chore: IIS Modernization #1542
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,87 +1,87 @@ | ||
| { | ||
| new(this): { | ||
| groups: [ | ||
| { | ||
| name: 'MicrosoftIISAlerts', | ||
| rules: [ | ||
| { | ||
| alert: 'MicrosoftIISRejectedAsyncIORequests', | ||
| expr: ||| | ||
| increase(windows_iis_rejected_async_io_requests_total[5m]) > %(alertsWarningHighRejectedAsyncIORequests)s | ||
| ||| % this.config, | ||
| 'for': '5m', | ||
| labels: { | ||
| severity: 'warning', | ||
| }, | ||
| annotations: { | ||
| summary: 'There are a high number of rejected async I/O requests for a site.', | ||
| description: | ||
| ('The number of rejected async IO requests is {{ printf "%%.0f" $value }} over the last 5m on {{ $labels.instance }} - {{ $labels.site }}, ' + | ||
| 'which is above the threshold of %(alertsWarningHighRejectedAsyncIORequests)s.') % this.config, | ||
| }, | ||
| }, | ||
| { | ||
| alert: 'MicrosoftIIS5xxRequestErrors', | ||
| expr: ||| | ||
| sum without (pid, status_code)(increase(windows_iis_worker_request_errors_total{status_code=~"5.."}[5m])) > %(alertsCriticalHigh5xxRequests)s | ||
| ||| % this.config, | ||
| 'for': '5m', | ||
| labels: { | ||
| severity: 'critical', | ||
| }, | ||
| annotations: { | ||
| summary: 'There are a high number of 5xx request errors for an application.', | ||
| description: | ||
| ('The number of 5xx request errors is {{ printf "%%.0f" $value }} over the last 5m on {{ $labels.instance }} - {{ $labels.app }}, ' + | ||
| 'which is above the threshold of %(alertsCriticalHigh5xxRequests)s.') % this.config, | ||
| }, | ||
| }, | ||
| { | ||
| alert: 'MicrosoftIISSuccessRateForWebsocket', | ||
| expr: ||| | ||
| sum without (pid) (increase(windows_iis_worker_websocket_connection_accepted_total[5m]) / clamp_min(increase(windows_iis_worker_websocket_connection_attempts_total[5m]),1)) * 100 > %(alertsCriticalLowWebsocketConnectionSuccessRate)s | ||
|
There was a problem hiding this comment. I know you didn't change this line but I think it has a bug:
I keep finding these bugs in the existing code and I am going to add this as an example to https://github.com/grafana/cloud-onboarding/issues/9972. |
||
| ||| % this.config, | ||
| 'for': '5m', | ||
| labels: { | ||
| severity: 'critical', | ||
| }, | ||
| annotations: { | ||
| summary: 'There is a low success rate for websocket connections for an application.', | ||
| description: | ||
| ('The success rate for websocket connections is {{ printf "%%.0f" $value }} over the last 5m on {{ $labels.instance }} - {{ $labels.app }}, ' + | ||
| 'which is above the threshold of %(alertsCriticalLowWebsocketConnectionSuccessRate)s.') % this.config, | ||
| }, | ||
| }, | ||
| { | ||
| alert: 'MicrosoftIISThreadpoolUtilization', | ||
| expr: ||| | ||
| sum without (pid, state)(windows_iis_worker_threads / windows_iis_worker_max_threads) * 100 > %(alertsCriticalHighThreadPoolUtilization)s | ||
| ||| % this.config, | ||
| 'for': '5m', | ||
| labels: { | ||
| severity: 'critical', | ||
| }, | ||
| annotations: { | ||
| summary: 'The thread pool utilization is nearing max capacity.', | ||
| description: | ||
| ('The threadpool utilization is at {{ printf "%%.0f" $value }} over the last 5m on {{ $labels.instance }} - {{ $labels.app }}, ' + | ||
| 'which is above the threshold of %(alertsCriticalHighThreadPoolUtilization)s.') % this.config, | ||
| }, | ||
| }, | ||
| { | ||
| alert: 'MicrosoftIISWorkerProcessFailures', | ||
| expr: ||| | ||
| increase(windows_iis_total_worker_process_failures[5m]) > %(alertsWarningHighWorkerProcessFailures)s | ||
| ||| % this.config, | ||
| 'for': '5m', | ||
| labels: { | ||
| severity: 'warning', | ||
| }, | ||
| annotations: { | ||
| summary: 'There are a high number of worker process failures for an application.', | ||
| description: | ||
| ('The number of worker process failures is at {{ printf "%%.0f" $value }} over the last 5m on {{ $labels.instance }} - {{ $labels.app }}, ' + | ||
| 'which is above the threshold of %(alertsWarningHighWorkerProcessFailures)s.') % this.config, | ||
| }, | ||
| }, | ||
| ], | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
| @@ -1,17 +1,39 @@ | ||||||
| { | ||||||
| local this = self, | ||||||
|
|
||||||
| filteringSelector: 'job="integrations/iis"', | ||||||
| groupLabels: ['job'], | ||||||
| instanceLabels: ['instance'], | ||||||
| logLabels: ['job', 'instance'], | ||||||
|
|
||||||
|
|
||||||
| // Dashboard settings | ||||||
| dashboardTags: [this.uid + '-mixin'], | ||||||
| uid: 'microsoft-iis', | ||||||
| dashboardNamePrefix: 'Microsoft IIS', | ||||||
| dashboardPeriod: 'now-30m', | ||||||
| dashboardTimezone: 'default', | ||||||
| dashboardRefresh: '1m', | ||||||
|
|
||||||
| // Logs configuration | ||||||
| enableLokiLogs: true, | ||||||
| extraLogLabels: ['level'], // Required by logs-lib | ||||||
| logsVolumeGroupBy: 'level', | ||||||
| showLogsVolume: true, | ||||||
|
|
||||||
| // Alert thresholds | ||||||
| alertsWarningHighRejectedAsyncIORequests: 20, // count | ||||||
| alertsCriticalHigh5xxRequests: 5, // % | ||||||
| alertsCriticalLowWebsocketConnectionSuccessRate: 80, // % | ||||||
| alertsCriticalHighThreadPoolUtilization: 90, // % | ||||||
| alertsWarningHighWorkerProcessFailures: 10, // count | ||||||
|
|
||||||
| // Metrics source | ||||||
| metricsSource: 'prometheus', | ||||||
|
There was a problem hiding this comment. Should this be an array instead?
Suggested change
|
||||||
|
|
||||||
| // Signal definitions grouped by dashboard | ||||||
| signals+: { | ||||||
| overview: (import './signals/overview.libsonnet')(this), | ||||||
| applications: (import './signals/applications.libsonnet')(this), | ||||||
| }, | ||||||
| } | ||||||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,132 @@ | ||
| local g = import './g.libsonnet'; | ||
| local logslib = import 'logs-lib/logs/main.libsonnet'; | ||
|
|
||
| { | ||
| local root = self, | ||
| new(this):: | ||
| local prefix = this.config.dashboardNamePrefix; | ||
| local links = this.grafana.links; | ||
| local tags = this.config.dashboardTags; | ||
| local uid = g.util.string.slugify(this.config.uid); | ||
| local vars = this.grafana.variables; | ||
| local annotations = this.grafana.annotations; | ||
| local refresh = this.config.dashboardRefresh; | ||
| local period = this.config.dashboardPeriod; | ||
| local timezone = this.config.dashboardTimezone; | ||
|
|
||
| { | ||
| // Microsoft IIS overview dashboard | ||
| 'microsoft-iis-overview.json': | ||
| g.dashboard.new(prefix + ' overview') | ||
| + g.dashboard.withDescription('Dashboard providing an overview of Microsoft IIS performance.') | ||
| + g.dashboard.withPanels( | ||
| g.util.panel.resolveCollapsedFlagOnRows( | ||
| g.util.grid.wrapPanels( | ||
| [ | ||
| this.grafana.rows.overviewRequests, | ||
| this.grafana.rows.overviewAsyncIO, | ||
| this.grafana.rows.overviewTraffic, | ||
| this.grafana.rows.overviewConnections, | ||
| ] | ||
| ) | ||
| ) | ||
| ) | ||
| + root.applyCommon( | ||
| vars.multiInstance + [ | ||
| g.dashboard.variable.query.new('site') | ||
| + g.dashboard.variable.query.withDatasourceFromVariable(vars.datasources.prometheus) | ||
| + g.dashboard.variable.query.queryTypes.withLabelValues('site', 'windows_iis_requests_total{job=~"$job", instance=~"$instance"}') | ||
| + g.dashboard.variable.query.generalOptions.withLabel('Site') | ||
| + g.dashboard.variable.query.selectionOptions.withMulti(true) | ||
| + g.dashboard.variable.query.selectionOptions.withIncludeAll(true, '.+') | ||
| + g.dashboard.variable.query.refresh.onTime(), | ||
| ], | ||
| uid + '_overview', | ||
| tags, | ||
| links { microsoftIISOverview+:: {} }, | ||
| annotations, | ||
| timezone, | ||
| refresh, | ||
| period | ||
| ), | ||
|
|
||
| // Microsoft IIS applications dashboard | ||
| 'microsoft-iis-applications.json': | ||
| g.dashboard.new(prefix + ' applications') | ||
| + g.dashboard.withDescription('Dashboard providing detailed application performance metrics for Microsoft IIS.') | ||
| + g.dashboard.withPanels( | ||
| g.util.panel.resolveCollapsedFlagOnRows( | ||
| g.util.grid.wrapPanels( | ||
| [ | ||
| this.grafana.rows.applicationsRequests, | ||
| this.grafana.rows.applicationsWebsocket, | ||
| this.grafana.rows.applicationsWorkerProcesses, | ||
| this.grafana.rows.applicationsCache, | ||
| ] | ||
| ) | ||
| ) | ||
| ) | ||
| + root.applyCommon( | ||
| vars.multiInstance + [ | ||
| g.dashboard.variable.query.new('application') | ||
| + g.dashboard.variable.query.withDatasourceFromVariable(vars.datasources.prometheus) | ||
| + g.dashboard.variable.query.queryTypes.withLabelValues('app', 'windows_iis_current_application_pool_state{job=~"$job", instance=~"$instance"}') | ||
| + g.dashboard.variable.query.generalOptions.withLabel('Application') | ||
| + g.dashboard.variable.query.selectionOptions.withMulti(true) | ||
| + g.dashboard.variable.query.selectionOptions.withIncludeAll(true, '.+') | ||
| + g.dashboard.variable.query.refresh.onLoad() | ||
| + g.dashboard.variable.query.refresh.onTime(), | ||
| ], | ||
| uid + '_applications', | ||
| tags, | ||
| links { microsoftIISApplications+:: {} }, | ||
| annotations, | ||
| timezone, | ||
| refresh, | ||
| period | ||
| ), | ||
| } | ||
| + | ||
| if this.config.enableLokiLogs then | ||
| { | ||
| 'microsoft-iis-logs.json': | ||
| logslib.new( | ||
| prefix + ' logs', | ||
| datasourceName=this.grafana.variables.datasources.loki.name, | ||
| datasourceRegex=this.grafana.variables.datasources.loki.regex, | ||
| filterSelector=this.config.filteringSelector, | ||
| labels=this.config.groupLabels + this.config.extraLogLabels, | ||
| formatParser=null, | ||
| showLogsVolume=this.config.showLogsVolume, | ||
| ) | ||
| { | ||
| dashboards+: | ||
| { | ||
| logs+: | ||
| root.applyCommon(super.logs.templating.list, uid=uid + '-logs', tags=tags, links=links { microsoftIISLogs+:: {} }, annotations=annotations, timezone=timezone, refresh=refresh, period=period), | ||
| }, | ||
| panels+: | ||
| { | ||
| logs+: | ||
| g.panel.logs.options.withEnableLogDetails(true) | ||
| + g.panel.logs.options.withShowTime(false) | ||
| + g.panel.logs.options.withWrapLogMessage(false), | ||
| }, | ||
| variables+: { | ||
| toArray+: [ | ||
| this.grafana.variables.datasources.prometheus { hide: 2 }, | ||
| ], | ||
| }, | ||
| }.dashboards.logs, | ||
| } else {}, | ||
|
|
||
| applyCommon(vars, uid, tags, links, annotations, timezone, refresh, period): | ||
| g.dashboard.withTags(tags) | ||
| + g.dashboard.withUid(uid) | ||
| + g.dashboard.withLinks(std.objectValues(links)) | ||
| + g.dashboard.withTimezone(timezone) | ||
| + g.dashboard.withRefresh(refresh) | ||
| + g.dashboard.time.withFrom(period) | ||
| + g.dashboard.withVariables(vars) | ||
| + g.dashboard.withAnnotations(std.objectValues(annotations)), | ||
| } |
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Do all or some of the alerts need to use the
{%(filteringSelector)s}? It's not present in any of them.