I'd be interested to see results from pre-CFS kernels.
Not that FreeBSD hasn't made major performance improvements.
Also, I think that a database test isn't a complete picture. For example, some OSes like IRIX or Mac OS X perform very well on streaming of local video and audio, but I wouldn't benchmark Oracle or PostgreSQL on either.
The linked PDF contains pre-CFS kernel benchmarks.
Prior to 2.6.23, the 2.6 kernel used the Completely Fair Queuing (CFQ) scheduler, which was also bad for database workloads. Please see this note by Werner Puschitz [puschitz.com]:
The Completely Fair Queuing (CFQ) scheduler is the default algorithm in RHEL4 which is suitable for a wide variety of applications and provides a good compromise between throughput and latency. In comparison to the CFQ algorithm, the Deadline scheduler caps maximum latency per request and mainta
CFS is a thread scheduler, CFQ is a disk IO scheduler. They are independent but can coexist (and in many modern distro releases, do so by default). Both seem to be focused on desktop user experience, although they're not exactly "bad" for servers either.
Well (Score:5, Interesting)
Not that FreeBSD hasn't made major performance improvements.
Also, I think that a database test isn't a complete picture. For example, some OSes like IRIX or Mac OS X perform very well on streaming of local video and audio, but I wouldn't benchmark Oracle or PostgreSQL on either.
Re: (Score:5, Informative)
Re: (Score:2)
Prior to 2.6.23, the 2.6 kernel used the Completely Fair Queuing (CFQ) scheduler, which was also bad for database workloads. Please see this note by Werner Puschitz [puschitz.com]:
Re:Well (Score:3, Informative)