Date: Fri, 22 Jan 2010 00:26:54 +0100 From: Attilio Rao <attilio@freebsd.org> To: Giovanni Trematerra <giovanni.trematerra@gmail.com> Cc: Jeff Roberson <jroberson@jroberson.net>, freebsd-current@freebsd.org, Kohji Okuno <okuno.kohji@jp.panasonic.com> Subject: Re: Bug about sched_4bsd? Message-ID: <3bbf2fe11001211526r1ac89d13md5fbc1e0d6b9a160@mail.gmail.com> In-Reply-To: <3bbf2fe11001211449je30b643y53fe0830bcbf3e5d@mail.gmail.com> References: <20100117.142200.321689433999177718.okuno.kohji@jp.panasonic.com> <20100117.152835.119882392487126976.okuno.kohji@jp.panasonic.com> <3bbf2fe11001171858o4568fe38l9b2db54ec9856b50@mail.gmail.com> <4e6cba831001192332j1e23bb1chdf2f47664d3cb14a@mail.gmail.com> <3bbf2fe11001211449je30b643y53fe0830bcbf3e5d@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
2010/1/21 Attilio Rao <attilio@freebsd.org>: > 2010/1/20 Giovanni Trematerra <giovanni.trematerra@gmail.com>: >> On Mon, Jan 18, 2010 at 3:58 AM, Attilio Rao <attilio@freebsd.org> wrote: >>> 2010/1/17 Kohji Okuno <okuno.kohji@jp.panasonic.com>: >>>> Hello, >>>> >>>> Could you check sched_4bsd.patch, please? >>> >>> I think, instead, that what needs to happen is to have sched_switch() >>> to do a lock handover from sleepq/turnstile spinlock to schedlock. >>> That way, if threads are willing to contest on td_lock they will be >>> still inhibited. >>> I'm not sure if this patch breaks any invariant, if you may test I >>> would appreciate: >>> http://www.freebsd.org/~attilio/sched_4bsd_schedlock.diff >> >> I stressed an 8-core machine with pho's stress2 kernel stress suite and >> your patch seems to break the invariant THREAD_LOCKPTR_ASSERT in >> turnstile_claim:subr_turnstile.c > > Oh, right, I guess what we really want is to block the td_lock. > This is the new patch: > http://www.freebsd.org/~attilio/sched_4bsd_schedlock2.diff FYI, I've updated the patch with a more correct use of thread_lock_block() and a merge of this interface with the custom interface of thread_block_switch() from ULE. The overall result should be better (and more correct). Please refresh your patch. Testing with ULE should be due as well. Thanks, Attilio -- Peace can only be achieved by understanding - A. Einstein
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3bbf2fe11001211526r1ac89d13md5fbc1e0d6b9a160>