10.0-RC1: bad mbuf leak?

[Michael Tuexen]

On Dec 25, 2013, at 2:33 PM, Gleb Smirnoff <glebius at FreeBSD.org> wrote:

>  Mark,
> 
> On Tue, Dec 24, 2013 at 10:54:33AM -0600, Mark Felder wrote:
> M> > finally found some free time today to try to look into this. I was digging into the SVN changelogs of sys/dev/e1000 and couldn't see any obvious changes that I should revert. Instead I went a different route and jumped to HEAD/CURRENT. I'm not seeing the mbufs leaking yet. I'll need another 24 hours to confirm. Hopefully this is a worthwhile clue. I'm a bit surprised nobody else has reported this type of behavior... maybe 10 isn't getting the amount of testing we expect? ...or maybe it's just my lonely, haunted hardware :(
> M> 
> M> Ok, I feel safe confirming that 10.0-RCs are not stable on my hardware. The mbuf problem went away completely when I jumped to head/current.
> M> 
> M> Can someone please suggest what patch I can attempt to back out to fix this? I'd like to try to assist in fixing this before 10.0-RELEASE happens or we're going to have some very angry users.
> 
> Is it possible for you to bisect head from the stable/10 branchpoint up
> to the current date and narrow down the revisions that introduced (and later
> fixed?) the leak?
I did a bisect and
http://svnweb.freebsd.org/changeset/base/258690
resolved the issue on my system:

[bsd4:~] tuexen% uname -a
FreeBSD bsd4.fh-muenster.de 11.0-CURRENT FreeBSD 11.0-CURRENT #192 r258689: Sat Jan  4 19:48:27 CET 2014     tuexen at bsd4.fh-muenster.de:/usr/home/tuexen/head/sys/amd64/compile/SCTP  amd64
[bsd4:~] tuexen% netstat -m
10755/315/11070 mbufs in use (current/cache/total)
10752/66/10818/508004 mbuf clusters in use (current/cache/total/max)
10752/30 mbuf+clusters out of packet secondary zone in use (current/cache)
0/0/0/254001 4k (page size) jumbo clusters in use (current/cache/total/max)
0/0/0/75259 9k jumbo clusters in use (current/cache/total/max)
0/0/0/42333 16k jumbo clusters in use (current/cache/total/max)
24192K/210K/24403K bytes allocated to network (current/cache/total)
150/5047/10782 requests for mbufs denied (mbufs/clusters/mbuf+clusters)
0/0/0 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 requests for sfbufs denied
0 requests for sfbufs delayed
0 requests for I/O initiated by sendfile


[bsd4:~] tuexen% uname -a
FreeBSD bsd4.fh-muenster.de 11.0-CURRENT FreeBSD 11.0-CURRENT #193 r258690: Sat Jan  4 19:56:38 CET 2014     tuexen at bsd4.fh-muenster.de:/usr/home/tuexen/head/sys/amd64/compile/SCTP  amd64
[bsd4:~] tuexen% netstat -m
10755/3000/13755 mbufs in use (current/cache/total)
10752/1374/12126/508004 mbuf clusters in use (current/cache/total/max)
10752/1373 mbuf+clusters out of packet secondary zone in use (current/cache)
0/0/0/254001 4k (page size) jumbo clusters in use (current/cache/total/max)
0/0/0/75259 9k jumbo clusters in use (current/cache/total/max)
0/0/0/42333 16k jumbo clusters in use (current/cache/total/max)
24192K/3498K/27690K bytes allocated to network (current/cache/total)
0/0/0 requests for mbufs denied (mbufs/clusters/mbuf+clusters)
0/0/0 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 requests for sfbufs denied
0 requests for sfbufs delayed
0 requests for I/O initiated by sendfile
[bsd4:~] tuexen% 


Best regards
Michael
> 
> -- 
> Totus tuus, Glebius.
> _______________________________________________
> freebsd-net at freebsd.org mailing list
> http://lists.freebsd.org/mailman/listinfo/freebsd-net
> To unsubscribe, send any mail to "freebsd-net-unsubscribe at freebsd.org"
>