LA output, video output, console input/output & netstat TIME_WAIT
Peter B. Pokryshev
ppb at valuehost.ru
Fri May 23 12:32:55 UTC 2014
On Tue, 6 May 2014 18:24:51 +0400
"Peter B. Pokryshev" <ppb at valuehost.ru> wrote:
> Hello all.
>
> 9.2-STABLE FreeBSD 9.2-STABLE #0 r261226
> highload servers
>
> /etc/sysctl.conf:
> security.bsd.see_other_uids=0
> security.bsd.unprivileged_proc_debug=0
> kern.ipc.somaxconn=4096
> net.inet.ip.fw.dyn_max=65536
> net.inet.ip.fw.dyn_syn_lifetime=10
> net.inet.ip.fw.dyn_ack_lifetime=60
> net.inet.ip.fw.dyn_buckets=512
> kern.ipc.shmall=6291456
> kern.ipc.shmmax=134217728
>
> /boot/loader.conf:
> kern.ipc.shmseg="512"
> kern.ipc.shmmni="1024"
>
>
> After 20-35 or more days of uptime,
> server stops showing realtime LA: show normal top, but first line not change:
> last pid: 29849; load averages: 2.36, 2.32, 2.28
> ^ ^ ^
> | | |
> Then, servers stops video output and TCP process in state TIME_WAIT starts grow
> until limits:
> # netstat -an |grep -c TIME_WAIT
> 27800
>
> At the console, when I try typing - nothing changes,
> BUT when I take out console - I see what I type previously at the monitor.
>
> Is any idea what is that?
>
> --
> Peter B. Pokryshev <ppb at valuehost.ru>
> _______________________________________________
> freebsd-bugs at freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-bugs
> To unsubscribe, send any mail to "freebsd-bugs-unsubscribe at freebsd.org"
Hi.
Is it normal after 16 days of uptime:
# vmstat -z
ITEM SIZE LIMIT USED FREE REQ FAIL SLEEP
...
16 Bucket: 152, 0, 24, 101, 193, 0, 0
32 Bucket: 280, 0, 38, 102, 329, 2, 0
64 Bucket: 536, 0, 30, 33, 487, 142, 0
128 Bucket: 1048, 0, 997, 11, 6717030,17345735, 0
...
mbuf_packet: 256, 12896820, 1449, 1646,9062649837,118865, 0
mbuf: 256, 12896820, 2193, 1762,17686258507, 0, 0
mbuf_cluster: 2048, 2015128, 3095, 1793,26759484,241537,1100807
mbuf_jumbo_page: 4096, 1007563, 2160, 864,2326876443, 0, 0
mbuf_jumbo_9k: 9216, 298537, 0, 0, 0, 0, 0
mbuf_jumbo_16k: 16384, 167927, 0, 0, 0, 0, 0
mbuf_ext_refcnt: 4, 0, 0, 0, 0, 0, 0
I mean 128 Bucket (FAIL) and mbuf_cluster (FAIL SLEEP)
# uname -a
FreeBSD v80.valuehost.ru 9.2-STABLE FreeBSD 9.2-STABLE #0 r265433: Tue May 6 18:28:22 MSK 2014 ppb at v80.valuehost.ru:/usr/obj/usr/src/sys/OMNIPOTENT amd64
# netstat -m
3099/3951/7050 mbufs in use (current/cache/total)
1392/3496/4888/2015128 mbuf clusters in use (current/cache/total/max)
1392/1703 mbuf+clusters out of packet secondary zone in use (current/cache)
1679/1345/3024/1007563 4k (page size) jumbo clusters in use (current/cache/total/max)
0/0/0/298537 9k jumbo clusters in use (current/cache/total/max)
0/0/0/167927 16k jumbo clusters in use (current/cache/total/max)
10274K/13359K/23634K bytes allocated to network (current/cache/total)
0/241537/118865 requests for mbufs denied (mbufs/clusters/mbuf+clusters)
0/1100807/0 requests for mbufs delayed (mbufs/clusters/mbuf+clusters)
0/0/0 requests for jumbo clusters delayed (4k/9k/16k)
0/0/0 requests for jumbo clusters denied (4k/9k/16k)
0/0/0 sfbufs in use (current/peak/max)
0 requests for sfbufs denied
0 requests for sfbufs delayed
0 requests for I/O initiated by sendfile
0 calls to protocol drain routines
# netstat -an |wc -l
29616
# netstat -an | grep -c TIME
27800
May be some problem with counters or timers (IMHO)?
--
Peter B. Pokryshev <ppb at valuehost.ru>
--
Peter B. Pokryshev <ppb at valuehost.ru>
More information about the freebsd-bugs
mailing list