kern/165903: mbuf leak

[Eugene M. Zheganin]

>Number:         165903
>Category:       kern
>Synopsis:       mbuf leak
>Confidential:   no
>Severity:       serious
>Priority:       medium
>Responsible:    freebsd-bugs
>State:          open
>Quarter:        
>Keywords:       
>Date-Required:
>Class:          sw-bug
>Submitter-Id:   current-users
>Arrival-Date:   Sat Mar 10 16:30:12 UTC 2012
>Closed-Date:
>Last-Modified:
>Originator:     Eugene M. Zheganin
>Release:        9.0-RELEASE
>Organization:
RealService LLC
>Environment:
FreeBSD taiga 9.0-RELEASE FreeBSD 9.0-RELEASE #1: Mon Jan 23 13:36:16 YEKT 2012     emz at taiga:/usr/obj/usr/src/sys/TAIGA  amd64
>Description:
# netstat -m
4776674/1561/4778235 mbufs in use (current/cache/total)
2040/1536/3576/25600 mbuf clusters in use (current/cache/total/max)
2040/758 mbuf+clusters out of packet secondary zone in use (current/cache)
1/599/600/12800 4k (page size) jumbo clusters in use (current/cache/total/max)
0/0/0/6400 9k jumbo clusters in use (current/cache/total/max)
0/0/0/3200 16k jumbo clusters in use (current/cache/total/max)
1198264K/5858K/1204123K 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
7172 requests for I/O initiated by sendfile
0 calls to protocol drain routines

# uptime
22:19  up 31 days,  5:59, 5 users, load averages: 0,16 0,16 0,17

and continues to grow over time.

This is a router; also it runs SMTP/Squid. Nothing unusual. Not intensely loaded. Network load is about 10-15 Megabit/sec most of the time, with bursts to 50-80 Megabits/sec.

There's an archive with a lots of reports taken every hour from the boot, with the script:

#!/bin/sh

reporttimestamp=`date +%d-%m-%Y-%H-%M`
reportname=${reporttimestamp}.txt

cd /home/emz/memory-mon

top -b > $reportname
echo "" >> $reportname
vmstat -m >> $reportname
echo "" >> $reportname
vmstat -z >> $reportname
echo "" >> $reportname
/usr/bin/perl /usr/local/bin/zfs-stats -a >> $reportname

They can be found here: http://tech.norma.perm.ru/files/memory-reports.tar.gz
>How-To-Repeat:
Install 9.0-RELEASE I guess. I don't know whats triggering the leak.
>Fix:
Reboot.

>Release-Note:
>Audit-Trail:
>Unformatted: