On Fri, Sep 21, 2012 at 11:46 AM, Timothy J Massey <tmassey AT obscorp DOT com> 
wrote:
>
> I would not expect the network speed changing from 100Mb to 1Gb to make a
> difference:  this server is literally unchanged from one run to the next.
> BackupPC literally shows zero files changed!  So the network bandwidth
> shouldn't make a difference:  all it should be doing is passing hashes back
> and forth...
>
> We'll see what happens, though, and I'll let you know.

I wouldn't expect any difference by adding more bandwidth than you
were already filling.   The real work here is that the --ignore-times
option that is hard-coded into the full runs causes the target to have
to read all the files and without checksum caching, the server does
too.  And regardless of what benchmarks might tell you about disks, if
anything else wants the disk head to be somewhere else, this is going
to be slow.  Backups will almost always thresh any disk buffer/cache
that might make other types of access seem faster.

However, I just run into a situation in an rsync restore where both
ends were sitting in a select() apparently waiting for each other for
so long I gave up and used a tar download.   Maybe there is a bug
somewhere.

-- 
   Les Mikesell
     lesmikesell AT gmail DOT com

------------------------------------------------------------------------------
Got visibility?
Most devs has no idea what their production app looks like.
Find out how fast your code is with AppDynamics Lite.
http://ad.doubleclick.net/clk;262219671;13503038;y?
http://info.appdynamics.com/FreeJavaPerformanceDownload.html
_______________________________________________
BackupPC-users mailing list
BackupPC-users AT lists.sourceforge DOT net
List:    https://lists.sourceforge.net/lists/listinfo/backuppc-users
Wiki:    http://backuppc.wiki.sourceforge.net
Project: http://backuppc.sourceforge.net/