Date: Fri, 23 Dec 2011 14:49:51 -0800 From: Adrian Chadd <adrian@freebsd.org> To: Steve Kargl <sgk@troutmask.apl.washington.edu> Cc: freebsd-stable@freebsd.org, Andriy Gapon <avg@freebsd.org> Subject: Re: SCHED_ULE should not be the default Message-ID: <CAJ-Vmon69r-341aMutBAHT_VCMkM9afzu=4sBd7s7zqFiK%2BEVA@mail.gmail.com> In-Reply-To: <20111223191146.GA56232@troutmask.apl.washington.edu> References: <4EE1EAFE.3070408@m5p.com> <CAJ-FndBSOS3hKYqmPnVkoMhPmowBBqy9-%2BeJJEMTdoVjdMTEdw@mail.gmail.com> <20111215215554.GA87606@troutmask.apl.washington.edu> <CAJ-FndD0vFWUnRPxz6CTR5JBaEaY3gh9y7-Dy6Gds69_aRgfpg@mail.gmail.com> <20111222005250.GA23115@troutmask.apl.washington.edu> <20111222103145.GA42457@onelab2.iet.unipi.it> <20111222184531.GA36084@troutmask.apl.washington.edu> <4EF37E7B.4020505@FreeBSD.org> <20111222194740.GA36796@troutmask.apl.washington.edu> <CAJ-VmokeyDrKb-yQkzTm8tnOYcRm603hz%2B6nen10F3zFQVmCEQ@mail.gmail.com> <20111223191146.GA56232@troutmask.apl.washington.edu>
next in thread | previous in thread | raw e-mail | index | archive | help
On 23 December 2011 11:11, Steve Kargl <sgk@troutmask.apl.washington.edu> w= rote: > Ah, so goods news! =A0I cannot reproduce this problem that > I saw 3+ years ago on the 4-cpu node, which is currently > running a ULE kernel. =A0When I killed the (N+1)th job, > the N remaining jobs are spread across the N cpus. Ah, good. > One difference between the 2008 tests and today tests is > the number of available cpus. =A0In 2008, I ran the tests > on a node with 8 cpus, while today's test used only a > node with only 4 cpus. =A0If this behavior is a scaling > issue, I can't currently test it. =A0But, today's tests > are certainly encouraging. Do you not have access to anything with 8 CPUs in it? It'd be nice to get clarification that this indeed was fixed. Does ULE care (much) if the nodes are hyperthreading or real cores? Would that play a part in what it tries to schedule/spread? Adrian
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAJ-Vmon69r-341aMutBAHT_VCMkM9afzu=4sBd7s7zqFiK%2BEVA>