kern/131360: [nfs] poor scaling behavior of the NFS server under load

[Martin Birgmeier]

The following reply was made to PR kern/131360; it has been noted by GNATS.

From: Martin Birgmeier <martin at email.aon.at>
To: bug-followup at FreeBSD.org
Cc:  
Subject: Re: kern/131360: [nfs] poor scaling behavior of the NFS server under load
Date: Wed, 4 Feb 2009 14:38:06 +0100 (CET)

 I just realized that there might also be an interaction with pppoa2
 (from /usr/ports/net/pppoa). The excessive load seems to happen
 more likely if at the same time I have heavy traffic through my
 ADSL connection, which goes through an Alcatel ADSL modem, pppoa2,
 and user-mode ppp.
 
 Syslog will continually show the following message:
 
 Feb  4 13:56:59 gandalf pppoa2[1491]: write_dest: 11800 ENOBUFS errors
 Feb  4 13:57:03 gandalf pppoa2[1491]: write_dest: 11900 ENOBUFS errors
 Feb  4 13:57:08 gandalf pppoa2[1491]: write_dest: 12000 ENOBUFS errors
 Feb  4 13:57:11 gandalf pppoa2[1491]: write_dest: 12100 ENOBUFS errors
 Feb  4 13:57:15 gandalf pppoa2[1491]: write_dest: 12200 ENOBUFS errors
 
 At the same time, netstat -m shows the following:
 
 # netstat -m
 233/412/645 mbufs in use (current/cache/total)
 207/241/448/25600 mbuf clusters in use (current/cache/total/max)
 204/180 mbuf+clusters out of packet secondary zone in use (current/cache)
 1/19/20/12800 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)
 476K/661K/1137K 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)
 0/5/6656 sfbufs in use (current/peak/max)
 0 requests for sfbufs denied
 0 requests for sfbufs delayed
 15 requests for I/O initiated by sendfile
 0 calls to protocol drain routines