benchmarking

The old phrase, ‘what cannot be measured cannot be improved’ is a favorite amongst those in the computer industry – and it contains more than a kernel of truth.  That logic has been behind the establishment of a variety of industry organizations, such as SPEC and TPC, which seek to establish standard benchmarks for various workloads.

Virtualization is certainly one of the trendiest technologies and ripe for measurement.  The latest announcements of CPUs from Intel and AMD have all explicitly mentioned and showcased improvements in virtualization performance, along with a flurry of feature names like VPID, Pacifica, Nested Page Tables and Extended Page Tables.  Most of these I’ve described in prior article, but to summarize, a lot of these features are about shifting the burden of virtualization from software (that is, the VMM) onto the hardware by making some hardware operations more complete.  Take for example, THE VPID in Nehalem (incidentally AMD has had an equivalent feature for a while), which reduces transition times between VMs by about a third (compared to the prior generation Penryn).  While it’s great that VM transitions are faster, it’s really hard for an average user to understand what that really means in terms of virtualization performance. Read More »

To properly plan for any migration to virtualization, or virtual infrastructure startup, proper capacity and resource planning is paramount. The hardware upon which the virtual platform is to be installed must exceed the processing power, memory capacity, and disk I/O required for the virtual machines as tasked.  Although the ability to dynamically allocate most resources “on the fly” is a benefit of virtualization, a proper measurement for peak usage must be established. Once this is established the need for additional headroom past this point has to be added to hardware requirements thus allowing for future increased demand. Some might say that if the time comes when present hardware resources are no longer able to sustain the workload of the virtual machine(s) new hardware should be purchased to either:

1.     Create similarly tasked virtual machines to share the load.

2.     Migrate the existing virtual machines over to.

Arguments can be made for either scenario but this impasse should never be reached due to poor planning as the negative economic and production impact could result in repercussions that affect business continuity or sustainability. Read More »