This is the mail archive of the
systemtap@sourceware.org
mailing list for the systemtap project.
[Bug runtime/17270] uprobes_onthefly.exp causing hang on ppc64
- From: "dsmith at redhat dot com" <sourceware-bugzilla at sourceware dot org>
- To: systemtap at sourceware dot org
- Date: Tue, 19 Aug 2014 16:09:59 +0000
- Subject: [Bug runtime/17270] uprobes_onthefly.exp causing hang on ppc64
- Auto-submitted: auto-generated
- References: <bug-17270-6586 at http dot sourceware dot org/bugzilla/>
https://sourceware.org/bugzilla/show_bug.cgi?id=17270
--- Comment #2 from David Smith <dsmith at redhat dot com> ---
The uprobes_onthefly.exp testcase is composed of several subtests. All the
tests run with 'run_subtest_valid' work fine:
otf_finish_at_start_disabled, otf_finish_at_start_enabled,
otf_start_disabled_iter_1, otf_start_enabled_iter_1, otf_start_disabled_iter_2,
otf_start_enabled_iter_2, otf_start_disabled_iter_3, otf_start_enabled_iter_3,
otf_start_disabled_iter_4, otf_start_enabled_iter_4, otf_start_disabled_iter_5,
otf_start_enabled_iter_5, otf_timer_100ms, and otf_timer_50ms
The stress tests (run with 'run_subtset_stress') are where the problem lies.
Here is what happens when you run each individually:
- otf_stress_10ms_iter_50: passes
- otf_stress_5ms_iter_50: passes
- otf_stress_1ms_iter_50: passes
- otf_stress_500us_iter_50: passes, but causes the "stap module notifier
triggered in unexpected state 3" message on the console
- otf_stress_100us_iter_50: ditto
- otf_stress_prof_iter_2000: ditto
- otf_stress_hard_iter_2000: hangs the system with the following on the
console:
[ 1902.414132] INFO: rcu_sched detected stalls on CPUs/tasks: { 0 2 5 6}
(detected by 4, t=6002 jiffies, g=4654, c=4653, q=0)
[ 1902.414422] Task dump for CPU 0:
[ 1902.414471] swapper/0 R running task 0 0 0 0x00000000
[ 1902.414570] Call Trace:
[ 1902.414616] [c000000001283820] [c00000000046cc78] .find_next_bit+0x38/0xf0
(unreliable)
[ 1902.414734] [c0000000012839f0] [c0000000000a4194]
.p970_compute_mmcr+0x8d4/0x9f0
[ 1902.414844] Task dump for CPU 2:
[ 1902.414889] swapper/2 R running task 0 0 1 0x00000800
[ 1902.414986] Call Trace:
[ 1902.415022] [c00000022df6f870] [c0000000008ad580] .__schedule+0x8d0/0xae0
(unreliable)
[ 1902.415131] [c00000022df6fa40] [c0000000000a4194]
.p970_compute_mmcr+0x8d4/0x9f0
[ 1902.415243] Task dump for CPU 5:
[ 1902.415290] swapper/5 R running task 0 0 1 0x00000800
[ 1902.415387] Call Trace:
[ 1902.415429] [c00000022df7b870] [000001ac274bfdaa] 0x1ac274bfdaa (unreliable)
[ 1902.415538] [c00000022df7ba40] [c0000000000a4194]
.p970_compute_mmcr+0x8d4/0x9f0
[ 1902.415647] Task dump for CPU 6:
[ 1902.415693] swapper/6 R running task 0 0 1 0x00000800
[ 1902.415785] Call Trace:
[ 1902.415818] [c00000022df7f870] [c0000000008ad574] .__schedule+0x8c4/0xae0
(unreliable)
[ 1902.415925] [c00000022df7fa40] [c0000000000a4194]
.p970_compute_mmcr+0x8d4/0x9f0
- otf_stress_max_iter_5000: causes a system hang with no output on the console
(BTW, the unexpected state 3 in the "stap module notifier triggered in
unexpected state 3" message is STAP_SESSION_STOPPING.)
--
You are receiving this mail because:
You are the assignee for the bug.