On 19 Oct, Curt Sampson wrote:


>> I already usese 8kb/blocks. (rsize,wsize when mounting).
> 
> You may find 1K blocks faster. Last I checked, Linux *still* did
> fragment reassembly by doing a full copy of all the fragments into
> a new buffer, rather than just chaining the buffers.

I have reached best performance when rsize is 4k and wsize is 32k (but
the difference between 8k and 32k is small).


On 19 Oct, Brian C. Grayson wrote:

>  Supposedly, the cause for such poor write performance is:
> Linux does everything in 1K blocks.  So when it writes to an
> NFS filesystem, it sends a write for the first 1K, which requires
> the server to read 4K from disk, modify 1K, and write 4K back to
> disk.  Then, Linux writes the next 1K, which requires 4K read, 1K
> modify, 4K write to disk.  Etc.  So, there is 4x the
> filesystem/disk traffic on the server than necessary.  This can
> be observed via running xosview on the server -- on our setup,
> the net traffic is a steady 160KB/sec, while the disk traffic is
> ~650K/sec.  From a NetBSD client, both net traffic and disk
> throughput go to near 1MB/sec (we are on 10Mb/sec Ethernet).

I checked this up with xosview, and it seems correct.


>  However, as far as I can tell, Linux does neither!  (Its NFSv3
> support is a sham/empty husk, and it doesn't always honor
> wsize, from what I've seen, or at least wsize=8192 seems to use
> 4096, and wsize=2048 seems to use 1024, IIRC.)

But it makes difference when i use 32k. I will take another look at
this later today.

>  Hope this helps!

A bit, thank you!

-- Andreas