From mboxrd@z Thu Jan  1 00:00:00 1970
From: Mathieu Desnoyers <mathieu.desnoyers-vg+e7yoeK/dWk0Htik3J/w@public.gmane.org>
Subject: Re: [RFC PATCH] getcpu_cache system call: caching current CPU
 number (x86)
Date: Fri, 17 Jul 2015 16:03:30 +0000 (UTC)
Message-ID: <626545401.1010.1437149010438.JavaMail.zimbra@efficios.com>
References: <1436724386-30909-1-git-send-email-mathieu.desnoyers@efficios.com> <5CDDBDF2D36D9F43B9F5E99003F6A0D48D5F39C6@PRN-MBX02-1.TheFacebook.com> <587954201.31.1436808992876.JavaMail.zimbra@efficios.com> <20150717105859.GB21915@domone>
Mime-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: QUOTED-PRINTABLE
Return-path: <linux-api-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>
In-Reply-To: <20150717105859.GB21915@domone>
Sender: linux-api-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
To: =?utf-8?Q?Ond=C5=99ej_B=C3=ADlka?= <neleai-9Vj9tDbzfuSlVyrhU4qvOw@public.gmane.org>
Cc: Ben Maurer <bmaurer-b10kYP2dOMg@public.gmane.org>, Paul Turner <pjt-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>, Andrew Hunter <ahh-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>, Peter Zijlstra <peterz-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>, Ingo Molnar <mingo-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>, rostedt <rostedt-nx8X9YLhiw1AfugRpC6u6w@public.gmane.org>, "Paul E. McKenney" <paulmck-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>, Josh Triplett <josh-iaAMLnmF4UmaiuxdJuQwMA@public.gmane.org>, Lai Jiangshan <laijs-BthXqXjhjHXQFUHtdCDX3A@public.gmane.org>, Linus Torvalds <torvalds-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>, Andrew Morton <akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>, linux-api <linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>, libc-alpha <libc-alpha-9JcytcrH/bA+uJoB2kUjGw@public.gmane.org>
List-Id: linux-api@vger.kernel.org

----- On Jul 17, 2015, at 6:58 AM, Ond=C5=99ej B=C3=ADlka neleai@seznam=
=2Ecz wrote:
[...]
>> If we invoke this per-thread registration directly in the glibc NPTL
>> implementation,
>> in start_thread, do you think it would fit your requirements ?
>>
> A generic solution would be adding eager initialization of thread_loc=
al
> variables which would fix more performance problems.

Concretely, what code would be in charge of this initialization ?

What changes does "eager initialization" imply from the current
implementation ?

> Second would be write patch to libc adding function
> pthread_create_add_hook_np to register function that would be ran aft=
er
> each thread creation.

Do you suggest that this callback should be registered once per thread,
or somehow attached to pthread_attr_t ? As maintainer of lttng-ust,
where we need some control over our own threads, but where we want mini=
mal
impact on the overall application, I would really prefer if we can atta=
ch
the callback to pthread_attr_t.

Thanks,

Mathieu


--=20
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com