Date: Wed, 06 Jul 2011 18:41:00 +0300 From: Andriy Gapon <avg@FreeBSD.org> To: "O. Hartmann" <ohartman@zedat.fu-berlin.de> Cc: FreeBSD Current <freebsd-current@FreeBSD.org> Subject: Re: Heavy I/O blocks FreeBSD box for several seconds Message-ID: <4E14820C.7080006@FreeBSD.org> In-Reply-To: <4E14802C.70907@zedat.fu-berlin.de> References: <4E1421D9.7080808@zedat.fu-berlin.de> <CALH631=F4bSgNDE4w0qcXGMgGxZRRwCP9n-H4M0c%2B1UEaqWr7Q@mail.gmail.com> <4E144913.3060503@FreeBSD.org> <CALH631kYhFHQycgVtgnnezCz-SU4d2GfqApDtc_RSb5D%2B9AaSA@mail.gmail.com> <4E14802C.70907@zedat.fu-berlin.de>
next in thread | previous in thread | raw e-mail | index | archive | help
on 06/07/2011 18:33 O. Hartmann said the following: > On 07/06/11 14:35, arrowdodger wrote: >> On Wed, Jul 6, 2011 at 3:37 PM, Andriy Gapon<avg@freebsd.org> wrote: >> >>> Just curious what your current value of sysctl kern.sched.preempt_thresh >>> is. >>> And if it's not 224 and if you haven't tried 224 yet, then could you please >>> try >>> it and see if there is any improvement? >>> >>> This assumes that you use SCHED_ULE (kern.sched.name is "ULE"). >>> >>> -- >>> Andriy Gapon >>> >> >> Whoa, it's definitely better! Thanks a lot. But still, when IO causes system >> to use swap, X11 became completely unusable. > > I had tkern.sched.preempt_thresh already set to 96. In what sense 'already'? -- Andriy Gapon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4E14820C.7080006>