This task tracks the conversion of mw metrics used for graphite-based alerting in Icinga.
======== modules/icinga/manifests/monitor/elasticsearch/cirrus_cluster_checks.pp
* [ ] monitoring::graphite_threshold { "mediawiki_cirrus_update_rate_${site}": metric => "movingAverage(transformNull(MediaWiki.CirrusSearch.${site}.updates.all.sent.rate),\"60minutes\")",
* [ ] monitoring::graphite_threshold { 'mediawiki_cirrus_pool_counter_rejections_rate': metric => "aliasByNode(sum(movingAverage(consolidateBy(transformNull(MediaWiki.CirrusSearch.poolCounter.*.failureMs.sample_rate, 0), \"max\"), \"5minutes\")), 1, 2)",
* [ ] monitoring::graphite_threshold { 'mediawiki_cirrussearch_indices_high_fix_rate': metric => 'smartSummarize(transformNull(MediaWiki.CirrusSearch.{eqiad,codfw,cloudelastic}.sanitization.fixed.sum, 0), "1wk", "sum")',
======== modules/profile/manifests/graphite/alerts.pp
* [ ] monitoring::graphite_threshold { 'mediawiki_session_loss': metric => 'transformNull(scale(consolidateBy(MediaWiki.edit.failures.session_loss.rate, "max"), 60), 0)',
* [ ] monitoring::graphite_threshold { 'mediawiki_bad_token': metric => 'transformNull(scale(consolidateBy(MediaWiki.edit.failures.bad_token.rate, "max"), 60), 0)',
* [ ] monitoring::graphite_threshold { 'mediawiki_centralauth_errors': metric => 'transformNull(sumSeries(MediaWiki.centralauth.centrallogin_errors.*.rate), 0)',
* [ ] monitoring::graphite_threshold { 'mediawiki_accountcreation_errors': metric => "asPercent( sumSeries(${account_failures}), sumSeries(${account_success}, ${account_failures}) )",
======== modules/role/manifests/elasticsearch/alerts.pp:
* [ ] monitoring::graphite_threshold { 'cirrussearch_eqiad_fulltext_95th_percentile': metric => 'fallbackSeries(useSeriesAbove(transformNull(MediaWiki.CirrusSearch.eqiad.requestTimeMs.comp_suggest.sample_rate, 0), 10, "requestTimeMs.comp_suggest.sample_rate", "requestTimeMs.full_text.p95"), constantLine(0))',
* [ ] monitoring::graphite_threshold { 'cirrussearch_codfw_fulltext_95th_percentile': metric => 'fallbackSeries(useSeriesAbove(transformNull(MediaWiki.CirrusSearch.codfw.requestTimeMs.comp_suggest.sample_rate, 0), 10, "requestTimeMs.comp_suggest.sample_rate", "requestTimeMs.full_text.p95"), constantLine(0))',
* [ ] monitoring::graphite_threshold { 'cirrussearch_eqiad_compsuggest_95th_percentile': metric => 'fallbackSeries(useSeriesAbove(transformNull(MediaWiki.CirrusSearch.eqiad.requestTimeMs.comp_suggest.sample_rate, 0), 10, "requestTimeMs.comp_suggest.sample_rate", "requestTimeMs.comp_suggest.p95"), constantLine(0))',
* [ ] monitoring::graphite_threshold { 'cirrussearch_codfw_compsuggest_95th_percentile': metric => 'fallbackSeries(useSeriesAbove(transformNull(MediaWiki.CirrusSearch.codfw.requestTimeMs.comp_suggest.sample_rate, 0), 10, "requestTimeMs.comp_suggest.sample_rate", "requestTimeMs.comp_suggest.p95"), constantLine(0))',
* [ ] monitoring::graphite_threshold { 'cirrussearch_eqiad_morelike_95th_percentile': metric => 'fallbackSeries(useSeriesAbove(transformNull(MediaWiki.CirrusSearch.eqiad.requestTimeMs.comp_suggest.sample_rate, 0), 10, "requestTimeMs.comp_suggest.sample_rate", "requestTimeMs.more_like.p95"), constantLine(0))',
* [ ] monitoring::graphite_threshold { 'cirrussearch_codfw_morelike_95th_percentile': metric => 'fallbackSeries(useSeriesAbove(transformNull(MediaWiki.CirrusSearch.codfw.requestTimeMs.comp_suggest.sample_rate, 0), 10, "requestTimeMs.comp_suggest.sample_rate", "requestTimeMs.more_like.p95"), constantLine(0))',
* [ ] monitoring::graphite_threshold { 'search_backend_failure_count': metric => 'transformNull(MediaWiki.CirrusSearch.eqiad.backend_failure.failed.count, 0)',