Pivot Point

Scott Drummonds on Virtualization

VMware Perfmon Counters Missing on vSphere?

8 Comments »

I was recently shown a problem where the ESX Perfmon counters we added to vSphere 4.0 virtual machines were not appearing in Windows virtual machines as of vSphere 4.0 U1.  The problem stems from an issue with mofcomp, which I will briefly describe below. For the impatient, the workaround is to manually uninstall and then reinstall VMware Tools.  It also appears that the counters can be added by running vmStatsProvider, as I described in a previous article.

Read the rest of this entry »

VMware Performance Class: "VMware vSphere: Manage for Performance"

10 Comments »

Nearly a year ago I approached the VMware Education Services about designing a single or multiple day class focused on performance management, troubleshooting performance problems, and designing solutions for maximum performance.  I cited the perennial popularity of the VMworld performance troubleshooting lab as a demonstration of the potential market for this class.  I am incredibly pleased to announce that the content for this class is complete and we are soon to be offering it to the general public.

Read the rest of this entry »

Virtual Storage Design: Application Consolidation

4 Comments »

Fixed recommendations for consolidation ratios are cancerous.  Whether we are talking about vCPUs per core, virtual machines per host, or VMDKs per LUN, there is no single number the represents the “right” ratio.  Accurate guidance requires workload characterization and fine tuning using vSphere’s performance counters.  Today I want to highlight one experiment that shows application choice impacting VMDK-to-LUN consolidation.  The inescapable conclusion is that sequential access data must be separated from random access files!

Read the rest of this entry »

esxplot 1.0 Released

5 Comments »

I am pleased to announce that Geoff White has completed the first official release of esxplot, version 1.0.  In an earlier blog article we discussed a beta version of this product and the response from VMware’s customers has been fantastic.  Those of you that have played with esxplot know its value in assisting with esxtop-based analysis.  I urge everyone to download the new version and give it a try.

Read the rest of this entry »

Optimizing Memory Utilization

10 Comments »

My recent series of blog articles have discussed ESX memory management the the performance specter of host swapping. My last article attempts to correct the misconception that VMware recommends against over-commit memory.  In that article I suggested that memory over-commit is requirement in optimizing memory utilization. Today I want to provide a specific example to show why this is true.   I am have also included tips for identifying host swapping in your environments.
Read the rest of this entry »

Misunderstanding Memory Management

2 Comments »

Twice in 2009 someone showed me competitive literature from Microsoft or Citrix claiming that VMware recommends against memory over-commitment.  Given the wide variety of literature we have provided in support of this feature, all of our customers recognize the absurdity of our competitions’ claims.  VMware and its customers love memory over-commitment.  Then where is the source of this misinformed guidance?

Read the rest of this entry »

Blog WebMastered by All in One Webmaster.

Switch to our mobile site

WP SlimStat