Date: Wed, 6 Jul 2011 15:28:50 +0000 From: Alexander Best <arundel@freebsd.org> To: Andriy Gapon <avg@FreeBSD.org> Cc: FreeBSD Current <freebsd-current@FreeBSD.org>, arrowdodger <6yearold@gmail.com> Subject: Re: Heavy I/O blocks FreeBSD box for several seconds Message-ID: <20110706152850.GA4139@freebsd.org> In-Reply-To: <4E14783C.9030909@FreeBSD.org> References: <4E1421D9.7080808@zedat.fu-berlin.de> <CALH631=F4bSgNDE4w0qcXGMgGxZRRwCP9n-H4M0c%2B1UEaqWr7Q@mail.gmail.com> <20110706133337.GA89910@freebsd.org> <4E14783C.9030909@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed Jul 6 11, Andriy Gapon wrote: > on 06/07/2011 16:33 Alexander Best said the following: > > you might also want to try enabling options IPI_PREEMPTION. no idea, if this > > improves your situation, though. > > Just in case, this option has effect for 4BSD scheduler only. thanks. i did not know that. maybe we could add a small note to NOTES or even mention in sched_ule(4) and sched_4bsd(4), which kernel options affect the according scheduler. sched_ule(4) e.g. doesn't mention kern.sched.preemption, so one can assume that defining PREEMPTION in the kernel or not doesn't make a difference. however it *does* make a huge difference. i believe sched_ule(4) in general needs a lot more details about the various sysctl vars available and their semantics. cheers. alex > > -- > Andriy Gapon
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20110706152850.GA4139>