RE: FreeBSD-6.1 reboots due to high mbufs

Hi,

Seems to be an old posting. Were you able to solve this problem. What is your ifconfig output.

Sunil Sunder Raj
http://daemon.in


From: Tek Bahadur Limbu <teklimbu@xxxxxxxxxxxx>
To: freebsd-performance@xxxxxxxxxxx
Subject: FreeBSD-6.1 reboots due to high mbufs
Date: Fri, 30 Mar 2007 12:28:58 +0545

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Dear All,

I am quite new to FreeBSD in general and I also don't have much experience and knowledge as required by this mailing list. I had posted this on freebsd-questions but till now have not received any kind of feedback which is fine.

I need some help and suggestions from this mailing list if permissible. I am sorry if I am posting this to the wrong mailing list.

I have squid proxy server running on a FreeBSD-6.1 (amd) box. I have been facing this problem for sometime now. It's related to mbufs. For some reasons, my mbufs usage is extremely high. This high mbufs usage causes slow responses from Squid and in rare occasions, it even causes my server to reboot or locks out SSH sessions.

This FreeBSD-6.1 squid box serves about 3000-4000 users.

Server specs are:

Dell 430 Intel(R) Pentium(R) D CPU 3.00GHz-Dual CPU
real memory = 2145959936 (2046 MB)
bge0: <Broadcom BCM5751 Gigabit Ethernet
traffic load: 10Mb/s (through satellite)

root@server# netstat -m

66713/2677/69390 mbufs in use (current/cache/total)
66686/2210/68896/0 mbuf clusters in use (current/cache/total/max)
66686/2178 mbuf+clusters out of packet secondary zone in use (current/cache)
0/0/0/0 4k (page size) jumbo clusters in use (current/cache/total/max)
0/0/0/0 9k jumbo clusters in use (current/cache/total/max)
0/0/0/0 16k jumbo clusters in use (current/cache/total/max)
150050K/5089K/155139K bytes allocated to network (current/cache/total)
0/0/0 requests for mbufs denied (mbufs/clusters/mbuf+clusters)
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


/etc/sysctl.conf:

kern.maxfilesperproc=8192
kern.ipc.somaxconn=8192
kern.maxprocperuid=8192
net.inet.ip.portrange.hifirst=10000
net.inet.ip.portrange.first=30000
net.inet.ip.portrange.last=65535
net.inet.tcp.recvspace=65535
net.inet.tcp.sendspace=65535
net.inet.tcp.blackhole=2
net.inet.udp.blackhole=1
net.inet.ip.fw.verbose_limit=5000
net.inet.icmp.icmplim=0
net.inet.tcp.msl=3000
net.isr.direct=1
vfs.read_max=16

/boot/loader.conf:

kern.ipc.nmbclusters=0
kern.maxusers=0
kern.maxfiles=16384
kern.maxproc=8192

Relevant Kernel Options:

options IPFIREWALL
options IPFIREWALL_VERBOSE
options IPFIREWALL_FORWARD
options IPFIREWALL_VERBOSE_LIMIT=5000
options IPFIREWALL_FORWARD_EXTENDED

options MSGMNB=16384
options MSGMNI=41
options MSGSEG=2049
options MSGSSZ=64
options MSGTQL=2048
options SHMSEG=128
options SHMMNI=192
options SHMMAX=33554432
options SHMMIN=1
options SHMALL=8192

options HZ=1000 #Polling Enabled


Note: Running IPFW. Also my other FreeBSD-4.x servers don't seem to suffer from this problem. They have almost the same IPFW, Squid and Sysctl configs.

Any feedback and suggestions will be highly appreciated.

Thanking you...


- --


With best regards and good wishes,

Yours sincerely,

Tek Bahadur Limbu

(TAG/TDG Group)
Jwl Systems Department

Worldlink Communications Pvt. Ltd.

Jawalakhel, Nepal

http://www.wlink.com.np
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.2.2 (FreeBSD)

iD8DBQFGDLGuVrOl+eVhOvYRAk8dAJ9dumhWCNTp6iHUy5PsQ0ie2OdMqQCgjG8u
eTxXgRCNSe3R2mmTGSbuSqo=
=mVGh
-----END PGP SIGNATURE-----
_______________________________________________
freebsd-performance@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to "freebsd-performance-unsubscribe@xxxxxxxxxxx"

_________________________________________________________________
Interest Rates Fall Again! $430,000 Mortgage for $1,399/mo - Calculate new payment http://www.lowermybills.com/lre/index.jsp?sourceid=lmb-9632-18679&moid=7581

_______________________________________________
freebsd-performance@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to "freebsd-performance-unsubscribe@xxxxxxxxxxx"

Relevant Pages

  • RE: Webrouting to a SQUID-proxy
    ... You can route to a Squid server, but if it requires authentication you ... How can I route all traffic for the above destination set ...
    (microsoft.public.isaserver)
  • Squid buffer overflow
    ... A certain kind of FTP request causes a Squid child process to coredump, ... and repeating such requests makes the server unusable. ... rfc1738_escape_partwhich returns the parameter string URL-escaped ...
    (Bugtraq)
  • Re: Server accelerator options: Squid, apaches built-in web caching or hardware "solutions"
    ... I have read about Squid as surrogate server, ... caching and is returning the appropriate caching information). ... layer which will add an additional hop to each request. ...
    (comp.infosystems.www.servers.unix)
  • Re: port forwarding and ipfw rules
    ... I don't think that this setup can be achieved using purely ipfw/natd. ... I believe squid can achieve this. ... should continue by trying to request from the next server in the list. ... > This configuration must be able to be added and removed dynamically without ...
    (freebsd-current)