From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <sourceware-bugzilla@sourceware.org>
Received: by sourceware.org (Postfix, from userid 48)
 id 155483940CEB; Sat,  4 Apr 2020 20:51:07 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 155483940CEB
From: "rigault.francois+glib at gmail dot com"
 <sourceware-bugzilla@sourceware.org>
To: glibc-bugs@sourceware.org
Subject: [Bug linuxthreads/25774] Suggestion: count number of retries in
 __lll_lock_wait
Date: Sat, 04 Apr 2020 20:51:06 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: glibc
X-Bugzilla-Component: linuxthreads
X-Bugzilla-Version: 2.30
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: enhancement
X-Bugzilla-Who: rigault.francois+glib at gmail dot com
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P2
X-Bugzilla-Assigned-To: unassigned at sourceware dot org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-25774-131-68GoDxZc58@http.sourceware.org/bugzilla/>
In-Reply-To: <bug-25774-131@http.sourceware.org/bugzilla/>
References: <bug-25774-131@http.sourceware.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: http://sourceware.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
X-BeenThere: glibc-bugs@sourceware.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Glibc-bugs mailing list <glibc-bugs.sourceware.org>
List-Unsubscribe: <http://sourceware.org/mailman/options/glibc-bugs>,
 <mailto:glibc-bugs-request@sourceware.org?subject=unsubscribe>
List-Archive: <https://sourceware.org/pipermail/glibc-bugs/>
List-Help: <mailto:glibc-bugs-request@sourceware.org?subject=help>
List-Subscribe: <http://sourceware.org/mailman/listinfo/glibc-bugs>,
 <mailto:glibc-bugs-request@sourceware.org?subject=subscribe>
X-List-Received-Date: Sat, 04 Apr 2020 20:51:07 -0000

https://sourceware.org/bugzilla/show_bug.cgi?id=3D25774

--- Comment #2 from Fran=C3=A7ois Rigault <rigault.francois+glib at gmail d=
ot com> ---
Thanks for the feedback! I will try to read all that.

In the meantime, I was scratching my head to make this work with an older g=
libc
2.23. It turns out that in glibc 2.23, there was already a second argument =
to
the probe, that used to dump the "futex_op" argument of the futex syscall

```
1:     LIBC_PROBE (lll_lock_wait, 2, %rdi, %rsi)
```

so, depending on the version of glibc you will find either a probe with a
single argument, either a probe which second argument is either futex_op, o=
r a
counter of how many times the thread was woken up uselessly. Hope it's not a
big deal.

Attaching what it looks like in glibc 2.23, purely fyi

--=20
You are receiving this mail because:
You are on the CC list for the bug.=