{"id":36486,"date":"2019-10-31T22:11:54","date_gmt":"2019-10-31T19:11:54","guid":{"rendered":"https:\/\/prohoster.info\/blog\/analiz-proizvoditelnosti-vm-v-vmware-vsphere-chast-3-storage\/"},"modified":"2019-10-31T22:11:54","modified_gmt":"2019-10-31T19:11:54","slug":"analiz-proizvoditelnosti-vm-v-vmware-vsphere-chast-3-storage","status":"publish","type":"post","link":"https:\/\/prohoster.info\/sv\/blog\/administrirovanie\/analiz-proizvoditelnosti-vm-v-vmware-vsphere-chast-3-storage","title":{"rendered":"Prestandaanalys av VM i VMware vSphere. Del 3: Lagring","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"<p><img decoding=\"async\" alt=\"Prestandaanalys av VM i VMware vSphere. Del 3: Lagring\" src=\"\/wp-content\/uploads\/2019\/07\/8f3ffe4a8666f3c2f7126d8fecfa1e3a.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/habr.com\/ru\/company\/dataline\/blog\/452884\/\">Del 1. Om CPU<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/habr.com\/ru\/company\/dataline\/blog\/455820\/\">Del 2. Om minnet<\/a><\/noindex><\/p>\n<p>Idag ska vi g\u00e5 igenom metrik f\u00f6r lagringssystemet i vSphere. Lagringsproblem \u00e4r den vanligaste orsaken till l\u00e5ngsam prestanda hos virtuella maskiner. Medan fels\u00f6kning av CPU och RAM ofta avslutas p\u00e5 hypervisor-niv\u00e5, kan det vid diskproblem vara n\u00f6dv\u00e4ndigt att titta p\u00e5 datan\u00e4tverket och lagringssystemet.<\/p>\n<p>Jag kommer att diskutera detta \u00e4mne med hj\u00e4lp av block\u00e5tkomst till lagringssystemet, \u00e4ven om m\u00e4tv\u00e4rdena \u00e4r ungef\u00e4r desamma vid fil\u00e5tkomst.<br \/>\n<noindex><a rel=\"nofollow\" name=\"habracut\"><\/a><\/noindex><\/p>\n<h3>Lite teori<\/h3>\n<p>\nN\u00e4r man pratar om prestanda hos lagringssystem f\u00f6r virtuella maskiner, fokuserar man vanligtvis p\u00e5 tre sammanl\u00e4nkade parametrar:<\/p>\n<ul>\n<li>antalet in- och utdataoperationer (Input\/Output Operations Per Second, IOPS);<\/li>\n<li>bandbredd (Throughput);<\/li>\n<li>f\u00f6rdr\u00f6jningen av in- och utdataoperationer (Latency).<\/li>\n<\/ul>\n<p>\n<b>Antalet IOPS<\/b> \u00e4r vanligtvis viktigt f\u00f6r belastningar av slumpm\u00e4ssig karakt\u00e4r: \u00e5tkomst till block p\u00e5 disken som ligger p\u00e5 olika platser. Exempel p\u00e5 s\u00e5dana belastningar kan vara databaser, aff\u00e4rsapplikationer (ERP, CRM) etc.<\/p>\n<p><b>Bandbredd<\/b> \u00e4r viktiga f\u00f6r belastningar av sekventiell karakt\u00e4r: \u00e5tkomst till block som ligger efter varandra. Till exempel kan s\u00e5dana belastningar genereras av filservrar (men inte alltid) och system f\u00f6r video\u00f6vervakning.<\/p>\n<p>Bandbredden \u00e4r relaterad till antalet in- och utdataoperationer p\u00e5 f\u00f6ljande s\u00e4tt:<\/p>\n<p><i>Throughput = IOPS * Blockstorlek<\/i>, d\u00e4r Blockstorlek \u00e4r storleken p\u00e5 blocket.<\/p>\n<p>Blockstorleken \u00e4r en ganska viktig egenskap. Moderna versioner av ESXi till\u00e5ter blockstorlekar upp till 32 767 KB. Om blocket \u00e4r \u00e4nnu st\u00f6rre delas det upp i flera. Inte alla lagringssystem kan effektivt hantera s\u00e5dana stora block, d\u00e4rf\u00f6r finns det en parameter i avancerade inst\u00e4llningar i ESXi som heter DiskMaxIOSize. Genom denna kan man minska den maximala blockstorlek som hypervisorn till\u00e5ter (mer information <noindex><a rel=\"nofollow\" href=\"https:\/\/kb.vmware.com\/s\/article\/1003469\">h\u00e4r<\/a><\/noindex>). Jag rekommenderar att man r\u00e5dfr\u00e5gar tillverkaren av lagringssystemet innan man \u00e4ndrar denna parameter, eller \u00e5tminstone testa \u00e4ndringarna p\u00e5 en laboratoriestand.\u00a0<\/p>\n<p>En stor blockstorlek kan negativt p\u00e5verka prestandan hos lagringssystemet. \u00c4ven om antalet IOPS och throughput \u00e4r relativt l\u00e5gt, kan det vid stor blockstorlek uppst\u00e5 h\u00f6ga f\u00f6rdr\u00f6jningar. S\u00e5 var uppm\u00e4rksam p\u00e5 denna parameter.<\/p>\n<p><b>F\u00f6rdr\u00f6jning<\/b> \u2013 den mest intressanta parametern f\u00f6r prestanda. F\u00f6rdr\u00f6jningen f\u00f6r in- och utdataoperationer f\u00f6r den virtuella maskinen best\u00e5r av:<\/p>\n<ul>\n<li>f\u00f6rdr\u00f6jningar inuti hypervisorn (KAVG, genomsnittlig k\u00e4rna milliSec\/L\u00e4s);<\/li>\n<li>f\u00f6rdr\u00f6jningar orsakade av datan\u00e4t och LUN (DAVG, genomsnittlig drivrutin milliSec\/kommando).<\/li>\n<\/ul>\n<p>\nDen totala f\u00f6rdr\u00f6jningen som syns i g\u00e4st-OS (GAVG, genomsnittlig g\u00e4st milliSec\/kommando) \u00e4r summan av KAVG och DAVG.<\/p>\n<p>GAVG och DAVG m\u00e4ts, medan KAVG ber\u00e4knas: GAVG\u2013DAVG.<\/p>\n<p><img decoding=\"async\" alt=\"Prestandaanalys av VM i VMware vSphere. Del 3: Lagring\" src=\"\/wp-content\/uploads\/2019\/07\/729f519b4fb72b3fbb74237847a05baa.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n <noindex><a rel=\"nofollow\" href=\"https:\/\/www.codyhosterman.com\/2018\/03\/what-is-the-latency-stat-qavg\/\"><i>K\u00e4lla<\/i><\/a><\/noindex><\/p>\n<p>L\u00e5t oss titta n\u00e4rmare p\u00e5 <b>KAVG<\/b>. Vid normal drift b\u00f6r KAVG str\u00e4va mot noll eller \u00e5tminstone vara mycket mindre \u00e4n DAVG. Det enda jag k\u00e4nner till d\u00e4r KAVG f\u00f6rv\u00e4ntas vara h\u00f6g \u00e4r diskens IOPS-begr\u00e4nsning f\u00f6r VMen. I s\u00e5dana fall kommer KAVG att \u00f6ka vid f\u00f6rs\u00f6k att \u00f6verskrida gr\u00e4nsen.<\/p>\n<p>Den mest signifikanta komponenten av KAVG \u00e4r QAVG \u2013 tiden i k\u00f6 f\u00f6r behandling inuti hypervisorn. \u00d6vriga komponenter av KAVG \u00e4r f\u00f6rsumbar sm\u00e5.<\/p>\n<p>K\u00f6n i diskdrivrutinen och k\u00f6erna till LUNarna har en fast storlek. F\u00f6r h\u00f6gbelastade milj\u00f6er kan det vara anv\u00e4ndbart att \u00f6ka denna storlek. <noindex><a rel=\"nofollow\" href=\"https:\/\/kb.vmware.com\/s\/article\/1267\">H\u00e4r<\/a><\/noindex> beskriver hur man \u00f6kar k\u00f6erna i adapterdrivrutinen (samtidigt \u00f6kar k\u00f6n till LUNarna). Denna inst\u00e4llning fungerar n\u00e4r bara en VM arbetar med LUNen, vilket \u00e4r s\u00e4llan. Om flera VMar \u00e4r anslutna till LUNen, m\u00e5ste \u00e4ven parameter <i>Disk.SchedNumReqOutstanding<\/i> (instruktion\u00a0 <noindex><a rel=\"nofollow\" href=\"https:\/\/kb.vmware.com\/s\/article\/1268\">h\u00e4r<\/a><\/noindex>). Genom att \u00f6ka k\u00f6n minskar du QAVG och KAVG i enlighet med detta.<\/p>\n<p>Men, som alltid, bekanta dig f\u00f6rst med dokumentationen fr\u00e5n HBA-leverant\u00f6ren och testa \u00e4ndringarna p\u00e5 ett laboratorium. <\/p>\n<p>K\u00f6n till LUNen kan p\u00e5verkas av aktiveringen av SIOC-mekanismen (Storage I\/O Control). Den s\u00e4kerst\u00e4ller j\u00e4mn tillg\u00e5ng till LUNen fr\u00e5n alla servrar i klustret genom att dynamiskt \u00e4ndra k\u00f6n till LUNen p\u00e5 servrarna. Det vill s\u00e4ga, om en VM p\u00e5 en av v\u00e4rdarna kr\u00e4ver oproportionerligt mycket prestanda (noisy neighbor VM), minskar SIOC l\u00e4ngden p\u00e5 k\u00f6n till LUNen p\u00e5 den v\u00e4rden (DQLEN). Mer information <noindex><a rel=\"nofollow\" href=\"http:\/\/www.yellow-bricks.com\/2019\/03\/05\/dqlen-changes-what-is-going-on\/\">h\u00e4r<\/a><\/noindex>.<\/p>\n<p>Vi har f\u00f6rst\u00e5tt KAVG, nu lite om <b>DAVG<\/b>. H\u00e4r \u00e4r allt enkelt: DAVG \u00e4r den f\u00f6rdr\u00f6jning som den externa milj\u00f6n (datan\u00e4t och LUN) ger. I varje modern och \u00e4ven \u00e4ldre LUN finns det egna prestandaindikatorer. F\u00f6r att analysera problem med DAVG \u00e4r det meningsfullt att titta p\u00e5 dem. Om allt ser bra ut fr\u00e5n ESXi och LUN, kontrollera datan\u00e4tverket.<\/p>\n<p>F\u00f6r att undvika prestandaproblem, v\u00e4lj r\u00e4tt Path Selection Policy (PSP) f\u00f6r din lagringsl\u00f6sning. N\u00e4stan alla moderna lagringssystem st\u00f6djer PSP Round-Robin (med ALUA, Asymmetric Logical Unit Access, eller utan). Denna policy m\u00f6jligg\u00f6r utnyttjande av alla tillg\u00e4ngliga v\u00e4gar till lagringssystemet. I fallet med ALUA anv\u00e4nds endast v\u00e4gar till den kontroller som \u00e4ger LUN:en. Det finns inte alltid standardregler f\u00f6r alla lagringssystem p\u00e5 ESXi, som st\u00e4ller in policyn Round-Robin. Om det inte finns n\u00e5gra regler f\u00f6r ditt lagringssystem, anv\u00e4nd leverant\u00f6rens plugin f\u00f6r att skapa motsvarande regel p\u00e5 alla v\u00e4rdar i klustret, eller skapa regeln sj\u00e4lv. Mer information <noindex><a rel=\"nofollow\" href=\"https:\/\/kb.vmware.com\/s\/article\/2053628\">h\u00e4r<\/a><\/noindex>.\u00a0<\/p>\n<p>\u00c4ven vissa lagringssystemstillverkare rekommenderar att \u00e4ndra antalet IOPS per v\u00e4g fr\u00e5n standardv\u00e4rdet 1000 till 1. I v\u00e5r praktik har detta gjort det m\u00f6jligt att \"pressa ut\" mer prestanda fr\u00e5n lagringssystemet och avsev\u00e4rt minska den tid som kr\u00e4vs f\u00f6r failover vid h\u00e5rdvarufel eller uppgraderingar av kontrollerna. Kontrollera med leverant\u00f6rens rekommendationer, och om det inte finns n\u00e5gra kontraindikationer, prova att \u00e4ndra detta parameter. Mer information <noindex><a rel=\"nofollow\" href=\"https:\/\/kb.vmware.com\/s\/article\/2069356\">h\u00e4r<\/a><\/noindex>.<\/p>\n<h3>Huvudsakliga prestandaindikatorer f\u00f6r diskunderlaget i den virtuella maskinen<\/h3>\n<p>\nPrestandaindikatorerna f\u00f6r diskunderlaget i vCenter \u00e4r samlade i avsnitten Datastore, Disk, Virtual Disk:<\/p>\n<p><img decoding=\"async\" alt=\"Prestandaanalys av VM i VMware vSphere. Del 3: Lagring\" src=\"\/wp-content\/uploads\/2019\/07\/ae852a6a128914a7aff36f461c5f0721.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n <br \/>\nI avsnittet <b>Datastore<\/b> h\u00e4r finns metrik f\u00f6r diskstorage vSphere (datastores) d\u00e4r virtuella maskinens diskar ligger. H\u00e4r hittar du standardindikatorer f\u00f6r:<\/p>\n<ul>\n<li>IOPS (genomsnittligt antal l\u00e4s-\/skrivf\u00f6rfr\u00e5gningar per sekund),\u00a0<\/li>\n<li>bandbredd (l\u00e4s-\/skrivhastighet),\u00a0<\/li>\n<li>f\u00f6rdr\u00f6jningar (l\u00e4s-\/skriv-\/h\u00f6gsta f\u00f6rdr\u00f6jning).<\/li>\n<\/ul>\n<p>\nFr\u00e5n namnen p\u00e5 indikatorerna framg\u00e5r i princip allt. Jag vill \u00e5terigen p\u00e5peka att h\u00e4r statistiken inte g\u00e4ller en specifik virtuell maskin (eller disk i den virtuella maskinen), utan \u00e4r generell f\u00f6r hela datastoren. Enligt min mening \u00e4r det l\u00e4ttare att se denna statistik i ESXTOP, \u00e4ven med tanke p\u00e5 att den minimi m\u00e4tperioden d\u00e4r \u00e4r 2 sekunder.<\/p>\n<p>I avsnittet <b>Disk<\/b> h\u00e4r finns metrik f\u00f6r blocklagringsenheterna som anv\u00e4nds av den virtuella maskinen. H\u00e4r finns indikatorer f\u00f6r IOPS av typen summation (antal in- och utdataoperationer under m\u00e4tperioden) och flera indikatorer relaterade till block\u00e5tkomst (Aborterade kommandon, Buss\u00e5terst\u00e4llningar). Denna information, enligt min mening, \u00e4r ocks\u00e5 l\u00e4ttare att se i ESXTOP.<\/p>\n<p>Avsnitt <b>Virtuell disk<\/b> \u2013 den mest anv\u00e4ndbara n\u00e4r det g\u00e4ller att s\u00f6ka efter prestandaproblem i diskunderlaget f\u00f6r VM. H\u00e4r kan du se prestanda per virtuell disk. Denna information \u00e4r avg\u00f6rande f\u00f6r att f\u00f6rst\u00e5 om det finns ett problem med en specifik virtuell maskin. F\u00f6rutom de standardr\u00e4knare f\u00f6r in-\/utdataoperationer, l\u00e4s-\/skrivvolymer och f\u00f6rdr\u00f6jningar, finns det anv\u00e4ndbara r\u00e4knare i denna avsnitt som visar blockstorlek: Read\/Write request size.<\/p>\n<p>I bilden nedan visas diskens VM-prestandadiagram, d\u00e4r du kan se antalet IOPS, f\u00f6rdr\u00f6jningar och blockstorlek.\u00a0<\/p>\n<p><img decoding=\"async\" alt=\"Prestandaanalys av VM i VMware vSphere. Del 3: Lagring\" src=\"\/wp-content\/uploads\/2019\/07\/36d2a4d006d2c1bfd4d9961c745f26b6.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nDu kan ocks\u00e5 se prestandametrik f\u00f6r hela datastoren om SIOC \u00e4r aktiverat. H\u00e4r presenteras grundl\u00e4ggande information om genomsnittlig latency och IOPS. Som standard kan denna information bara ses i realtid.<\/p>\n<p><img decoding=\"async\" alt=\"Prestandaanalys av VM i VMware vSphere. Del 3: Lagring\" src=\"\/wp-content\/uploads\/2019\/07\/7872dd131008dfdae09141553b4e42f6.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<\/p>\n<h3>ESXTOP<\/h3>\n<p>\nI ESXTOP finns flera sk\u00e4rmar som visar information om v\u00e4rdens diskunderlag, specifika virtuella maskiner och deras diskar.<\/p>\n<p>Vi b\u00f6rjar med information om virtuella maskiner. Sk\u00e4rmen 'Disk VM' aktiveras med tangenten 'v':<\/p>\n<p><img decoding=\"async\" alt=\"Prestandaanalys av VM i VMware vSphere. Del 3: Lagring\" src=\"\/wp-content\/uploads\/2019\/07\/793273e19fca1e4f19b96204202019fb.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\n<b>NVDISK<\/b> \u2013 \u00e4r antalet diskar f\u00f6r VM. F\u00f6r att se information om varje disk, tryck p\u00e5 'e' och ange GID f\u00f6r den intressanta VM:n.<\/p>\n<p>V\u00e4rdena f\u00f6r de \u00f6vriga parametrarna p\u00e5 denna sk\u00e4rm \u00e4r tydliga fr\u00e5n deras namn.<\/p>\n<p>En annan anv\u00e4ndbar sk\u00e4rm n\u00e4r man s\u00f6ker efter problem \u00e4r Disk adapter. Den aktiveras med tangenten 'd' (i bilden nedan har f\u00e4lten A, B, C, D, E, G valts):<\/p>\n<p><img decoding=\"async\" alt=\"Prestandaanalys av VM i VMware vSphere. Del 3: Lagring\" src=\"\/wp-content\/uploads\/2019\/07\/71a7f1e3f1e40f3dbacf61385a3c07cc.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\n<b>NPTH<\/b> \u2013 antalet v\u00e4gar till lun som syns fr\u00e5n denna adapter. F\u00f6r att f\u00e5 information om varje v\u00e4g p\u00e5 adaptern, tryck p\u00e5 'e' och ange namnet p\u00e5 adaptern:<\/p>\n<p><img decoding=\"async\" alt=\"Prestandaanalys av VM i VMware vSphere. Del 3: Lagring\" src=\"\/wp-content\/uploads\/2019\/07\/12661003ce8be542ed4c5e262da77d90.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\n<b>AQLEN<\/b> \u2013 den maximala storleken p\u00e5 k\u00f6n p\u00e5 adaptern.<\/p>\n<p>Dessutom visas r\u00e4knare f\u00f6r f\u00f6rdr\u00f6jningar p\u00e5 denna sk\u00e4rm, om vilka jag talade tidigare: <b>KAVG\/cmd, GAVG\/cmd, DAVG\/cmd, QAVG\/cmd<\/b>. <\/p>\n<p>P\u00e5 sk\u00e4rmen Disk device, som aktiveras med tangenten 'u', visas information om enskilda blockenheter \u2013 lun (i bilden nedan har f\u00e4lten A, B, F, G, I valts). H\u00e4r kan du se k\u00f6status f\u00f6r lun. <\/p>\n<p><img decoding=\"async\" alt=\"Prestandaanalys av VM i VMware vSphere. Del 3: Lagring\" src=\"\/wp-content\/uploads\/2019\/07\/6331ee64398fe7057c0eec015165f0a5.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\n<b>DQLEN<\/b> \u2013 storleken p\u00e5 k\u00f6n f\u00f6r blockenheten.<br \/>\n<b>ACTV<\/b> \u2013 antalet in-\/utdataoperationer i ESXi-k\u00e4rnan.<br \/>\n<b>QUED<\/b> \u2013 antalet in-\/utdataoperationer i k\u00f6n.<br \/>\n<b>%USD<\/b> \u2013 AACTIVE \/ DQLEN \u00d7 100%.<br \/>\n<b>LOAD<\/b> \u2013 (ACTV + QUED) \/ DQLEN.<\/p>\n<p>Om %USD \u00e4r h\u00f6gt, b\u00f6r du \u00f6verv\u00e4ga att \u00f6ka k\u00f6n. Ju fler kommandon i k\u00f6n, desto h\u00f6gre QAVG och, i sin tur, KAVG.<\/p>\n<p>P\u00e5 Disk-enhets-sk\u00e4rmen kan du ocks\u00e5 se om VAAI (vStorage API for Array Integration) fungerar p\u00e5 lagringssystemet. F\u00f6r att g\u00f6ra detta m\u00e5ste du v\u00e4lja f\u00e4lten A och O. <\/p>\n<p>VAAI-mekanismen m\u00f6jligg\u00f6r att en del av arbetet flyttas fr\u00e5n hypervisorn direkt till lagringssystemet, till exempel nollst\u00e4llning, blockkopiering eller blockering.<\/p>\n<p><img decoding=\"async\" alt=\"Prestandaanalys av VM i VMware vSphere. Del 3: Lagring\" src=\"\/wp-content\/uploads\/2019\/07\/131342d74e69af9c0898a1b350e883c8.jpg\" style=\"display:block;margin: 0 auto;\" \/><br \/>\n<br \/>\nSom visas p\u00e5 bilden ovan fungerar VAAI p\u00e5 detta lagringssystem: primitiverna Zero och ATS anv\u00e4nds aktivt.<\/p>\n<h3>Tips f\u00f6r att optimera diskundersystemets prestationer p\u00e5 ESXi<\/h3>\n<p><\/p>\n<ul>\n<li>Var uppm\u00e4rksam p\u00e5 blockstorleken.<\/li>\n<li>St\u00e4ll in den optimala k\u00f6storleken p\u00e5 HBA.<\/li>\n<li>Gl\u00f6m inte att aktivera SIOC p\u00e5 datalagringsutrymmen.<\/li>\n<li>V\u00e4lj PSP i enlighet med tillverkarens rekommendationer f\u00f6r lagringssystemet.<\/li>\n<li>Se till att VAAI fungerar.<\/li>\n<\/ul>\n<p>\n<b class=\"spoiler_title\">Nyttiga artiklar om \u00e4mnet:<\/b><noindex><a rel=\"nofollow\" href=\"http:\/\/www.yellow-bricks.com\/2011\/06\/23\/disk-schednumreqoutstanding-the-story\/\">http:\/\/www.yellow-bricks.com\/2011\/06\/23\/disk-schednumreqoutstanding-the-story\/<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"http:\/\/www.yellow-bricks.com\/2009\/09\/29\/whats-that-alua-exactly\/\">http:\/\/www.yellow-bricks.com\/2009\/09\/29\/whats-that-alua-exactly\/<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"http:\/\/www.yellow-bricks.com\/2019\/03\/05\/dqlen-changes-what-is-going-on\/\">http:\/\/www.yellow-bricks.com\/2019\/03\/05\/dqlen-changes-what-is-going-on\/<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/www.codyhosterman.com\/2017\/02\/understanding-vmware-esxi-queuing-and-the-flasharray\/\">https:\/\/www.codyhosterman.com\/2017\/02\/understanding-vmware-esxi-queuing-and-the-flasharray\/<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/www.codyhosterman.com\/2018\/03\/what-is-the-latency-stat-qavg\/\">https:\/\/www.codyhosterman.com\/2018\/03\/what-is-the-latency-stat-qavg\/<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/kb.vmware.com\/s\/article\/1267\">https:\/\/kb.vmware.com\/s\/article\/1267<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/kb.vmware.com\/s\/article\/1268\">https:\/\/kb.vmware.com\/s\/article\/1268<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/kb.vmware.com\/s\/article\/1027901\">https:\/\/kb.vmware.com\/s\/article\/1027901<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/kb.vmware.com\/s\/article\/2069356\">https:\/\/kb.vmware.com\/s\/article\/2069356<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/kb.vmware.com\/s\/article\/2053628\">https:\/\/kb.vmware.com\/s\/article\/2053628<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/kb.vmware.com\/s\/article\/1003469\">https:\/\/kb.vmware.com\/s\/article\/1003469<\/a><\/noindex><br \/>\n<noindex><a rel=\"nofollow\" href=\"https:\/\/www.vmware.com\/content\/dam\/digitalmarketing\/vmware\/en\/pdf\/techpaper\/performance\/vsphere-esxi-vcenter-server-67-performance-best-practices.pdf\">https:\/\/www.vmware.com\/content\/dam\/digitalmarketing\/vmware\/en\/pdf\/techpaper\/performance\/vsphere-esxi-vcenter-server-67-performance-best-practices.pdf<\/a><\/noindex><\/p>\n<p>K\u00e4lla: <a content=\"nofollow\" rel=\"nofollow\" href=\"https:\/\/habr.com\/ru\/company\/dataline\/blog\/461127\/\">habr.com<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"<p>\u0427\u0430\u0441\u0442\u044c 1. \u041f\u0440\u043e CPU \u0427\u0430\u0441\u0442\u044c 2. \u041f\u0440\u043e Memory \u0421\u0435\u0433\u043e\u0434\u043d\u044f \u0440\u0430\u0437\u0431\u0435\u0440\u0435\u043c \u043c\u0435\u0442\u0440\u0438\u043a\u0438 \u0434\u0438\u0441\u043a\u043e\u0432\u043e\u0439 \u043f\u043e\u0434\u0441\u0438\u0441\u0442\u0435\u043c\u044b \u0432 vSphere. \u041f\u0440\u043e\u0431\u043b\u0435\u043c\u0430 \u0441\u043e \u0441\u0442\u043e\u0440\u0430\u0434\u0436\u0435\u043c \u2013 \u0441\u0430\u043c\u0430\u044f \u0447\u0430\u0441\u0442\u0430\u044f \u043f\u0440\u0438\u0447\u0438\u043d\u0430 \u043c\u0435\u0434\u043b\u0435\u043d\u043d\u043e\u0439 \u0440\u0430\u0431\u043e\u0442\u044b \u0432\u0438\u0440\u0442\u0443\u0430\u043b\u044c\u043d\u043e\u0439 \u043c\u0430\u0448\u0438\u043d\u044b. \u0415\u0441\u043b\u0438 \u0432 \u0441\u043b\u0443\u0447\u0430\u044f\u0445 \u0441 CPU \u0438 RAM \u0442\u0440\u0430\u0431\u043b\u0448\u0443\u0442\u0438\u043d\u0433 \u0437\u0430\u043a\u0430\u043d\u0447\u0438\u0432\u0430\u0435\u0442\u0441\u044f \u043d\u0430 \u0443\u0440\u043e\u0432\u043d\u0435 \u0433\u0438\u043f\u0435\u0440\u0432\u0438\u0437\u043e\u0440\u0430, \u0442\u043e \u043f\u0440\u0438 \u043f\u0440\u043e\u0431\u043b\u0435\u043c\u0430\u0445 \u0441 \u0434\u0438\u0441\u043a\u043e\u043c, \u0432\u043e\u0437\u043c\u043e\u0436\u043d\u043e, \u043f\u0440\u0438\u0434\u0435\u0442\u0441\u044f \u0440\u0430\u0437\u0431\u0438\u0440\u0430\u0442\u044c\u0441\u044f \u0441 \u0441\u0435\u0442\u044c\u044e \u043f\u0435\u0440\u0435\u0434\u0430\u0447\u0438 \u0434\u0430\u043d\u043d\u044b\u0445 \u0438 \u0421\u0425\u0414. \u0422\u0435\u043c\u0443 \u0431\u0443\u0434\u0443 \u0440\u0430\u0437\u0431\u0438\u0440\u0430\u0442\u044c [&hellip;]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":27306,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[688],"tags":[],"class_list":["post-36486","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-administrirovanie"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.4 - 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\/sv\/blog\/administrirovanie\/analiz-proizvoditelnosti-vm-v-vmware-vsphere-chast-3-storage\" \/>\n\t\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.4\" \/>\n\t\t<meta property=\"og:locale\" content=\"sv_SE\" \/>\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 \u0412\u041c \u0432 VMware vSphere. \u0427\u0430\u0441\u0442\u044c 3: Storage | ProHoster\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/prohoster.info\/sv\/blog\/administrirovanie\/analiz-proizvoditelnosti-vm-v-vmware-vsphere-chast-3-storage\" \/>\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=\"2019-10-31T19:11:54+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2019-10-31T19:11:54+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\udd47Prestandaanalys av VM i VMware vSphere. Del 3: Lagring | ProHoster","description":"","canonical_url":"https:\/\/prohoster.info\/sv\/blog\/administrirovanie\/analiz-proizvoditelnosti-vm-v-vmware-vsphere-chast-3-storage","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"sv_SE","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 \u0412\u041c \u0432 VMware vSphere. \u0427\u0430\u0441\u0442\u044c 3: Storage | ProHoster","og:url":"https:\/\/prohoster.info\/sv\/blog\/administrirovanie\/analiz-proizvoditelnosti-vm-v-vmware-vsphere-chast-3-storage","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":"2019-10-31T19:11:54+00:00","article:modified_time":"2019-10-31T19:11:54+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"36486","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":"2026-01-22 03:31:19","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-03-01 01:44:22","updated":"2026-01-22 03:31:19","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/sv\/wp-json\/wp\/v2\/posts\/36486","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/sv\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/sv\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sv\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sv\/wp-json\/wp\/v2\/comments?post=36486"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/sv\/wp-json\/wp\/v2\/posts\/36486\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sv\/wp-json\/wp\/v2\/media\/27306"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/sv\/wp-json\/wp\/v2\/media?parent=36486"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/sv\/wp-json\/wp\/v2\/categories?post=36486"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/sv\/wp-json\/wp\/v2\/tags?post=36486"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}