{"id":34335,"date":"2019-10-31T21:57:43","date_gmt":"2019-10-31T18:57:43","guid":{"rendered":"https:\/\/prohoster.info\/blog\/analiz-proizvoditelnosti-virtualnoj-mashiny-v-vmware-vsphere-chast-1-cpu\/"},"modified":"2019-10-31T21:57:43","modified_gmt":"2019-10-31T18:57:43","slug":"analiz-proizvoditelnosti-virtualnoj-mashiny-v-vmware-vsphere-chast-1-cpu","status":"publish","type":"post","link":"https:\/\/prohoster.info\/sq\/blog\/administrirovanie\/analiz-proizvoditelnosti-virtualnoj-mashiny-v-vmware-vsphere-chast-1-cpu","title":{"rendered":"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/0c077a1754c2e32c1f339999ceacf03a.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nN\u00ebse administroni nj\u00eb infrastruktur\u00eb virtuale t\u00eb bazuar n\u00eb VMware vSphere (ose ndonj\u00eb stek tjet\u00ebr teknologjik), ndoshta shpesh d\u00ebgjoni nga p\u00ebrdoruesit ankesat: \"Makin\u00eb virtuale po punon ngadal\u00eb!\". N\u00eb k\u00ebt\u00eb cik\u00ebl artikujsh do t\u00eb shqyrtoj metrikat e performanc\u00ebs dhe do t\u00eb tregoj se \u00e7far\u00eb dhe pse \"ngadal\u00ebson\" dhe si t\u00eb b\u00ebni q\u00eb t\u00eb mos \"ngadal\u00ebsohet\".<\/p>\n<p>Do t\u00eb shqyrtoj aspekte t\u00eb m\u00ebposhtme t\u00eb performanc\u00ebs s\u00eb makinave virtuale:<\/p>\n<ul>\n<li>CPU,<\/li>\n<li>RAM,<\/li>\n<li>DISK,<\/li>\n<li>Rrjeti.<\/li>\n<\/ul>\n<p>\nT\u00eb filloj me CPU.<\/p>\n<p>P\u00ebr analiz\u00ebn e performanc\u00ebs, do na duhen:<\/p>\n<ul>\n<li><b>VCenter Performance Counters<\/b> \u2013 num\u00ebrues t\u00eb performanc\u00ebs, t\u00eb cilat grafiket e t\u00eb cil\u00ebve mund t\u00eb shihni p\u00ebrmes vSphere Client. Informacioni mbi k\u00ebta num\u00ebrues \u00ebsht\u00eb i disponuesh\u00ebm n\u00eb \u00e7do version t\u00eb klientit (klienti \"i r\u00ebnd\u00eb\" n\u00eb C#, klienti web n\u00eb Flex dhe klienti web n\u00eb HTML5). N\u00eb k\u00ebto artikuj do t\u00eb p\u00ebrdorim captura ekranesh nga klienti C#, thjesht sepse duken m\u00eb mir\u00eb n\u00eb miniatur\u00eb:)<\/li>\n<li><b>ESXTOP<\/b> \u2013 nj\u00eb utilitar q\u00eb niset nga komanda e linj\u00ebs ESXi. Me ndihm\u00ebn e tij, mund t\u00eb merrni vlera t\u00eb num\u00ebruesve t\u00eb performanc\u00ebs n\u00eb koh\u00eb reale ose t'i eksportoni k\u00ebto vlera p\u00ebr nj\u00eb periudh\u00eb t\u00eb caktuar n\u00eb nj\u00eb skedar .csv p\u00ebr analiz\u00eb t\u00eb m\u00ebtejshme. M\u00eb pas do t\u00eb flas p\u00ebr k\u00ebt\u00eb mjet m\u00eb n\u00eb detaje dhe do t\u00eb jap disa lidhje t\u00eb dobishme n\u00eb dokumentacionin dhe artikujt lidhur me tem\u00ebn.<\/li>\n<\/ul>\n<p>\n<noindex><a rel=\"nofollow\" name=\"habracut\"><\/a><\/noindex><\/p>\n<h3>Pak teori<\/h3>\n<p>\n<img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/bc415aace7653c45850d26b7104483c9.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nN\u00eb ESXi, \u00e7do vCPU (n\u00eb terminologjin\u00eb e VMware) p\u00ebrfaq\u00ebsohet nga nj\u00eb proces i ve\u00e7ant\u00eb \u2013 world. Ka gjithashtu procese sh\u00ebrbimi, por nga k\u00ebndv\u00ebshtrimi i analiz\u00ebs s\u00eb performanc\u00ebs s\u00eb VM-ve, ato jan\u00eb m\u00eb pak interesante.<\/p>\n<p>Nj\u00eb proces n\u00eb ESXi mund t\u00eb ndodhet n\u00eb nj\u00ebr\u00ebn nga kat\u00ebr gjendjet:<\/p>\n<ul>\n<li><b>Ekzekuto<\/b> \u2013 procesi b\u00ebn ndonj\u00eb pun\u00eb t\u00eb dobishme.<\/li>\n<li><b>Pritja<\/b> \u2013 procesi nuk b\u00ebn asnj\u00eb pun\u00eb (idle) ose po pret p\u00ebr input\/output.<\/li>\n<li><b>Costop<\/b> \u2013 nj\u00eb gjendje q\u00eb ndodh n\u00eb makina virtuale me shum\u00eb b\u00ebrtham\u00eb. Ajo ndodh kur planifikuesi i CPU-s\u00eb i hipervizorit (ESXi CPU Scheduler) nuk mund t\u00eb planifikoj\u00eb ekzekutimin e nj\u00ebkohsh\u00ebm n\u00eb b\u00ebrthamat fizike t\u00eb serverit p\u00ebr t\u00eb gjitha b\u00ebrthamat aktive t\u00eb makin\u00ebs virtuale. N\u00eb bot\u00ebn fizike, t\u00eb gjitha b\u00ebrthamat e procesorit punojn\u00eb paralelisht, nd\u00ebrsa sistemi operacional i mysafir\u00ebve brenda VM-s\u00eb llogarit n\u00eb nj\u00eb sjellje t\u00eb ngjashme, prandaj hipervizori detyrohet t\u00eb ngadal\u00ebsoj\u00eb b\u00ebrthamat e VM-s\u00eb, t\u00eb cilat kan\u00eb mund\u00ebsin\u00eb t\u00eb p\u00ebrfundojn\u00eb ciklin m\u00eb shpejt. N\u00eb versionet moderne t\u00eb ESXi, planifikuesi i CPU-s\u00eb p\u00ebrdor nj\u00eb mekaniz\u00ebm q\u00eb quhet co-scheduling i relaksuar: hipervizori llogarit diferenc\u00ebn nd\u00ebrmjet b\u00ebrtham\u00ebs \"m\u00eb t\u00eb shpejt\u00eb\" dhe b\u00ebrtham\u00ebs \"m\u00eb t\u00eb ngadalshme\" t\u00eb makin\u00ebs virtuale (skew). N\u00ebse diferenca tejkalon nj\u00eb prag t\u00eb caktuar, b\u00ebrthama \"m\u00eb e shpejt\u00eb\" kalon n\u00eb gjendjen costop. N\u00ebse b\u00ebrthamat e VM-s\u00eb kalojn\u00eb shum\u00eb koh\u00eb n\u00eb k\u00ebt\u00eb gjendje, mund t\u00eb shkaktoj\u00eb probleme me performanc\u00ebn.<\/li>\n<li><b>Gati<\/b> \u2013 procesi kalon n\u00eb k\u00ebt\u00eb gjendje kur hipervizori nuk ka mund\u00ebsi t\u00eb alokoj\u00eb burime p\u00ebr ekzekutimin e tij. Vlerat e larta t\u00eb gatishm\u00ebris\u00eb (ready) mund t\u00eb shkaktojn\u00eb probleme me performanc\u00ebn e VM-s\u00eb.<\/li>\n<\/ul>\n<p><\/p>\n<h3>Numrat kryesor\u00eb t\u00eb performanc\u00ebs s\u00eb CPU-s\u00eb s\u00eb makin\u00ebs virtuale<\/h3>\n<p>\n<b>P\u00ebrdorimi i CPU-s\u00eb, %.<\/b> Tregon p\u00ebrqindjen e p\u00ebrdorimit t\u00eb CPU-s\u00eb p\u00ebr nj\u00eb periudh\u00eb t\u00eb caktuar.<\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/7a5da7dcd45329c3aae8e394c5d35a30.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\n<b>Si t\u00eb analizohet?<\/b> N\u00ebse VM-ja p\u00ebrdor stabilisht CPU-n\u00eb n\u00eb 90% ose ka pika deri n\u00eb 100%, at\u00ebher\u00eb kemi probleme. Problemet mund t\u00eb shfaqen jo vet\u00ebm n\u00eb \"pun\u00ebn e ngadalshme\" t\u00eb aplikacionit brenda VM-s\u00eb, por edhe n\u00eb krijimin e paq\u00ebndrueshm\u00ebrive t\u00eb VM-s\u00eb n\u00eb rrjet. N\u00ebse sistema i monitorimit tregon se VM-ja her\u00eb pas here \u201cndalon,\u201d kushtoni v\u00ebmendje pikave n\u00eb grafikun e P\u00ebrdorimit t\u00eb CPU-s\u00eb.<\/p>\n<p>Ekziston nj\u00eb Alarm standard q\u00eb tregon ngarkes\u00ebn e CPU-s\u00eb s\u00eb makin\u00ebs virtuale:<\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/9bfd9bb5b43b9b02e8bbfac307d6c9f9.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\n<b>\u00c7far\u00eb t\u00eb b\u00ebjm\u00eb?<\/b> N\u00ebse VM-ja vazhdimisht kalon p\u00ebrdorimin e CPU-s\u00eb, at\u00ebher\u00eb mund t\u00eb mendoni p\u00ebr rritjen e numrit t\u00eb vCPU (p\u00ebr fat t\u00eb keq, kjo nuk ndihmon gjithmon\u00eb) ose p\u00ebr transferimin e VM-s\u00eb n\u00eb nj\u00eb server me procesor\u00eb m\u00eb t\u00eb fuqish\u00ebm.<\/p>\n<h3>P\u00ebrdorimi i CPU-s\u00eb n\u00eb Mhz<\/h3>\n<p>\nN\u00eb grafik\u00ebt n\u00eb vCenter, P\u00ebrdorimi n\u00eb % mund t\u00eb shikohet vet\u00ebm p\u00ebr t\u00eb gjith\u00eb makin\u00ebn virtuale, nuk ka grafik\u00eb p\u00ebr b\u00ebrthama t\u00eb ve\u00e7anta (nd\u00ebrsa n\u00eb Esxtop, vlerat n\u00eb % p\u00ebr b\u00ebrthamat ekzistojn\u00eb). P\u00ebr \u00e7do b\u00ebrtham\u00eb mund t\u00eb shikohet P\u00ebrdorimi n\u00eb MHz.<\/p>\n<p><b>Si t\u00eb analizohet?<\/b> Ndonj\u00ebher\u00eb, aplikacioni nuk \u00ebsht\u00eb optimizuar p\u00ebr arkitektur\u00ebn shum\u00eb-n\u00ebndeshkuese: p\u00ebrdor 100% vet\u00ebm nj\u00eb b\u00ebrtham\u00eb, nd\u00ebrsa b\u00ebrthamat e tjera q\u00ebndrojn\u00eb pa ngarkes\u00eb. P\u00ebr shembull, me cil\u00ebsimet e paracaktuara t\u00eb backup-it, MS SQL fillon procesin vet\u00ebm n\u00eb nj\u00eb b\u00ebrtham\u00eb. Si rezultat, kopjimi i rezervave ngadal\u00ebsohet jo p\u00ebr shkak t\u00eb shpejt\u00ebsis\u00eb s\u00eb ngadalte t\u00eb disqeve (p\u00ebr k\u00ebt\u00eb fillimisht ankohej p\u00ebrdoruesi), por p\u00ebr shkak t\u00eb kapacitetit t\u00eb pamjaftuesh\u00ebm t\u00eb procesorit. Problemi u zgjidh duke ndryshuar parametrat: kopjimi i rezervave filloi t\u00eb ekzekutohet paralelisht n\u00eb disa skedar\u00eb (p\u00ebrkat\u00ebsisht, n\u00eb disa procese).<\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/d1bce5fe5ef89a69c31a6a8f043d5d24.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<i>Shembulli i ngarkes\u00ebs s\u00eb pabarabart\u00eb t\u00eb b\u00ebrthamave.<\/i><\/p>\n<p>Gjithashtu ndodh nj\u00eb situat\u00eb (si\u00e7 duket n\u00eb grafik) kur b\u00ebrthamat jan\u00eb t\u00eb ngarkuara n\u00eb m\u00ebnyr\u00eb t\u00eb pabarabart\u00eb dhe disa prej tyre kan\u00eb maja deri n\u00eb 100%. Ashtu si\u00e7 ndodh kur ngarkohet vet\u00ebm nj\u00eb b\u00ebrtham\u00eb, alarmi p\u00ebr P\u00ebrdorimin e CPU-s\u00eb nuk do t\u00eb aktivizohet (ai \u00ebsht\u00eb p\u00ebr t\u00eb gjith\u00eb VM-n\u00eb), por do t\u00eb ket\u00eb probleme me performance-n.<\/p>\n<p><b>\u00c7far\u00eb t\u00eb b\u00ebjm\u00eb? <\/b>N\u00ebse software-i n\u00eb makin\u00eb virtuale ngarkon b\u00ebrthamat n\u00eb m\u00ebnyr\u00eb t\u00eb pabarabart\u00eb (p\u00ebrdor vet\u00ebm nj\u00eb b\u00ebrtham\u00eb ose disa b\u00ebrthama), nuk ka kuptim t\u00eb rritet numri i tyre. N\u00eb k\u00ebt\u00eb rast, \u00ebsht\u00eb m\u00eb mir\u00eb t\u00eb zhvendosni VM-n\u00eb n\u00eb nj\u00eb server me procesor\u00eb m\u00eb t\u00eb fuqish\u00ebm.<\/p>\n<p>Gjithashtu mund t\u00eb provoni t\u00eb kontrolloni cil\u00ebsimet e konsumit t\u00eb energjis\u00eb n\u00eb BIOS t\u00eb serverit. Shum\u00eb administrator\u00eb aktivizojn\u00eb n\u00eb BIOS modin High Performance dhe k\u00ebshtu \u00e7aktivizojn\u00eb teknologjit\u00eb e kursimit t\u00eb energjis\u00eb C-states dhe P-states. N\u00eb procesor\u00ebt moderne Intel p\u00ebrdoret teknologjia Turbo Boost, e cila rrit frekuenc\u00ebn e b\u00ebrthamave individuale t\u00eb procesorit p\u00ebr shkak t\u00eb b\u00ebrthamave t\u00eb tjera. Por ajo funksionon vet\u00ebm kur teknologjit\u00eb e kursimit t\u00eb energjis\u00eb jan\u00eb t\u00eb aktivizuara. N\u00ebse i \u00e7aktivizojm\u00eb, procesori nuk mund t\u00eb zvog\u00ebloj\u00eb konsumimin e energjis\u00eb t\u00eb b\u00ebrthamave q\u00eb nuk jan\u00eb t\u00eb ngarkuara. <\/p>\n<p>VMware rekomandon t\u00eb mos \u00e7aktivizoni teknologjit\u00eb e kursimit t\u00eb energjis\u00eb n\u00eb servera, por t\u00eb zgjidhni m\u00ebnyra q\u00eb maksimizojn\u00eb dor\u00ebzimin e kontrollit t\u00eb konsumit t\u00eb energjis\u00eb hiper-vizorit. N\u00eb t\u00eb nj\u00ebjt\u00ebn koh\u00eb, n\u00eb cil\u00ebsimet e konsumit t\u00eb energjis\u00eb t\u00eb hiper-vizorit duhet t\u00eb zgjidhni High Performance. <\/p>\n<p>N\u00ebse n\u00eb infrastruktur\u00ebn tuaj VM t\u00eb ve\u00e7anta (ose b\u00ebrthama t\u00eb VM) k\u00ebrkojn\u00eb nj\u00eb frekuenc\u00eb t\u00eb rritur CPU, nj\u00eb konfigurim i sakt\u00eb i konsumit t\u00eb energjis\u00eb mund t\u00eb p\u00ebrmir\u00ebsoj\u00eb ndjesh\u00ebm performanc\u00ebn e tyre.<\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/59aec2b77fa87e413d90371a11388629.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<\/p>\n<h3>CPU Ready (Gati) <\/h3>\n<p>\nN\u00ebse b\u00ebrthama e VM (vCPU) \u00ebsht\u00eb n\u00eb gjendje Gatsh\u00ebm, ajo nuk po kryen pun\u00eb t\u00eb dobishme. Kjo gjendje ndodh kur hipervizori nuk gjen nj\u00eb b\u00ebrtham\u00eb fizike t\u00eb lir\u00eb p\u00ebr t\u00eb caktuar procesin e vCPU t\u00eb makineris\u00eb virtuale.<\/p>\n<p><b>Si t\u00eb analizohet?<\/b> N\u00eb p\u00ebrgjith\u00ebsi, n\u00ebse b\u00ebrthamat e makinerive virtuale jan\u00eb n\u00eb gjendje Gatsh\u00ebm m\u00eb shum\u00eb se 10% t\u00eb koh\u00ebs, at\u00ebher\u00eb do t\u00eb v\u00ebreni probleme me performanc\u00ebn. Thjesht, m\u00eb shum\u00eb se 10% t\u00eb koh\u00ebs VM pret disponueshm\u00ebrin\u00eb e resurseve fizike.<\/p>\n<p>N\u00eb vCenter mund t\u00eb shihni 2 num\u00ebrues q\u00eb lidhen me Gatshm\u00ebrin\u00eb e CPU:<\/p>\n<ul>\n<li>Gatshm\u00ebria,<\/li>\n<li>Gatsh\u00ebm.<\/li>\n<\/ul>\n<p>\nVlerat e t\u00eb dy num\u00ebruesve mund t\u00eb shihen si p\u00ebr t\u00eb gjith\u00eb VM-n\u00eb, ashtu edhe p\u00ebr b\u00ebrthamat e ve\u00e7anta.<br \/>\nGatshm\u00ebria tregon vler\u00ebn menj\u00ebher\u00eb n\u00eb p\u00ebrqindje, por vet\u00ebm n\u00eb koh\u00eb reale (t\u00eb dh\u00ebnat p\u00ebr or\u00ebn e fundit, intervali i matjeve 20 sekonda). Ky num\u00ebrues \u00ebsht\u00eb m\u00eb mir\u00eb t\u00eb p\u00ebrdoret vet\u00ebm p\u00ebr t\u00eb gjetur probleme \"n\u00eb gjurm\u00ebt e nxehta\".<\/p>\n<p>Vlerat e num\u00ebruesit Gatsh\u00ebm mund t\u00eb shihen gjithashtu n\u00eb nj\u00eb perspektiv\u00eb historike. Kjo \u00ebsht\u00eb e dobishme p\u00ebr t\u00eb identifikuar tendencat dhe p\u00ebr nj\u00eb analiz\u00eb m\u00eb t\u00eb thell\u00eb t\u00eb problemit. P\u00ebr shembull, n\u00ebse nj\u00eb makin\u00eb virtuale fillon t\u00eb ket\u00eb probleme me performanc\u00ebn n\u00eb nj\u00eb koh\u00eb t\u00eb caktuar, mund t\u00eb p\u00ebrputhet intervalet e rritjes s\u00eb vler\u00ebs s\u00eb Gatsh\u00ebm CPU me ngarkes\u00ebn totale n\u00eb serverin ku funksionon kjo VM dhe t\u00eb merren masa p\u00ebr t\u00eb ulur ngarkes\u00ebn (n\u00ebse DRS nuk ka arritur).<\/p>\n<p>Gatsh\u00ebm, ndryshe nga Gatshm\u00ebria, tregohet jo n\u00eb p\u00ebrqindje, por n\u00eb milisekonda. Ky \u00ebsht\u00eb nj\u00eb num\u00ebrues i llojit Summation, q\u00eb do t\u00eb thot\u00eb se tregon sa koh\u00eb gjat\u00eb periudh\u00ebs s\u00eb matjes b\u00ebrthama e VM ishte n\u00eb gjendje Gatsh\u00ebm. Mund ta konvertosh k\u00ebt\u00eb vler\u00eb n\u00eb p\u00ebrqindje p\u00ebrmes nj\u00eb formule t\u00eb thjesht\u00eb:<\/p>\n<p>(vlera e sh summation t\u00eb Gatsh\u00ebm \\\/ (intervali i p\u00ebrdit\u00ebsimit t\u00eb grafik\u00ebve n\u00eb sekonda * 1000)) * 100 = Gatsh\u00ebm %<\/p>\n<p>P\u00ebr shembull, p\u00ebr VM-n\u00eb n\u00eb grafik\u00ebn m\u00eb posht\u00eb, vlera maksimale e Gatsh\u00ebm p\u00ebr t\u00eb gjith\u00eb makinerin\u00eb virtuale do t\u00eb rezultoj\u00eb si vijon: <\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/3e2df8bca55b572502d88b838cbc306e.jpg\" style=\"display:block;margin: 0 auto;\" \/> <\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/f0371c9cd655c1e4785e90debde61dc8.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nKur llogaritni vler\u00ebn e Gatsh\u00ebm n\u00eb p\u00ebrqindje, duhen marr\u00eb parasysh dy \u00e7\u00ebshtje:<\/p>\n<ul>\n<li>Vlera Gatsh\u00ebm p\u00ebr t\u00eb gjith\u00eb VM-n\u00eb \u2013 \u00ebsht\u00eb shuma e Gatsh\u00ebm p\u00ebr b\u00ebrthamat.<\/li>\n<li>Intervali i matjes. P\u00ebr koh\u00eb reale \u2013 \u00ebsht\u00eb 20 sekonda, nd\u00ebrsa, p\u00ebr shembull, n\u00eb grafik\u00ebt ditor\u00eb \u2013 \u00ebsht\u00eb 300 sekonda.<\/li>\n<\/ul>\n<p>\nKur jeni duke kryer trajtim t\u00eb problemeve, k\u00ebto momente t\u00eb thjeshta mund t\u00eb leht\u00ebsisht t\u00eb injorohen dhe t\u00eb harxhohet koh\u00eb e \u00e7muar p\u00ebr ndihm\u00ebn n\u00eb problemet q\u00eb nuk ekzistojn\u00eb. <\/p>\n<p>Ne do ta\u00eb parashikojm\u00eb Ready bazuar n\u00eb t\u00eb dh\u00ebnat nga grafiku m\u00eb posht\u00eb. (324474\/(20*1000))*100 = 1622% p\u00ebr t\u00eb gjith\u00eb VM. N\u00ebse shohim sipas b\u00ebrthamave, duket m\u00eb e menaxhueshme: 1622\/64 = 25% p\u00ebr b\u00ebrtham\u00eb. N\u00eb k\u00ebt\u00eb rast, zbulimi i nj\u00eb mashtrimi \u00ebsht\u00eb mjaft i thjesht\u00eb: vlera Ready \u00ebsht\u00eb e paarsyeshme. Por n\u00ebse diskutohet rreth 10\u201320% p\u00ebr t\u00eb gjith\u00eb VM me disa b\u00ebrthama, at\u00ebher\u00eb vlera p\u00ebr secil\u00ebn b\u00ebrtham\u00eb mund t\u00eb jet\u00eb brenda normales.<\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/703ab2b1f1fab8bda10aad781c2cef78.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\n<b>\u00c7far\u00eb t\u00eb b\u00ebjm\u00eb? <\/b>Nj\u00eb vler\u00eb e lart\u00eb Ready tregon se serverit i mungojn\u00eb burimet e CPU p\u00ebr funksionimin normal t\u00eb nd\u00ebrtimeve virtuale. N\u00eb nj\u00eb situat\u00eb t\u00eb till\u00eb, mund\u00ebsia e vetme \u00ebsht\u00eb t\u00eb zvog\u00ebloni mbivendosjen e procesor\u00ebve (vCPU:pCPU). \u00cbsht\u00eb e qart\u00eb se kjo mund t\u00eb arrihet duke ulur parametrat e nd\u00ebrtimeve ekzistuese ose duke migruar disa nd\u00ebrtime n\u00eb server\u00eb t\u00eb tjer\u00eb.<\/p>\n<h3>Co-stop<\/h3>\n<p>\n<b>Si t\u00eb analizohet?<\/b> Ky num\u00ebrues gjithashtu ka llojin Summation dhe p\u00ebrkthehet n\u00eb p\u00ebrqindje n\u00eb m\u00ebnyr\u00eb t\u00eb ngjashme me Ready:<\/p>\n<p>(CPU co-stop summation value \/ (intervali standard i p\u00ebrdit\u00ebsimit t\u00eb grafik\u00ebve n\u00eb sekonda * 1000)) * 100 = CPU co-stop %<\/p>\n<p>K\u00ebtu gjithashtu duhet t\u00eb merret parasysh numri i b\u00ebrthamave n\u00eb VM dhe intervali i matjes.<br \/>\nN\u00eb gjendjen co-stop, b\u00ebrthama nuk b\u00ebn pun\u00eb t\u00eb dobishme. Me p\u00ebrzgjedhjen e duhur t\u00eb madh\u00ebsis\u00eb s\u00eb VM dhe ngarkes\u00eb normale n\u00eb server, num\u00ebruesi co-stop duhet t\u00eb jet\u00eb af\u00ebr zeros.<\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/e226afbf91155c2d5d3fdc4571e7383a.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<i>N\u00eb k\u00ebt\u00eb rast, ngarkesa \u00ebsht\u00eb duksh\u00ebm anormale :)<\/i><\/p>\n<p><b>\u00c7far\u00eb t\u00eb b\u00ebjm\u00eb?<\/b> N\u00ebse n\u00eb nj\u00eb hipervizor punojn\u00eb disa VM me numra t\u00eb m\u00ebdha b\u00ebrthamash dhe ka mbivendosje mbi CPU, at\u00ebher\u00eb num\u00ebruesi co-stop mund t\u00eb rritet, \u00e7ka do t\u00eb \u00e7oj\u00eb n\u00eb probleme me performanc\u00ebn e k\u00ebtyre VM. <\/p>\n<p>Po ashtu, co-stop do t\u00eb rritet n\u00ebse p\u00ebr b\u00ebrthamat aktive t\u00eb nj\u00eb VM p\u00ebrdoren thredds n\u00eb nj\u00eb b\u00ebrtham\u00eb fizike t\u00eb serverit me hyper-threading t\u00eb aktivizuar. Kjo situat\u00eb mund t\u00eb ndodh\u00eb, p\u00ebr shembull, n\u00ebse VM ka m\u00eb shum\u00eb b\u00ebrthama se ato fizike q\u00eb ka serveri, ku ajo funksionon, ose n\u00ebse p\u00ebr VM \u00ebsht\u00eb aktivizuar konfigurimi 'preferHT'. Rreth k\u00ebsaj konfigurate mund t\u00eb lexoni <noindex><a rel=\"nofollow\" href=\"https:\/\/blogs.vmware.com\/vsphere\/2014\/03\/perferht-use-2.html\">k\u00ebtu<\/a><\/noindex>. <\/p>\n<p>P\u00ebr t\u00eb shmangur problemet me performanc\u00ebn e VM p\u00ebr shkak t\u00eb nj\u00eb co-stop t\u00eb lart\u00eb, zgjidhni madh\u00ebsin\u00eb e VM sipas rekomandimeve t\u00eb prodhuesit t\u00eb softuerit q\u00eb funksionon mbi k\u00ebt\u00eb VM, dhe sipas kapaciteteve t\u00eb serverit fizik ku funksionon VM. <\/p>\n<p>Mos shtoni b\u00ebrthama p\u00ebr rezerv\u00eb; kjo mund t\u00eb shkaktoj\u00eb probleme me performanc\u00ebn jo vet\u00ebm t\u00eb vet\u00eb VM, por edhe t\u00eb fqinj\u00ebve t\u00eb saj n\u00eb server.<\/p>\n<h3>Metrika t\u00eb tjera t\u00eb dobishme t\u00eb CPU<\/h3>\n<p>\n<b>Ekzekuto<\/b> \u2013 sa koh\u00eb (ms) gjat\u00eb periudh\u00ebs s\u00eb matjes vCPU ka qen\u00eb n\u00eb gjendjen RUN, q\u00eb do t\u00eb thot\u00eb se v\u00ebrtet ka b\u00ebr\u00eb pun\u00eb t\u00eb dobishme.<\/p>\n<p><b>P\u00ebrgjith\u00ebsisht<\/b> \u2013 sa sa \u00ebsht\u00eb koha (ms) gjat\u00eb periudh\u00ebs s\u00eb matjes q\u00eb vCPU ka qen\u00eb n\u00eb gjendje t\u00eb pap\u00ebrdorur. Vlerat e larta t\u00eb Idle nuk jan\u00eb nj\u00eb problem; thjesht vCPU nuk kishte \u00abgj\u00eb p\u00ebr t\u00eb b\u00ebr\u00eb\u00bb.<\/p>\n<p><b>Pritja<\/b> \u2013 sa koh\u00eb (ms) gjat\u00eb periudh\u00ebs s\u00eb matjes q\u00eb vCPU ka qen\u00eb n\u00eb gjendje Wait. Duke qen\u00eb se n\u00eb k\u00ebt\u00eb num\u00ebr perfshihen IDLE, vlerat e larta t\u00eb Wait gjithashtu nuk tregojn\u00eb p\u00ebr nj\u00eb problem. N\u00ebse, megjithat\u00eb, IDLE \u00ebsht\u00eb i ul\u00ebt me nj\u00eb Wait t\u00eb lart\u00eb, at\u00ebher\u00eb VM ka pritur p\u00ebrfundimin e operacioneve t\u00eb hyrjes\/daljes, e cila mund t\u00eb tregoj\u00eb p\u00ebr nj\u00eb problem me performanc\u00ebn e hard diskut ose ndonj\u00eb pajisje virtuale t\u00eb VM.<\/p>\n<p><b>Maksimal i limituar<\/b> \u2013 sa koh\u00eb (ms) gjat\u00eb periudh\u00ebs s\u00eb matjes q\u00eb vCPU ka qen\u00eb n\u00eb gjendje Ready p\u00ebr shkak t\u00eb nj\u00eb limiti t\u00eb vendosur p\u00ebr burimet. N\u00ebse performanca \u00ebsht\u00eb pa shpjegim e ul\u00ebt, \u00ebsht\u00eb e dobishme t\u00eb kontrolloni vler\u00ebn e k\u00ebtij numri dhe limitin e CPU n\u00eb cil\u00ebsimet e VM. VM mund t\u00eb ket\u00eb limite t\u00eb vendosura, t\u00eb cilat ju nuk i dini. P\u00ebr shembull, kjo ndodh kur VM \u00ebsht\u00eb klonuar nga nj\u00eb model, n\u00eb t\u00eb cilin ishte vendosur nj\u00eb limit p\u00ebr CPU.<\/p>\n<p><b>Pritja e Swap<\/b> \u2013 sa koh\u00eb gjat\u00eb periudh\u00ebs s\u00eb matjes q\u00eb vCPU ka pritur p\u00ebr operacionet me VMkernel Swap. N\u00ebse vlerat e k\u00ebtij numri jan\u00eb mbi zero, at\u00ebher\u00eb VM ka p\u00ebr siguri probleme me performanc\u00ebn. M\u00eb shum\u00eb mbi SWAP do t\u00eb flasim n\u00eb artikullin p\u00ebr numrat e memorie.<\/p>\n<h3>ESXTOP<\/h3>\n<p>\nN\u00ebse numrat e performanc\u00ebs n\u00eb vCenter jan\u00eb t\u00eb mir\u00eb p\u00ebr analizimin e t\u00eb dh\u00ebnave historike, analiza e menj\u00ebhershme e problemeve \u00ebsht\u00eb m\u00eb mir\u00eb t\u00eb b\u00ebhet n\u00eb ESXTOP. K\u00ebtu t\u00eb gjitha vlerat jan\u00eb t\u00eb paraqitura n\u00eb nj\u00eb form\u00eb t\u00eb gatshme (nuk ka nevoj\u00eb t\u00eb p\u00ebrkthehet asgj\u00eb) dhe periudha minimale e matjes \u00ebsht\u00eb 2 sekonda.<br \/>\nEkrani i ESXTOP p\u00ebr CPU aktivizohet me \u00e7el\u00ebsin \u00abc\u00bb dhe duket si m\u00eb posht\u00eb:<\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/f4f3611bc383007bdbaa0948001923c4.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nP\u00ebr leht\u00ebsin\u00eb, mund t\u00eb lini vet\u00ebm proceset e makinave virtuale duke shtypur Shift-V.<br \/>\nP\u00ebr t\u00eb par\u00eb metrikat p\u00ebr \u00e7do b\u00ebrtham\u00eb t\u00eb VM, shtypni \u00abe\u00bb dhe futni GID e VM-s\u00eb q\u00eb ju intereson (30919 n\u00eb screenshotin m\u00eb posht\u00eb):<\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/5f2c0226cee6e4e43128537bd4da843f.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nS\u00eb shpejti do ta kaloj mbi kolonat q\u00eb jan\u00eb paraqitur sipas parazgjedhjes. Kolona shtes\u00eb mund t\u00eb shtohen duke shtypur \u00abf\u00bb.<\/p>\n<p><b>NWLD (Numri i Bot\u00ebve)<\/b> \u2013 numri i proceseve n\u00eb grup. P\u00ebr t\u00eb zgjeruar grupin dhe par\u00eb metrikat p\u00ebr \u00e7do proces (p\u00ebr shembull, p\u00ebr \u00e7do b\u00ebrtham\u00eb t\u00eb VM me shum\u00eb b\u00ebrthama), shtypni \u201ce\u201d. N\u00ebse n\u00eb grup ka m\u00eb shum\u00eb se nj\u00eb proces, vlerat e metrikave p\u00ebr grupin jan\u00eb t\u00eb barabarta me shum\u00ebn e metrikave p\u00ebr proceset e ve\u00e7anta.<\/p>\n<p><b>%E P\u00cbRDORUR<\/b> \u2013 sa cikle CPU e serverit p\u00ebrdor procesi ose grupi i proceseve.<\/p>\n<p><b>%E EKZISTUES<\/b> \u2013 sa sa ka n\u00eb koh\u00eb t\u00eb periudh\u00ebs, procesi ka qen\u00eb n\u00eb gjendje RUN, dmth ka kryer pun\u00eb t\u00eb dobishme. Ndryshon nga %USED n\u00eb at\u00eb q\u00eb nuk merr parasysh hyper-threading, frekuenc\u00ebn e shkall\u00ebzimit dhe koh\u00ebn e kaluar n\u00eb detyra sistematike (%SYS).<\/p>\n<p><b>%SYS<\/b> \u2013 koha e kaluar n\u00eb detyra sistematike, p\u00ebr shembull: p\u00ebrpunimi i nd\u00ebrprerjeve, hyrja\/dalja, puna e rrjetit, etj. Vlera mund t\u00eb jet\u00eb e lart\u00eb n\u00ebse n\u00eb VM ka hyrje\/dalje t\u00eb madhe.<\/p>\n<p><b>%OVRLP<\/b> \u2013 sa koh\u00eb nj\u00eb b\u00ebrtham\u00eb fizike, n\u00eb t\u00eb cil\u00ebn po ekzekutohej procesi VM, kaloi n\u00eb detyra t\u00eb proceseve t\u00eb tjera.<\/p>\n<p>K\u00ebto metrika lidhen me nj\u00ebra-tjetr\u00ebn n\u00eb m\u00ebnyr\u00ebn e m\u00ebposhtme:<\/p>\n<p>%USED = %RUN + %SYS \u2014 %OVRLP.<\/p>\n<p>Normalisht, metrika %USED \u00ebsht\u00eb m\u00eb informuese.<\/p>\n<p><b>%WAIT<\/b> \u2013 sa koh\u00eb gjat\u00eb periudh\u00ebs procesi ka qen\u00eb n\u00eb gjendje Wait. P\u00ebfshin IDLE.<\/p>\n<p><b>%IDLE<\/b> \u2013 sa koh\u00eb gjat\u00eb periudh\u00ebs procesi ka qen\u00eb n\u00eb gjendje IDLE.<\/p>\n<p><b>%SWPWT<\/b> \u2013 sa koh\u00eb gjat\u00eb periudh\u00ebs vCPU ka pritur operacionin me VMkernel Swap.<\/p>\n<p><b>%VMWAIT<\/b> \u2013 sa koh\u00eb gjat\u00eb periudh\u00ebs vCPU ka qen\u00eb n\u00eb gjendje pritjeje p\u00ebr nj\u00eb ngjarje (zakonisht hyrje\/dalja). Nuk ka nj\u00eb num\u00ebr t\u00eb ngjash\u00ebm n\u00eb vCenter. Vlerat e larta tregojn\u00eb p\u00ebr probleme me hyrje\/dalje n\u00eb VM.<\/p>\n<p>%WAIT = %VMWAIT + %IDLE + %SWPWT.<\/p>\n<p>N\u00ebse VM nuk p\u00ebrdor VMkernel Swap, \u00ebsht\u00eb e arsyeshme t\u00eb shikoni %VMWAIT kur analizoni problemet me performanc\u00ebn, sepse kjo metrik\u00eb nuk merr parasysh koh\u00ebn kur VM nuk ka b\u00ebr\u00eb asgj\u00eb (%IDLE).<\/p>\n<p><b>%RDY<\/b> \u2013 sa koh\u00eb gjat\u00eb periudh\u00ebs procesi ka qen\u00eb n\u00eb gjendje Ready.<\/p>\n<p><b>%CSTP<\/b> \u2013 sa koh\u00eb gjat\u00eb periudh\u00ebs procesi ka qen\u00eb n\u00eb gjendje costop.<\/p>\n<p><b>%MLMTD<\/b> \u2013 sa koh\u00eb gjat\u00eb periudh\u00ebs vCPU ka qen\u00eb n\u00eb gjendje Ready p\u00ebr shkak t\u00eb kufizimit t\u00eb vendosur mbi burimet.<\/p>\n<p>%WAIT + %RDY + %CSTP + %RUN = 100% \u2013 b\u00ebrthama e VM \u00ebsht\u00eb gjithmon\u00eb n\u00eb nj\u00eb nga k\u00ebto kat\u00ebr gjendje.<\/p>\n<h3>CPU n\u00eb hipervizor<\/h3>\n<p>\nN\u00eb vCenter ka gjithashtu num\u00ebrues t\u00eb performanc\u00ebs CPU p\u00ebr hipervizorin, por ato nuk paraqesin ndonj\u00eb gj\u00eb interesante \u2013 \u00ebsht\u00eb thjesht shuma e num\u00ebruesve p\u00ebr t\u00eb gjitha VM n\u00eb server.<br \/>\nM\u00eb leht\u00eb \u00ebsht\u00eb t\u00eb shikoni gjendjen e CPU n\u00eb server n\u00eb sked\u00ebn P\u00ebrmbledhje:<\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/15b6b9a6da136d892fbaf7f80fc206c1.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nP\u00ebr serverin, ashtu si p\u00ebr makin\u00ebn virtuale, ka nj\u00eb Alarm standard:<\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/c3ae19ce3acd55cfff40d71437ee3a08.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nKur ngarkesa n\u00eb CPU t\u00eb serverit \u00ebsht\u00eb e lart\u00eb, VM-t\u00eb q\u00eb punojn\u00eb mbi t\u00eb fillojn\u00eb t\u00eb ken\u00eb probleme me performanc\u00ebn.<\/p>\n<p>N\u00eb ESXTOP, t\u00eb dh\u00ebnat e ngarkes\u00ebs s\u00eb CPU-s s\u00eb serverit paraqiten n\u00eb pjes\u00ebn e sip\u00ebrme t\u00eb ekranit. P\u00ebrve\u00e7 ngarkes\u00ebs standarde t\u00eb CPU-s, e cila \u00ebsht\u00eb pak informuese p\u00ebr hipervizor\u00ebt, ka edhe tre metrika t\u00eb tjera:<\/p>\n<p><b>CORE UTIL(%)<\/b> \u2013 ngarkesa e b\u00ebrtham\u00ebs s\u00eb serverit fizik. Ky num\u00ebrator tregon se sa koh\u00eb, gjat\u00eb periudh\u00ebs s\u00eb matjes, b\u00ebrthama ka kryer pun\u00eb.<\/p>\n<p><b>PCPU UTIL(%)<\/b> \u2013 n\u00ebse \u00ebsht\u00eb e aktivizuar hyper-threading, p\u00ebr \u00e7do b\u00ebrtham\u00eb fizike ka dy rrjedha (PCPU). Kjo metrik\u00eb tregon se sa koh\u00eb \u00e7do rrjedh ka kryer pun\u00eb.<\/p>\n<p><b>PCPU USED(%)<\/b> \u2013 e nj\u00ebjta si PCPU UTIL(%), por merr parasysh shkall\u00ebzimin e frekuenc\u00ebs (ose uljen e frekuenc\u00ebs s\u00eb b\u00ebrtham\u00ebs p\u00ebr q\u00ebllime kursimi energjie, ose rritjen e frekuenc\u00ebs s\u00eb b\u00ebrtham\u00ebs p\u00ebrmes teknologjis\u00eb Turbo Boost) dhe hyper-threading.<\/p>\n<p>PCPU_USED% = PCPU_UTIL% * frekuenc\u00ebn efektive t\u00eb b\u00ebrtham\u00ebs \/ frekuenc\u00ebn nominale t\u00eb b\u00ebrtham\u00ebs.<\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/dd8562ea91bee55bbf630358df26c217.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<i>N\u00eb k\u00ebt\u00eb screenshot, p\u00ebr disa b\u00ebrthama p\u00ebr shkak t\u00eb funksionimit t\u00eb Turbo Boost, vlera USED \u00ebsht\u00eb m\u00eb e madhe se 100%, pasi frekuenca e b\u00ebrtham\u00ebs \u00ebsht\u00eb m\u00eb e lart\u00eb se ajo nominale.<\/i><\/p>\n<p>Nj\u00eb fjal\u00eb p\u00ebr m\u00ebnyr\u00ebn se si llogaritet hyper-threading. N\u00ebse proceset ekzekutohen 100% t\u00eb koh\u00ebs n\u00eb t\u00eb dy rrjedhat e b\u00ebrtham\u00ebs fizike t\u00eb serverit, nd\u00ebrsa b\u00ebrthama punon me frekuenc\u00ebn nominale, at\u00ebher\u00eb:<\/p>\n<ul>\n<li>CORE UTIL p\u00ebr b\u00ebrtham\u00ebn do t\u00eb jet\u00eb 100%,<\/li>\n<li>PCPU UTIL p\u00ebr t\u00eb dy rrjedhat do t\u00eb jet\u00eb 100%,<\/li>\n<li>PCPU USED p\u00ebr t\u00eb dy rrjedhat do t\u00eb jet\u00eb 50%.<\/li>\n<\/ul>\n<p>\nN\u00ebse t\u00eb dy rrjedhat nuk kan\u00eb punuar 100% t\u00eb koh\u00ebs gjat\u00eb periudh\u00ebs s\u00eb matjes, at\u00ebher\u00eb n\u00eb ato periudha, kur rrjedhat punonin paralelisht, PCPU USED p\u00ebr b\u00ebrthamat ndahet n\u00eb dy pjes\u00eb.<\/p>\n<p>N\u00eb ESXTOP ka gjithashtu nj\u00eb ekran me parametrat e konsumit t\u00eb energjis\u00eb t\u00eb CPU-s s\u00eb serverit. K\u00ebtu mund t\u00eb shihni n\u00ebse serveri po p\u00ebrdor teknologjit\u00eb p\u00ebr kursim energjie: C-states dhe P-states. Aktivizohet me \u00e7el\u00ebsin 'p':<\/p>\n<p><img decoding=\"async\" alt=\"Performance analysis of a virtual machine in VMware vSphere. Part 1: CPU\" src=\"\/wp-content\/uploads\/2019\/05\/531bf847b99f86bec0bd90e005919c79.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<\/p>\n<h3>Problemet standarde t\u00eb performanc\u00ebs s\u00eb CPU-s<\/h3>\n<p>\nN\u00eb fund, do t\u00eb kaloj mbi arsyet tipike q\u00eb shkaktojn\u00eb probleme me performanc\u00ebn e CPU-s n\u00eb VM dhe do t'i jap disa k\u00ebshilla t\u00eb shkurtra p\u00ebr zgjidhjen e tyre:<\/p>\n<p><b>Mungon frekuenca e b\u00ebrtham\u00ebs.<\/b> N\u00ebse nuk ka mund\u00ebsi p\u00ebr t\u00eb transferuar VM n\u00eb b\u00ebrthama m\u00eb t\u00eb fuqishme, mund t\u00eb provoni t\u00eb ndryshoni konfigurimet e konsumit t\u00eb energjis\u00eb, n\u00eb m\u00ebnyr\u00eb q\u00eb Turbo Boost t\u00eb funksionoj\u00eb m\u00eb efikas.<\/p>\n<p><b>Dimensionimi i gabuar i VM (shum\u00eb ose pak b\u00ebrthama).<\/b> N\u00ebse vendosni pak b\u00ebrthama, do t\u00eb ket\u00eb nj\u00eb ngarkes\u00eb t\u00eb lart\u00eb t\u00eb CPU-s s\u00eb VM. N\u00ebse shum\u00eb, do t\u00eb p\u00ebrballeni me nj\u00eb co-stop t\u00eb lart\u00eb.<\/p>\n<p><b>Rishp\u00ebrndarje e madhe e CPU-s n\u00eb server.<\/b> N\u00ebse VM ka nj\u00eb Ready t\u00eb lart\u00eb, ulni rishp\u00ebrndarjen e CPU-s.<\/p>\n<p><b>Topologjia e gabuar NUMA n\u00eb VM-t\u00eb e m\u00ebdha.<\/b> Topologjia NUMA, q\u00eb e sheh VM (vNUMA), duhet t\u00eb p\u00ebrputhet me topologjin\u00eb NUMA t\u00eb serverit (pNUMA). P\u00ebr diagnostikim dhe mund\u00ebsit\u00eb e zgjidhjes s\u00eb k\u00ebsaj problemi, \u00ebsht\u00eb shkruar, p\u00ebr shembull, n\u00eb librin <noindex><a rel=\"nofollow\" href=\"https:\/\/pages.rubrik.com\/host-resources-deep-dive_request.html\">\u00abVMware vSphere 6.5 Host Resources Deep Dive\u00bb<\/a><\/noindex>. N\u00ebse nuk d\u00ebshironi t\u00eb thelloheni dhe nuk keni kufizime licencash p\u00ebr OS-n\u00eb e instaluar n\u00eb VM, krijoni shum\u00eb sokete virtuale n\u00eb VM me nj\u00eb b\u00ebrthame. Nuk do t\u00eb humbni shum\u00eb \ud83d\ude42<\/p>\n<p>K\u00ebtu p\u00ebr CPU-n\u00eb kam p\u00ebrfunduar. B\u00ebni pyetje. N\u00eb pjes\u00ebn tjet\u00ebr do flas p\u00ebr memorien operative.<\/p>\n<p><b class=\"spoiler_title\">Useful links<\/b><noindex><a rel=\"nofollow\" href=\"http:\/\/virtual-red-dot.info\/vm-cpu-counters-vsphere\/\">http:\/\/virtual-red-dot.info\/vm-cpu-counters-vsphere\/<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/kb.vmware.com\/kb\/1017926\">https:\/\/kb.vmware.com\/kb\/1017926<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"http:\/\/www.yellow-bricks.com\/2012\/07\/17\/why-is-wait-so-high\/\">http:\/\/www.yellow-bricks.com\/2012\/07\/17\/why-is-wait-so-high\/<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/communities.vmware.com\/docs\/DOC-9279\">https:\/\/communities.vmware.com\/docs\/DOC-9279<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/www.vmware.com\/content\/dam\/digitalmarketing\/vmware\/en\/pdf\/techpaper\/performance\/whats-new-vsphere65-perf.pdf\">https:\/\/www.vmware.com\/content\/dam\/digitalmarketing\/vmware\/en\/pdf\/techpaper\/performance\/whats-new-vsphere65-perf.pdf<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/pages.rubrik.com\/host-resources-deep-dive_request.html\">https:\/\/pages.rubrik.com\/host-resources-deep-dive_request.html<\/a><\/noindex><br \/>\n<br \/>Burimi: <a content=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/habr.com\/ru\/company\/dataline\/blog\/452884\/\">habr.com<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u0415\u0441\u043b\u0438 \u0432\u044b \u0430\u0434\u043c\u0438\u043d\u0438\u0441\u0442\u0440\u0438\u0440\u0443\u0435\u0442\u0435 \u0432\u0438\u0440\u0442\u0443\u0430\u043b\u044c\u043d\u0443\u044e \u0438\u043d\u0444\u0440\u0430\u0441\u0442\u0440\u0443\u043a\u0442\u0443\u0440\u0443 \u043d\u0430 \u0431\u0430\u0437\u0435 VMware vSphere (\u0438\u043b\u0438 \u043b\u044e\u0431\u043e\u0433\u043e \u0434\u0440\u0443\u0433\u043e\u0433\u043e \u0441\u0442\u0435\u043a\u0430 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0439), \u0442\u043e \u043d\u0430\u0432\u0435\u0440\u043d\u044f\u043a\u0430 \u0447\u0430\u0441\u0442\u043e \u0441\u043b\u044b\u0448\u0438\u0442\u0435 \u043e\u0442 \u043f\u043e\u043b\u044c\u0437\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439 \u0436\u0430\u043b\u043e\u0431\u044b: \u00ab\u0412\u0438\u0440\u0442\u0443\u0430\u043b\u044c\u043d\u0430\u044f \u043c\u0430\u0448\u0438\u043d\u0430 \u0440\u0430\u0431\u043e\u0442\u0430\u0435\u0442 \u043c\u0435\u0434\u043b\u0435\u043d\u043d\u043e!\u00bb. \u0412 \u044d\u0442\u043e\u043c \u0446\u0438\u043a\u043b\u0435 \u0441\u0442\u0430\u0442\u0435\u0439 \u0440\u0430\u0437\u0431\u0435\u0440\u0443 \u043c\u0435\u0442\u0440\u0438\u043a\u0438 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u0438 \u0438 \u0440\u0430\u0441\u0441\u043a\u0430\u0436\u0443, \u0447\u0442\u043e \u0438 \u043f\u043e\u0447\u0435\u043c\u0443 \u00ab\u0442\u043e\u0440\u043c\u043e\u0437\u0438\u0442\u00bb \u0438 \u043a\u0430\u043a \u0441\u0434\u0435\u043b\u0430\u0442\u044c \u0442\u0430\u043a, \u0447\u0442\u043e\u0431\u044b \u043d\u0435 \u00ab\u0442\u043e\u0440\u043c\u043e\u0437\u0438\u043b\u043e\u00bb. \u0411\u0443\u0434\u0443 \u0440\u0430\u0441\u0441\u043c\u0430\u0442\u0440\u0438\u0432\u0430\u0442\u044c \u0441\u043b\u0435\u0434\u0443\u044e\u0449\u0438\u0435 \u0430\u0441\u043f\u0435\u043a\u0442\u044b \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u0438 \u0432\u0438\u0440\u0442\u0443\u0430\u043b\u044c\u043d\u044b\u0445 \u043c\u0430\u0448\u0438\u043d: CPU, RAM, DISK, [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":25892,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[688],"tags":[],"class_list":["post-34335","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-administrirovanie"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.2 - aioseo.com -->\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"Yuri Gagarin\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/prohoster.info\/sq\/blog\/administrirovanie\/analiz-proizvoditelnosti-virtualnoj-mashiny-v-vmware-vsphere-chast-1-cpu\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.2\" \/>\n\t\t<meta property=\"og:locale\" content=\"sq_AL\" \/>\n\t\t<meta property=\"og:site_name\" content=\"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"\ud83e\udd47\u0410\u043d\u0430\u043b\u0438\u0437 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u0438 \u0432\u0438\u0440\u0442\u0443\u0430\u043b\u044c\u043d\u043e\u0439 \u043c\u0430\u0448\u0438\u043d\u044b \u0432 VMware vSphere. \u0427\u0430\u0441\u0442\u044c 1: CPU | ProHoster\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/sq\/blog\/administrirovanie\/analiz-proizvoditelnosti-virtualnoj-mashiny-v-vmware-vsphere-chast-1-cpu\" \/>\n\t\t<meta property=\"og:image\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:secure_url\" content=\"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg\" \/>\n\t\t<meta property=\"og:image:width\" content=\"350\" \/>\n\t\t<meta property=\"og:image:height\" content=\"350\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2019-10-31T18:57:43+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2019-10-31T18:57:43+00:00\" \/>\n\t\t<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<meta property=\"article:author\" content=\"https:\/\/www.facebook.com\/prohoster\" \/>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"\ud83e\udd47Analiza e performanc\u00ebs s\u00eb makin\u00ebs virtuale n\u00eb VMware vSphere. Pjesa 1: CPU | ProHoster","description":"","canonical_url":"https:\/\/prohoster.info\/sq\/blog\/administrirovanie\/analiz-proizvoditelnosti-virtualnoj-mashiny-v-vmware-vsphere-chast-1-cpu","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"sq_AL","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47\u0410\u043d\u0430\u043b\u0438\u0437 \u043f\u0440\u043e\u0438\u0437\u0432\u043e\u0434\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0441\u0442\u0438 \u0432\u0438\u0440\u0442\u0443\u0430\u043b\u044c\u043d\u043e\u0439 \u043c\u0430\u0448\u0438\u043d\u044b \u0432 VMware vSphere. \u0427\u0430\u0441\u0442\u044c 1: CPU | ProHoster","og:url":"https:\/\/prohoster.info\/sq\/blog\/administrirovanie\/analiz-proizvoditelnosti-virtualnoj-mashiny-v-vmware-vsphere-chast-1-cpu","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2019-10-31T18:57:43+00:00","article:modified_time":"2019-10-31T18:57:43+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"34335","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":"2026-01-21 18:48:19","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-03-01 02:23:17","updated":"2026-01-21 18:48:19","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/posts\/34335","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/comments?post=34335"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/posts\/34335\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/media\/25892"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/media?parent=34335"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/categories?post=34335"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/sq\/wp-json\/wp\/v2\/tags?post=34335"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}