Virtual machine sizing is a tricky issue for many VMware administrators. It is important to find the right number of virtual CPUs to maximize application performance and minimize wasted CPU cycles. The optimal number of vCPUs can never be easily identified. But I can offer a few suggestions to help get this number right.
How Many Virtual CPUs Per VM?
April 30th, 2010
Apr, 30 2010
4 Comments »
New Look, New Host
April 23rd, 2010
Apr, 23 2010
I just moved Pivot Point off of wordpress.com and onto my own hosting provider. I would not be surprised to learn that I screwed something up and half the site is non-functioning. Please let me know via Twitter, Facebook, LinkedIn, or email if you see a problem. I am not tough to find using any of these channels.
Thanks for bearing with me while I go through this important upgrade!
A Performance Tip for ESX 3.0 and ESX 3.5
April 20th, 2010
Apr, 20 2010
Do you have any running instances of ESX 3.5 or older? Are those instances running on processors that are no more than a couple of years old? If so, I have a tip for you: update your hosts to ESX 4.0. Seriously, upgrade to vSphere already. It’s been out for a year!
Windows Guest Defragmentation, Take Two
April 14th, 2010
Apr, 14 2010
I have received questions about guest defragmentation tools for years. Until today I could only pose theories as to the value of guest defragmentation. But previous theories spawned new research and one of VMware’s partners is now putting data behind their argument that file systems in Windows virtual machines require defragmentation. This partner, Raxco Software, shared early results of this investigation with me. Raxco used their NTFS defragmentation tool PerfectDisk to evaluate the impact of guest defragmentation on a single virtual machine.
First Ever TPC Result on VMware, New Records
April 12th, 2010
Apr, 12 2010
A new era has dawned on VMware virtualization: the Transaction Processing Performance Council (TPC) has posted an audited result on a virtual platform. That platform, VMware vSphere 4, ran ParAccel’s Analytic Database (PADB) to set new records for the TPC-H benchmark using a 1,000 GB database. You can read more about ParAccel’s work in their recent press release.
Processor Utilization Calculations
April 9th, 2010
Apr, 09 2010
A little Friday esxtop trivia for the performance massive: did you ever notice your Hyper-Threaded systems have three rows showing CPU utilization in the CPU panel header? They are labeled “PCPU USED(%)”, “PCPU UTIL(%)”, and “CORE UTIL(%)”. Here is a screen shot to jog your memory:
Upping VMware's Storage Game
April 2nd, 2010
Apr, 02 2010
If you have heard me talk in the past year, you have heard me relate stories of storage issues causing performance problems that are wrongly blamed on VMware. Mark Bowker of ESG recently presented a generalized version of a customer story that relates the same tale. Luckily (for me) the customer caught the problem before completing the deployment. This may have saved me a customer call to unravel a basic problem. But the customer was burned and virtualization progress slowed if not stopped.
Hyper-V's Lack of Memory Over-commit
April 1st, 2010
Apr, 01 2010
I find it interesting that one day after I wrote about memory over-commitment in vSphere, Greg Shields wrote about the lack of memory over-commitment in Hyper-V. In today’s short blog entry, I want provide one paragraph that Greg’s article currently lacks:
While memory over-subscription is a critical feature for production environments, balancing the demands of heterogenous applications of varying demands in a resource starved environment is difficult. Without guidance from administrators on the relative importance of the virtual machines running these applications, a hypervisor will be forced to make arbitrary decisions in assigning limited resources. Effective use of over-commitment requires a sound resource control system. The only product on the market that does this well is VMware vSphere.
Both Greg and my articles only talked of memory over-commitment, but the rules apply for CPU over-commitment, too. Microsoft will realize how important resource controls are somewhere between year two and five of their product’s life. I can only imagine where vSphere will be by then.