Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Delete unsupported alarm rule (version before 4.0) and standby tenant related rules #604

Merged
merged 5 commits into from
Nov 4, 2024
Merged

Delete unsupported alarm rule (version before 4.0) and standby tenant related rules #604

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
3a4d355
chore(release): bump version of dashboard chart (#563)
powerfooI Sep 6, 2024
bc03bfc
Supplement types of tenant operations to align cluster operations (#545)
powerfooI Sep 6, 2024
f44b0d1
delete alert before 4.0 or standby tenant
chris-sun-star Nov 4, 2024
8deefae
merge master
chris-sun-star Nov 4, 2024
0ababef
merge master
chris-sun-star Nov 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion api/v1alpha1/zz_generated.deepcopy.go
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

102 changes: 7 additions & 95 deletions charts/oceanbase-dashboard/templates/prom-rule-config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ data:
- name: ob-rule
rules:
- alert: cluster_active_session
expr: sum(ob_session_active_num) by (ob_cluster_name, obzone, svr_ip) > 10000
expr: sum(ob_active_session_num) by (ob_cluster_name, obzone, svr_ip) > 10000
for: 1m
labels:
instance_type: obcluster
Expand Down Expand Up @@ -44,63 +44,8 @@ data:
annotations:
description: 'Cluster {{ $labels.ob_cluster_name }} has {{ $value }} index fail tables.'
summary: 'Found index fail table in cluster {{ $labels.ob_cluster_name }}.'
- alert: frozen_version_check
expr: max(ob_zone_stat{name="frozen_version"}) by (ob_cluster_name) - min(ob_zone_stat{name="last_merged_version"}) by (ob_cluster_name) > 1
for: 1m
labels:
instance_type: obcluster
rule_name: frozen_version_check
rule_type: builtin
severity: warning
annotations:
description: 'Cluster {{ $labels.ob_cluster_name }} has {{ $value }} delta versions between merged and frozen data.'
summary: 'Frozen version is too much larger than merged version.'
- alert: cluster_merge_error
expr: max(ob_zone_stat{name="is_merge_error"}) by (ob_cluster_name) > 0
for: 1m
labels:
instance_type: obcluster
rule_name: cluster_merge_error
rule_type: builtin
severity: warning
annotations:
description: 'Cluster {{ $labels.ob_cluster_name }} merge error.'
summary: 'Cluster {{ $labels.ob_cluster_name }} merge error.'
- alert: cluster_merge_timeout
expr: max(ob_zone_stat{name="is_merge_timeout"}) by (ob_cluster_name) > 0
for: 1m
labels:
instance_type: obcluster
rule_name: cluster_merge_timeout
rule_type: builtin
severity: warning
annotations:
description: 'Cluster {{ $labels.ob_cluster_name }} merge timeout.'
summary: 'Cluster {{ $labels.ob_cluster_name }} merge timeout.'
- alert: cluster_no_frozen
expr: (max(ob_zone_current_timestamp{name="frozen_time"}) by (ob_cluster_name) - max(ob_zone_stat{name="frozen_time"}) by (ob_cluster_name)) / 1000000 > 90000
for: 1m
labels:
instance_type: obcluster
rule_name: cluster_no_frozen
rule_type: builtin
severity: warning
annotations:
description: 'Cluster {{ $labels.ob_cluster_name }} has not frozen for {{ $value }} seconds.'
summary: 'Cluster {{ $labels.ob_cluster_name }} has not frozen for a long time.'
- alert: cluster_no_merge
expr: (max(ob_zone_current_timestamp{name="merge_start_time"}) by (ob_cluster_name) - max(ob_zone_stat{name="merge_start_time"}) by (ob_cluster_name)) / 1000000 > 90000
for: 1m
labels:
instance_type: obcluster
rule_name: cluster_no_merge
rule_type: builtin
severity: warning
annotations:
description: 'Cluster {{ $labels.ob_cluster_name }} has not merge for {{ $value }} seconds.'
summary: 'Cluster {{ $labels.ob_cluster_name }} has not merge for a long time.'
- alert: tenant_active_session
expr: sum(ob_session_active_num) by (ob_cluster_name, obzone, svr_ip, tenant_name) > 2000
expr: sum(ob_active_session_num) by (ob_cluster_name, obzone, svr_ip, tenant_name) > 2000
for: 1m
labels:
instance_type: obtenant
Expand Down Expand Up @@ -176,28 +121,17 @@ data:
annotations:
description: 'Tenant {{ $labels.tenant_name }} of obcluster {{ $labels.ob_cluster_name }} has not frozen for {{ $value }} seconds.'
summary: 'Tenant {{ $labels.tenant_name }} of obcluster {{ $labels.ob_cluster_name }} has not frozen for a long time.'
- alert: tenant_partition_leader_absent
expr: max(partition_leader_absent_count) by (ob_cluster_name, tenant_name) > 100
for: 3m
labels:
instance_type: obtenant
rule_name: tenant_partition_leader_absent
rule_type: builtin
severity: warning
annotations:
description: 'Tenant {{ $labels.tenant_name }} of obcluster {{ $labels.ob_cluster_name }} found {{ $value }} partition leader absent.'
summary: 'Tenant {{ $labels.tenant_name }} of obcluster {{ $labels.ob_cluster_name }} found partition leader absent.'
- alert: tenant_partition_replica_absent
expr: max(partition_replica_absent_count) by (ob_cluster_name, tenant_name) > 100
- alert: tenant500_mem_hold_percent
expr: 100 * sum(ob_tenant500_memory_hold_bytes) by (@GBLABELS) / sum(ob_server_resource_memory_bytes) by (@GBLABELS) > 95
for: 3m
labels:
instance_type: obtenant
rule_name: tenant_partition_replica_absent
rule_name: tenant500_mem_hold_percent
rule_type: builtin
severity: warning
annotations:
description: 'Tenant {{ $labels.tenant_name }} of obcluster {{ $labels.ob_cluster_name }} found {{ $value }} partition replica absent.'
summary: 'Tenant {{ $labels.tenant_name }} of obcluster {{ $labels.ob_cluster_name }} found partition replica absent.'
description: 'Tenant 500 of obcluster {{ $labels.ob_cluster_name }} memory hold percent too high, {{ $value }}.'
summary: 'Tenant 500 of obcluster {{ $labels.ob_cluster_name }} memory hold percent too high.'
- alert: tenant_task_timeout
expr: max(ob_tenant_task_max_duration_seconds) by (ob_cluster_name, tenant_name) > 10800
for: 1m
Expand All @@ -209,28 +143,6 @@ data:
annotations:
description: 'Tenant {{ $labels.tenant_name }} of obcluster {{ $labels.ob_cluster_name }} found task not finished for {{ $value }} seconds.'
summary: 'Tenant {{ $labels.tenant_name }} of obcluster {{ $labels.ob_cluster_name }} found task not finished for a long time.'
- alert: standby_tenant_sync_delay
expr: max(standby_tenant_delay_seconds) by (ob_cluster_name, tenant_name) > 600
for: 1m
labels:
instance_type: obtenant
rule_name: standby_tenant_sync_delay
rule_type: builtin
severity: caution
annotations:
description: 'Standby tenant {{ $labels.tenant_name }} of obcluster {{ $labels.ob_cluster_name }} sync delay {{ $value }} seconds.'
summary: 'Standby tenant {{ $labels.tenant_name }} of obcluster {{ $labels.ob_cluster_name }} sync delay too long.'
- alert: standby_tenant_sync_error
expr: max(standby_tenant_restore_status_code) by (ob_cluster_name, tenant_name) == 2
for: 1m
labels:
instance_type: obtenant
rule_name: standby_tenant_sync_error
rule_type: builtin
severity: warning
annotations:
description: 'Standby tenant {{ $labels.tenant_name }} of obcluster {{ $labels.ob_cluster_name }} sync error.'
summary: 'Standby tenant {{ $labels.tenant_name }} of obcluster {{ $labels.ob_cluster_name }} sync error.'
- alert: tenant_memstore_percent
expr: 100 * sum(ob_sysstat{stat_id="130001"}) by (ob_cluster_name, obzone, svr_ip, tenant_name) / sum(ob_sysstat{stat_id="130004"}) by (ob_cluster_name, obzone, svr_ip, tenant_name) > 95
for: 2m
Expand Down
Loading