[Networker] Weird parallelism issue?
2010-05-23 19:01:50
I'm running 7.4.5 on a CentOS 4 box.
Normally my backups go to a VTL first, but the VTL is offline so I'm
having the backups go direct to tape tonight. I only have one LTO-3 tape
drive operating as well (usually it is used for cloning/staging, and the
second drive started acting up today as well).
When the savegrp first runs, 4 backup streams write to the tape as
expected for the device parallelism setting. But after the initial four
are completed, it looks like only a single stream is permitted. I'm not
sure what exactly is happening...it seems like each additional client
that was waiting for a writable Default tape comes out of that state one
at a time, with the mounted tape having to reverify its label each time,
thus slowing things way down.
I checked other parallelism settings I could find. Server is set to 16,
while savegrp is set to 0. Only one savegrp was running at the time.
Any ideas how I can speed this up?
-Brian
To sign off this list, send email to listserv AT listserv.temple DOT edu and type
"signoff networker" in the body of the email. Please write to networker-request
AT listserv.temple DOT edu if you have any problems with this list. You can access the
archives at http://listserv.temple.edu/archives/networker.html or
via RSS at http://listserv.temple.edu/cgi-bin/wa?RSS&L=NETWORKER
|
<Prev in Thread] |
Current Thread |
[Next in Thread>
|
- [Networker] Weird parallelism issue?,
Brian O'Neill <=
|
|
|