Date: Tue, 06 Sep 2005 09:46:12 +0200 From: "O. Hartmann" <ohartman@mail.uni-mainz.de> To: Kris Kennaway <kris@obsecurity.org> Cc: freebsd-amd64@freebsd.org Subject: Re: Which SCHED_ for DB server Message-ID: <431D4944.9020907@mail.uni-mainz.de> In-Reply-To: <20050906000016.GA91835@xor.obsecurity.org> References: <4316A5BC.1000405@meijome.net> <b41c7552050901015317d5942e@mail.gmail.com> <20050906000016.GA91835@xor.obsecurity.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Kris Kennaway wrote: >On Thu, Sep 01, 2005 at 10:53:39AM +0200, Claus Guttesen wrote: > > >>>I'm building a server that will run PostgreSQL with a database >>>containing several 10s of million records. The only things happening on >>>this box will be the SQL processes and other processes to parse raw data >>>and load into the DB. Users = a few connections via HTTP from an >>>intranet server (not more than 5 concurrently). >>> >>>I was wondering what is the best SCHED_ to set in the kernel. >>>I currently have SCHED_4BSD but was wondering if _ULE would be better >>>for this >>> >>> >>For prod. use I would recommend SCHED_4BSD atm. The 4BSD-scheduler >>does seem to be more stable on SMP and up. >> >> > >ULE might be OK on SMP with 6.0 and above, but performance seems to be >a bit lower than 4BSD in my tests. Try it yourself and see which is >better. > >Kris > > Interesting. An, by the way, what are the benefits of ULE at this moment? Is it still a more experimental scheduler for the far future on SMP based machines or do we have benefits in UP/SMP?
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?431D4944.9020907>