37 Star 411 Fork 76

GVPrancher/rancher

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
克隆/下载
metricExpression.go 144.32 KB
一键复制 编辑 原始数据 按行查看 历史
Frank Mai 提交于 2019-03-16 17:51 . Remove Ingress Upstream Response Graph
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096309730983099310031013102310331043105310631073108310931103111311231133114311531163117311831193120312131223123312431253126312731283129313031313132313331343135313631373138313931403141314231433144314531463147314831493150315131523153315431553156315731583159316031613162316331643165316631673168316931703171317231733174317531763177317831793180318131823183318431853186318731883189319031913192319331943195319631973198319932003201320232033204320532063207320832093210321132123213321432153216321732183219322032213222322332243225322632273228322932303231323232333234323532363237323832393240324132423243324432453246324732483249325032513252325332543255325632573258325932603261326232633264326532663267326832693270327132723273327432753276327732783279328032813282328332843285328632873288328932903291329232933294329532963297329832993300330133023303330433053306330733083309331033113312331333143315331633173318331933203321332233233324332533263327332833293330333133323333333433353336333733383339334033413342334333443345334633473348334933503351335233533354335533563357335833593360336133623363336433653366336733683369337033713372337333743375337633773378337933803381338233833384338533863387338833893390339133923393339433953396339733983399340034013402340334043405340634073408340934103411341234133414341534163417341834193420342134223423342434253426342734283429343034313432343334343435343634373438343934403441344234433444344534463447344834493450345134523453345434553456345734583459346034613462346334643465346634673468346934703471347234733474347534763477347834793480348134823483348434853486348734883489349034913492349334943495349634973498349935003501350235033504350535063507350835093510351135123513351435153516351735183519352035213522352335243525352635273528352935303531353235333534353535363537353835393540354135423543354435453546354735483549355035513552355335543555355635573558355935603561356235633564356535663567356835693570357135723573357435753576357735783579358035813582358335843585358635873588358935903591359235933594359535963597359835993600360136023603360436053606360736083609361036113612361336143615361636173618361936203621362236233624362536263627362836293630363136323633363436353636363736383639364036413642364336443645364636473648364936503651365236533654365536563657365836593660366136623663366436653666366736683669367036713672367336743675367636773678367936803681368236833684368536863687368836893690369136923693369436953696369736983699370037013702370337043705370637073708370937103711371237133714371537163717371837193720372137223723372437253726372737283729373037313732373337343735373637373738373937403741374237433744374537463747374837493750375137523753375437553756375737583759376037613762376337643765376637673768376937703771377237733774377537763777377837793780378137823783378437853786378737883789379037913792379337943795379637973798379938003801380238033804380538063807380838093810381138123813381438153816381738183819382038213822382338243825382638273828382938303831383238333834383538363837383838393840384138423843384438453846384738483849385038513852385338543855385638573858385938603861386238633864386538663867386838693870387138723873387438753876387738783879388038813882388338843885388638873888388938903891389238933894389538963897389838993900390139023903390439053906390739083909391039113912391339143915391639173918391939203921392239233924392539263927392839293930393139323933393439353936393739383939394039413942394339443945394639473948394939503951395239533954395539563957395839593960396139623963396439653966396739683969397039713972397339743975397639773978397939803981398239833984398539863987398839893990399139923993399439953996399739983999400040014002400340044005400640074008400940104011401240134014401540164017401840194020402140224023402440254026402740284029403040314032403340344035403640374038403940404041404240434044404540464047404840494050405140524053405440554056405740584059406040614062406340644065406640674068406940704071407240734074407540764077407840794080408140824083408440854086408740884089409040914092409340944095409640974098409941004101410241034104410541064107410841094110411141124113411441154116411741184119412041214122412341244125412641274128412941304131413241334134413541364137413841394140414141424143414441454146414741484149415041514152415341544155415641574158415941604161416241634164416541664167416841694170417141724173417441754176417741784179418041814182418341844185418641874188418941904191419241934194419541964197419841994200420142024203420442054206420742084209421042114212421342144215421642174218421942204221422242234224422542264227422842294230423142324233423442354236423742384239424042414242424342444245424642474248424942504251425242534254425542564257425842594260426142624263426442654266426742684269427042714272427342744275427642774278427942804281428242834284428542864287428842894290429142924293429442954296429742984299430043014302430343044305430643074308430943104311431243134314431543164317431843194320432143224323432443254326432743284329433043314332433343344335433643374338433943404341434243434344434543464347434843494350435143524353435443554356435743584359436043614362436343644365436643674368436943704371437243734374437543764377437843794380438143824383438443854386438743884389439043914392439343944395439643974398439944004401440244034404440544064407440844094410441144124413441444154416441744184419442044214422442344244425442644274428442944304431443244334434443544364437443844394440444144424443444444454446444744484449445044514452445344544455445644574458445944604461446244634464446544664467446844694470447144724473447444754476447744784479448044814482448344844485448644874488448944904491449244934494449544964497449844994500450145024503450445054506450745084509451045114512451345144515451645174518451945204521452245234524452545264527452845294530453145324533453445354536453745384539454045414542454345444545454645474548454945504551455245534554455545564557455845594560456145624563456445654566456745684569457045714572457345744575457645774578457945804581458245834584458545864587458845894590459145924593459445954596459745984599460046014602460346044605460646074608460946104611461246134614461546164617461846194620462146224623462446254626462746284629463046314632463346344635463646374638463946404641464246434644464546464647464846494650465146524653465446554656465746584659466046614662466346644665466646674668466946704671467246734674467546764677467846794680468146824683468446854686468746884689469046914692469346944695469646974698469947004701470247034704470547064707470847094710471147124713471447154716471747184719472047214722472347244725472647274728472947304731473247334734473547364737473847394740474147424743474447454746474747484749475047514752475347544755475647574758475947604761476247634764476547664767476847694770477147724773477447754776477747784779478047814782478347844785478647874788478947904791479247934794479547964797479847994800480148024803480448054806480748084809481048114812481348144815481648174818481948204821482248234824482548264827482848294830483148324833483448354836483748384839484048414842484348444845484648474848484948504851485248534854485548564857485848594860486148624863486448654866486748684869487048714872487348744875487648774878487948804881488248834884488548864887488848894890489148924893489448954896489748984899490049014902490349044905490649074908490949104911491249134914491549164917491849194920492149224923492449254926492749284929493049314932493349344935493649374938493949404941494249434944494549464947494849494950495149524953495449554956495749584959496049614962496349644965496649674968496949704971497249734974497549764977497849794980498149824983498449854986498749884989499049914992499349944995499649974998499950005001500250035004500550065007500850095010501150125013501450155016501750185019502050215022502350245025502650275028502950305031503250335034503550365037503850395040504150425043504450455046504750485049505050515052505350545055505650575058505950605061506250635064506550665067506850695070507150725073507450755076507750785079508050815082508350845085508650875088508950905091509250935094509550965097509850995100510151025103510451055106510751085109511051115112511351145115511651175118511951205121512251235124512551265127512851295130513151325133513451355136513751385139514051415142514351445145514651475148514951505151515251535154515551565157515851595160516151625163516451655166516751685169517051715172517351745175517651775178517951805181518251835184518551865187518851895190519151925193519451955196519751985199520052015202520352045205520652075208520952105211521252135214521552165217521852195220522152225223522452255226522752285229523052315232523352345235523652375238523952405241524252435244524552465247524852495250525152525253525452555256525752585259526052615262526352645265526652675268526952705271527252735274527552765277527852795280528152825283528452855286528752885289529052915292529352945295529652975298529953005301530253035304530553065307530853095310531153125313531453155316531753185319532053215322532353245325532653275328532953305331533253335334533553365337533853395340534153425343534453455346534753485349535053515352535353545355535653575358535953605361536253635364536553665367
package monitoring
import (
"bytes"
"encoding/json"
"fmt"
"strings"
"text/template"
"github.com/ghodss/yaml"
managementv3 "github.com/rancher/types/apis/management.cattle.io/v3"
)
var (
preDefinedClusterMetrics = getPredefinedClusterMetrics()
preDefinedClusterGraph = getPredefinedClusterGraph()
preDefinedProjectGraph = getPredefinedProjectGraph()
)
type templateData struct {
ProjectName string
}
func getPredefinedClusterMetrics() []*managementv3.MonitorMetric {
yamls := strings.Split(MonitorMetricsTemplate, "\n---\n")
var rtn []*managementv3.MonitorMetric
for _, yml := range yamls {
var tmp managementv3.MonitorMetric
if err := yamlToObject(yml, &tmp); err != nil {
panic(err)
}
if tmp.Name == "" {
continue
}
rtn = append(rtn, &tmp)
}
return rtn
}
func getPredefinedClusterGraph() []*managementv3.ClusterMonitorGraph {
yamls := strings.Split(ClusterMetricExpression, "\n---\n")
var rtn []*managementv3.ClusterMonitorGraph
for _, yml := range yamls {
var tmp managementv3.ClusterMonitorGraph
if err := yamlToObject(yml, &tmp); err != nil {
panic(err)
}
if tmp.Name == "" {
continue
}
rtn = append(rtn, &tmp)
}
return rtn
}
func getPredefinedProjectGraph() []*managementv3.ProjectMonitorGraph {
yamls := strings.Split(ProjectMetricExpression, "\n---\n")
var rtn []*managementv3.ProjectMonitorGraph
for _, yml := range yamls {
var tmp managementv3.ProjectMonitorGraph
if err := yamlToObject(yml, &tmp); err != nil {
panic(err)
}
if tmp.Name == "" {
continue
}
rtn = append(rtn, &tmp)
}
return rtn
}
func yamlToObject(yml string, obj interface{}) error {
jsondata, err := yaml.YAMLToJSON([]byte(yml))
if err != nil {
return err
}
if err := json.Unmarshal(jsondata, obj); err != nil {
return err
}
return nil
}
func generate(text string, data templateData) (string, error) {
t, err := template.New("expression-yaml").Parse(text)
if err != nil {
return "", fmt.Errorf("parse template expression-yaml failed, %v", err)
}
var contentBuf bytes.Buffer
err = t.Execute(&contentBuf, data)
if err != nil {
return "", fmt.Errorf("failed to execute template expression-yaml, %v", err)
}
return contentBuf.String(), nil
}
var (
ClusterMetricExpression = `
---
# Source: metric-expression-cluster/templates/graphapiserver.yaml
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: apiserver
cluster-graph: kube-component
name: apiserver-request-latency
spec:
resourceType: apiserver
displayResourceType: kube-component
priority: 300
title: apiserver-request-latency
detailsMetricsSelector:
component: apiserver
details: "true"
metric: request-latency-milliseconds-avg
metricsSelector:
details: "false"
component: apiserver
metric: request-latency-milliseconds-avg
yAxis:
unit: ms
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: apiserver
cluster-graph: kube-component
name: apiserver-request-count
spec:
resourceType: apiserver
displayResourceType: kube-component
priority: 301
title: apiserver-request-count
detailsMetricsSelector:
component: apiserver
details: "true"
metric: request-count-sum-rate
metricsSelector:
details: "false"
component: apiserver
metric: request-count-sum-rate
yAxis:
unit: number
---
# Source: metric-expression-cluster/templates/graphcluster.yaml
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: cluster
name: cluster-cpu-usage
spec:
resourceType: cluster
priority: 100
title: cluster-cpu-usage
metricsSelector:
details: "false"
component: cluster
metric: cpu-usage-seconds-sum-rate
detailsMetricsSelector:
details: "true"
component: cluster
metric: cpu-usage-seconds-sum-rate
yAxis:
unit: percent
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: cluster
name: cluster-cpu-load
spec:
resourceType: cluster
priority: 101
title: cluster-cpu-load
metricsSelector:
details: "false"
component: cluster
graph: cpu-load
detailsMetricsSelector:
details: "true"
component: cluster
graph: cpu-load
yAxis:
unit: number
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: cluster
name: cluster-memory-usage
spec:
resourceType: cluster
priority: 102
title: cluster-memory-usage
metricsSelector:
details: "false"
component: cluster
metric: memory-usage-percent
detailsMetricsSelector:
details: "true"
component: cluster
metric: memory-usage-percent
yAxis:
unit: percent
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: cluster
name: cluster-fs-usage-percent
spec:
resourceType: cluster
priority: 103
title: cluster-fs-usage-percent
thresholds: 10
metricsSelector:
details: "false"
component: cluster
metric: fs-usage-percent
detailsMetricsSelector:
details: "true"
component: cluster
metric: fs-usage-percent
yAxis:
unit: percent
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: cluster
name: cluster-disk-io
spec:
resourceType: cluster
priority: 104
title: cluster-disk-io
thresholds: 10
metricsSelector:
details: "false"
component: cluster
graph: disk-io
detailsMetricsSelector:
details: "true"
component: cluster
graph: disk-io
yAxis:
unit: bps
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: cluster
name: cluster-network-io
spec:
resourceType: cluster
priority: 105
title: cluster-network-io
thresholds: 10
metricsSelector:
details: "false"
component: cluster
graph: network-io
detailsMetricsSelector:
details: "true"
component: cluster
graph: network-io
yAxis:
unit: bps
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: cluster
name: cluster-network-packet
spec:
resourceType: cluster
priority: 106
title: cluster-network-packet
thresholds: 10
metricsSelector:
details: "false"
component: cluster
graph: network-packet
detailsMetricsSelector:
details: "true"
component: cluster
graph: network-packet
yAxis:
unit: pps
---
# Source: metric-expression-cluster/templates/graphcontrollermanager.yaml
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: controllermanager
cluster-graph: kube-component
name: controllermanager-queue-depth
spec:
resourceType: controllermanager
displayResourceType: kube-component
priority: 310
title: controllermanager-queue-depth
metricsSelector:
details: "false"
component: controllermanager
detailsMetricsSelector:
details: "true"
component: controllermanager
yAxis:
unit: number
---
# Source: metric-expression-cluster/templates/graphetcd.yaml
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: etcd
name: etcd-server-leader-sum
spec:
resourceType: etcd
priority: 200
title: etcd-server-leader-sum
description: etcd server leader sum
metricsSelector:
details: "false"
component: etcd
metric: server-leader-sum
detailsMetricsSelector:
details: "true"
component: etcd
metric: server-leader-sum
yAxis:
unit: number
graphType: singlestat
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: etcd
name: etcd-server-failed-proposal
spec:
resourceType: etcd
priority: 201
title: etcd-server-failed-proposal
description: etcd server failed proposal
metricsSelector:
details: "false"
component: etcd
metric: server-failed-proposal
detailsMetricsSelector:
details: "true"
component: etcd
metric: server-failed-proposal
yAxis:
unit: number
graphType: singlestat
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: etcd
name: etcd-leader-change
spec:
resourceType: etcd
priority: 202
title: etcd-leader-change
description: etcd leader change
metricsSelector:
details: "false"
component: etcd
metric: server-leader-changes-seen-sum-increase
detailsMetricsSelector:
details: "true"
component: etcd
metric: server-leader-changes-seen-sum-increase
yAxis:
unit: number
graphType: singlestat
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: etcd
name: etcd-grpc-client
spec:
resourceType: etcd
priority: 203
title: etcd-grpc-client
description: etcd grpc client receive/send bytes sum rate
metricsSelector:
details: "false"
component: etcd
graph: rpc-client-traffic
detailsMetricsSelector:
details: "true"
component: etcd
graph: rpc-client-traffic
yAxis:
unit: bps
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: etcd
metric: db-bytes-sum
name: etcd-db-bytes-sum
spec:
resourceType: etcd
priority: 204
title: etcd-db-bytes-sum
description: etcd db bytes sum
metricsSelector:
details: "false"
component: etcd
metric: db-bytes-sum
detailsMetricsSelector:
details: "true"
component: etcd
metric: db-bytes-sum
yAxis:
unit: byte
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: etcd
name: etcd-stream
spec:
resourceType: etcd
priority: 205
title: etcd-stream
description: Etcd lease/watch stream
metricsSelector:
details: "false"
component: etcd
graph: etcd-stream
detailsMetricsSelector:
details: "true"
component: etcd
graph: etcd-stream
yAxis:
unit: number
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: etcd
name: etcd-peer-traffic
spec:
resourceType: etcd
priority: 206
title: etcd-peer-traffic
description: Etcd peer traffic in/out
metricsSelector:
details: "false"
component: etcd
graph: etcd-peer-traffic
detailsMetricsSelector:
details: "true"
component: etcd
graph: etcd-peer-traffic
yAxis:
unit: bps
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: etcd
name: etcd-raft-proposals
spec:
resourceType: etcd
priority: 207
title: etcd-raft-proposals
description: Etcd raft proposals
metricsSelector:
details: "false"
component: etcd
graph: proposal
detailsMetricsSelector:
details: "true"
component: etcd
graph: proposal
yAxis:
unit: number
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: etcd
name: etcd-rpc-rate
spec:
resourceType: etcd
priority: 208
title: etcd-rpc-rate
description: Etcd rpc-rate
metricsSelector:
details: "false"
component: etcd
graph: rpc-rate
detailsMetricsSelector:
details: "true"
component: etcd
graph: rpc-rate
yAxis:
unit: ops
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: etcd
name: etcd-disk-operate
spec:
resourceType: etcd
priority: 209
title: etcd-disk-operate
description: Etcd disk operate
metricsSelector:
details: "false"
component: etcd
graph: disk-operate
detailsMetricsSelector:
details: "true"
component: etcd
graph: disk-operate
yAxis:
unit: seconds
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: etcd
name: etcd-sync-duration
spec:
resourceType: etcd
priority: 209
title: etcd-sync-duration
description: Etcd sync-duration
metricsSelector:
details: "false"
component: etcd
graph: sync-duration
detailsMetricsSelector:
details: "true"
component: etcd
graph: sync-duration
yAxis:
unit: seconds
---
# Source: metric-expression-cluster/templates/graphfluentd.yaml
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: fluentd
cluster-graph: rancher-component
name: fluentd-input-record-number
spec:
resourceType: fluentd
displayResourceType: rancher-component
priority: 300
title: fluentd-input-record-number
metricsSelector:
details: "false"
component: fluentd
metric: input-record
detailsMetricsSelector:
details: "true"
component: fluentd
metric: input-record
yAxis:
unit: number
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: fluentd
cluster-graph: rancher-component
name: fluentd-output-record-number
spec:
resourceType: fluentd
displayResourceType: rancher-component
priority: 301
title: fluentd-output-record-number
metricsSelector:
details: "false"
component: fluentd
metric: output-record
detailsMetricsSelector:
details: "true"
component: fluentd
metric: output-record
yAxis:
unit: number
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: fluentd
cluster-graph: rancher-component
name: fluentd-output-errors
spec:
resourceType: fluentd
displayResourceType: rancher-component
priority: 301
title: fluentd-output-errors
metricsSelector:
details: "false"
component: fluentd
metric: output-errors
detailsMetricsSelector:
details: "true"
component: fluentd
metric: output-errors
yAxis:
unit: number
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: fluentd
cluster-graph: rancher-component
name: fluentd-buffer-queue-length
spec:
resourceType: fluentd
displayResourceType: rancher-component
priority: 301
title: fluentd-buffer-queue-length
metricsSelector:
details: "false"
component: fluentd
metric: buffer-queue-length
detailsMetricsSelector:
details: "true"
component: fluentd
metric: buffer-queue-length
yAxis:
unit: number
---
# Source: metric-expression-cluster/templates/graphingresscontroller.yaml
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: ingresscontroller
cluster-graph: kube-component
name: ingresscontroller-nginx-connection
spec:
resourceType: ingresscontroller
displayResourceType: kube-component
priority: 330
title: ingresscontroller-nginx-connection
metricsSelector:
details: "false"
component: ingresscontroller
graph: nginx-connection
detailsMetricsSelector:
details: "true"
component: ingresscontroller
graph: nginx-connection
yAxis:
unit: number
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: ingresscontroller
cluster-graph: kube-component
name: ingresscontroller-request-process-time
spec:
resourceType: ingresscontroller
displayResourceType: kube-component
priority: 331
title: ingresscontroller-request-process-time
metricsSelector:
details: "false"
component: ingresscontroller
metric: request-process-seconds
detailsMetricsSelector:
details: "true"
component: ingresscontroller
metric: request-process-seconds
yAxis:
unit: seconds
---
# Source: metric-expression-cluster/templates/graphnode.yaml
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: node
name: node-cpu-usage
spec:
resourceType: node
priority: 500
title: node-cpu-usage
metricsSelector:
details: "false"
component: node
metric: cpu-usage-seconds-sum-rate
detailsMetricsSelector:
details: "true"
component: node
metric: cpu-usage-seconds-sum-rate
yAxis:
unit: percent
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: node
name: node-cpu-load
spec:
resourceType: node
priority: 501
title: node-cpu-load
metricsSelector:
details: "false"
component: node
graph: cpu-load
detailsMetricsSelector:
details: "true"
component: node
graph: cpu-load
yAxis:
unit: number
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: node
name: node-memory-usage
spec:
resourceType: node
priority: 502
title: node-memory-usage
metricsSelector:
details: "false"
component: node
metric: memory-usage-percent
detailsMetricsSelector:
details: "true"
component: node
metric: memory-usage-percent
yAxis:
unit: percent
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: node
name: node-fs-usage-percent
spec:
resourceType: node
priority: 503
title: node-fs-usage-percent
thresholds: 10
metricsSelector:
details: "false"
component: node
metric: fs-usage-percent
detailsMetricsSelector:
details: "true"
component: node
metric: fs-usage-percent
yAxis:
unit: percent
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: node
name: node-disk-io
spec:
resourceType: node
priority: 504
title: node-disk-io
thresholds: 10
metricsSelector:
details: "false"
component: node
graph: disk-io
detailsMetricsSelector:
details: "true"
component: node
graph: disk-io
yAxis:
unit: bps
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: node
name: node-network-io
spec:
resourceType: node
priority: 505
title: node-network-io
thresholds: 10
metricsSelector:
details: "false"
component: node
graph: network-io
detailsMetricsSelector:
details: "true"
component: node
graph: network-io
yAxis:
unit: bps
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: node
name: node-network-packet
spec:
resourceType: node
priority: 506
title: node-network-packet
thresholds: 10
metricsSelector:
details: "false"
component: node
graph: network-packet
detailsMetricsSelector:
details: "true"
component: node
graph: network-packet
yAxis:
unit: pps
---
# Source: metric-expression-cluster/templates/graphscheduler.yaml
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: scheduler
cluster-graph: kube-component
name: scheduler-e-2-e-scheduling-latency-seconds-quantile
spec:
resourceType: scheduler
displayResourceType: kube-component
priority: 320
title: scheduler-e-2-e-scheduling-latency-seconds-quantile
thresholds: 10
metricsSelector:
details: "false"
component: scheduler
metric: e-2-e-scheduling-latency-seconds-quantile
detailsMetricsSelector:
details: "true"
component: scheduler
metric: e-2-e-scheduling-latency-seconds-quantile
yAxis:
unit: seconds
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: scheduler
cluster-graph: kube-component
name: scheduler-total-preemption-attempts
spec:
resourceType: scheduler
displayResourceType: kube-component
priority: 321
title: scheduler-total-preemption-attempts
thresholds: 10
metricsSelector:
details: "false"
component: scheduler
metric: total-preemption-attempts
detailsMetricsSelector:
details: "true"
component: scheduler
metric: total-preemption-attempts
yAxis:
unit: number
---
apiVersion: management.cattle.io/v3
kind: ClusterMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: cluster
component: scheduler
cluster-graph: kube-component
name: scheduler-pod-unscheduler
spec:
resourceType: scheduler
displayResourceType: kube-component
priority: 322
title: scheduler-pod-unscheduler
thresholds: 10
metricsSelector:
details: "false"
component: scheduler
metric: pod-unscheduler
detailsMetricsSelector:
details: "true"
component: scheduler
metric: pod-unscheduler
yAxis:
unit: number
---
`
MonitorMetricsTemplate = `
---
# Source: metric-expression-cluster/templates/expressionapiserver.yaml
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: apiserver-request-latency-milliseconds-avg
labels:
app: metric-expression
component: apiserver
details: "false"
level: cluster
metric: request-latency-milliseconds-avg
source: rancher-monitoring
spec:
expression: avg(apiserver_request_latencies_sum / apiserver_request_latencies_count)
by (instance) /1e+06
legendFormat: '[[instance]]'
description: apiserver request latency milliseconds avg
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: apiserver-request-latency-milliseconds-avg-details
labels:
app: metric-expression
component: apiserver
details: "true"
level: cluster
metric: request-latency-milliseconds-avg
source: rancher-monitoring
spec:
expression: avg(apiserver_request_latencies_sum / apiserver_request_latencies_count)
by (instance, verb) /1e+06
legendFormat: '[[verb]]([[instance]])'
description: apiserver request latency milliseconds avg
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: apiserver-request-count-sum-rate
labels:
app: metric-expression
component: apiserver
details: "false"
graph: request-count
level: cluster
metric: request-count-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(apiserver_request_count[5m])) by (instance)
legendFormat: '[[instance]]'
description: apiserver request count sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: apiserver-request-count-sum-rate-details
labels:
app: metric-expression
component: apiserver
details: "true"
graph: request-count
level: cluster
metric: request-count-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(apiserver_request_count[5m])) by (instance,
code)
legendFormat: '[[code]]([[instance]])'
description: apiserver request count sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: apiserver-request-error-count-sum-rate
labels:
app: metric-expression
component: apiserver
details: "false"
graph: request-count
level: cluster
metric: request-error-count-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(apiserver_request_count{instance=~"$instance", code!~"2.."}[5m]))
by (instance)
legendFormat: '[[instance]]'
description: apiserver request error count sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: apiserver-request-error-count-sum-rate-details
labels:
app: metric-expression
component: apiserver
details: "true"
graph: request-count
level: cluster
metric: request-error-count-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(apiserver_request_count{instance=~"$instance", code!~"2.."}[5m]))
by (instance, code)
legendFormat: '[[code]]([[instance]])'
description: apiserver request error count sum rate
---
---
# Source: metric-expression-cluster/templates/expressioncluster.yaml
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-disk-io-reads-bytes-sum-rate
labels:
app: metric-expression
component: cluster
details: "false"
graph: disk-io
level: cluster
metric: disk-io-reads-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_disk_read_bytes_total[5m]))
legendFormat: Read
description: cluster disk io reads bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-disk-io-reads-bytes-sum-rate-details
labels:
app: metric-expression
component: cluster
details: "true"
graph: disk-io
level: cluster
metric: disk-io-reads-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_disk_read_bytes_total[5m])) by
(instance)
legendFormat: Read([[instance]])
description: cluster disk io reads bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-transmit-bytes-sum
labels:
app: metric-expression
component: cluster
details: "false"
graph: network-io
level: cluster
metric: network-transmit-bytes-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
legendFormat: Transmit
description: cluster network transmit bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-transmit-bytes-sum-details
labels:
app: metric-expression
component: cluster
details: "true"
graph: network-io
level: cluster
metric: network-transmit-bytes-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
by (instance)
legendFormat: Transmit([[instance]])
description: cluster network transmit bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-cpu-load-5
labels:
app: metric-expression
component: cluster
details: "false"
graph: cpu-load
level: cluster
metric: cpu-load-5
source: rancher-monitoring
spec:
expression: sum(node_load5) / count(node_cpu_seconds_total{mode="system"})
legendFormat: Load5
description: cluster cpu load 5
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-cpu-load-5-details
labels:
app: metric-expression
component: cluster
details: "true"
graph: cpu-load
level: cluster
metric: cpu-load-5
source: rancher-monitoring
spec:
expression: sum(node_load5) by (instance) / count(node_cpu_seconds_total{mode="system"})
by (instance)
legendFormat: Load5([[instance]])
description: cluster cpu load 5
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-cpu-load-1
labels:
app: metric-expression
component: cluster
details: "false"
graph: cpu-load
level: cluster
metric: cpu-load-1
source: rancher-monitoring
spec:
expression: sum(node_load1) / count(node_cpu_seconds_total{mode="system"})
legendFormat: Load1
description: cluster cpu load 1
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-cpu-load-1-details
labels:
app: metric-expression
component: cluster
details: "true"
graph: cpu-load
level: cluster
metric: cpu-load-1
source: rancher-monitoring
spec:
expression: sum(node_load1) by (instance) / count(node_cpu_seconds_total{mode="system"})
by (instance)
legendFormat: Load1([[instance]])
description: cluster cpu load 1
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-disk-io-writes-bytes-sum-rate
labels:
app: metric-expression
component: cluster
details: "false"
graph: disk-io
level: cluster
metric: disk-io-writes-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_disk_written_bytes_total[5m]))
legendFormat: Write
description: cluster disk io writes bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-disk-io-writes-bytes-sum-rate-details
labels:
app: metric-expression
component: cluster
details: "true"
graph: disk-io
level: cluster
metric: disk-io-writes-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_disk_written_bytes_total[5m]))
by (instance)
legendFormat: Write([[instance]])
description: cluster disk io writes bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-fs-usage-percent
labels:
app: metric-expression
component: cluster
details: "false"
level: cluster
metric: fs-usage-percent
source: rancher-monitoring
spec:
expression: (sum(node_filesystem_size_bytes{device!="rootfs"})
- sum(node_filesystem_free_bytes{device!="rootfs"})
) / sum(node_filesystem_size_bytes{device!="rootfs"})
legendFormat: Disk usage
description: cluster fs usage percent
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-fs-usage-percent-details
labels:
app: metric-expression
component: cluster
details: "true"
level: cluster
metric: fs-usage-percent
source: rancher-monitoring
spec:
expression: (sum(node_filesystem_size_bytes{device!="rootfs"})
by (instance) - sum(node_filesystem_free_bytes{device!="rootfs"})
by (instance)) / sum(node_filesystem_size_bytes{device!="rootfs"})
by (instance)
legendFormat: '[[instance]]'
description: cluster fs usage percent
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-receive-errors-sum
labels:
app: metric-expression
component: cluster
details: "false"
graph: network-packet
level: cluster
metric: network-receive-errors-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
legendFormat: Receive errors
description: cluster network receive errors sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-receive-errors-sum-details
labels:
app: metric-expression
component: cluster
details: "true"
graph: network-packet
level: cluster
metric: network-receive-errors-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
by (instance)
legendFormat: Receive errors([[instance]])
description: cluster network receive errors sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-cpu-load-15
labels:
app: metric-expression
component: cluster
details: "false"
graph: cpu-load
level: cluster
metric: cpu-load-15
source: rancher-monitoring
spec:
expression: sum(node_load15) / count(node_cpu_seconds_total{mode="system"})
legendFormat: Load15
description: cluster cpu load 15
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-cpu-load-15-details
labels:
app: metric-expression
component: cluster
details: "true"
graph: cpu-load
level: cluster
metric: cpu-load-15
source: rancher-monitoring
spec:
expression: sum(node_load15) by (instance) / count(node_cpu_seconds_total{mode="system"})
by (instance)
legendFormat: Load15([[instance]])
description: cluster cpu load 15
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-receive-bytes-sum
labels:
app: metric-expression
component: cluster
details: "false"
graph: network-io
level: cluster
metric: network-receive-bytes-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
legendFormat: Receive
description: cluster network receive bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-receive-bytes-sum-details
labels:
app: metric-expression
component: cluster
details: "true"
graph: network-io
level: cluster
metric: network-receive-bytes-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
by (instance)
legendFormat: Receive([[instance]])
description: cluster network receive bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-receive-packets-sum
labels:
app: metric-expression
component: cluster
details: "false"
graph: network-packet
level: cluster
metric: network-receive-packets-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
legendFormat: Receive packets
description: cluster network receive packets sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-receive-packets-sum-details
labels:
app: metric-expression
component: cluster
details: "true"
graph: network-packet
level: cluster
metric: network-receive-packets-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
by (instance)
legendFormat: Receive packets([[instance]])
description: cluster network receive packets sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-transmit-errors-sum
labels:
app: metric-expression
component: cluster
details: "false"
graph: network-packet
level: cluster
metric: network-transmit-errors-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
legendFormat: Transmit errors
description: cluster network transmit errors sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-transmit-errors-sum-details
labels:
app: metric-expression
component: cluster
details: "true"
graph: network-packet
level: cluster
metric: network-transmit-errors-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
by (instance)
legendFormat: Transmit errors([[instance]])
description: cluster network transmit errors sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-receive-packets-dropped-sum
labels:
app: metric-expression
component: cluster
details: "false"
graph: network-packet
level: cluster
metric: network-receive-packets-dropped-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
legendFormat: Receive dropped
description: cluster network receive packets dropped sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-receive-packets-dropped-sum-details
labels:
app: metric-expression
component: cluster
details: "true"
graph: network-packet
level: cluster
metric: network-receive-packets-dropped-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
by (instance)
legendFormat: Receive dropped([[instance]])
description: cluster network receive packets dropped sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-transmit-packets-dropped-sum
labels:
app: metric-expression
component: cluster
details: "false"
graph: network-packet
level: cluster
metric: network-transmit-packets-dropped-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
legendFormat: Transmit dropped
description: cluster network transmit packets dropped sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-transmit-packets-dropped-sum-details
labels:
app: metric-expression
component: cluster
details: "true"
graph: network-packet
level: cluster
metric: network-transmit-packets-dropped-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
by (instance)
legendFormat: Transmit dropped([[instance]])
description: cluster network transmit packets dropped sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-transmit-packets-sum
labels:
app: metric-expression
component: cluster
details: "false"
graph: network-packet
level: cluster
metric: network-transmit-packets-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
legendFormat: Transmit packets
description: cluster network transmit packets sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-network-transmit-packets-sum-details
labels:
app: metric-expression
component: cluster
details: "true"
graph: network-packet
level: cluster
metric: network-transmit-packets-sum
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*"}[5m]))
by (instance)
legendFormat: Transmit packets([[instance]])
description: cluster network transmit packets sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-cpu-usage-seconds-sum-rate
labels:
app: metric-expression
component: cluster
details: "false"
level: cluster
metric: cpu-usage-seconds-sum-rate
source: rancher-monitoring
spec:
expression: 1 - (avg(irate(node_cpu_seconds_total{mode="idle"}[5m])))
legendFormat: CPU usage
description: cluster cpu usage seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-cpu-usage-seconds-sum-rate-details
labels:
app: metric-expression
component: cluster
details: "true"
level: cluster
metric: cpu-usage-seconds-sum-rate
source: rancher-monitoring
spec:
expression: 1 - (avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) by (instance))
legendFormat: '[[instance]]'
description: cluster cpu usage seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-memory-usage-percent
labels:
app: metric-expression
component: cluster
details: "false"
level: cluster
metric: memory-usage-percent
source: rancher-monitoring
spec:
expression: 1 - sum(node_memory_MemAvailable_bytes)
/ sum(node_memory_MemTotal_bytes)
legendFormat: Memory usage
description: cluster memory usage percent
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cluster-memory-usage-percent-details
labels:
app: metric-expression
component: cluster
details: "true"
level: cluster
metric: memory-usage-percent
source: rancher-monitoring
spec:
expression: 1 - sum(node_memory_MemAvailable_bytes) by (instance)
/ sum(node_memory_MemTotal_bytes) by (instance)
legendFormat: '[[instance]]'
description: cluster memory usage percent
---
---
# Source: metric-expression-cluster/templates/expressioncontainer.yaml
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: container-cpu-cfs-throttled-seconds-sum-rate-details
labels:
app: metric-expression
component: container
details: "true"
graph: cpu-usage
level: project
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_cfs_throttled_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
container_name=~"$containerName"}[5m]))
legendFormat: CPU cfs throttled
description: container cpu cfs throttled seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: cpu-usage-seconds-sum-rate-details
labels:
app: metric-expression
component: container
details: "true"
graph: cpu-usage
level: project
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_usage_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
container_name=~"$containerName"}[5m]))
legendFormat: CPU usage
description: container cpu usage seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: container-cpu-system-seconds-sum-rate-details
labels:
app: metric-expression
component: container
details: "true"
graph: cpu-usage
level: project
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_system_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
container_name=~"$containerName"}[5m]))
legendFormat: CPU system seconds
description: container cpu system seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: container-cpu-user-seconds-sum-rate-details
labels:
app: metric-expression
component: container
details: "true"
graph: cpu-usage
level: project
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_user_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
container_name=~"$containerName"}[5m]))
legendFormat: CPU user seconds
description: container cpu user seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: container-memory-usage-bytes-sum-details
labels:
app: metric-expression
component: container
details: "true"
level: project
metric: memory-usage-bytes-sum
source: rancher-monitoring
spec:
expression: sum(container_memory_working_set_bytes{name!~"POD", namespace=~"$namespace",pod_name=~"$podName",
container_name=~"$containerName"})
legendFormat: Memory usage
description: container memory usage bytes sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: container-disk-io-writes-bytes-sum-rate-details
labels:
app: metric-expression
component: container
details: "true"
graph: disk-io
level: project
metric: disk-io-writes-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_fs_writes_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name=~"$containerName"}[5m]))
legendFormat: Write
description: container disk io writes bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: container-disk-io-reads-bytes-sum-rate-details
labels:
app: metric-expression
component: container
details: "true"
graph: disk-io
level: project
metric: disk-io-reads-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_fs_reads_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name=~"$containerName"}[5m]))
legendFormat: Read
description: container disk io reads bytes sum rate
---
---
# Source: metric-expression-cluster/templates/expressioncontrollermanager.yaml
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-volumes-depth
labels:
app: metric-expression
component: controllermanager
details: "false"
level: cluster
metric: volumes-depth
source: rancher-monitoring
spec:
expression: sum(volumes_depth)
legendFormat: Volumes depth
description: controllermanager volumes depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-volumes-depth-details
labels:
app: metric-expression
component: controllermanager
details: "true"
level: cluster
metric: volumes-depth
source: rancher-monitoring
spec:
expression: sum(volumes_depth) by (instance)
legendFormat: Volumes depth([[instance]])
description: controllermanager volumes depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-deployment-depth
labels:
app: metric-expression
component: controllermanager
details: "false"
level: cluster
metric: deployment-depth
source: rancher-monitoring
spec:
expression: sum(deployment_depth)
legendFormat: Deployment depth
description: controllermanager deployment adds
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-deployment-depth-details
labels:
app: metric-expression
component: controllermanager
details: "true"
level: cluster
metric: deployment-depth
source: rancher-monitoring
spec:
expression: sum(deployment_depth) by (instance)
legendFormat: Deployment depth([[instance]])
description: controllermanager deployment adds
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-replicaset-depth
labels:
app: metric-expression
component: controllermanager
details: "false"
level: cluster
metric: replicaset-depth
source: rancher-monitoring
spec:
expression: sum(replicaset_depth)
legendFormat: Replicaset depth
description: controllermanager replicaset depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-replicaset-depth-details
labels:
app: metric-expression
component: controllermanager
details: "true"
level: cluster
metric: replicaset-depth
source: rancher-monitoring
spec:
expression: sum(replicaset_depth) by (instance)
legendFormat: Replicaset depth([[instance]])
description: controllermanager replicaset depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-service-depth
labels:
app: metric-expression
component: controllermanager
details: "false"
level: cluster
metric: service-depth
source: rancher-monitoring
spec:
expression: sum(service_depth)
legendFormat: Service depth
description: controllermanager service depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-service-depth-details
labels:
app: metric-expression
component: controllermanager
details: "true"
level: cluster
metric: service-depth
source: rancher-monitoring
spec:
expression: sum(service_depth) by (instance)
legendFormat: Service depth([[instance]])
description: controllermanager service depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-serviceaccount-depth
labels:
app: metric-expression
component: controllermanager
details: "false"
level: cluster
metric: serviceaccount-depth
source: rancher-monitoring
spec:
expression: sum(serviceaccount_depth)
legendFormat: Serviceaccount depth
description: controllermanager serviceaccount depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-serviceaccount-depth-details
labels:
app: metric-expression
component: controllermanager
details: "true"
level: cluster
metric: serviceaccount-depth
source: rancher-monitoring
spec:
expression: sum(serviceaccount_depth) by (instance)
legendFormat: Serviceaccount depth([[instance]])
description: controllermanager serviceaccount depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-endpoint-depth
labels:
app: metric-expression
component: controllermanager
details: "false"
level: cluster
metric: endpoint-depth
source: rancher-monitoring
spec:
expression: sum(endpoint_depth)
legendFormat: Endpoint depth
description: controllermanager endpoint depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-endpoint-depth-details
labels:
app: metric-expression
component: controllermanager
details: "true"
level: cluster
metric: endpoint-depth
source: rancher-monitoring
spec:
expression: sum(endpoint_depth) by (instance)
legendFormat: Endpoint depth([[instance]])
description: controllermanager endpoint depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-daemonset-depth
labels:
app: metric-expression
component: controllermanager
details: "false"
level: cluster
metric: daemonset-depth
source: rancher-monitoring
spec:
expression: sum(daemonset_depth)
legendFormat: Daemonset depth
description: controllermanager daemonset depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-daemonset-depth-details
labels:
app: metric-expression
component: controllermanager
details: "true"
level: cluster
metric: daemonset-depth
source: rancher-monitoring
spec:
expression: sum(daemonset_depth) by (instance)
legendFormat: Daemonset depth([[instance]])
description: controllermanager daemonset depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-deployment-depth
labels:
app: metric-expression
component: controllermanager
details: "false"
level: cluster
metric: deployment-depth
source: rancher-monitoring
spec:
expression: sum(deployment_depth)
legendFormat: Deployment depth
description: controllermanager deployment depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-deployment-depth-details
labels:
app: metric-expression
component: controllermanager
details: "true"
level: cluster
metric: deployment-depth
source: rancher-monitoring
spec:
expression: sum(deployment_depth) by (instance)
legendFormat: Deployment depth([[instance]])
description: controllermanager deployment depth
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-statefulset-depth
labels:
app: metric-expression
component: controllermanager
details: "false"
level: cluster
metric: statefulset-depth
source: rancher-monitoring
spec:
expression: sum(statefulset_depth)
legendFormat: Statefulset depth
description: controllermanager statefulset adds
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-statefulset-depth-details
labels:
app: metric-expression
component: controllermanager
details: "true"
level: cluster
metric: statefulset-depth
source: rancher-monitoring
spec:
expression: sum(statefulset_depth) by (instance)
legendFormat: Statefulset depth([[instance]])
description: controllermanager statefulset adds
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-replicationmanager-depth
labels:
app: metric-expression
component: controllermanager
details: "false"
level: cluster
metric: replicationmanager-depth
source: rancher-monitoring
spec:
expression: sum(replicationmanager_depth)
legendFormat: ReplicationManager depth
description: controllermanager replicationmanager adds
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: controllermanager-replicationmanager-depth-details
labels:
app: metric-expression
component: controllermanager
details: "true"
level: cluster
metric: replicationmanager-depth
source: rancher-monitoring
spec:
expression: sum(replicationmanager_depth) by (instance)
legendFormat: ReplicationManager depth([[instance]])
description: controllermanager replicationmanager adds
---
---
# Source: metric-expression-cluster/templates/expressionetcd.yaml
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-failed-proposal
labels:
app: metric-expression
component: etcd
details: "false"
level: cluster
metric: server-failed-proposal
source: rancher-monitoring
spec:
expression: sum(etcd_server_proposals_failed_total)
legendFormat: Failed proposal
description: etcd Server failed proposal
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-failed-proposal-details
labels:
app: metric-expression
component: etcd
details: "true"
level: cluster
metric: server-failed-proposal
source: rancher-monitoring
spec:
expression: sum(etcd_server_proposals_failed_total)
legendFormat: Failed proposal
description: etcd Server failed proposal
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-leader-changes-seen-sum-increase
labels:
app: metric-expression
component: etcd
details: "false"
level: cluster
metric: server-leader-changes-seen-sum-increase
source: rancher-monitoring
spec:
expression: max(etcd_server_leader_changes_seen_total)
legendFormat: Number of leader changes per hour
description: etcd server leader changes seen sum increase
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-leader-changes-seen-sum-increase-details
labels:
app: metric-expression
component: etcd
details: "true"
level: cluster
metric: server-leader-changes-seen-sum-increase
source: rancher-monitoring
spec:
expression: max(etcd_server_leader_changes_seen_total)
legendFormat: Number of leader changes per hour
description: etcd server leader changes seen sum increase
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-grpc-client-receive-bytes-sum-rate
labels:
app: metric-expression
component: etcd
details: "false"
graph: rpc-client-traffic
level: cluster
metric: grpc-client-receive-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(etcd_network_client_grpc_received_bytes_total[5m]))
legendFormat: Client traffic in
description: etcd grpc client receive bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-grpc-client-receive-bytes-sum-rate-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: rpc-client-traffic
level: cluster
metric: grpc-client-receive-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(etcd_network_client_grpc_received_bytes_total[5m])) by (instance)
legendFormat: Client traffic in([[instance]])
description: etcd grpc client receive bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-db-bytes-sum
labels:
app: metric-expression
component: etcd
details: "false"
level: cluster
metric: db-bytes-sum
source: rancher-monitoring
spec:
expression: sum(etcd_debugging_mvcc_db_total_size_in_bytes)
legendFormat: DB size
description: etcd db bytes sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-db-bytes-sum-details
labels:
app: metric-expression
component: etcd
details: "true"
level: cluster
metric: db-bytes-sum
source: rancher-monitoring
spec:
expression: sum(etcd_debugging_mvcc_db_total_size_in_bytes) by (instance)
legendFormat: DB size([[instance]])
description: etcd db bytes sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-grpc-client-transmit-bytes-sum-rate
labels:
app: metric-expression
component: etcd
details: "false"
graph: rpc-client-traffic
level: cluster
metric: grpc-client-transmit-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(etcd_network_client_grpc_sent_bytes_total[5m]))
legendFormat: Client traffic out
description: etcd grpc client transmit bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-grpc-client-transmit-bytes-sum-rate-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: rpc-client-traffic
level: cluster
metric: grpc-client-transmit-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(etcd_network_client_grpc_sent_bytes_total[5m])) by (instance)
legendFormat: Client traffic out([[instance]])
description: etcd grpc client transmit bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-leader-sum
labels:
app: metric-expression
component: etcd
details: "false"
level: cluster
metric: server-leader-sum
source: rancher-monitoring
spec:
expression: max(etcd_server_has_leader)
legendFormat: Has leader
description: etcd server leader sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-leader-sum-details
labels:
app: metric-expression
component: etcd
details: "true"
level: cluster
metric: server-leader-sum
source: rancher-monitoring
spec:
expression: max(etcd_server_has_leader)
legendFormat: Has leader
description: etcd server leader sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-proposals-committed-sum-increase
labels:
app: metric-expression
component: etcd
details: "false"
graph: proposal
level: cluster
metric: server-proposals-committed-sum-increase
source: rancher-monitoring
spec:
expression: sum(increase(etcd_server_proposals_committed_total[5m]))
legendFormat: Proposal commit rate
description: etcd server proposals committed sum increase
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-proposals-committed-sum-increase-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: proposal
level: cluster
metric: server-proposals-committed-sum-increase
source: rancher-monitoring
spec:
expression: sum(increase(etcd_server_proposals_committed_total[5m])) by (instance)
legendFormat: Proposal commit rate([[instance]])
description: etcd server proposals committed sum increase
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-proposals-applied-sum-increase
labels:
app: metric-expression
component: etcd
details: "false"
graph: proposal
level: cluster
metric: server-proposals-applied-sum-increase
source: rancher-monitoring
spec:
expression: sum(increase(etcd_server_proposals_applied_total[5m]))
legendFormat: Proposal applied
description: etcd server proposals applied sum increase
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-proposals-applied-sum-increase-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: proposal
level: cluster
metric: server-proposals-applied-sum-increase
source: rancher-monitoring
spec:
expression: sum(increase(etcd_server_proposals_applied_total[5m])) by (instance)
legendFormat: Proposal applied([[instance]])
description: etcd server proposals applied sum increase
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-proposals-failed-sum-increase
labels:
app: metric-expression
component: etcd
details: "false"
graph: proposal
level: cluster
metric: server-proposals-failed-sum-increase
source: rancher-monitoring
spec:
expression: sum(increase(etcd_server_proposals_failed_total[5m]))
legendFormat: Proposal failed
description: etcd server proposals failed sum increase
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-proposals-failed-sum-increase-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: proposal
level: cluster
metric: server-proposals-failed-sum-increase
source: rancher-monitoring
spec:
expression: sum(increase(etcd_server_proposals_failed_total[5m])) by (instance)
legendFormat: Proposal failed([[instance]])
description: etcd server proposals failed sum increase
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-proposals-pending-sum-increase
labels:
app: metric-expression
component: etcd
details: "false"
graph: proposal
level: cluster
metric: server-proposals-pending-sum-increase
source: rancher-monitoring
spec:
expression: sum(increase(etcd_server_proposals_pending[5m]))
legendFormat: Proposal pending
description: etcd server proposals pending sum increase
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-server-proposals-pending-sum-increase-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: proposal
level: cluster
metric: server-proposals-pending-sum-increase
source: rancher-monitoring
spec:
expression: sum(increase(etcd_server_proposals_pending[5m])) by (instance)
legendFormat: Proposal pending([[instance]])
description: etcd server proposals pending sum increase
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-disk-wal-fsync-duration-seconds-sum-quantile
labels:
app: metric-expression
component: etcd
details: "false"
graph: sync-duration
level: cluster
metric: disk-wal-fsync-duration-seconds-sum-quantile
source: rancher-monitoring
spec:
expression: sum(histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])) by (instance, le)))
legendFormat: WAL fsync
description: etcd disk wal fsync duration seconds sum quantile
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-disk-wal-fsync-duration-seconds-sum-quantile-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: sync-duration
level: cluster
metric: disk-wal-fsync-duration-seconds-sum-quantile
source: rancher-monitoring
spec:
expression: histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket[5m])) by (instance, le))
legendFormat: WAL fsync([[instance]])
description: etcd disk wal fsync duration seconds sum quantile
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-grpc-request-error-percent
labels:
app: metric-expression
component: etcd
details: "false"
level: cluster
metric: grpc-request-error-percent
source: rancher-monitoring
spec:
expression: sum(rate(grpc_server_handled_total{grpc_code!="OK"}[5m])) / sum(rate(grpc_server_handled_total[5m]))
legendFormat: Rpc failed rate
description: etcd grpc request error percent
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-grpc-request-error-percent-details
labels:
app: metric-expression
component: etcd
details: "true"
level: cluster
metric: grpc-request-error-percent
source: rancher-monitoring
spec:
expression: sum(rate(grpc_server_handled_total{grpc_code!="OK"}[5m])) by (instance)
/ sum(rate(grpc_server_handled_total[5m])) by (instance)
legendFormat: RPC failed rate([[instance]])
description: etcd grpc request error percent
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-disk-commit-duration-seconds-sum-quantile
labels:
app: metric-expression
component: etcd
details: "false"
graph: sync-duration
level: cluster
metric: disk-commit-duration-seconds-sum-quantile
source: rancher-monitoring
spec:
expression: sum(histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])) by (instance, le)))
legendFormat: DB fsync
description: etcd disk commit duration seconds sum quantile
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-disk-commit-duration-seconds-sum-quantile-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: sync-duration
level: cluster
metric: disk-commit-duration-seconds-sum-quantile
source: rancher-monitoring
spec:
expression: histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket[5m])) by (instance, le))
legendFormat: DB fsync([[instance]])
description: etcd disk commit duration seconds sum quantile
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-grpc-request-slow-quantile
labels:
app: metric-expression
component: etcd
details: "false"
level: cluster
metric: grpc-request-slow-quantile
source: rancher-monitoring
spec:
expression: sum(histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{grpc_service=~"etcdserverpb.*",grpc_type="unary"}[5m])) by (instance,le)))
legendFormat: Request slow"
description: etcd grpc request slow quantile
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-grpc-request-slow-quantile-details
labels:
app: metric-expression
component: etcd
details: "true"
level: cluster
metric: grpc-request-slow-quantile
source: rancher-monitoring
spec:
expression: histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{grpc_service=~"etcdserverpb.*",grpc_type="unary"}[5m])) by (instance,le))
legendFormat: Request slow([[instance]])
description: etcd grpc request slow quantile
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-active-watch-stream
labels:
app: metric-expression
component: etcd
details: "false"
graph: etcd-stream
level: cluster
metric: active-watch-stream
source: rancher-monitoring
spec:
expression: sum(grpc_server_started_total{grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"})
- sum(grpc_server_handled_total{grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"})
legendFormat: Watch streams
description: Etcd watch stream
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-active-watch-stream-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: etcd-stream
level: cluster
metric: active-watch-stream
source: rancher-monitoring
spec:
expression: sum(grpc_server_started_total{grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"})
by (instance) - sum(grpc_server_handled_total{grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"})
by (instance)
legendFormat: Watch streams([[instance]])
description: Etcd watch stream
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-lease-watch-stream
labels:
app: metric-expression
component: etcd
details: "false"
graph: etcd-stream
level: cluster
metric: lease-watch-stream
source: rancher-monitoring
spec:
expression: sum(grpc_server_started_total{grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"})
- sum(grpc_server_handled_total{grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"})
legendFormat: Lease watch stream
description: Etcd lease stream
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-lease-watch-stream-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: etcd-stream
level: cluster
metric: lease-watch-stream
source: rancher-monitoring
spec:
expression: sum(grpc_server_started_total{grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"})
by (instance) - sum(grpc_server_handled_total{grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"})
by (instance)
legendFormat: Lease watch stream([[instance]])
description: Etcd lease stream
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-peer-traffic-in
labels:
app: metric-expression
component: etcd
details: "false"
graph: etcd-peer-traffic
level: cluster
metric: peer-traffic-in
source: rancher-monitoring
spec:
expression: sum(rate(etcd_network_peer_received_bytes_total[5m]))
legendFormat: Traffic in"
description: Etcd peer traffic in
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-peer-traffic-in-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: etcd-peer-traffic
level: cluster
metric: peer-traffic-in
source: rancher-monitoring
spec:
expression: sum(rate(etcd_network_peer_received_bytes_total[5m])) by (instance)
legendFormat: Traffic in([[instance]])
description: Etcd peer traffic in
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-peer-traffic-out
labels:
app: metric-expression
component: etcd
details: "false"
graph: etcd-peer-traffic
level: cluster
metric: peer-traffic-out
source: rancher-monitoring
spec:
expression: sum(rate(etcd_network_peer_sent_bytes_total[5m]))
legendFormat: Traffic out"
description: Etcd peer traffic out
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-peer-traffic-out-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: etcd-peer-traffic
level: cluster
metric: peer-traffic-out
source: rancher-monitoring
spec:
expression: sum(rate(etcd_network_peer_sent_bytes_total[5m])) by (instance)
legendFormat: Traffic out([[instance]])
description: Etcd peer traffic out
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-rpc-rate
labels:
app: metric-expression
component: etcd
details: "false"
graph: rpc-rate
level: cluster
source: rancher-monitoring
spec:
expression: sum(rate(grpc_server_started_total{grpc_type="unary"}[5m]))
legendFormat: RPC rate
description: rpc-rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-rpc-rate-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: rpc-rate
level: cluster
source: rancher-monitoring
spec:
expression: sum(rate(grpc_server_started_total{grpc_type="unary"}[5m])) by (instance)
legendFormat: Rpc rate([[instance]])
description: rpc-rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-rpc-rate-failed
labels:
app: metric-expression
component: etcd
details: "false"
graph: rpc-rate
level: cluster
source: rancher-monitoring
spec:
expression: sum(rate(grpc_server_handled_total{grpc_type="unary",grpc_code!="OK"}[5m]))
legendFormat: Rpc failed rate
description: rpc-rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-rpc-rate-failed-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: rpc-rate
level: cluster
source: rancher-monitoring
spec:
expression: sum(rate(grpc_server_handled_total{grpc_type="unary",grpc_code!="OK"}[5m])) by (instance)
legendFormat: Rpc failed rate([[instance]])
description: rpc-rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-latency-distributions-of-commit-called-by-backend
labels:
app: metric-expression
component: etcd
details: "false"
graph: disk-operate
level: cluster
source: rancher-monitoring
spec:
expression: sum(rate(etcd_disk_backend_commit_duration_seconds_sum[1m]))
legendFormat: Commit latency called by backend
description: The latency distributions of commit called by backend
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-latency-distributions-of-commit-called-by-backend-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: disk-operate
level: cluster
source: rancher-monitoring
spec:
expression: sum(rate(etcd_disk_backend_commit_duration_seconds_sum[1m])) by (instance)
legendFormat: Commit latency called by backend([[instance]])
description: The latency distributions of commit called by backend
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-latency-distributions-of-fsync-called-by-wal
labels:
app: metric-expression
component: etcd
details: "false"
graph: disk-operate
level: cluster
source: rancher-monitoring
spec:
expression: sum(rate(etcd_disk_wal_fsync_duration_seconds_sum[1m]))
legendFormat: Fsync latency called by wal
description: The latency distributions of fsync called by wal
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: etcd-latency-distributions-of-fsync-called-by-wal-details
labels:
app: metric-expression
component: etcd
details: "true"
graph: disk-operate
level: cluster
source: rancher-monitoring
spec:
expression: sum(rate(etcd_disk_wal_fsync_duration_seconds_sum[1m])) by (instance)
legendFormat: Fsync latency called by wal([[instance]])
description: The latency distributions of fsync called by wal
---
---
# Source: metric-expression-cluster/templates/expressionfluentd.yaml
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: input-record-number
labels:
app: metric-expression
component: fluentd
details: "false"
level: cluster
metric: input-record
source: rancher-monitoring
spec:
expression: sum(rate(fluentd_input_status_num_records_total[5m]))
legendFormat: Input record number
description: Fluentd input status num records total
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: input-record-number-details
labels:
app: metric-expression
component: fluentd
details: "true"
level: cluster
metric: input-record
source: rancher-monitoring
spec:
expression: sum(rate(fluentd_input_status_num_records_total[5m])) by (instance)
legendFormat: Input record number([[instance]])
description: Fluentd input status num records total
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: output-record-number
labels:
app: metric-expression
component: fluentd
details: "false"
level: cluster
metric: output-record
source: rancher-monitoring
spec:
expression: sum(rate(fluentd_output_status_num_records_total[5m]))
legendFormat: Output record number
description: Fluentd output status num records total
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: output-record-number-details
labels:
app: metric-expression
component: fluentd
details: "true"
level: cluster
metric: output-record
source: rancher-monitoring
spec:
expression: sum(rate(fluentd_output_status_num_records_total[5m])) by (instance)
legendFormat: Output record number([[instance]])
description: Fluentd output status num records total
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: output-errors
labels:
app: metric-expression
component: fluentd
details: "false"
level: cluster
metric: output-errors
source: rancher-monitoring
spec:
expression: sum(rate(fluentd_output_status_num_errors[5m]))
legendFormat: Plugin Output errors
description: Fluentd output errors number
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: output-errors-details
labels:
app: metric-expression
component: fluentd
details: "true"
level: cluster
metric: output-errors
source: rancher-monitoring
spec:
expression: sum(rate(fluentd_output_status_num_errors[5m])) by (type)
legendFormat: Plugin([[type]])
description: Fluentd output errors number
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: buffer-queue-length
labels:
app: metric-expression
component: fluentd
details: "false"
level: cluster
metric: buffer-queue-length
source: rancher-monitoring
spec:
expression: sum(rate(fluentd_output_status_buffer_queue_length[5m]))
legendFormat: Buffer queue
description: Fluentd Buffer queue length
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: buffer-queue-length-details
labels:
app: metric-expression
component: fluentd
details: "true"
level: cluster
metric: buffer-queue-length
source: rancher-monitoring
spec:
expression: sum(rate(fluentd_output_status_buffer_queue_length[5m])) by (instance)
legendFormat: '[[instance]]'
description: Fluentd Buffer queue length
---
---
# Source: metric-expression-cluster/templates/expressioningresscontroller.yaml
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-connection-reading
labels:
app: metric-expression
component: ingresscontroller
details: "false"
graph: nginx-connection
level: cluster
source: rancher-monitoring
spec:
expression: sum(nginx_ingress_controller_nginx_process_connections{state="reading"})
legendFormat: Reading
description: ingresscontroller nginx connection reading
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-connection-reading-details
labels:
app: metric-expression
component: ingresscontroller
details: "true"
graph: nginx-connection
level: cluster
source: rancher-monitoring
spec:
expression: sum(nginx_ingress_controller_nginx_process_connections{state="reading"}) by (instance)
legendFormat: Reading([[instance]])
description: ingresscontroller nginx connection reading
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-connection-waiting
labels:
app: metric-expression
component: ingresscontroller
details: "false"
graph: nginx-connection
level: cluster
source: rancher-monitoring
spec:
expression: sum(nginx_ingress_controller_nginx_process_connections{state="waiting"})
legendFormat: Waiting
description: ingresscontroller nginx connection waiting
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-connection-waiting-details
labels:
app: metric-expression
component: ingresscontroller
details: "true"
graph: nginx-connection
level: cluster
source: rancher-monitoring
spec:
expression: sum(nginx_ingress_controller_nginx_process_connections{state="waiting"}) by (instance)
legendFormat: Waiting([[instance]])
description: ingresscontroller nginx connection waiting
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-connection-writing
labels:
app: metric-expression
component: ingresscontroller
details: "false"
graph: nginx-connection
level: cluster
source: rancher-monitoring
spec:
expression: sum(nginx_ingress_controller_nginx_process_connections{state="writing"})
legendFormat: Writing
description: ingresscontroller nginx connection writing
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-connection-writing-details
labels:
app: metric-expression
component: ingresscontroller
details: "true"
graph: nginx-connection
level: cluster
source: rancher-monitoring
spec:
expression: sum(nginx_ingress_controller_nginx_process_connections{state="writing"}) by (instance)
legendFormat: Writing([[instance]])
description: ingresscontroller nginx connection writing
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-connection-accepted
labels:
app: metric-expression
component: ingresscontroller
details: "false"
graph: nginx-connection
level: cluster
source: rancher-monitoring
spec:
expression: sum(ceil(increase(nginx_ingress_controller_nginx_process_connections_total{state="accepted"}[5m])))
legendFormat: Accepted
description: ingresscontroller nginx connection accepted
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-connection-accepted-details
labels:
app: metric-expression
component: ingresscontroller
details: "true"
graph: nginx-connection
level: cluster
source: rancher-monitoring
spec:
expression: sum(ceil(increase(nginx_ingress_controller_nginx_process_connections_total{state="accepted"}[5m]))) by (instance)
legendFormat: Accepted([[instance]])
description: ingresscontroller nginx connection accepted
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-connection-active
labels:
app: metric-expression
component: ingresscontroller
details: "false"
graph: nginx-connection
level: cluster
source: rancher-monitoring
spec:
expression: sum(ceil(increase(nginx_ingress_controller_nginx_process_connections_total{state="active"}[5m])))
legendFormat: Active
description: ingresscontroller nginx connection active
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-connection-active-details
labels:
app: metric-expression
component: ingresscontroller
details: "true"
graph: nginx-connection
level: cluster
source: rancher-monitoring
spec:
expression: sum(ceil(increase(nginx_ingress_controller_nginx_process_connections_total{state="active"}[5m]))) by (instance)
legendFormat: Active([[instance]])
description: ingresscontroller nginx connection active
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-connection-handled
labels:
app: metric-expression
component: ingresscontroller
details: "false"
graph: nginx-connection
level: cluster
source: rancher-monitoring
spec:
expression: sum(ceil(increase(nginx_ingress_controller_nginx_process_connections_total{state="handled"}[5m])))
legendFormat: Handled
description: ingresscontroller nginx connection handled
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-connection-handled-details
labels:
app: metric-expression
component: ingresscontroller
details: "true"
graph: nginx-connection
level: cluster
source: rancher-monitoring
spec:
expression: sum(ceil(increase(nginx_ingress_controller_nginx_process_connections_total{state="handled"}[5m]))) by (instance)
legendFormat: Handled([[instance]])
description: ingresscontroller nginx connection handled
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-process-seconds-by-host
labels:
app: metric-expression
component: ingresscontroller
details: "false"
level: cluster
metric: request-process-seconds
source: rancher-monitoring
spec:
expression: topk(10, histogram_quantile(0.95,sum by (le, host)(rate(nginx_ingress_controller_request_duration_seconds_bucket{host!="_"}[5m]))))
legendFormat: Request duration(host:[[host]])
description: top 10 ingresscontroller nginx request duration by host
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: ingresscontroller-nginx-process-seconds-by-host-details
labels:
app: metric-expression
component: ingresscontroller
details: "true"
level: cluster
metric: request-process-seconds
source: rancher-monitoring
spec:
expression: topk(10, histogram_quantile(0.95,sum by (le, host, path)(rate(nginx_ingress_controller_request_duration_seconds_bucket{host!="_"}[5m]))))
legendFormat: Request duration(host:[[host]] path:[[path]])
description: top 10 ingresscontroller nginx request duration by path
---
---
# Source: metric-expression-cluster/templates/expressionnode.yaml
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-transmit-bytes-sum-rate
labels:
app: metric-expression
component: node
details: "false"
graph: network-io
level: cluster
metric: network-transmit-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
legendFormat: Transmit
description: node network transmit bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-transmit-bytes-sum-rate-details
labels:
app: metric-expression
component: node
details: "true"
graph: network-io
level: cluster
metric: network-transmit-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
by (device)
legendFormat: 'Transmit([[device]])'
description: node network transmit bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-receive-packets-dropped-sum-rate
labels:
app: metric-expression
component: node
details: "false"
graph: network-packet
level: cluster
metric: network-receive-packets-dropped-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
legendFormat: Receive packets
description: node network receive packets dropped sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-receive-packets-dropped-sum-rate-details
labels:
app: metric-expression
component: node
details: "true"
graph: network-packet
level: cluster
metric: network-receive-packets-dropped-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
by (device)
legendFormat: Receive packets([[device]])
description: node network receive packets dropped sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-transmit-packets-sum-rate
labels:
app: metric-expression
component: node
details: "false"
graph: network-packet
level: cluster
metric: network-transmit-packets-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
legendFormat: Transmit packets
description: node network transmit packets sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-transmit-packets-sum-rate-details
labels:
app: metric-expression
component: node
details: "true"
graph: network-packet
level: cluster
metric: network-transmit-packets-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
by (device)
legendFormat: Transmit packets([[device]])
description: node network transmit packets sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-disk-io-writes-bytes-sum-rate
labels:
app: metric-expression
component: node
details: "false"
graph: disk-io
level: cluster
metric: disk-io-writes-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_disk_written_bytes_total{instance=~"$instance"}[5m]))
legendFormat: Write
description: node disk io writes bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-disk-io-writes-bytes-sum-rate-details
labels:
app: metric-expression
component: node
details: "true"
graph: disk-io
level: cluster
metric: disk-io-writes-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_disk_written_bytes_total{instance=~"$instance"}[5m]))
by (device)
legendFormat: Write([[device]])
description: node disk io writes bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-disk-io-reads-bytes-sum-rate
labels:
app: metric-expression
component: node
details: "false"
graph: disk-io
level: cluster
metric: disk-io-reads-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_disk_read_bytes_total{instance=~"$instance"}[5m]))
legendFormat: Read
description: node disk io reads bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-disk-io-reads-bytes-sum-rate-details
labels:
app: metric-expression
component: node
details: "true"
graph: disk-io
level: cluster
metric: disk-io-reads-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_disk_read_bytes_total{instance=~"$instance"}[5m])) by
(device)
legendFormat: Read([[device]])
description: node disk io reads bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-fs-usage-percent
labels:
app: metric-expression
component: node
details: "false"
level: cluster
metric: fs-usage-percent
source: rancher-monitoring
spec:
expression: (sum(node_filesystem_size_bytes{device!="rootfs",instance=~"$instance"})
- sum(node_filesystem_free_bytes{device!="rootfs",instance=~"$instance"})
) / sum(node_filesystem_size_bytes{device!="rootfs",instance=~"$instance"})
legendFormat: Disk usage
description: node fs usage percent
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-fs-usage-percent-details
labels:
app: metric-expression
component: node
details: "true"
level: cluster
metric: fs-usage-percent
source: rancher-monitoring
spec:
expression: (sum(node_filesystem_size_bytes{device!="rootfs",instance=~"$instance"})
by (device) - sum(node_filesystem_free_bytes{device!="rootfs",instance=~"$instance"})
by (device)) / sum(node_filesystem_size_bytes{device!="rootfs",instance=~"$instance"})
by (device)
legendFormat: '[[device]]'
description: node fs usage percent
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-receive-packets-sum-rate
labels:
app: metric-expression
component: node
details: "false"
graph: network-packet
level: cluster
metric: network-receive-packets-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
legendFormat: Receive packets
description: node network receive packets sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-receive-packets-sum-rate-details
labels:
app: metric-expression
component: node
details: "true"
graph: network-packet
level: cluster
metric: network-receive-packets-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_packets_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
by (device)
legendFormat: Receive packets([[device]])
description: node network receive packets sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-transmit-errors-sum-rate
labels:
app: metric-expression
component: node
details: "false"
graph: network-packet
level: cluster
metric: network-transmit-errors-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
legendFormat: Transmit errors
description: node network transmit errors sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-transmit-errors-sum-rate-details
labels:
app: metric-expression
component: node
details: "true"
graph: network-packet
level: cluster
metric: network-transmit-errors-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
by (device)
legendFormat: Transmit errors([[device]])
description: node network transmit errors sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-cpu-load-1
labels:
app: metric-expression
component: node
details: "false"
graph: cpu-load
level: cluster
metric: cpu-load-1
source: rancher-monitoring
spec:
expression: sum(node_load1{instance=~"$instance"}) / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
legendFormat: Load1
description: node cpu load 1
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-cpu-load-1-details
labels:
app: metric-expression
component: node
details: "true"
graph: cpu-load
level: cluster
metric: cpu-load-1
source: rancher-monitoring
spec:
expression: sum(node_load1{instance=~"$instance"}) / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
legendFormat: Load1
description: node cpu load 1
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-cpu-load-15
labels:
app: metric-expression
component: node
details: "false"
graph: cpu-load
level: cluster
metric: cpu-load-15
source: rancher-monitoring
spec:
expression: sum(node_load15{instance=~"$instance"}) / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
legendFormat: Load15
description: node cpu load 15
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-cpu-load-15-details
labels:
app: metric-expression
component: node
details: "true"
graph: cpu-load
level: cluster
metric: cpu-load-15
source: rancher-monitoring
spec:
expression: sum(node_load15{instance=~"$instance"}) / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
legendFormat: Load15
description: node cpu load 15
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-cpu-usage-seconds-sum-rate
labels:
app: metric-expression
component: node
details: "false"
level: cluster
metric: cpu-usage-seconds-sum-rate
source: rancher-monitoring
spec:
expression: 1 - (avg(irate(node_cpu_seconds_total{mode="idle", instance=~"$instance"}[5m])) by (instance))
legendFormat: CPU
description: node cpu usage seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-cpu-usage-seconds-sum-rate-details
labels:
app: metric-expression
component: node
details: "true"
level: cluster
metric: cpu-usage-seconds-sum-rate
source: rancher-monitoring
spec:
expression: avg(irate(node_cpu_seconds_total{mode!="idle", instance=~"$instance"}[5m]))by (mode)
legendFormat: '[[mode]]'
description: node cpu usage seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-memory-usage-percent
labels:
app: metric-expression
component: node
details: "false"
level: cluster
metric: memory-usage-percent
source: rancher-monitoring
spec:
expression: 1 - sum(node_memory_MemAvailable_bytes{instance=~"$instance"})
/ sum(node_memory_MemTotal_bytes{instance=~"$instance"})
legendFormat: Memory usage
description: node memory usage percent
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-memory-usage-percent-details
labels:
app: metric-expression
component: node
details: "true"
level: cluster
metric: memory-usage-percent
source: rancher-monitoring
spec:
expression: 1 - sum(node_memory_MemAvailable_bytes{instance=~"$instance"})
/ sum(node_memory_MemTotal_bytes{instance=~"$instance"})
legendFormat: Memory usage
description: node memory usage percent
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-receive-bytes-sum-rate
labels:
app: metric-expression
component: node
details: "false"
graph: network-io
level: cluster
metric: network-receive-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
legendFormat: Receive
description: node network receive bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-receive-bytes-sum-rate-details
labels:
app: metric-expression
component: node
details: "true"
graph: network-io
level: cluster
metric: network-receive-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_bytes_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
by (device)
legendFormat: Receive([[device]])
description: node network receive bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-receive-errors-sum-rate
labels:
app: metric-expression
component: node
details: "false"
graph: network-packet
level: cluster
metric: network-receive-errors-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
legendFormat: Receive packets
description: node network receive errors sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-receive-errors-sum-rate-details
labels:
app: metric-expression
component: node
details: "true"
graph: network-packet
level: cluster
metric: network-receive-errors-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_receive_errs_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
by (device)
legendFormat: Receive packets([[device]])
description: node network receive errors sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-cpu-load-5
labels:
app: metric-expression
component: node
details: "false"
graph: cpu-load
level: cluster
metric: cpu-load-5
source: rancher-monitoring
spec:
expression: sum(node_load5{instance=~"$instance"}) / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
legendFormat: Load5
description: node cpu load 5
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-cpu-load-5-details
labels:
app: metric-expression
component: node
details: "true"
graph: cpu-load
level: cluster
metric: cpu-load-5
source: rancher-monitoring
spec:
expression: sum(node_load5{instance=~"$instance"}) / count(node_cpu_seconds_total{mode="system",instance=~"$instance"})
legendFormat: Load5
description: node cpu load 5
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-transmit-packets-dropped-sum-rate
labels:
app: metric-expression
component: node
details: "false"
graph: network-packet
level: cluster
metric: network-transmit-packets-dropped-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
legendFormat: Transmit dropped
description: node network transmit packets dropped sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: node-network-transmit-packets-dropped-sum-rate-details
labels:
app: metric-expression
component: node
details: "true"
graph: network-packet
level: cluster
metric: network-transmit-packets-dropped-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(node_network_transmit_drop_total{device!~"lo|veth.*|docker.*|flannel.*|cali.*|cbr.*",instance=~"$instance"}[5m]))
by (device)
legendFormat: Transmit dropped([[device]])
description: node network transmit packets dropped sum rate
---
---
# Source: metric-expression-cluster/templates/expressionpod.yaml
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-cpu-cfs-throttled-seconds-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: cpu-usage
level: project
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_cfs_throttled_seconds_total{container_name!="POD",namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: CPU cfs throttled
description: pod cpu cfs throttled seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-cpu-cfs-throttled-seconds-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: cpu-usage
level: project
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_cfs_throttled_seconds_total{container_name!="POD",namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (container_name)
legendFormat: CPU cfs throttled([[container_name]])
description: pod cpu cfs throttled seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-fs-bytes-sum
labels:
app: metric-expression
component: pod
details: "false"
level: project
metric: fs-bytes-sum
source: rancher-monitoring
spec:
expression: sum(container_fs_usage_bytes{namespace=~"$namespace", pod_name=~"$podName",
container_name!=""})
legendFormat: Filesystem usage
description: pod fs bytes sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-fs-bytes-sum-details
labels:
app: metric-expression
component: pod
details: "true"
level: project
metric: fs-bytes-sum
source: rancher-monitoring
spec:
expression: sum(container_fs_usage_bytes{namespace=~"$namespace", pod_name=~"$podName",
container_name!=""}) by (container_name)
legendFormat: Filesystem usage([[container_name]])
description: pod fs bytes sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-receive-packets-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: network-packet
level: project
metric: network-receive-packets-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_packets_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Receive packets
description: pod network receive packets sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-receive-packets-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: network-packet
level: project
metric: network-receive-packets-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_packets_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Receive packets
description: pod network receive packets sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-transmit-packets-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: network-packet
level: project
metric: network-transmit-packets-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_packets_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Transmit packets
description: pod network transmit packets sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-transmit-packets-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: network-packet
level: project
metric: network-transmit-packets-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_packets_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Transmit packets
description: pod network transmit packets sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-cpu-user-seconds-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: cpu-usage
level: project
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_user_seconds_total{container_name!="POD",namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: CPU user seconds
description: pod cpu user seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-cpu-user-seconds-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: cpu-usage
level: project
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_user_seconds_total{container_name!="POD",namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (container_name)
legendFormat: CPU user seconds([[container_name]])
description: pod cpu user seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-disk-io-reads-bytes-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: disk-io
level: project
metric: disk-io-reads-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_fs_reads_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Read
description: pod disk io reads bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-disk-io-reads-bytes-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: disk-io
level: project
metric: disk-io-reads-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_fs_reads_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (container_name)
legendFormat: Read([[container_name]])
description: pod disk io reads bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-receive-bytes-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: network-io
level: project
metric: network-receive-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Receive
description: pod network receive bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-receive-bytes-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: network-io
level: project
metric: network-receive-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Receive
description: pod network receive bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-transmit-bytes-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: network-io
level: project
metric: network-transmit-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Transmit
description: pod network transmit bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-transmit-bytes-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: network-io
level: project
metric: network-transmit-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Transmit
description: pod network transmit bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-receive-packets-dropped-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: network-packet
level: project
metric: network-receive-packets-dropped-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Receive dropped
description: pod network receive packets dropped sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-receive-packets-dropped-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: network-packet
level: project
metric: network-receive-packets-dropped-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Receive dropped
description: pod network receive packets dropped sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-memory-usage-bytes-sum
labels:
app: metric-expression
component: pod
details: "false"
level: project
metric: memory-usage-bytes-sum
source: rancher-monitoring
spec:
expression: sum(container_memory_working_set_bytes{container_name!="POD",namespace=~"$namespace",pod_name=~"$podName",
container_name!=""})
legendFormat: Memory usage
description: pod memory usage bytes sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-memory-usage-bytes-sum-details
labels:
app: metric-expression
component: pod
details: "true"
level: project
metric: memory-usage-bytes-sum
source: rancher-monitoring
spec:
expression: sum(container_memory_working_set_bytes{container_name!="POD",namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}) by (container_name)
legendFormat: Memory usage([[container_name]])
description: pod memory usage bytes sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-disk-io-writes-bytes-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: disk-io
level: project
metric: disk-io-writes-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_fs_writes_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Write
description: pod disk io writes bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-disk-io-writes-bytes-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: disk-io
level: project
metric: disk-io-writes-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_fs_writes_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (container_name)
legendFormat: Write([[container_name]])
description: pod disk io writes bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-receive-errors-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: network-packet
level: project
metric: network-receive-errors-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_errors_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Receive errors
description: pod network receive errors sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-receive-errors-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: network-packet
level: project
metric: network-receive-errors-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_errors_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Receive errors
description: pod network receive errors sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-cpu-usage-seconds-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: cpu-usage
level: project
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_usage_seconds_total{container_name!="POD",namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: CPU usage
description: pod CPU usage sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-cpu-usage-seconds-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: cpu-usage
level: project
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_usage_seconds_total{container_name!="POD",namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (container_name)
legendFormat: CPU usage([[container_name]])
description: pod CPU usage sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-transmit-errors-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: network-packet
level: project
metric: network-transmit-errors-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_errors_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Transmit errors
description: pod network transmit errors sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-transmit-errors-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: network-packet
level: project
metric: network-transmit-errors-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_errors_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Transmit errors
description: pod network transmit errors sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-transmit-packets-dropped-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: network-packet
level: project
metric: network-transmit-packets-dropped-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Transmit dropped
description: pod network transmit packets dropped sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-network-transmit-packets-dropped-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: network-packet
level: project
metric: network-transmit-packets-dropped-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Transmit dropped
description: pod network transmit packets dropped sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-cpu-system-seconds-sum-rate
labels:
app: metric-expression
component: pod
details: "false"
graph: cpu-usage
level: project
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_system_seconds_total{container_name!="POD",namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: CPU system seconds
description: pod cpu system seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: pod-cpu-system-seconds-sum-rate-details
labels:
app: metric-expression
component: pod
details: "true"
graph: cpu-usage
level: project
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_system_seconds_total{container_name!="POD",namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (container_name)
legendFormat: CPU system seconds([[container_name]])
description: pod cpu system seconds sum rate
---
---
# Source: metric-expression-cluster/templates/expressionscheduler.yaml
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: scheduler-e-2-e-scheduling-latency-seconds-quantile
labels:
app: metric-expression
component: scheduler
details: "false"
level: cluster
metric: e-2-e-scheduling-latency-seconds-quantile
source: rancher-monitoring
spec:
expression: sum(histogram_quantile(0.99, sum(scheduler_e2e_scheduling_latency_microseconds_bucket) by (le, instance)) / 1e+06)
legendFormat: E2E latency
description: scheduler e 2 e scheduling latency seconds quantile
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: scheduler-e-2-e-scheduling-latency-seconds-quantile-details
labels:
app: metric-expression
component: scheduler
details: "true"
level: cluster
metric: e-2-e-scheduling-latency-seconds-quantile
source: rancher-monitoring
spec:
expression: histogram_quantile(0.99, sum(scheduler_e2e_scheduling_latency_microseconds_bucket) by (le, instance)) / 1e+06
legendFormat: E2E latency([[instance]])
description: scheduler e 2 e scheduling latency seconds quantile
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: scheduler-total-preemption-attempts
labels:
app: metric-expression
component: scheduler
details: "false"
level: cluster
metric: total-preemption-attempts
source: rancher-monitoring
spec:
expression: sum(rate(scheduler_total_preemption_attempts[5m])) by (instance)
legendFormat: Preemption attempts
description: Scheduler scheduling algorithm latency seconds quantile
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: scheduler-total-preemption-attempts-details
labels:
app: metric-expression
component: scheduler
details: "true"
level: cluster
metric: total-preemption-attempts
source: rancher-monitoring
spec:
expression: sum(rate(scheduler_total_preemption_attempts[5m])) by (instance)
legendFormat: Preemption attempts([[instance]])
description: Scheduler scheduling algorithm latency seconds quantile
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: scheduler-pod-unscheduler
labels:
app: metric-expression
component: scheduler
details: "false"
level: cluster
metric: pod-unscheduler
source: rancher-monitoring
spec:
expression: sum(kube_pod_status_scheduled{condition="false"})
legendFormat: Scheduling failed pods
description: pod unscheduler
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: scheduler-pod-unscheduler-details
labels:
app: metric-expression
component: scheduler
details: "true"
level: cluster
metric: pod-unscheduler
source: rancher-monitoring
spec:
expression: sum(kube_pod_status_scheduled{condition="false"})
legendFormat: Scheduling failed pods
description: pod unscheduler
---
---
# Source: metric-expression-cluster/templates/expressionworkload.yaml
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-disk-io-writes-bytes-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: disk-io
level: project
metric: disk-io-writes-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_fs_writes_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Write
description: workload disk io writes bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-disk-io-writes-bytes-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: disk-io
level: project
metric: disk-io-writes-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_fs_writes_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: Write([[pod_name]])
description: workload disk io writes bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-disk-io-reads-bytes-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: disk-io
level: project
metric: disk-io-reads-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_fs_reads_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Read
description: workload disk io reads bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-disk-io-reads-bytes-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: disk-io
level: project
metric: disk-io-reads-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_fs_reads_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: Read([[pod_name]])
description: workload disk io reads bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-fs-bytes-sum
labels:
app: metric-expression
component: workload
details: "false"
level: project
metric: fs-bytes-sum
source: rancher-monitoring
spec:
expression: sum(container_fs_usage_bytes{namespace=~"$namespace", pod_name=~"$podName",
container_name!=""})
legendFormat: File usage
description: workload fs bytes sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-fs-bytes-sum-details
labels:
app: metric-expression
component: workload
details: "true"
level: project
metric: fs-bytes-sum
source: rancher-monitoring
spec:
expression: sum(container_fs_usage_bytes{namespace=~"$namespace", pod_name=~"$podName",
container_name!=""}) by (pod_name)
legendFormat: pod_name]]
description: workload fs bytes sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-transmit-packets-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: network-packet
level: project
metric: network-transmit-packets-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_packets_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Transmit packets
description: workload network transmit packets sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-transmit-packets-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: network-packet
level: project
metric: network-transmit-packets-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_packets_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: Transmit packets([[pod_name]])
description: workload network transmit packets sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-receive-packets-dropped-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: network-packet
level: project
metric: network-receive-packets-dropped-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Receive dropped
description: workload network receive packets dropped sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-receive-packets-dropped-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: network-packet
level: project
metric: network-receive-packets-dropped-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: Receive dropped([[pod_name]])
description: workload network receive packets dropped sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-cpu-usage-seconds-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: cpu-usage
level: project
metric: cpu-usage-seconds-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_usage_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: CPU usage
description: workload cpu usage seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-cpu-usage-seconds-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: cpu-usage
level: project
metric: cpu-usage-seconds-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_usage_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: CPU usage([[pod_name]])
description: workload cpu usage seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-cpu-system-seconds-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: cpu-usage
level: project
metric: cpu-system-seconds-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_system_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: CPU system seconds
description: workload cpu system seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-cpu-system-seconds-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: cpu-usage
level: project
metric: cpu-system-seconds-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_system_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: CPU system seconds([[pod_name]])
description: workload cpu system seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-receive-bytes-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: network-io
level: project
metric: network-receive-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Receive
description: workload network receive bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-receive-bytes-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: network-io
level: project
metric: network-receive-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: Receive([[pod_name]])
description: workload network receive bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-receive-errors-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: network-packet
level: project
metric: network-receive-errors-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_errors_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Receive errors
description: workload network receive errors sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-receive-errors-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: network-packet
level: project
metric: network-receive-errors-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_errors_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: Receive errors([[pod_name]])
description: workload network receive errors sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-receive-packets-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: network-packet
level: project
metric: network-receive-packets-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_packets_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Receive packets
description: workload network receive packets sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-receive-packets-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: network-packet
level: project
metric: network-receive-packets-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_receive_packets_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: Receive packets([[pod_name]])
description: workload network receive packets sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-memory-usage-bytes-sum
labels:
app: metric-expression
component: workload
details: "false"
level: project
metric: memory-usage-bytes-sum
source: rancher-monitoring
spec:
expression: sum(container_memory_working_set_bytes{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""})
legendFormat: Memory
description: workload memory usage bytes sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-memory-usage-bytes-sum-details
labels:
app: metric-expression
component: workload
details: "true"
level: project
metric: memory-usage-bytes-sum
source: rancher-monitoring
spec:
expression: sum(container_memory_working_set_bytes{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}) by (pod_name)
legendFormat: '[[pod_name]]'
description: workload memory usage bytes sum
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-transmit-bytes-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: network-io
level: project
metric: network-transmit-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Transmit
description: workload network transmit bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-transmit-bytes-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: network-io
level: project
metric: network-transmit-bytes-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_bytes_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: Transmit([[pod_name]])
description: workload network transmit bytes sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-transmit-errors-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: network-packet
level: project
metric: network-transmit-errors-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_errors_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Transmit errors
description: workload network transmit errors sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-transmit-errors-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: network-packet
level: project
metric: network-transmit-errors-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_errors_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: Transmit errors([[pod_name]])
description: workload network transmit errors sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-transmit-packets-dropped-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: network-packet
level: project
metric: network-transmit-packets-dropped-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: Transmit dropped
description: workload network transmit packets dropped sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-network-transmit-packets-dropped-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: network-packet
level: project
metric: network-transmit-packets-dropped-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_network_transmit_packets_dropped_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: Transmit dropped([[pod_name]])
description: workload network transmit packets dropped sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-cpu-user-seconds-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: cpu-usage
level: project
metric: cpu-user-seconds-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_user_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: CPU user seconds
description: workload cpu user seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-cpu-user-seconds-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: cpu-usage
level: project
metric: cpu-user-seconds-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_user_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: CPU user seconds([[pod_name]])
description: workload cpu user seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-cpu-cfs-throttled-seconds-sum-rate
labels:
app: metric-expression
component: workload
details: "false"
graph: cpu-usage
level: project
metric: cpu-cfs-throttled-seconds-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_cfs_throttled_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m]))
legendFormat: CPU cfs throttled
description: workload cpu cfs throttled seconds sum rate
---
kind: MonitorMetric
apiVersion: management.cattle.io/v3
metadata:
name: workload-cpu-cfs-throttled-seconds-sum-rate-details
labels:
app: metric-expression
component: workload
details: "true"
graph: cpu-usage
level: project
metric: cpu-cfs-throttled-seconds-sum-rate
source: rancher-monitoring
spec:
expression: sum(rate(container_cpu_cfs_throttled_seconds_total{namespace=~"$namespace",pod_name=~"$podName",
container_name!=""}[5m])) by (pod_name)
legendFormat: CPU cfs throttled([[pod_name]])
description: workload cpu cfs throttled seconds sum rate
---
`
ProjectMetricExpression = `
apiVersion: management.cattle.io/v3
kind: ProjectMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: project
component: container
name: container-cpu-usage
spec:
resourceType: container
priority: 800
title: container-cpu-usage
detailsMetricsSelector:
details: "true"
component: container
graph: cpu-usage
yAxis:
unit: mcpu
---
apiVersion: management.cattle.io/v3
kind: ProjectMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: project
component: container
name: container-memory-usage-bytes-sum
spec:
resourceType: container
priority: 801
title: container-memory-usage-bytes-sum
detailsMetricsSelector:
details: "true"
component: container
metric: memory-usage-bytes-sum
yAxis:
unit: byte
---
apiVersion: management.cattle.io/v3
kind: ProjectMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: project
component: container
name: container-disk-io
spec:
resourceType: container
priority: 804
title: container-disk-io
detailsMetricsSelector:
details: "true"
component: container
graph: disk-io
yAxis:
unit: bps
---
apiVersion: management.cattle.io/v3
kind: ProjectMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: project
component: pod
name: pod-cpu-usage
spec:
resourceType: pod
priority: 700
title: pod-cpu-usage
metricsSelector:
details: "false"
component: pod
graph: cpu-usage
detailsMetricsSelector:
details: "true"
component: pod
graph: cpu-usage
yAxis:
unit: mcpu
---
apiVersion: management.cattle.io/v3
kind: ProjectMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: project
component: pod
name: pod-memory-usage-bytes-sum
spec:
resourceType: pod
priority: 701
title: pod-memory-usage-bytes-sum
metricsSelector:
details: "false"
component: pod
metric: memory-usage-bytes-sum
detailsMetricsSelector:
details: "true"
component: pod
metric: memory-usage-bytes-sum
yAxis:
unit: byte
---
apiVersion: management.cattle.io/v3
kind: ProjectMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: project
component: pod
name: pod-network-io
spec:
resourceType: pod
priority: 702
title: pod-network-io
metricsSelector:
details: "false"
component: pod
graph: network-io
detailsMetricsSelector:
details: "true"
component: pod
graph: network-io
yAxis:
unit: bps
---
apiVersion: management.cattle.io/v3
kind: ProjectMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: project
component: pod
name: pod-network-packet
spec:
resourceType: pod
priority: 703
title: pod-network-packet
metricsSelector:
details: "false"
component: pod
graph: network-packet
detailsMetricsSelector:
details: "true"
component: pod
graph: network-packet
yAxis:
unit: pps
---
apiVersion: management.cattle.io/v3
kind: ProjectMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: project
component: pod
name: pod-disk-io
spec:
resourceType: pod
priority: 704
title: pod-disk-io
metricsSelector:
details: "false"
component: pod
graph: disk-io
detailsMetricsSelector:
details: "true"
component: pod
graph: disk-io
yAxis:
unit: bps
---
apiVersion: management.cattle.io/v3
kind: ProjectMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: project
component: workload
name: workload-cpu-usage
spec:
resourceType: workload
priority: 600
title: workload-cpu-usage
metricsSelector:
details: "false"
component: workload
graph: cpu-usage
detailsMetricsSelector:
details: "true"
component: workload
graph: cpu-usage
yAxis:
unit: mcpu
---
apiVersion: management.cattle.io/v3
kind: ProjectMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: project
component: workload
name: workload-memory-usage-bytes-sum
spec:
resourceType: workload
priority: 601
title: workload-memory-usage-bytes-sum
metricsSelector:
details: "false"
component: workload
metric: memory-usage-bytes-sum
detailsMetricsSelector:
details: "true"
component: workload
metric: memory-usage-bytes-sum
yAxis:
unit: byte
---
apiVersion: management.cattle.io/v3
kind: ProjectMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: project
component: workload
name: workload-network-io
spec:
resourceType: workload
priority: 602
title: workload-network-io
metricsSelector:
details: "false"
component: workload
graph: network-io
detailsMetricsSelector:
details: "true"
component: workload
graph: network-io
yAxis:
unit: bps
---
apiVersion: management.cattle.io/v3
kind: ProjectMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: project
component: workload
name: workload-network-packet
spec:
resourceType: workload
priority: 603
title: workload-network-packet
metricsSelector:
details: "false"
component: workload
graph: network-packet
detailsMetricsSelector:
details: "true"
component: workload
graph: network-packet
yAxis:
unit: pps
---
apiVersion: management.cattle.io/v3
kind: ProjectMonitorGraph
metadata:
labels:
app: metric-expression
source: rancher-monitoring
level: project
component: workload
name: workload-disk-io
spec:
resourceType: workload
priority: 604
title: workload-disk-io
metricsSelector:
details: "false"
component: workload
graph: disk-io
detailsMetricsSelector:
details: "true"
component: workload
graph: disk-io
yAxis:
unit: bps
---
`
)
Loading...
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
Go
1
https://gitee.com/rancher/rancher.git
git@gitee.com:rancher/rancher.git
rancher
rancher
rancher
v2.2.2

搜索帮助

0d507c66 1850385 C8b1a773 1850385