Linux NFS Problems (90% wait) over WLAN

Hello,

with my notebook connected by WLAN to my NFS-server I see as soon as I write
on NFS an io wait rate of about 90% and above. nfsstat shows a retrans rate
of about 5%. I don't this explains it at all. All the other values I see are
INMHO okay. The WLAN router is a Linksys WRT54G running OpenWrt. The load on
the router is about 0.1.

Both sides run a debian etch system with a self compiled Linux
2.6.12.2. linux kernel

Does anybody know where to look at?

TIA -- Peter

~:1> sar 1 10

Linux Astor 2.6.12.2astor #1 SMP Sat Sep 10 14:44:35 CEST 2005 i686 11/06/2005

23:07:52 cpu %usr %nice %sys %irq %softirq %wait %idle _cpu_
23:07:53 all 0 0 0 0 0 0 100
23:07:54 all 0 0 1 1 6 0 92
23:07:55 all 1 0 1 0 6 0 92
23:07:56 all 0 0 0 1 4 10 85
23:07:57 all 0 0 0 1 6 93 0
23:07:58 all 0 0 0 0 5 94 1
23:07:59 all 0 0 1 1 5 94 0
23:08:00 all 0 0 0 1 6 93 0
23:08:01 all 0 0 1 0 5 92 2
23:08:02 all 5 0 2 1 5 88 0
~:1> nfsstat
Server rpc stats:
calls badcalls badauth badclnt xdrcall
1 0 0 0 0
Server nfs v2:
null getattr setattr root lookup readlink
0 0% 0 0% 0 0% 0 0% 0 0% 0 0%
read wrcache write create remove rename
0 0% 0 0% 0 0% 0 0% 0 0% 0 0%
link symlink mkdir rmdir readdir fsstat
0 0% 0 0% 0 0% 0 0% 0 0% 0 0%

Server nfs v3:
null getattr setattr lookup access readlink
1 100% 0 0% 0 0% 0 0% 0 0% 0 0%
read write create mkdir symlink mknod
0 0% 0 0% 0 0% 0 0% 0 0% 0 0%
remove rmdir rename link readdir readdirplus
0 0% 0 0% 0 0% 0 0% 0 0% 0 0%
fsstat fsinfo pathconf commit
0 0% 0 0% 0 0% 0 0%

Client rpc stats:
calls retrans authrefrsh
159344 8848 0
Client nfs v2:
null getattr setattr root lookup readlink
0 0% 0 0% 0 0% 0 0% 0 0% 0 0%
read wrcache write create remove rename
0 0% 0 0% 0 0% 0 0% 0 0% 0 0%
link symlink mkdir rmdir readdir fsstat
0 0% 0 0% 0 0% 0 0% 0 0% 0 0%

Client nfs v3:
null getattr setattr lookup access readlink
0 0% 405 0% 2 0% 45 0% 68 0% 0 0%
read write create mkdir symlink mknod
101823 63% 45006 28% 6 0% 1 0% 0 0% 0 0%
remove rmdir rename link readdir readdirplus
5 0% 0 0% 0 0% 0 0% 0 0% 33 0%
fsstat fsinfo pathconf commit
0 0% 10 0% 0 0% 11940 7%

~:1> ifconfig -a
eth0 Link encap:Ethernet HWaddr 00:02:3F:BE:4E:27
inet addr:127.0.0.2 Bcast:127.255.255.255 Mask:255.255.255.0
inet6 addr: fe80::202:3fff:febe:4e27/64 Scope:Link
UP BROADCAST MULTICAST MTU:1500 Metric:1
RX packets:0 errors:0 dropped:0 overruns:0 frame:0
TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:0 (0.0 b) TX bytes:0 (0.0 b)
Interrupt:10 Base address:0xa000

eth1 Link encap:Ethernet HWaddr 00:04:23:79:C0:9E
inet addr:192.168.93.3 Bcast:192.168.93.255 Mask:255.255.255.0
inet6 addr: fe80::204:23ff:fe79:c09e/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:2984351 errors:0 dropped:0 overruns:0 frame:0
TX packets:2262384 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:3530225910 (3.2 GiB) TX bytes:3157065621 (2.9 GiB)
Interrupt:10 Base address:0x6000 Memory:d0000000-d0000fff

eth2 Link encap:UNSPEC HWaddr 00-02-3F-3A-45-00-21-13-00-00-00-00-00-00-00-00
BROADCAST MULTICAST MTU:1500 Metric:1
RX packets:0 errors:0 dropped:0 overruns:0 frame:0
TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:1000
RX bytes:0 (0.0 b) TX bytes:0 (0.0 b)

lo Link encap:Local Loopback
inet addr:127.0.0.1 Mask:255.0.0.0
inet6 addr: ::1/128 Scope:Host
UP LOOPBACK RUNNING MTU:16436 Metric:1
RX packets:807474 errors:0 dropped:0 overruns:0 frame:0
TX packets:807474 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:499558671 (476.4 MiB) TX bytes:499558671 (476.4 MiB)

sit0 Link encap:IPv6-in-IPv4
NOARP MTU:1480 Metric:1
RX packets:0 errors:0 dropped:0 overruns:0 frame:0
TX packets:0 errors:0 dropped:0 overruns:0 carrier:0
collisions:0 txqueuelen:0
RX bytes:0 (0.0 b) TX bytes:0 (0.0 b)

~:1> cat /proc/net/wireless
Inter-| sta-| Quality | Discarded packets | Missed | WE
face | tus | link level noise | nwid crypt frag retry misc | beacon | 17
eth1: 0004 100. 200. 0. 0 0 0 0 0 0
~:1> netstat -i
Kernel Interface table
Iface MTU Met RX-OK RX-ERR RX-DRP RX-OVR TX-OK TX-ERR TX-DRP TX-OVR Flg
eth0 1500 0 0 0 0 0 0 0 0 0 BMU
eth1 1500 0 2986751 0 0 0 2324098 0 0 0 BMRU
lo 16436 0 817277 0 0 0 817277 0 0 0 LRU

TIA -- Peter

--
(E-Mail Removed) ConSol* Software GmbH
Phone +49 89 45841-100 Consulting & Solutions
Mobile +49 177 6040121 Franziskanerstr. 38
http://www.consol.de D-81669 München

In comp.os.linux.networking Peter Weiss <(E-Mail Removed)>:
> Hello,

> with my notebook connected by WLAN to my NFS-server I see as soon as I write
> on NFS an io wait rate of about 90% and above. nfsstat shows a retrans rate
> of about 5%. I don't this explains it at all. All the other values I see are
> INMHO okay. The WLAN router is a Linksys WRT54G running OpenWrt. The load on
> the router is about 0.1.

Is the transfer speed reasonable? What's the problem with the i/o
wait?

> Both sides run a debian etch system with a self compiled Linux
> 2.6.12.2. linux kernel

> Does anybody know where to look at?

I'd enable 'tcp' for NFS at first and see if this improves
things, personally tunnel anything through ssh which is using
WLAN for security reasons (don't use nfs over WLAN).

[..]

--
Michael Heiming (X-PGP-Sig > GPG-Key ID: EDD27B94)
mail: echo (E-Mail Removed) | perl -pe 'y/a-z/n-za-m/'
#bofh excuse 64: CPU needs recalibration