From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 18358 invoked by alias); 11 Jul 2012 10:38:38 -0000 Received: (qmail 18348 invoked by uid 22791); 11 Jul 2012 10:38:36 -0000 X-SWARE-Spam-Status: No, hits=-5.9 required=5.0 tests=BAYES_00,DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,FREEMAIL_FROM,KHOP_RCVD_TRUST,KHOP_THREADED,RCVD_IN_DNSWL_LOW,RCVD_IN_HOSTKARMA_YE X-Spam-Check-By: sourceware.org Received: from mail-gg0-f169.google.com (HELO mail-gg0-f169.google.com) (209.85.161.169) by sourceware.org (qpsmtpd/0.43rc1) with ESMTP; Wed, 11 Jul 2012 10:38:23 +0000 Received: by ggm4 with SMTP id 4so1183003ggm.0 for ; Wed, 11 Jul 2012 03:38:23 -0700 (PDT) MIME-Version: 1.0 Received: by 10.50.202.8 with SMTP id ke8mr14150774igc.6.1342003102820; Wed, 11 Jul 2012 03:38:22 -0700 (PDT) Received: by 10.64.107.102 with HTTP; Wed, 11 Jul 2012 03:38:22 -0700 (PDT) In-Reply-To: References: Date: Wed, 11 Jul 2012 10:38:00 -0000 Message-ID: Subject: Re: How can I explain for this? what is __kernel_vsyscall () ? From: Bjoern Doebel To: Tom Frank Cc: gdb@sourceware.org Content-Type: text/plain; charset=ISO-8859-1 X-IsSubscribed: yes Mailing-List: contact gdb-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Archive: List-Post: List-Help: , Sender: gdb-owner@sourceware.org X-SW-Source: 2012-07/txt/msg00023.txt.bz2 2012/7/11 Tom Frank : > I debug a multithreads programme with gdb,as it runs I use the > 'info threads' command, and find that most of the threads running at > __kernel_vsyscall () function > > as below: > > 6 Thread 0xb61e4b90 (LWP 322) 0x008e7402 in __kernel_vsyscall () > 5 Thread 0xb6be5b90 (LWP 320) 0x008e7402 in __kernel_vsyscall () > 4 Thread 0xb7fe7b90 (LWP 318) 0x008e7402 in __kernel_vsyscall () > 3 Thread 0xb75e6b90 (LWP 316) 0x008e7402 in __kernel_vsyscall () > * 1 Thread 0xb7fe86d0 (LWP 312) 0x0074c2b8 in clone () from > /lib/i686/nosegneg/libc.so.6 > > > > what is __kernel_vsyscall (), why most threads's frame is in that step ? __kernel_vsyscall() is Linux' system call entry point and the threads you are looking at seem to be blocking in such a syscall. To find out which it is, you might want to have a look at their EAX register (assuming you're on x86). Bjoern