Date: Thu, 26 Apr 2012 10:45:28 +0800 From: David Xu <listlog2011@gmail.com> To: linimon@FreeBSD.org Cc: davidxu@FreeBSD.org, freebsd-threads@FreeBSD.org Subject: Re: threads/167308: Performance regression in thread locking on 8-stable [regression] Message-ID: <4F98B6C8.30703@gmail.com> In-Reply-To: <201204260144.q3Q1iQnG018668@freefall.freebsd.org> References: <201204260144.q3Q1iQnG018668@freefall.freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On 2012/4/26 9:44, linimon@FreeBSD.org wrote: > Old Synopsis: Perf regression in thread locking on 8-stable > New Synopsis: Performance regression in thread locking on 8-stable [regression] > > Responsible-Changed-From-To: freebsd-threads->davidxu > Responsible-Changed-By: linimon > Responsible-Changed-When: Thu Apr 26 01:41:20 UTC 2012 > Responsible-Changed-Why: > Over to committer of r234373. > > http://www.freebsd.org/cgi/query-pr.cgi?pr=167308 > This is a known problem that the unlocking is not optimized when the mutex is heavily contented, I may MFC wake2 later.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4F98B6C8.30703>