The real value of ESX Server memory overcommit capability

Posted by virtualization.info Staff   |   Friday, March 14th, 2008   |  

The virtualization phenomenon changed (and it’s still changing) a lot of things in the IT world. Some of them, anyway, have nothing to do with technology.

One is the new level of competition that the vendors can reach when pitching their products, probably the highest ever seen in the computer industry.
Such fierce conflict is made of claims and refusals and accusations going back and forth from one corporate blog to another.
Who benefits the most from this modern media fight is the end-user which has a surprisingly efficient tool to spot some obscure statements in this or that vendor’s offering.

This long and unusal premise was needed to introduce a concrete example.

Recently VMware opened a new corporate blog to debate on those press articles or competitors statements which are not considered fair enough.

The last post published on this blog, Virtual Reality, covers the frequent complains about the VMware Infrastructure price (complains that actually exist since much before Microsoft announced the price for its upcoming Hyper-V).
To justify the cost difference between its hypervisor and the competing ones, VMware focus on the so called cost per virtual machine and invokes the memory overcommit feature, something that nor Citrix XenServer neither Microsoft Hyper-V can offer today.

The achievements described in that post (a 4GB RAM physical server runs up to 40 concurrent VMs busy with light activity or up to 14 VMs busy with heavy activity) instantly provoked reaction from Microsoft and from Citrix.

The three positions are all interesting and worthwhile of a full analysis but readers should be aware that metrics can be manipulated without limits to support one position or another.

The value of ESX Server memory overcommit exist. Despite that, the scenario described by VMware seems far away from many real-world deployments.

VMware used the identical OS image for all the virtual machine instances but it’s highly unlikely that a virtual infrastructures can host tens of virtual machines with the same identical Windows edition, service pack, patch level and running applications. Thus the chances to have many memory pages to share are probably lower than the ones available in the tested environment.

Surely there are batteries of identical virtual machines (at least at the OS level) deployed out there, for example for web server farms or VDI farms, but to match a realistic average scenario VMware should use a mixed environment made of Windows 2000, 2003 and 2008 VMs, with different SP and patch levels, and with different installed applications.

In such environment the memory overcommit ratio would assume a more concrete value and a cost per VM calculation would be more precise.

Update: VMware posted a new scenario to validate its memory overcommit technology in the real-world.
It’s the case of a VDI farm with 178 virtual machines (512 MB virtual RAM each) which consumes less than 20GB physical RAM instead of 89GB.

Definitively an interesting environment but, as noted in the original post above, we’d like to see the memory overcommit ratio achieved where you cannot have a farm of identical guest OSes with identical applications.



blog comments powered by Disqus


virtualization.info Newest articles
Release: VMware vRealize Log Insight 4.5

June 13th, 2017

Log Insight is a log aggregation, management and analysis tool, that VMware first introduced in 2013 and considered a competitor of Splunk.
Yesterday VMware announced the release of version 4.5, available for…

Release: VMware vRealize Automation 7.3

June 6th, 2017

Today VMware announced the latest release of its cloud management platform vRealize Automation, former vCloud Automation Center.
VMware vRealize Automation 7.3 release notes can be found at this link.

The…

Paper: Introducing the NSX-T Platform

February 9th, 2017

“We see greater potential strategic opportunity in NSX over the next decade than our franchise product vSphere has had for the past decade.”
said VMware’s CEO Pat Gelsinger talking about…

Paper: VMware vSphere Virtual Machine Encryption Performance

November 22nd, 2016

Encryption of virtual machines is something that has been requested for years by the security community. VMware continued to postpone its implementation due to the negative operational impact that many…

Quest Software leaves Dell

November 1st, 2016

In September 2012 Dell announced to have completed the acquisition of Quest Software, a Californian company with an history in systems management, security, business intelligence and, falling back in our…

Citrix announces Q3 2016 results

October 21st, 2016

Citrix announced its financial results for third quarter 2016.
The revenues for the second quarter were $841 million for an increase of 3% compared to Q3 2015.
Net income was $132…

Release: VMware vSphere 6.5 & Virtual SAN 6.5

October 19th, 2016

2016 edition of VMworld US has been quite turbulent, on the other hand during VMworld Europe, happening these days in Barcelona, the company announced a few more products for the…

Release: VMware vRealize Log Insight 4.0

October 18th, 2016

Log Insight is a log aggregation, management and analisys tool, that VMware first introduced in 2013 and now is usually compared with Splunk.
Yesterday VMware announced Log Insight’s new major…

Release: Windows Server 2016 with support for Window Server & Hyper-V containers

October 13th, 2016

Yesterday Microsoft announced the general availability of Windows Server 2016 which the company defines as a cloud-ready OS.
Beside fancy definitions, one of the most relevant perks of this release…

Release: Oracle VM 3.4.2

September 22nd, 2016

During Oracle OpenWorld 2016 the company released version 3.4.2 of its enterprise virtualization solution.
Oracle VM is available for both x86 and SPARC based processor architectures and uses the Xen hypervisor…

VMworld US 2016 Wrap-up

September 1st, 2016

Today was the last day of VMware’s flagship conference VMworld in Las Vegas, an highly controversial edition which left a good chunk of the audience disoriented if not properly disappointed….

Gartner releases its Magic Quadrant for Cloud Infrastructure as a Service for 2016

August 11th, 2016

Last week Gartner updated its Magic Quadrant for Cloud Infrastructure as a Service (IaaS) for the year 2016. The Magic Quadrant for the year 2015 was released in May last year…

Release: Ansible Tower 3 by Red Hat

August 2nd, 2016

Ansible is one of the four main players in the automation market, younger then the well known Chef and Puppet, has been launched in 2013 in Durham, N.C. and acquired…

IBM announces earnings for Q2 2016

July 19th, 2016

Yesterday IBM announced its results for Q2 2016.

If we compare with the same quarter in 2015 earnings per share, from continuing operations, decreased 22%. Net income, from continuing operations,…

 
Monthly Archive