linux-kernel - Re: futex system call in write

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <20120603121603.047c86c4@mdontu-l>
Date:	Sun, 3 Jun 2012 12:16:03 +0300
From:	Mihai Donțu <mihai.dontu@...il.com>
To:	Xin Tong <xerox.time.tech@...il.com>
Cc:	linux-kernel <linux-kernel@...r.kernel.org>
Subject: Re: futex system call in write

On Sun, 3 Jun 2012 01:58:55 -0400 Xin Tong wrote:
> I am a program with 2 threads, each of which calling printf in a loop.
> when i strace this programs. i see besides write() gets calls a good
> number of times. futex gets call many times as well. it seems to be
> related to the write system call ? how is the futex system call used
> here ? maybe write() is blocking and futex is used to wait the thread
> up when the write finishes ? if that is the case, what about other
> blocking system calls ?
> 

You should probably ask this question on a glibc mailing list.

What you're seeing is the effect of using the locking version of the
standard IO calls, where before each output a mutex is acquired to
ensure thread safety. Thus futex() has nothing to do with write(), it
is merely the underlaying system call for pthread_mutex_xxxx() calls.

-- 
Mihai Donțu
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/