Date: Fri, 26 Sep 2008 07:31:53 -0700 From: Jeremy Chadwick <koitsu@FreeBSD.org> To: Danny Braniss <danny@cs.huji.ac.il> Cc: freebsd-hackers@freebsd.org, freebsd-stable@freebsd.org Subject: Re: bad NFS/UDP performance Message-ID: <20080926143153.GA26978@icarus.home.lan> In-Reply-To: <E1KjDTZ-000Jqb-Bh@cs1.cs.huji.ac.il> References: <E1Kj7NA-000FXz-3F@cs1.cs.huji.ac.il> <20080926081806.GA19055@icarus.home.lan> <E1Kj9bR-000H7t-0g@cs1.cs.huji.ac.il> <20080926095230.GA20789@icarus.home.lan> <E1KjDTZ-000Jqb-Bh@cs1.cs.huji.ac.il>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, Sep 26, 2008 at 04:35:17PM +0300, Danny Braniss wrote: > > On Fri, Sep 26, 2008 at 12:27:08PM +0300, Danny Braniss wrote: > > > > On Fri, Sep 26, 2008 at 10:04:16AM +0300, Danny Braniss wrote: > > > > > Hi, > > > > > There seems to be some serious degradation in performance. > > > > > Under 7.0 I get about 90 MB/s (on write), while, on the same machine > > > > > under 7.1 it drops to 20! > > > > > Any ideas? > > > > > > > > 1) Network card driver changes, > > > could be, but at least iperf/tcp is ok - can't get udp numbers, do you > > > know of any tool to measure udp performance? > > > BTW, I also checked on different hardware, and the badness is there. > > > > According to INDEX, benchmarks/iperf does UDP bandwidth testing. > > I know, but I get about 1mgb, which seems somewhat low :-( > > > > > benchmarks/nttcp should as well. > > > > What network card is in use? If Intel, what driver version (should be > > in dmesg). > > bge: <Broadcom NetXtreme Gigabit Ethernet Controller, ASIC rev. 0x9003> > and > bce: <Broadcom NetXtreme II BCM5708 1000Base-T (B2)> > and intels, but haven't tested there yet. Both bge(4) and bce(4) claim to support checksum offloading. You might try disabling it (ifconfig ... -txcsum -rxcsum) to see if things improve. If not, more troubleshooting is needed. You might also try turning off TSO if it's supported (check your ifconfig output for TSO in the options=<> section. Then use ifconfig ... -tso) > > Do you have any NFS-related tunings in /etc/rc.conf or /etc/sysctl.conf? > > > no, but diffing the sysctl show: > > -vfs.nfs.realign_test: 22141777 > +vfs.nfs.realign_test: 498351 > > -vfs.nfsrv.realign_test: 5005908 > +vfs.nfsrv.realign_test: 0 > > +vfs.nfsrv.commit_miss: 0 > +vfs.nfsrv.commit_blks: 0 > > changing them did nothing - or at least with respect to nfs throughput :-) I'm not sure what any of these do, as NFS is a bit out of my league. :-) I'll be following this thread though! -- | Jeremy Chadwick jdc at parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB |
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20080926143153.GA26978>