Date: Wed, 05 Jul 2017 19:09:01 +0000 From: bugzilla-noreply@freebsd.org To: freebsd-net@FreeBSD.org Subject: [Bug 186114] net/mpd5 hangs after a certain number of users connect Message-ID: <bug-186114-2472-tfPRFuz8qU@https.bugs.freebsd.org/bugzilla/> In-Reply-To: <bug-186114-2472@https.bugs.freebsd.org/bugzilla/> References: <bug-186114-2472@https.bugs.freebsd.org/bugzilla/>
next in thread | previous in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D186114 --- Comment #104 from Cassiano Peixoto <peixoto.cassiano@gmail.com> --- Hi, It wasn't zombie, it looks like zombie because the kind of behavior. See process top output below: PID USERNAME THR PRI NICE SIZE RES STATE C TIME WCPU COM= MAND 1295 root 30 73 0 327M 147M CPU3 3 627:10 101.55% m= pd5 Pay attention to WCPU, it's too high. I never ran mpd5 in detached mode, but if you need it, i can. Regarding logs, there is nothing relevant in mpd5 logs, but in kernel logs i have: Jul 5 11:59:59 B-ras kernel: Accessing freed hook: name l4658, 0 refs, Last touched: Jul 5 11:59:59 B-ras kernel: Last active @ /usr/src/sys/netgraph/ng_base.c, line 1196 Jul 5 11:59:59 B-ras kernel: problem discovered at file /usr/src/sys/netgraph/ng_base.c, line 1131 Jul 5 11:59:59 B-ras kernel: KDB: stack backtrace: Jul 5 11:59:59 B-ras kernel: #0 0xffffffff80aa4ad7 at kdb_backtrace+0x67 Jul 5 11:59:59 B-ras kernel: #1 0xffffffff80bb2acc at ng_findhook+0xac Jul 5 11:59:59 B-ras kernel: #2 0xffffffff80bb96bc at ng_con_nodes+0x2c Jul 5 11:59:59 B-ras kernel: #3 0xffffffff80bb4e70 at ng_apply_item+0xa90 Jul 5 11:59:59 B-ras kernel: #4 0xffffffff80bb413b at ng_snd_item+0x1db Jul 5 11:59:59 B-ras kernel: #5 0xffffffff82451469 at ngc_send+0x209 Jul 5 11:59:59 B-ras kernel: #6 0xffffffff80aea8ec at sosend_generic+0x4ec Jul 5 11:59:59 B-ras kernel: #7 0xffffffff80af11c1 at kern_sendit+0x291 Jul 5 11:59:59 B-ras kernel: #8 0xffffffff80af1523 at sendit+0x1a3 Jul 5 11:59:59 B-ras kernel: #9 0xffffffff80af136d at sys_sendto+0x4d Jul 5 11:59:59 B-ras kernel: #10 0xffffffff80e36394 at amd64_syscall+0x6c4 Jul 5 12:00:00 B-ras kernel: #11 0xffffffff80e194eb at Xfast_syscall+0xfb Remember, i was using web status to collect info, i'll disable it, maybe it could be the problem, don't you think? --=20 You are receiving this mail because: You are on the CC list for the bug.=
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-186114-2472-tfPRFuz8qU>