How to debug 100x variance in writing the same file?

[Henrik Nordstrom]

On Thu, 20 Jan 2005, John Gerth wrote:

> However, writing to the Xserve's Samba is just all over the map.
> xcopys of even 10M files, vary from .2 to 55 seconds (files of
> other sizes up to 100M show similar ratios). I even went
> so far as to symlink a target filename to /dev/null to try and
> remove any vagaries with respect to actually writing to disk,
> but the wild variations continue (usually very fast or very slow).


Make sure your switch and server agrees on the network speed/settings, and 
that there is no network packet loss.

SMB is very sensitive to these things due to the request/response nature 
of the protocol while SCP, FTP etc is not so sensitive due to the stream 
nature of these protocols.

Regards
Henrik