tuning the estimate phase?
2006-05-02 10:24:58
Hi all,
Is it possible to tune the estimate phase of a backup run? We appear to be getting NFS timeouts experienced by our NFS clients during the estimate phase when the NFS server is getting backed up.
The going theory is this that during the estimation phase, amanda is doing a gtar|gzip -c >/dev/null. And, as we all know, the bandwidth of /dev/null is damn near impossible to beat :)
During the actual dumping of data, the gtar|gzip is getting sent back
across the wire, and therefore gtar gets constrained by the bandwidth of the network, which even at GigE is significantly lower than that of /dev/null. As a result, during the estimation phase, amanda is taking
over the disk IO to the RAID array and the NFS daemons are competing for r/w access.
Since the entire array is a single file system, even the backup of individual hierarchies seems to result in this blocking.
Does this sound like a reasonable theory? If so, is there a way I can tune the estimation to be "nicer" ?
Any pointers, comments, suggestions, etc. welcome.
-- Seeya, Paul
|
<Prev in Thread] |
Current Thread |
[Next in Thread>
|
- tuning the estimate phase?,
Paul Lussier <=
|
|
|