This is the mail archive of the systemtap@sourceware.org mailing list for the systemtap project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

[Bug runtime/17270] uprobes_onthefly.exp causing hang on ppc64


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.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]