[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <e6906764-66bb-437d-8082-b1d6a48ffa55@efficios.com>
Date: Mon, 18 Aug 2025 13:38:34 -0400
From: Michael Jeanson <mjeanson@...icios.com>
To: Thomas Gleixner <tglx@...utronix.de>, Jens Axboe <axboe@...nel.dk>,
LKML <linux-kernel@...r.kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Peter Zijlstra <peterz@...radead.org>, "Paul E. McKenney"
<paulmck@...nel.org>, Boqun Feng <boqun.feng@...il.com>,
Wei Liu <wei.liu@...nel.org>
Subject: Re: [patch 00/11] rseq: Optimize exit to user space
On 2025-08-17 17:23, Thomas Gleixner wrote:
> Michael, can you please run your librseq tests against that too? They
> have the same segfault problem as the kernel and they lack a run script,
> so I couldn't be bothered to test against them. See commit 2bff3a0e5998
> in that branch. I'll send out a patch with a proper change log later.
I ran the librseq test suite on the new branch on a Debian Trixie amd64
system and it succeeds, here are the rseq stats before and after.
Before:
exit: 746809
signal: 3
slowp: 99
ids: 1053
cs: 0
clear: 0
fixup: 0
After:
exit: 229294046
signal: 11
slowp: 4570
ids: 615950
cs: 2493682
clear: 194637
fixup: 2299044
And I also ran the same test suite in a 32bit chroot on the same system
which also succeeds with the following rseq stats.
Before:
exit: 717945
signal: 1
slowp: 102
ids: 1039
cs: 0
clear: 0
fixup: 0
After:
exit: 201051038
signal: 9
slowp: 4909
ids: 793551
cs: 28887
clear: 12871
fixup: 16016
If you want to run the librseq tests on your system, just do the regular
autotools dance and then run 'make check'.
Regards,
Michael
Powered by blists - more mailing lists