Skip to content

chore: Modernize mongodb-atlas-mixin #1530

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

Draft
wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

chore: Modernize mongodb-atlas-mixin #1530

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,3 +2,4 @@
vendor
jsonnetfile.lock.json
*.zip
.worktrees
76 changes: 38 additions & 38 deletions mongodb-atlas-mixin/alerts/alerts.libsonnet → mongodb-atlas-mixin/alerts.libsonnet
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,14 +1,14 @@
{
prometheusAlerts+:: {
groups+: [
new(this): {
groups: [
{
name: 'mongodb-atlas-alerts',
name: this.config.uid + '-alerts',
rules: [
{
alert: 'MongoDBAtlasHighNumberOfCollectionExclusiveDeadlocks',
alert: 'MongoDBAtlasCollExclusiveDeadlocks',
expr: |||
sum without(cl_role,process_port,rs_nm,rs_state) (increase(mongodb_locks_Collection_deadlockCount_W[5m])) > %(alertsDeadlocks)s
||| % $._config,
||| % this.config,
'for': '5m',
labels: {
severity: 'warning',
Expand All @@ -18,14 +18,14 @@
description:
(
'The number of collection exclusive-lock deadlocks occurring on node {{$labels.instance}} in cluster {{$labels.cl_name}} is {{printf "%%.0f" $value}} which is above the threshold of %(alertsDeadlocks)s.'
) % $._config,
) % this.config,
},
},
{
alert: 'MongoDBAtlasHighNumberOfCollectionIntentExclusiveDeadlocks',
alert: 'MongoDBAtlasCollIntentExclDeadlocks',
expr: |||
sum without(cl_role,process_port,rs_nm,rs_state) (increase(mongodb_locks_Collection_deadlockCount_w[5m])) > %(alertsDeadlocks)s
||| % $._config,
||| % this.config,
'for': '5m',
labels: {
severity: 'warning',
Expand All @@ -35,14 +35,14 @@
description:
(
'The number of collection intent-exclusive-lock deadlocks occurring on node {{$labels.instance}} in cluster {{$labels.cl_name}} is {{printf "%%.0f" $value}} which is above the threshold of %(alertsDeadlocks)s.'
) % $._config,
) % this.config,
},
},
{
alert: 'MongoDBAtlasHighNumberOfCollectionSharedDeadlocks',
alert: 'MongoDBAtlasCollSharedDeadlocks',
expr: |||
sum without(cl_role,process_port,rs_nm,rs_state) (increase(mongodb_locks_Collection_deadlockCount_R[5m])) > %(alertsDeadlocks)s
||| % $._config,
||| % this.config,
'for': '5m',
labels: {
severity: 'warning',
Expand All @@ -52,14 +52,14 @@
description:
(
'The number of collection shared-lock deadlocks occurring on node {{$labels.instance}} in cluster {{$labels.cl_name}} is {{printf "%%.0f" $value}} which is above the threshold of %(alertsDeadlocks)s.'
) % $._config,
) % this.config,
},
},
{
alert: 'MongoDBAtlasHighNumberOfCollectionIntentSharedDeadlocks',
alert: 'MongoDBAtlasCollIntentSharedDeadlocks',
expr: |||
sum without(cl_role,process_port,rs_nm,rs_state) (increase(mongodb_locks_Collection_deadlockCount_r[5m])) > %(alertsDeadlocks)s
||| % $._config,
||| % this.config,
'for': '5m',
labels: {
severity: 'warning',
Expand All @@ -69,14 +69,14 @@
description:
(
'The number of collection intent-shared-lock deadlocks occurring on node {{$labels.instance}} in cluster {{$labels.cl_name}} is {{printf "%%.0f" $value}} which is above the threshold of %(alertsDeadlocks)s.'
) % $._config,
) % this.config,
},
},
{
alert: 'MongoDBAtlasHighNumberOfDatabaseExclusiveDeadlocks',
alert: 'MongoDBAtlasDBExclusiveDeadlocks',
expr: |||
sum without(cl_role,process_port,rs_nm,rs_state) (increase(mongodb_locks_Database_deadlockCount_W[5m])) > %(alertsDeadlocks)s
||| % $._config,
||| % this.config,
'for': '5m',
labels: {
severity: 'warning',
Expand All @@ -86,14 +86,14 @@
description:
(
'The number of database exclusive-lock deadlocks occurring on node {{$labels.instance}} in cluster {{$labels.cl_name}} is {{printf "%%.0f" $value}} which is above the threshold of %(alertsDeadlocks)s.'
) % $._config,
) % this.config,
},
},
{
alert: 'MongoDBAtlasHighNumberOfDatabaseIntentExclusiveDeadlocks',
alert: 'MongoDBAtlasDBIntentExclDeadlocks',
expr: |||
sum without(cl_role,process_port,rs_nm,rs_state) (increase(mongodb_locks_Database_deadlockCount_w[5m])) > %(alertsDeadlocks)s
||| % $._config,
||| % this.config,
'for': '5m',
labels: {
severity: 'warning',
Expand All @@ -103,14 +103,14 @@
description:
(
'The number of database intent-exclusive-lock deadlocks occurring on node {{$labels.instance}} in cluster {{$labels.cl_name}} is {{printf "%%.0f" $value}} which is above the threshold of %(alertsDeadlocks)s.'
) % $._config,
) % this.config,
},
},
{
alert: 'MongoDBAtlasHighNumberOfDatabaseSharedDeadlocks',
alert: 'MongoDBAtlasDBSharedDeadlocks',
expr: |||
sum without(cl_role,process_port,rs_nm,rs_state) (increase(mongodb_locks_Database_deadlockCount_R[5m])) > %(alertsDeadlocks)s
||| % $._config,
||| % this.config,
'for': '5m',
labels: {
severity: 'warning',
Expand All @@ -120,14 +120,14 @@
description:
(
'The number of database shared-lock deadlocks occurring on node {{$labels.instance}} in cluster {{$labels.cl_name}} is {{printf "%%.0f" $value}} which is above the threshold of %(alertsDeadlocks)s.'
) % $._config,
) % this.config,
},
},
{
alert: 'MongoDBAtlasHighNumberOfDatabaseIntentSharedDeadlocks',
alert: 'MongoDBAtlasDBIntentSharedDeadlocks',
expr: |||
sum without(cl_role,process_port,rs_nm,rs_state) (increase(mongodb_locks_Database_deadlockCount_r[5m])) > %(alertsDeadlocks)s
||| % $._config,
||| % this.config,
'for': '5m',
labels: {
severity: 'warning',
Expand All @@ -137,14 +137,14 @@
description:
(
'The number of database intent-shared-lock deadlocks occurring on node {{$labels.instance}} in cluster {{$labels.cl_name}} is {{printf "%%.0f" $value}} which is above the threshold of %(alertsDeadlocks)s.'
) % $._config,
) % this.config,
},
},
{
alert: 'MongoDBAtlasHighNumberOfSlowNetworkRequests',
alert: 'MongoDBAtlasSlowNetworkRequests',
expr: |||
sum without (cl_role,rs_nm,rs_state,process_port) (increase(mongodb_network_numSlowSSLOperations[5m])) + sum without (cl_role,rs_nm,rs_state,process_port) (increase(mongodb_network_numSlowDNSOperations[5m])) > %(alertsSlowNetworkRequests)s
||| % $._config,
||| % this.config,
'for': '5m',
labels: {
severity: 'warning',
Expand All @@ -154,14 +154,14 @@
description:
(
'The number of DNS and SSL operations taking more than 1 second to complete on node {{$labels.instance}} in cluster {{$labels.cl_name}} is {{printf "%%.0f" $value}} which is above the threshold of %(alertsSlowNetworkRequests)s.'
) % $._config,
) % this.config,
},
},
{
alert: 'MongoDBAtlasDiskSpaceLow',
expr: |||
100 * ((sum without (disk_name) (hardware_disk_metrics_disk_space_used_bytes)) / clamp_min((sum without (disk_name) (hardware_disk_metrics_disk_space_used_bytes)) + (sum without (disk_name) (hardware_disk_metrics_disk_space_free_bytes)), 1)) > %(alertsHighDiskUsage)s
||| % $._config,
||| % this.config,
'for': '5m',
labels: {
severity: 'warning',
Expand All @@ -171,14 +171,14 @@
description:
(
'The amount of hardware disk space being used on node {{$labels.instance}} in cluster {{$labels.cl_name}} is {{printf "%%.0f" $value}}%% which is above the threshold of %(alertsHighDiskUsage)s%%.'
) % $._config,
) % this.config,
},
},
{
alert: 'MongoDBAtlasSlowHardwareIO',
expr: |||
(sum without (disk_name) (increase(hardware_disk_metrics_read_time_milliseconds[5m])) + sum without (disk_name) (increase(hardware_disk_metrics_write_time_milliseconds[5m]))) / 1000 > %(alertsSlowHardwareIO)s
||| % $._config,
||| % this.config,
'for': '5m',
labels: {
severity: 'warning',
Expand All @@ -188,14 +188,14 @@
description:
(
'The latency time for read and write I/Os on node {{$labels.instance}} in cluster {{$labels.cl_name}} is {{printf "%%.0f" $value}} seconds which is above the threshold of %(alertsSlowHardwareIO)s seconds.'
) % $._config,
) % this.config,
},
},
{
alert: 'MongoDBAtlasHighNumberOfTimeoutElections',
alert: 'MongoDBAtlasElectionTimeouts',
expr: |||
sum without (cl_role,process_port,instance,rs_state) (increase(mongodb_electionMetrics_electionTimeout_called[5m])) > %(alertsHighTimeoutElections)s
||| % $._config,
||| % this.config,
'for': '5m',
labels: {
severity: 'warning',
Expand All @@ -204,8 +204,8 @@
summary: 'There is a high number of elections being called due to the primary node timing out.',
description:
(
'The number of elections being called due to the primary node timing out in replica set {{$labels.rs_m}} in cluster {{$labels.cl_name}} is {{printf "%%.0f" $value}} which is above the threshold of %(alertsHighTimeoutElections)s.'
) % $._config,
'The number of elections being called due to the primary node timing out in replica set {{$labels.rs_nm}} in cluster {{$labels.cl_name}} is {{printf "%%.0f" $value}} which is above the threshold of %(alertsHighTimeoutElections)s.'
) % this.config,
},
},
],
Expand Down
63 changes: 48 additions & 15 deletions mongodb-atlas-mixin/config.libsonnet
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,18 +1,51 @@
{
_config+:: {
// sharding dashboard flag
enableShardingOverview: false,

dashboardTags: ['mongodb-atlas-mixin'],
dashboardPeriod: 'now-30m',
dashboardTimezone: 'default',
dashboardRefresh: '1m',

// alerts thresholds
alertsDeadlocks: 10, // count
alertsSlowNetworkRequests: 10, // count
alertsHighDiskUsage: 90, // percentage: 0-100
alertsSlowHardwareIO: 3, // seconds
alertsHighTimeoutElections: 10, // count
local this = self,

// Basic filtering - MongoDB Atlas uses job and cl_name (cluster name) as primary filters
filteringSelector: 'job=~"$job", cl_name=~"$cl_name"',
groupLabels: ['job', 'cl_name'],
instanceLabels: ['instance'],

// Dashboard settings
dashboardTags: ['mongodb-atlas-mixin'],
uid: 'mongodb-atlas',
dashboardNamePrefix: 'MongoDB Atlas',
dashboardRefresh: '1m',
dashboardPeriod: 'now-30m',
dashboardTimezone: 'default',

// Sharding dashboard flag
enableShardingOverview: false,

// Logs configuration (MongoDB Atlas does not have Loki logs by default)
enableLokiLogs: false,
logLabels: [],
extraLogLabels: [],
logsVolumeGroupBy: 'level',
showLogsVolume: false,

// Alert thresholds with units
alertsDeadlocks: 10, // count
alertsSlowNetworkRequests: 10, // count
alertsHighDiskUsage: 90, // %
alertsSlowHardwareIO: 3, // seconds
alertsHighTimeoutElections: 10, // count

// Metrics source
metricsSource: 'prometheus',

// Legend template for instance labels
legendCustomTemplate: std.join(' ', std.map(function(label) '{{' + label + '}}', this.instanceLabels)),

// Import signal definitions
signals+: {
hardware: (import './signals/hardware.libsonnet')(this),
memory: (import './signals/memory.libsonnet')(this),
network: (import './signals/network.libsonnet')(this),
connections: (import './signals/connections.libsonnet')(this),
operations: (import './signals/operations.libsonnet')(this),
locks: (import './signals/locks.libsonnet')(this),
elections: (import './signals/elections.libsonnet')(this),
sharding: (import './signals/sharding.libsonnet')(this),
},
}
Loading
Loading