Archive for the ‘Performance’ Category

Flash & Phase Change Memory Talks

Monday, October 26th, 2009

  This week, I attended talks at the international high performance transaction workshop. Following are my rough notes from the Flash Memory discussions. First up Steve Kleiman from Network Appliance spoke about their intent to move  flash into the clients that access NAS, so that it can intelligently cache and interact with the ...

RISC to x86, Physical to Virtual

Tuesday, April 21st, 2009

Many of the virtualization customers I speak with have been asking about what database can be virtualized, so I typically present a green, yellow and red set of criteria to help guide the process. We typically look at I/O rates, SMP width and capacity of the source physical system as ...

The Solaris Internals Virtual Shell Game

Monday, March 2nd, 2009

In a stark contrast to recent past when Solaris Internals was hosted on physical machines, we've just experienced one of the core values of virtualization -- encapsulated, portable state allowing geographic mobility. Solaris Internals has over the last two weeks been teleported out of my datacenter (As Jim notes, the ...

Saving Joules II

Thursday, November 6th, 2008

[ there was a bad youtube server hosting the first video, so here's a resubmit with a pointer to an alternative youtube copy It's been well talked up that consolidating physical systems can save a lot of datacenter engery -- for example, consolidating 20 systems, all with 3-5% utilization can reduce ...

VMware Performance Tutorial next week at Usenix LISA

Wednesday, November 5th, 2008

Heads up for those interested in understanding VMware performance in more details -- I'm running my performance and tuning of VMware ESX server class at Usenix LISA again this November in San Diego. The session is on Friday, November 14, and is an all-day class. Given our obsession with ...

Saving Joules

Wednesday, November 5th, 2008

It's been well talked up that consolidating physical systems can save a lot of datacenter engery -- for example, consolidating 20 systems, all with 3-5% utilization can reduce power by up to 10-15x -- or considered in more tractable terms, each server removed is equivalent to taking four cars off ...

IO Challenge Update 5: 102,240 IOPS

Wednesday, May 21st, 2008

We're really excited to announce that we hit over 100k IOPS! This was done using 77TB of storage, adding a 3rd rack totalling 495 disks -- enough storage to hold the entire printed library of congress, and all being driven from a single ESX server! Chethan's just written a detailed report over ...

File System Benchmarking Workshop in Santa Cruz

Monday, May 19th, 2008

We're at Santa Cruz this week at the workshop for file system benchmarking. , chaired by Erez Zadok of StonyBrook University. The objective of this week is to converge on a set of strategies and recommendations towards more accurate and representative benchmarking of file systems and storage. Many of the File Systems ...

IO Challenge Update 3: 31,323 IOPS

Monday, May 19th, 2008

We now starting to see some of the more enterprise-league I/O rates... In contrast to the simple NVRAM cached 3 disk configurations used in the previous posts, we've moved to one of the more typical SAN based setups used for running the bigger applications. In this case, we now have ...

Realistic Virtualization Benchmarks

Tuesday, May 6th, 2008

A recent comment about 'bench-marketing' caught my attention. I much prefer to see performance analysis of real-world benchmarks, because well-designed studies server as reference examples to guide solid decisions when planning for virtualization. The specific comments were about wanting to see more examples of scale-out performance - a term I ...