On Tue, Dec 13, 2011 at 02:28:52PM -0500, Brian O'Neill wrote:
> The buffer has little bearing on this. It just means it can go four
> seconds longer before having to shoe-shine than if it didn't have
> the buffer. The fact still remains that the tape had to stop,
> reposition, and start during which is time not spent writing to the
> tape, so you are NOT getting the same performance.

But the stopping shouldn't affect the throughput of the client.

The drive won't stop until the buffer is empty.  Assuming the client
doesn't pick that moment to speed up, the drive can stop, reposition,
and start, and the client will still not have filled the buffer at that
rate.  So it notices no issue.  Once the tape is moving, it can drain
the buffer quickly, so again, nothing should be seen by the client.

Unless the client drops a burst right at the stop (which fills the
buffer in less time than restart), it shouldn't notice.

-- 
Darren

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