| 1 |
On Thu, 2008-01-24 at 19:19 -0600, Dan Farrell wrote: |
| 2 |
|
| 3 |
[...] |
| 4 |
> and as the client (from `mount`): |
| 5 |
> |
| 6 |
> nfs:/mnt/storage on /home/media/storage type |
| 7 |
> nfs(rw,rsize=65536,wsize=65536,soft,timeo=300,addr=192.168.1.88) |
| 8 |
> |
| 9 |
> /etc/fstab on the client looks like: |
| 10 |
> |
| 11 |
> nfs:/mnt/storage /home/media/storage nfs |
| 12 |
> rsize=65536,wsize=65536,rw,async,soft,timeo=300 0 0 |
| 13 |
> |
| 14 |
> |
| 15 |
> Of these options, rsize,wsize,and async are reputed to effect |
| 16 |
> performance. However, I do not see much of an effect between different |
| 17 |
> rsize and wsize settings. I believe that over an uncongested 100T |
| 18 |
> network it probably doesn't matter too much what rsize and wsize are. |
| 19 |
> On a different share (same server) mounted async without [r|w]size set, |
| 20 |
> performance (write, this time) was 11.2mb/s, roughly the same. |
| 21 |
> Furthermore, I'm not sure these values are even valid. |
| 22 |
> http://www.linuxdocs.org/HOWTOs/NFS-HOWTO/performance.html said that |
| 23 |
> nfs3 goes only to 32768. |
| 24 |
[...] |
| 25 |
|
| 26 |
As far as I remember, rsize and wsize are negotiated between client and |
| 27 |
server. Those mount options just set an upper limit which is certainly |
| 28 |
not what you want. I'm even wondering that those settings are accepted |
| 29 |
at all! Normally, unsigned 16bit integer has a range from 0 to 65535. If |
| 30 |
you ask me, that's an off-by-one error just waiting to happen... |
Archives