
Deploy grafana resources / ${{ github.event_name == 'push' && 'Deploy grafana resources' || 'Validate grafana resources (dry run)' }} (push) Failing after 0s
End to end tests (dotcom) / Check for relevant changes (push) Failing after 0s
End to end tests (examples) / Check for relevant changes (push) Failing after 0s
End to end tests (mermaid readability) / Check for relevant changes (push) Failing after 1s
End to end tests (perf) / Check for relevant changes (push) Failing after 0s
Publish editor extensions / Publish editor extensions (push) Failing after 1s
Publish SDK packages / Remove the publish-packages label (push) Has been skipped
Checks / Tests & checks (push) Has been cancelled
Checks / Build all projects (push) Has been cancelled
Deploy templates / Deploy templates (push) Has been cancelled
End to end tests (dotcom) / End to end tests (dotcom) (push) Has been cancelled
End to end tests (mermaid readability) / End to end tests (mermaid readability) (push) Has been cancelled
End to end tests (perf) / End to end tests (perf) (push) Has been cancelled
Deploy .com / Deploy dotcom to ${{ (github.ref == 'refs/heads/production' && 'production') || (github.ref == 'refs/heads/main' && 'staging') || 'preview' }} (push) Has been cancelled
End to end tests (examples) / End to end tests (examples) (push) Has been cancelled
Publish SDK packages / Publish SDK packages (push) Has been cancelled
Publish SDK packages / Tell user released version (push) Has been cancelled
Publish SDK packages / Publishes code templates to separate repositories (push) Has been cancelled
Publish SDK packages / Deploys the template demos with the new SDK version (push) Has been cancelled
Some checks failed
Deploy analytics worker / Deploy analytics worker to ${{ (github.ref == 'refs/heads/production' && 'production') || (github.ref == 'refs/heads/main' && 'staging') || 'preview' }} (push) Failing after 1s
i18n upload strings / Upload latest strings (push) Failing after 1s
Deploy bemo / Deploy bemo to ${{ (github.ref == 'refs/heads/bemo-production' && 'production') || (github.ref == 'refs/heads/main' && 'staging') || 'preview' }} (push) Failing after 1s
Deploy grafana resources / ${{ github.event_name == 'push' && 'Deploy grafana resources' || 'Validate grafana resources (dry run)' }} (push) Failing after 0s
End to end tests (dotcom) / Check for relevant changes (push) Failing after 0s
End to end tests (examples) / Check for relevant changes (push) Failing after 0s
End to end tests (mermaid readability) / Check for relevant changes (push) Failing after 1s
End to end tests (perf) / Check for relevant changes (push) Failing after 0s
Publish editor extensions / Publish editor extensions (push) Failing after 1s
Publish SDK packages / Remove the publish-packages label (push) Has been skipped
Checks / Tests & checks (push) Has been cancelled
Checks / Build all projects (push) Has been cancelled
Deploy templates / Deploy templates (push) Has been cancelled
End to end tests (dotcom) / End to end tests (dotcom) (push) Has been cancelled
End to end tests (mermaid readability) / End to end tests (mermaid readability) (push) Has been cancelled
End to end tests (perf) / End to end tests (perf) (push) Has been cancelled
Deploy .com / Deploy dotcom to ${{ (github.ref == 'refs/heads/production' && 'production') || (github.ref == 'refs/heads/main' && 'staging') || 'preview' }} (push) Has been cancelled
End to end tests (examples) / End to end tests (examples) (push) Has been cancelled
Publish SDK packages / Publish SDK packages (push) Has been cancelled
Publish SDK packages / Tell user released version (push) Has been cancelled
Publish SDK packages / Publishes code templates to separate repositories (push) Has been cancelled
Publish SDK packages / Deploys the template demos with the new SDK version (push) Has been cancelled
This commit is contained in:
upstream-mirror
@@ -0,0 +1,112 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: anthropic
|
||||
grafana.com/provenance: ''
|
||||
grafana.com/updateTimestamp: '2026-03-20T11:22:55Z'
|
||||
grafana.com/updatedBy: bf1wptf89bpq8d
|
||||
labels:
|
||||
grafana.app/folder: anthropic
|
||||
grafana.com/group: anthropic
|
||||
grafana.com/group-index: '1'
|
||||
name: 8451fbba-5835-56e2-b2f5-7f5e44c520b8
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
annotations:
|
||||
description: 'Anthropic API usage over the last hour averaged {{ $value | humanize }}
|
||||
tokens/sec excluding cache reads, above the 1000 tokens/sec floor (about 3.6M
|
||||
tokens/hour). Check the scrape overview dashboard for which key and model.'
|
||||
summary: Anthropic API token burst detected.
|
||||
execErrState: Ok
|
||||
expressions:
|
||||
prometheus_math:
|
||||
model:
|
||||
datasource:
|
||||
IsPrunable: false
|
||||
access: ''
|
||||
apiVersion: ''
|
||||
basicAuth: false
|
||||
basicAuthUser: ''
|
||||
created: '0001-01-01T00:00:00Z'
|
||||
database: ''
|
||||
id: -100
|
||||
isDefault: false
|
||||
jsonData: {}
|
||||
name: __expr__
|
||||
readOnly: false
|
||||
secureJsonData: {}
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
updated: '0001-01-01T00:00:00Z'
|
||||
url: ''
|
||||
user: ''
|
||||
withCredentials: false
|
||||
expression: is_number($query) || is_nan($query) || is_inf($query)
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: prometheus_math
|
||||
type: math
|
||||
queryType: math
|
||||
query:
|
||||
datasourceUID: grafanacloud-prom
|
||||
model:
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: grafanacloud-prom
|
||||
expr: |
|
||||
sum(
|
||||
rate(gen_ai_usage_tokens_total{job=~"integrations/anthropic/.*", gen_ai_token_type!="input_cache_read"}[1h])
|
||||
) > 1000
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
range: false
|
||||
refId: query
|
||||
queryType: prometheus
|
||||
relativeTimeRange:
|
||||
from: 11m0s
|
||||
to: 1m0s
|
||||
threshold:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 0
|
||||
type: gt
|
||||
datasource:
|
||||
IsPrunable: false
|
||||
access: ''
|
||||
apiVersion: ''
|
||||
basicAuth: false
|
||||
basicAuthUser: ''
|
||||
created: '0001-01-01T00:00:00Z'
|
||||
database: ''
|
||||
id: -100
|
||||
isDefault: false
|
||||
jsonData: {}
|
||||
name: __expr__
|
||||
readOnly: false
|
||||
secureJsonData: {}
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
updated: '0001-01-01T00:00:00Z'
|
||||
url: ''
|
||||
user: ''
|
||||
withCredentials: false
|
||||
expression: prometheus_math
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: threshold
|
||||
type: threshold
|
||||
queryType: threshold
|
||||
source: true
|
||||
for: 15m0s
|
||||
labels:
|
||||
__converted_prometheus_rule__: 'true'
|
||||
severity: warning
|
||||
missingSeriesEvalsToResolve: 10
|
||||
noDataState: Ok
|
||||
title: AnthropicTokenBurst
|
||||
trigger:
|
||||
interval: 1m
|
||||
@@ -0,0 +1,66 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/provenance: ''
|
||||
grafana.com/updateTimestamp: '2026-04-21T09:07:11Z'
|
||||
grafana.com/updatedBy: ae5t47muqbegwf
|
||||
labels:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/group: zero-alerts-fast
|
||||
grafana.com/group-index: '2'
|
||||
name: afjn4kz1g4jk0a
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
execErrState: Error
|
||||
expressions:
|
||||
A:
|
||||
datasourceUID: grafanacloud-prom
|
||||
model:
|
||||
editorMode: code
|
||||
expr: zero_replication_total_lag_millisecond{deployment_environment="production",
|
||||
service_name="zero-rm"}
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
legendFormat: __auto
|
||||
maxDataPoints: 43200
|
||||
range: false
|
||||
refId: A
|
||||
relativeTimeRange:
|
||||
from: 10m0s
|
||||
to: 0s
|
||||
C:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 1000
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
queryType: expression
|
||||
source: true
|
||||
for: 5m0s
|
||||
labels:
|
||||
service: zero
|
||||
severity: warning
|
||||
noDataState: NoData
|
||||
title: Zero replication lag elevated
|
||||
trigger:
|
||||
interval: 5m
|
||||
@@ -0,0 +1,81 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/provenance: ''
|
||||
grafana.com/updateTimestamp: '2026-04-28T08:48:46Z'
|
||||
grafana.com/updatedBy: ae5t47muqbegwf
|
||||
labels:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/group: zero-fly-alerts
|
||||
grafana.com/group-index: '5'
|
||||
name: bfjyilovht2pse
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
annotations:
|
||||
description: |-
|
||||
Fires when the 5-minute rolling count of logs with detected_level error or fatal is greater than zero for service_name matching zero-(rm|vs) and deployment_environment=production.
|
||||
|
||||
Investigate in Grafana Explore (grafanacloud-tldraw-logs):
|
||||
|
||||
{service_name=~"zero-(rm|vs)", deployment_environment="production"} | detected_level=~"error|fatal"
|
||||
|
||||
Typical causes include failed upstream connections, auth/sync failures, or crashes; use log fields (component, worker, status, message) to narrow the blast radius.
|
||||
summary: 'Production Zero: error/fatal logs in the last evaluation window.'
|
||||
execErrState: Ok
|
||||
expressions:
|
||||
A:
|
||||
datasourceUID: grafanacloud-logs
|
||||
model:
|
||||
datasource:
|
||||
type: loki
|
||||
uid: grafanacloud-logs
|
||||
editorMode: code
|
||||
expr:
|
||||
sum(count_over_time({service_name=~"zero-(rm|vs)", deployment_environment="production"}
|
||||
| detected_level=~"error|fatal" [5m]))
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
queryType: instant
|
||||
refId: A
|
||||
queryType: instant
|
||||
relativeTimeRange:
|
||||
from: 10m0s
|
||||
to: 0s
|
||||
C:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 0
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
queryType: expression
|
||||
source: true
|
||||
for: 1m0s
|
||||
labels:
|
||||
service: zero
|
||||
severity: critical
|
||||
noDataState: Ok
|
||||
paused: true
|
||||
title: Zero error log (production)
|
||||
trigger:
|
||||
interval: 1m
|
||||
@@ -0,0 +1,72 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/provenance: ''
|
||||
grafana.com/updateTimestamp: '2026-04-28T08:48:46Z'
|
||||
grafana.com/updatedBy: ae5t47muqbegwf
|
||||
labels:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/group: zero-fly-alerts
|
||||
grafana.com/group-index: '2'
|
||||
name: cfjnb1whljcowe
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
annotations:
|
||||
summary: Zero container disk utilization exceeds 80%
|
||||
execErrState: Error
|
||||
expressions:
|
||||
A:
|
||||
datasourceUID: afj5re4yk9og0e
|
||||
model:
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: afj5re4yk9og0e
|
||||
editorMode: code
|
||||
expr: |-
|
||||
(fly_instance_filesystem_blocks{app=~"production-zero-rm|production-zero-vs"} - fly_instance_filesystem_blocks_avail{app=~"production-zero-rm|production-zero-vs"}) * fly_instance_filesystem_block_size{app=~"production-zero-rm|production-zero-vs"} /
|
||||
(fly_instance_filesystem_blocks{app=~"production-zero-rm|production-zero-vs"} * fly_instance_filesystem_block_size{app=~"production-zero-rm|production-zero-vs"})
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
legendFormat: __auto
|
||||
maxDataPoints: 43200
|
||||
range: false
|
||||
refId: A
|
||||
relativeTimeRange:
|
||||
from: 10m0s
|
||||
to: 0s
|
||||
C:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 0.8
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
queryType: expression
|
||||
source: true
|
||||
for: 10m0s
|
||||
labels:
|
||||
service: zero
|
||||
severity: critical
|
||||
noDataState: NoData
|
||||
title: Flyio zero container disk high
|
||||
trigger:
|
||||
interval: 1m
|
||||
@@ -0,0 +1,72 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/provenance: ''
|
||||
grafana.com/updateTimestamp: '2026-04-28T08:48:46Z'
|
||||
grafana.com/updatedBy: ae5t47muqbegwf
|
||||
labels:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/group: zero-fly-alerts
|
||||
grafana.com/group-index: '3'
|
||||
name: cfjnbehzmlhxcc
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
annotations:
|
||||
summary: Zero container CPU utilization exceeds 85%
|
||||
execErrState: Error
|
||||
expressions:
|
||||
A:
|
||||
datasourceUID: afj5re4yk9og0e
|
||||
model:
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: afj5re4yk9og0e
|
||||
editorMode: code
|
||||
expr:
|
||||
sum by (instance, app)(rate(fly_instance_cpu{app=~"production-zero-rm|production-zero-vs",mode!="idle"}[5m]))
|
||||
/ sum by (instance, app)(rate(fly_instance_cpu{app=~"production-zero-rm|production-zero-vs"}[5m]))
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
legendFormat: __auto
|
||||
maxDataPoints: 43200
|
||||
range: false
|
||||
refId: A
|
||||
relativeTimeRange:
|
||||
from: 10m0s
|
||||
to: 0s
|
||||
C:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 0.85
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
queryType: expression
|
||||
source: true
|
||||
for: 15m0s
|
||||
labels:
|
||||
service: zero
|
||||
severity: warning
|
||||
noDataState: NoData
|
||||
title: Flyio zero container cpu high
|
||||
trigger:
|
||||
interval: 1m
|
||||
@@ -0,0 +1,80 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/provenance: ''
|
||||
grafana.com/updateTimestamp: '2026-04-28T08:48:46Z'
|
||||
grafana.com/updatedBy: ae5t47muqbegwf
|
||||
labels:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/group: zero-fly-alerts
|
||||
grafana.com/group-index: '6'
|
||||
name: cfjyl9tbrury8b
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
annotations:
|
||||
description: |-
|
||||
Fires when the 5-minute rolling count of logs with detected_level error or fatal is greater than zero for service_name matching zero-(rm|vs) and deployment_environment=staging.
|
||||
|
||||
Investigate in Grafana Explore (grafanacloud-tldraw-logs):
|
||||
|
||||
{service_name=~"zero-(rm|vs)", deployment_environment="staging"} | detected_level=~"error|fatal"
|
||||
|
||||
Typical causes include failed upstream connections, auth/sync failures, or crashes; use log fields (component, worker, status, message) to narrow the blast radius.
|
||||
summary: 'Staging Zero: error/fatal logs in the last evaluation window.'
|
||||
execErrState: Ok
|
||||
expressions:
|
||||
A:
|
||||
datasourceUID: grafanacloud-logs
|
||||
model:
|
||||
datasource:
|
||||
type: loki
|
||||
uid: grafanacloud-logs
|
||||
editorMode: code
|
||||
expr: sum(count_over_time({service_name=~"zero-(rm|vs)", deployment_environment="staging"}
|
||||
| detected_level=~"error|fatal" [5m]))
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
queryType: instant
|
||||
refId: A
|
||||
queryType: instant
|
||||
relativeTimeRange:
|
||||
from: 10m0s
|
||||
to: 0s
|
||||
C:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 0
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
queryType: expression
|
||||
source: true
|
||||
for: 5m0s
|
||||
labels:
|
||||
service: zero
|
||||
severity: warning
|
||||
noDataState: Ok
|
||||
paused: true
|
||||
title: Zero error log (staging)
|
||||
trigger:
|
||||
interval: 1m
|
||||
@@ -0,0 +1,69 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/provenance: ''
|
||||
grafana.com/updateTimestamp: '2026-04-21T09:06:29Z'
|
||||
grafana.com/updatedBy: ae5t47muqbegwf
|
||||
labels:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/group: zero-alerts
|
||||
grafana.com/group-index: '1'
|
||||
name: dfjn3qe3l7w8wc
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
execErrState: Error
|
||||
expressions:
|
||||
A:
|
||||
datasourceUID: grafanacloud-prom
|
||||
model:
|
||||
editorMode: code
|
||||
expr: zero_replica_backup_lag_millisecond{deployment_environment="production",
|
||||
service_name="zero-rm"}
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
legendFormat: __auto
|
||||
maxDataPoints: 43200
|
||||
range: false
|
||||
refId: A
|
||||
relativeTimeRange:
|
||||
from: 10m0s
|
||||
to: 0s
|
||||
C:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 1200000
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
queryType: expression
|
||||
source: true
|
||||
for: 20m0s
|
||||
labels:
|
||||
service: zero
|
||||
severity: critical
|
||||
noDataState: NoData
|
||||
notificationSettings:
|
||||
receiver: Discord
|
||||
type: SimplifiedRouting
|
||||
title: Zero replica backup lag
|
||||
trigger:
|
||||
interval: 20m
|
||||
@@ -0,0 +1,72 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/provenance: ''
|
||||
grafana.com/updateTimestamp: '2026-04-28T08:48:46Z'
|
||||
grafana.com/updatedBy: ae5t47muqbegwf
|
||||
labels:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/group: zero-fly-alerts
|
||||
grafana.com/group-index: '1'
|
||||
name: dfjn9xellhibka
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
annotations:
|
||||
summary: Zero container memory utilization exceeds 90%
|
||||
execErrState: Error
|
||||
expressions:
|
||||
A:
|
||||
datasourceUID: afj5re4yk9og0e
|
||||
model:
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: afj5re4yk9og0e
|
||||
editorMode: code
|
||||
expr: 1 - (fly_instance_memory_mem_available{app=~"production-zero-rm|production-zero-vs"}
|
||||
/ fly_instance_memory_mem_total{app=~"production-zero-rm|production-zero-vs"})
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
legendFormat: __auto
|
||||
maxDataPoints: 43200
|
||||
range: false
|
||||
refId: A
|
||||
relativeTimeRange:
|
||||
from: 10m0s
|
||||
to: 0s
|
||||
C:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 0.9
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
queryType: expression
|
||||
source: true
|
||||
for: 1m0s
|
||||
keepFiringFor: 5m0s
|
||||
labels:
|
||||
service: zero
|
||||
severity: warning
|
||||
noDataState: NoData
|
||||
title: Flyio zero container memory high
|
||||
trigger:
|
||||
interval: 1m
|
||||
@@ -0,0 +1,94 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: dotcom
|
||||
grafana.com/provenance: ''
|
||||
labels:
|
||||
grafana.app/folder: dotcom
|
||||
grafana.com/group: dotcom-alerts
|
||||
grafana.com/group-index: '1'
|
||||
name: dotcom-file-do-exceptions
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
annotations:
|
||||
description: TLFileDurableObject threw more than 300 uncaught exceptions in the
|
||||
last hour. Quiet hours run 1-50; the bursts that followed hibernation being
|
||||
enabled on 2026-08-13 run 700-1300. Check the "DO exceptions by namespace"
|
||||
panel on the Cloudflare platform metrics dashboard, then Sentry for the
|
||||
matching source tag.
|
||||
summary: File room durable objects are throwing uncaught exceptions
|
||||
execErrState: Error
|
||||
expressions:
|
||||
A:
|
||||
datasourceUID: ffuyblsuemj28b
|
||||
model:
|
||||
columns:
|
||||
- selector: sum.requests
|
||||
text: exceptions
|
||||
type: number
|
||||
format: table
|
||||
global_query_id: ''
|
||||
parser: backend
|
||||
refId: A
|
||||
root_selector: data.viewer.accounts[0].durableObjectsInvocationsAdaptiveGroups
|
||||
source: url
|
||||
type: graphql
|
||||
url: https://api.cloudflare.com/client/v4/graphql
|
||||
url_options:
|
||||
body_content_type: application/json
|
||||
body_graphql_query: |-
|
||||
query {
|
||||
viewer {
|
||||
accounts(filter: {accountTag: "c34edc4e76350954b63adebde86d5eb1"}) {
|
||||
durableObjectsInvocationsAdaptiveGroups(limit: 1, filter: {datetime_geq: "${__from:date:iso}", datetime_leq: "${__to:date:iso}", namespaceId: "5864db4344ac4c55bfd94e81dd25a043", status: "scriptThrewException"}) {
|
||||
sum { requests }
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
body_type: graphql
|
||||
method: POST
|
||||
relativeTimeRange:
|
||||
from: 1h0m0s
|
||||
to: 0s
|
||||
C:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 300
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
queryType: expression
|
||||
source: true
|
||||
for: 10m0s
|
||||
labels:
|
||||
service: dotcom
|
||||
severity: warning
|
||||
# The query filters to scriptThrewException, so a healthy hour returns no rows at
|
||||
# all rather than a zero. NoData here means "nothing threw" — alerting on it would
|
||||
# invert the rule.
|
||||
noDataState: Ok
|
||||
notificationSettings:
|
||||
receiver: Discord
|
||||
type: SimplifiedRouting
|
||||
title: File room DO exceptions
|
||||
trigger:
|
||||
interval: 10m
|
||||
@@ -0,0 +1,95 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: dotcom
|
||||
grafana.com/provenance: ''
|
||||
labels:
|
||||
grafana.app/folder: dotcom
|
||||
grafana.com/group: version-chain-alerts
|
||||
grafana.com/group-index: '1'
|
||||
name: dotcom-version-chain-verify-failures
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
annotations:
|
||||
description: More than two retired version chains failed to reproduce the state
|
||||
the durable object persisted, in the last hour. Check the "Verify results"
|
||||
panel on the Dotcom events dashboard for the reason. head-mismatch is the
|
||||
serious one — the delta encoding is producing a different board — while
|
||||
missing and legacy-fallback mean the chain did not answer at all. Until the
|
||||
legacy full copies are turned off these versions still read; after that they
|
||||
are unreadable and there is no rebuild path, so this should block the
|
||||
rollout advancing.
|
||||
summary: Version chain reconstructions are not reproducing persisted state
|
||||
execErrState: Error
|
||||
expressions:
|
||||
A:
|
||||
datasourceUID: bdgu7tk03irr4e
|
||||
model:
|
||||
dateTimeType: DATETIME
|
||||
editorMode: code
|
||||
extrapolate: true
|
||||
format: table
|
||||
formatAs: table
|
||||
intervalFactor: 1
|
||||
# rawQuery must be the boolean, not a copy of the SQL. The dashboard panels
|
||||
# carry the SQL in both fields, but that shape reaches the plugin as
|
||||
# already-interpolated text and dies on "unsupported value type: $from".
|
||||
# Matches 'fail' rather than negating 'ok': a check the durable object
|
||||
# declined to run (outcome 'skipped') is not a failing chain, and on a
|
||||
# board big enough to skip, a negated match would page on every retire.
|
||||
query: |-
|
||||
SELECT count() as fails
|
||||
FROM 'MEASURE'
|
||||
WHERE timestamp >= toDateTime($from) AND timestamp <= toDateTime($to)
|
||||
AND blob1 = 'version_chain_verify'
|
||||
AND blob2 = 'production-tldraw-multiplayer'
|
||||
AND blob3 = 'fail'
|
||||
rawQuery: true
|
||||
refId: A
|
||||
round: 0s
|
||||
skip_comments: true
|
||||
step: ''
|
||||
relativeTimeRange:
|
||||
from: 1h0m0s
|
||||
to: 0s
|
||||
C:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 2
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
queryType: expression
|
||||
source: true
|
||||
for: 10m0s
|
||||
labels:
|
||||
service: dotcom
|
||||
severity: warning
|
||||
# count() with no GROUP BY returns a row holding 0 rather than no rows, so a
|
||||
# healthy hour evaluates a real zero. NoData here means the Analytics Engine
|
||||
# datasource itself is down, which is not a version chain problem.
|
||||
noDataState: Ok
|
||||
notificationSettings:
|
||||
receiver: Discord
|
||||
type: SimplifiedRouting
|
||||
title: Version chain verify failures
|
||||
trigger:
|
||||
interval: 10m
|
||||
@@ -0,0 +1,85 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: dotcom
|
||||
grafana.com/provenance: ''
|
||||
labels:
|
||||
grafana.app/folder: dotcom
|
||||
grafana.com/group: version-chain-alerts
|
||||
grafana.com/group-index: '2'
|
||||
name: dotcom-version-chain-write-errors
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
annotations:
|
||||
description: A chain write failed non-transiently in the last hour. These have
|
||||
already retried three times and fallen back to writing a legacy full copy,
|
||||
so no version is lost and boards are unaffected — but the chain is unhealthy
|
||||
and the rollout should not advance while this fires. Check the "Chain write
|
||||
errors" panel on the Dotcom events dashboard, then Sentry for the underlying
|
||||
exception. Expected rate is zero.
|
||||
summary: Version chain writes are failing and falling back to legacy copies
|
||||
execErrState: Error
|
||||
expressions:
|
||||
A:
|
||||
datasourceUID: bdgu7tk03irr4e
|
||||
model:
|
||||
dateTimeType: DATETIME
|
||||
editorMode: code
|
||||
extrapolate: true
|
||||
format: table
|
||||
formatAs: table
|
||||
intervalFactor: 1
|
||||
# See the verify-failures rule: rawQuery is the boolean, and the SQL lives
|
||||
# only in `query`, or $from reaches the plugin uninterpolated.
|
||||
query: |-
|
||||
SELECT count() as errors
|
||||
FROM 'MEASURE'
|
||||
WHERE timestamp >= toDateTime($from) AND timestamp <= toDateTime($to)
|
||||
AND blob1 = 'version_chain_error'
|
||||
AND blob2 = 'production-tldraw-multiplayer'
|
||||
rawQuery: true
|
||||
refId: A
|
||||
round: 0s
|
||||
skip_comments: true
|
||||
step: ''
|
||||
relativeTimeRange:
|
||||
from: 1h0m0s
|
||||
to: 0s
|
||||
C:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 0
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
queryType: expression
|
||||
source: true
|
||||
for: 10m0s
|
||||
labels:
|
||||
service: dotcom
|
||||
severity: warning
|
||||
noDataState: Ok
|
||||
notificationSettings:
|
||||
receiver: Discord
|
||||
type: SimplifiedRouting
|
||||
title: Version chain write errors
|
||||
trigger:
|
||||
interval: 10m
|
||||
@@ -0,0 +1,116 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: anthropic
|
||||
grafana.com/provenance: ''
|
||||
grafana.com/updateTimestamp: '2026-03-20T11:22:55Z'
|
||||
grafana.com/updatedBy: bf1wptf89bpq8d
|
||||
labels:
|
||||
grafana.app/folder: anthropic
|
||||
grafana.com/group: anthropic
|
||||
grafana.com/group-index: '0'
|
||||
name: e75d2f6c-44cf-54bf-8a74-ced2e045fcb6
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
annotations:
|
||||
description: 'The last completed day cost ${{ $value | humanize }}, more than
|
||||
1.5x the day before. The cost metric updates once a day at about 03:00 UTC,
|
||||
so this describes yesterday.'
|
||||
summary: Anthropic API daily cost spike detected.
|
||||
execErrState: Ok
|
||||
expressions:
|
||||
prometheus_math:
|
||||
model:
|
||||
datasource:
|
||||
IsPrunable: false
|
||||
access: ''
|
||||
apiVersion: ''
|
||||
basicAuth: false
|
||||
basicAuthUser: ''
|
||||
created: '0001-01-01T00:00:00Z'
|
||||
database: ''
|
||||
id: -100
|
||||
isDefault: false
|
||||
jsonData: {}
|
||||
name: __expr__
|
||||
readOnly: false
|
||||
secureJsonData: {}
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
updated: '0001-01-01T00:00:00Z'
|
||||
url: ''
|
||||
user: ''
|
||||
withCredentials: false
|
||||
expression: is_number($query) || is_nan($query) || is_inf($query)
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: prometheus_math
|
||||
type: math
|
||||
queryType: math
|
||||
query:
|
||||
datasourceUID: grafanacloud-prom
|
||||
model:
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: grafanacloud-prom
|
||||
expr: |
|
||||
(
|
||||
sum(increase(gen_ai_cost{job=~"integrations/anthropic/.*"}[1d])) / 100
|
||||
>
|
||||
1.5 * sum(increase(gen_ai_cost{job=~"integrations/anthropic/.*"}[1d] offset 1d)) / 100
|
||||
)
|
||||
and
|
||||
sum(increase(gen_ai_cost{job=~"integrations/anthropic/.*"}[1d])) / 100 > 50
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
range: false
|
||||
refId: query
|
||||
queryType: prometheus
|
||||
relativeTimeRange:
|
||||
from: 11m0s
|
||||
to: 1m0s
|
||||
threshold:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 0
|
||||
type: gt
|
||||
datasource:
|
||||
IsPrunable: false
|
||||
access: ''
|
||||
apiVersion: ''
|
||||
basicAuth: false
|
||||
basicAuthUser: ''
|
||||
created: '0001-01-01T00:00:00Z'
|
||||
database: ''
|
||||
id: -100
|
||||
isDefault: false
|
||||
jsonData: {}
|
||||
name: __expr__
|
||||
readOnly: false
|
||||
secureJsonData: {}
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
updated: '0001-01-01T00:00:00Z'
|
||||
url: ''
|
||||
user: ''
|
||||
withCredentials: false
|
||||
expression: prometheus_math
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: threshold
|
||||
type: threshold
|
||||
queryType: threshold
|
||||
source: true
|
||||
for: 5m0s
|
||||
labels:
|
||||
__converted_prometheus_rule__: 'true'
|
||||
severity: warning
|
||||
missingSeriesEvalsToResolve: 10
|
||||
noDataState: Ok
|
||||
title: AnthropicDailyCostSpike
|
||||
trigger:
|
||||
interval: 1m
|
||||
@@ -0,0 +1,110 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: anthropic
|
||||
grafana.com/provenance: ''
|
||||
grafana.com/updateTimestamp: '2026-03-20T11:22:55Z'
|
||||
grafana.com/updatedBy: bf1wptf89bpq8d
|
||||
labels:
|
||||
grafana.app/folder: anthropic
|
||||
grafana.com/group: anthropic
|
||||
grafana.com/group-index: '2'
|
||||
name: eec2ad9e-30b9-5c8f-802f-53e26ab8fdc9
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
annotations:
|
||||
description: 'The last completed day cost ${{ $value | humanize }}, above the
|
||||
$1000 threshold. The cost metric updates once a day at about 03:00 UTC, so
|
||||
this describes yesterday.'
|
||||
summary: Anthropic API cost threshold exceeded.
|
||||
execErrState: Ok
|
||||
expressions:
|
||||
prometheus_math:
|
||||
model:
|
||||
datasource:
|
||||
IsPrunable: false
|
||||
access: ''
|
||||
apiVersion: ''
|
||||
basicAuth: false
|
||||
basicAuthUser: ''
|
||||
created: '0001-01-01T00:00:00Z'
|
||||
database: ''
|
||||
id: -100
|
||||
isDefault: false
|
||||
jsonData: {}
|
||||
name: __expr__
|
||||
readOnly: false
|
||||
secureJsonData: {}
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
updated: '0001-01-01T00:00:00Z'
|
||||
url: ''
|
||||
user: ''
|
||||
withCredentials: false
|
||||
expression: is_number($query) || is_nan($query) || is_inf($query)
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: prometheus_math
|
||||
type: math
|
||||
queryType: math
|
||||
query:
|
||||
datasourceUID: grafanacloud-prom
|
||||
model:
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: grafanacloud-prom
|
||||
expr: |
|
||||
sum(increase(gen_ai_cost{job=~"integrations/anthropic/.*"}[1d])) / 100 > 1000
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
range: false
|
||||
refId: query
|
||||
queryType: prometheus
|
||||
relativeTimeRange:
|
||||
from: 11m0s
|
||||
to: 1m0s
|
||||
threshold:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 0
|
||||
type: gt
|
||||
datasource:
|
||||
IsPrunable: false
|
||||
access: ''
|
||||
apiVersion: ''
|
||||
basicAuth: false
|
||||
basicAuthUser: ''
|
||||
created: '0001-01-01T00:00:00Z'
|
||||
database: ''
|
||||
id: -100
|
||||
isDefault: false
|
||||
jsonData: {}
|
||||
name: __expr__
|
||||
readOnly: false
|
||||
secureJsonData: {}
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
updated: '0001-01-01T00:00:00Z'
|
||||
url: ''
|
||||
user: ''
|
||||
withCredentials: false
|
||||
expression: prometheus_math
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: threshold
|
||||
type: threshold
|
||||
queryType: threshold
|
||||
source: true
|
||||
for: 15m0s
|
||||
labels:
|
||||
__converted_prometheus_rule__: 'true'
|
||||
severity: critical
|
||||
missingSeriesEvalsToResolve: 10
|
||||
noDataState: Ok
|
||||
title: AnthropicHighCostThreshold
|
||||
trigger:
|
||||
interval: 1m
|
||||
@@ -0,0 +1,66 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/provenance: ''
|
||||
grafana.com/updateTimestamp: '2026-04-21T09:07:11Z'
|
||||
grafana.com/updatedBy: ae5t47muqbegwf
|
||||
labels:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/group: zero-alerts-fast
|
||||
grafana.com/group-index: '1'
|
||||
name: efjn4hgdlhc00f
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
execErrState: Error
|
||||
expressions:
|
||||
A:
|
||||
datasourceUID: grafanacloud-prom
|
||||
model:
|
||||
editorMode: code
|
||||
expr: zero_replication_total_lag_millisecond{deployment_environment="production",
|
||||
service_name="zero-rm"}
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
legendFormat: __auto
|
||||
maxDataPoints: 43200
|
||||
range: false
|
||||
refId: A
|
||||
relativeTimeRange:
|
||||
from: 10m0s
|
||||
to: 0s
|
||||
C:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 2000
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
queryType: expression
|
||||
source: true
|
||||
for: 5m0s
|
||||
labels:
|
||||
service: zero
|
||||
severity: critical
|
||||
noDataState: NoData
|
||||
title: Zero replication lag high
|
||||
trigger:
|
||||
interval: 5m
|
||||
@@ -0,0 +1,69 @@
|
||||
apiVersion: rules.alerting.grafana.app/v0alpha1
|
||||
kind: AlertRule
|
||||
metadata:
|
||||
annotations:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/provenance: ''
|
||||
grafana.com/updateTimestamp: '2026-04-28T08:48:46Z'
|
||||
grafana.com/updatedBy: ae5t47muqbegwf
|
||||
labels:
|
||||
grafana.app/folder: f6hsw6
|
||||
grafana.com/group: zero-fly-alerts
|
||||
grafana.com/group-index: '4'
|
||||
name: efjnbq9h4iha8a
|
||||
namespace: stacks-890472
|
||||
spec:
|
||||
annotations:
|
||||
summary: Zero container OOM kill detected
|
||||
execErrState: Ok
|
||||
expressions:
|
||||
A:
|
||||
datasourceUID: afj5re4yk9og0e
|
||||
model:
|
||||
datasource:
|
||||
type: prometheus
|
||||
uid: afj5re4yk9og0e
|
||||
editorMode: code
|
||||
expr: fly_instance_exit_oom{app=~"production-zero-rm|production-zero-vs"}
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
legendFormat: __auto
|
||||
maxDataPoints: 43200
|
||||
range: false
|
||||
refId: A
|
||||
relativeTimeRange:
|
||||
from: 10m0s
|
||||
to: 0s
|
||||
C:
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 0
|
||||
type: gt
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
queryType: expression
|
||||
source: true
|
||||
labels:
|
||||
service: zero
|
||||
severity: critical
|
||||
noDataState: Ok
|
||||
title: Flyio zero container oom kill
|
||||
trigger:
|
||||
interval: 1m
|
||||
Reference in New Issue
Block a user