Displaying 2 results from an estimated 2 matches for "cpustop_handl".
Did you mean:
cpustop_handler
2009 Jan 28
0
smp_tlb_shootdown bottleneck?
...me to time. Usually this sysbench test
passed in a few seconds, and at this time it runs in more than 10 seconds.
breaking to ddb while seen too much system load shows many sysbench threads
waiting for a mutex in smp_tlb_shootdown:
db> bt 100133
Tracing pid 810 tid 100133 td 0xffffff00032d56e0
cpustop_handler() at cpustop_handler+0x40
ipi_nmi_handler() at ipi_nmi_handler+0x30
trap() at trap+0x378
nmi_calltrap() at nmi_calltrap+0x8
--- trap 0x13, rip = 0xffffffff8074c912, rsp = 0xffffffffab79fff0, rbp
= 0xffffffffb4acf6f0 ---
smp_tlb_shootdown() at smp_tlb_shootdown+0x82
pmap_invalidate_range() at pmap...
2012 Nov 13
1
thread taskq / unp_gc() using 100% cpu and stalling unix socket IPC
...3:19 12.89% pop3-login
[3]
db:0:kdb.enter.sysctl> run lockinfo
db:1:lockinfo> show locks
No such command
db:1:locks> show alllocks
No such command
db:1:alllocks> show lockedvnods
Locked vnodes
db:0:kdb.enter.sysctl> trace 100058
Tracing pid 0 tid 100058 td 0xfffffe00262fc000
cpustop_handler() at cpustop_handler+0x28
ipi_nmi_handler() at ipi_nmi_handler+0x3d
trap() at trap+0x2ea
nmi_calltrap() at nmi_calltrap+0x8
--- trap 0x13, rip = 0xffffffff809a2a3e, rsp = 0xffffff800039efe0, rbp = 0xffffff975cf4aa10 ---
unp_gc() at unp_gc+0x20e
taskqueue_run_locked() at taskqueue_run_locked+0x85...