Re: CPU affinity in new ULE scheduler
On Wed, 9 Nov 2005, Ian Lord wrote: Are you saying that ULE is slower then 4BSD ? I'm new to this and when I compiled my kernel, it was clear ULE was a better alternative for performance then 4BSD Schedulers are one of the hardest things to do right in OS design, as they rely a great deal on how workloads behave and interact. I've seen significantly varied performance between the two -- there are a lot of anecdotal reports that ULE is better for interactive workloads on a busy desktop machine, but keep in mind that 4BSD has seen a number of improvements in the last few years also. Right now, 4BSD is considered the production scheduler for FreeBSD, although there's continuing interest in improving ULE, as well as integrating some of the techniques used in ULE into 4BSD. For example, ULE used to see a significant performance win over 4BSD on SMP as it did a better job of identifying idle CPUs and migrating work to those CPUs. 4BSD has improved a lot on this front in the last year or two, and so has caught up with some of those benefits. In the end, only by measuring will you be able to tell if ULE is better for your workload. Measurement can mean qualitative experience (everything seems snappier) or quantitative (I get 14% more transactions per second with scheduler X). Robert N M Watson Thanks At 19:05 2005-11-09, Kris Kennaway wrote: On Wed, Nov 09, 2005 at 04:16:31PM -0600, Jon Brisbin wrote: I can't find any information on how to set the CPU affinity for processes in the FreeBSD 6 ULE scheduler. That's because you can't. ULE gives lower performance on the workloads I have tested anyway. This may be fixed in the future. Kris ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED] ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
CPU affinity in new ULE scheduler
I can't find any information on how to set the CPU affinity for processes in the FreeBSD 6 ULE scheduler. On the linux box, which we're moving from, I have dual Xeon HTT's that I have JBoss scheduled round-robin with the CPU affinity set to the first two processors, nice -15. I have Postgres scheduled SCHED_FIFO on the last two processors, nice -15. This gives me the greatest bandwidth possible in our scenario as it eliminates the CPU contention I had noticed before doing it this way. How do I do the same thing in FreeBSD? I have found a lot of information that talks about setting CPU affinity, but I have yet to find one example of how to do this. On linux, I'm using a CK-patched kernel and schedtool Is there something similar on FreeBSD? Thanks! Jon Brisbin Webmaster NPC International, Inc. ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: CPU affinity in new ULE scheduler
On Wed, Nov 09, 2005 at 04:16:31PM -0600, Jon Brisbin wrote: I can't find any information on how to set the CPU affinity for processes in the FreeBSD 6 ULE scheduler. That's because you can't. ULE gives lower performance on the workloads I have tested anyway. This may be fixed in the future. Kris pgpo1zlUcDBeK.pgp Description: PGP signature
Re: CPU affinity in new ULE scheduler
Are you saying that ULE is slower then 4BSD ? I'm new to this and when I compiled my kernel, it was clear ULE was a better alternative for performance then 4BSD Thanks At 19:05 2005-11-09, Kris Kennaway wrote: On Wed, Nov 09, 2005 at 04:16:31PM -0600, Jon Brisbin wrote: I can't find any information on how to set the CPU affinity for processes in the FreeBSD 6 ULE scheduler. That's because you can't. ULE gives lower performance on the workloads I have tested anyway. This may be fixed in the future. Kris ___ freebsd-questions@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-questions To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: CPU affinity in new ULE scheduler
On Wed, Nov 09, 2005 at 07:08:12PM -0500, Ian Lord wrote: Are you saying that ULE is slower then 4BSD ? I'm new to this and when I compiled my kernel, it was clear ULE was a better alternative for performance then 4BSD Yes, in the workloads I have tested. Others have reported similar things. You should carefully measure it yourself on your workloads to verify which is better. Kris pgp66BefrOC6Z.pgp Description: PGP signature