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 021413858C52; Wed, 21 Sep 2022 08:00:08 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 021413858C52
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org;
	s=default; t=1663747208;
	bh=MIz1QdImRfZe4DonS6quVCRB/hEyax11pQLgXfJSqmI=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=fupQZLzxYxVtv9t3ue7IW65owbflEkahtt8IyLkEgIdABQM1XzJ8ZWXWTxAfgjQQZ
	 mJlG2R3MeS/NdN3ra2I9rD1yfI+jCMALZLPbdSW0tIQduEVLyEFr2dT85TP5Hfygey
	 O6dmhwkYElk87HmUsLzxycaz4C7SrMRWtnOYj8Qw=
From: "mjbaars1977 at gmail dot com" <sourceware-bugzilla@sourceware.org>
To: glibc-bugs@sourceware.org
Subject: [Bug libc/29585] sched_getcpu returns invalid results
Date: Wed, 21 Sep 2022 08:00:07 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: glibc
X-Bugzilla-Component: libc
X-Bugzilla-Version: 2.35
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: mjbaars1977 at gmail dot com
X-Bugzilla-Status: WAITING
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P2
X-Bugzilla-Assigned-To: unassigned at sourceware dot org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: security-
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-29585-131-7SeZGrQtkw@http.sourceware.org/bugzilla/>
In-Reply-To: <bug-29585-131@http.sourceware.org/bugzilla/>
References: <bug-29585-131@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
List-Id: <glibc-bugs.sourceware.org>

https://sourceware.org/bugzilla/show_bug.cgi?id=3D29585

--- Comment #2 from Mischa Baars <mjbaars1977 at gmail dot com> ---
(In reply to Mischa Baars from comment #0)
> Hello,
>=20
> I noticed the following while I was trying SCHED_FIFO, because FIFO
> processes are not supposed to migrate from processor to processor.
>=20
> When looking at the manual page of sched_getcpu(), it states that:
>=20
> The call
>=20
>            cpu =3D sched_getcpu();
>=20
>        is equivalent to the following getcpu(2) call:
>=20
>            int c, s;
>            s =3D getcpu(&c, NULL, NULL);
>            cpu =3D (s =3D=3D -1) ? s : c;
>=20
> But when you compare the output of these two in a multi-threaded program
> (using clone()), the two produce very different outcomes. Only the second
> one will give you the right answer.
>=20
> The results can be reproduced with sched_setaffinity() before calling
> clone() and a call to both methods above from within the child process. My
> version uses a timer_create() to make this call periodically.
>=20
> 	sched_get_cpu_timer_init(0);
> //	core_from     =3D	sched_get_cpu() + 1;=09
>=20
> 	double x =3D 1.0;
> 	double y =3D (double) (random() + 1) * 1.00E-19f;
>=20
> 	for	(long i =3D 0; i < ((long) 1 << 32); i++)	x *=3D 1.00f + y;
>=20
> //	sleep	(1);
> //	usleep	(random() % 1000000L);
>=20=09
> //	core_upto     =3D	sched_get_cpu() + 1;
> 	sched_get_cpu_timer_free();
>=20
> Compilation is done with -Ofast -mfpmath=3D387 -fno-toplevel-reorder, for=
 sake
> of completeness.
>=20
> Best regards,
> Mischa Baars.

(In reply to Florian Weimer from comment #1)
> Would you please post a complete, self-contained reproducer, and state yo=
ur
> glibc and kernel versions? Thanks.

Yes... working on it.

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