This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: TSX lock elision for glibc v15
- From: "Carlos O'Donell" <carlos at redhat dot com>
- To: Andi Kleen <andi at firstfloor dot org>
- Cc: libc-alpha at sourceware dot org, Torvald Riegel <triegel at redhat dot com>, Rich Felker <dalias at aerifal dot cx>, Roland McGrath <roland at hack dot frob dot com>, Andreas Jaeger <aj at suse dot com>, "Joseph S. Myers" <joseph at codesourcery dot com>
- Date: Sun, 30 Jun 2013 17:26:39 -0400
- Subject: Re: TSX lock elision for glibc v15
- References: <1372452807-25216-1-git-send-email-andi at firstfloor dot org>
On 06/28/2013 04:53 PM, Andi Kleen wrote:
> Proposed NEWS entry:
>
> * Added support for TSX lock elision for pthread mutexes and read/write
> locks on i386 and x86-64.
> This allows to improve lock scaling of existing programs.
> When the --enable-lock-elision=yes parameter is specified at configure
> time lock elision will be enabled by default for all PTHREAD_MUTEX_DEFAULT
> mutexes and rwlock.
>
> History:
> + v15:
> Readd hunk lost in v14 to set rwlock status
> Remove most extra test cases for extra lock types.
> Split test suite in minimal fixes and pure elision test cases.
> Elision test cases are only done late in the series now.
> Remove environment variable checks in test suite.
> Move manual in series. Typo fixes for manual (thanks Carlos)
> Rename --enable-lock-elision=on to yes
> Split configure changes.
> Fix some broken ChangeLogs.
At present I feel that patches 1 - 7 could be committed immediately
as a no-ABI/no-API checkpoint for elision which would allow you to
build and test with elision turned on via configuring with
--enable-elision=yes.
The only thing that blocks this is a need for consensus on patch
#6 to add elision to rwlocks. I would like someone else to agree
with Andi and my interpretation that deadlock on relock is not
required by POSIX for rwlocks.
Patches 8 through 14 are under review.
Cheers,
Carlos.