On Mon, Mar 19, 2007 at 02:46:04PM -0400, George Sinclair wrote:
> When you say parallelism of 16, do you mean the server parallelism, or
> are you referring to the actual number of target sessions you have set
> per drive? You have 2 drives, what do you have the target sessions set
> to on each?
16 target sessions, with a third non-jukebox drive set also to 16 target
sessions.
> Yeah, I could crank the target sessions for any one drive well beyond
> the server parallelism - it allows that - but can the total number of
> allowed "running" target sessions on the storage node exceed 32 if
> your server will actually allow a parallelism of, say, 96? For
> example, if one snode is running 20 sessions, and the server has no
> attached libraries, then could the other snode run 50 save sets?
I don't have storage nodes in my environment, so I don't know. I don't
recall if we've ever exceeded 32 or not. Networker's been known to have
some "bugs" where certain licensing rules aren't enforced; that's why I
mentioned my version.
> So would recovering data from an LTO-3 tape wherein multiplexing is
> set to, say, 12, versus from an LTO-1 where multiplexing is set to 4,
> maybe 5 be about as fast? Do the LTO-3 drives read data by a fast
> enough difference over the LTO-1 drives to make up for the increased
> target sessions?
I don't know how they compare. I was coming from DLT, and noticed a
high enough speed boost I didn't care. I don't know if an LTO1 to LTO3
jump is as large or how they compare at different multiplexing levels.
Dave
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
|