Date: Wed, 16 Mar 2011 20:51:17 +0100 From: Ivan Voras <ivoras@freebsd.org> To: Roman Divacky <rdivacky@freebsd.org> Cc: svn-src-head@freebsd.org, svn-src-all@freebsd.org, src-committers@freebsd.org Subject: Re: svn commit: r219699 - head/sys/kern Message-ID: <AANLkTika25WRx=TWJXeNg_2786U11ff7_O68DkBz1oKc@mail.gmail.com> In-Reply-To: <20110316174642.GB6367@freebsd.org> References: <201103161622.p2GGMxNp097642@svn.freebsd.org> <20110316174642.GB6367@freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On 16 March 2011 18:46, Roman Divacky <rdivacky@freebsd.org> wrote: > > On Wed, Mar 16, 2011 at 04:22:59PM +0000, Ivan Voras wrote: > > Author: ivoras > > Date: Wed Mar 16 16:22:59 2011 > > New Revision: 219699 > > URL: http://svn.freebsd.org/changeset/base/219699 > > > > Log: > > =C2=A0 The hardware has caught up; improvements are now observed even a= t 128, > > =C2=A0 but stay conservative and bump read_max to "only" 64 (it will pr= obably be > > =C2=A0 a good idea to increase this to 128 after the next major release= ). > > how did you measure this? Specifically for this commit: my desktop 2xSATA 7200 RPM drives, gmirror, single read "dd" stream, bs=3D1m. (Are there any ready read multi-stream read tests which are not trivial i.e. they start from different positions in the file?) results: read_max=3D32 -> 78 MB/s read_max=3D64 -> 136 MB/s read_max=3D128 -> 141 MB/s I'm the one who previously bumped read_max from 8 to 32 about a year ago, based on tests under an (otherwise idle, naturally) VMWare cluster on a FC SAN, and a similar point of saturation was at read_max=3D64. Now it is at 128 with raw hardware. Maybe it should be tuned at 2^(major_freebsd_version-2) :) (as for safety & stability, I've put 2-3 new web servers in production this year with read_max=3D128 irregardless of this commit. It's stable).
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?AANLkTika25WRx=TWJXeNg_2786U11ff7_O68DkBz1oKc>