From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 27282 invoked by alias); 17 Nov 2006 15:40:57 -0000 Received: (qmail 27222 invoked by uid 48); 17 Nov 2006 15:40:35 -0000 Date: Fri, 17 Nov 2006 18:22:00 -0000 Message-ID: <20061117154035.27221.qmail@sourceware.org> From: "wcohen at redhat dot com" To: systemtap@sources.redhat.com In-Reply-To: <20060601184524.2725.ldimaggi@redhat.com> References: <20060601184524.2725.ldimaggi@redhat.com> Reply-To: sourceware-bugzilla@sourceware.org Subject: [Bug runtime/2725] Attempting to probe all kernel functions hangs FC5 X-Bugzilla-Reason: AssignedTo Mailing-List: contact systemtap-help@sourceware.org; run by ezmlm Precedence: bulk List-Subscribe: List-Post: List-Help: , Sender: systemtap-owner@sourceware.org X-SW-Source: 2006-q4/txt/msg00459.txt.bz2 ------- Additional Comments From wcohen at redhat dot com 2006-11-17 15:40 ------- Logged into each machine remotely and ran the 20061117 snapshot with the following script: ./stap_testing_200611170930/install/bin/stap -v -p5 -e 'probe kernel.function("*") { printf ("%s %s %d %s ","test-> ", execname(), pid(), probefunc() ) }' fc6 i686 UP kernel: 2.6.18-1.2849.fc6 #1 SMP Fri Nov 10 12:36:14 EST 2006 i686 i686 i386 GNU/Linux Got the following output to the console when running the mentioned script: BUG: unable to handle kernel paging request atf printing eip: 8c60c02f *pde = 00000000 Oops: 0000 [#1] BUG: unable to handle kernel paging request at virtual address 8c60c02f printing eip: c0629c0b *pde = 00000000 Oops: 0000 [#2] BUG: unable to handle kernel NULL pointer dereference at virtual address 0000000 printing eip: c0629c0b *pde = 00000000 Recursive die() failure, output suppressed <0>BUG: spinlock lockup on CPU#0, staprun/2683, c066fbac (Not tainted) Got same output even when printf taken out of script. rawhide i686 SMP 2.6.18-1.2849.fc6PAE #1 SMP Fri Nov 10 13:27:10 EST 2006 i686 i686 i386 GNU/Linux The machine hangs with the script with the printf in the body. No output or oops or anything However, the following script didn't kill the machine: ./stap_testing_200611170930/install/bin/stap -v -p5 -e 'probe kernel.function("*") { }' It took significant time for the probes to be removed (about a minute). rawhide x86-64 Linux dhcp59-198.rdu.redhat.com 2.6.18-1.2849.fc6 #1 SMP Fri Nov 10 12:34:46 EST 2006 x86_64 x86_64 x86_64 GNU/Linux The machine oops with the printf script. Simplified the script. The following script killed the machine by setting off the watchdog timer: ./stap_testing_200611170930/install/bin/stap -v -p5 -e 'probe kernel.function("*") { }' Following transcribed from the screen: [] do_nmi+0x45/0x63 [] nmi+0x7f/0x88 [] nmi+0x80/0x88 <> [] nmi+0x80/0x88 Kernel panic- not syncing: Aiee, killing interrupt handler! Bug: warning at kernel/panic.c:137/panic() (Not tainted) Call Trace: [] show_trace+0x34/0x47 [] dump_stack+0x12/0x17 [] panic_0x1e3/0x1f4 [] do_exit+0x8c/0x8c2 [] sync_regs+0x0/0x67 [] DWARF2 unwinder stuck at 0xffffffff80678290 Leftover inexact backtrace: [] nmi_watchdog_tick+0x105/0x1a6 [] default_do_nmi+0x86/0x1de [] do_nmi+0x45/0x63 [] nmi+0x7f/0x88 [] nmi+0x80/0x88 <> [] nmi+0x80/0x88 -- http://sourceware.org/bugzilla/show_bug.cgi?id=2725 ------- You are receiving this mail because: ------- You are the assignee for the bug, or are watching the assignee.