- ----Original
Message-----
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Clooney, David
Sent: October 16, 2006 6:08 AM
To: Brenton Carbins
Cc: veritas-bu@mailman.eng.auburn.edu
Subject: Re: [Veritas-bu] 9940B
I have performed some tests after analysing bpbkar and bptm logs all all media servers and a number of their bptm logs indicate that they are not waiting for empty buffers, in turn telling me that an increase of the buffer size and number should have a positive impact .
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Clooney, David
Sent: October 16, 2006 6:08 AM
To: Brenton Carbins
Cc: veritas-bu@mailman.eng.auburn.edu
Subject: Re: [Veritas-bu] 9940B
I have performed some tests after analysing bpbkar and bptm logs all all media servers and a number of their bptm logs indicate that they are not waiting for empty buffers, in turn telling me that an increase of the buffer size and number should have a positive impact .
Assuming you were getting "waiting for empty
buffer" previously, then you increased the number of buffers and you are no
longer getting the messages, then yes, increasing the number of buffers DID have a positive
impact.
If you are
NOT currently getting "waiting for empty" messages, then increase the buffer
count will do nothing but consume more
shared memory.
If you are
not getting any waiting for full, or waiting for empty buffer messages, then
there is no reason to change anything, unless you would like to "decrease" the
buffer numbers to gain more available memory outside of the
buffers.
After testing our throughput has
jumped around from around 11mb/sec to 40+ mb/sec which is fantastic,
my concern is for the latter part of your mail regarding tapes which have
been written with a different
SIZE_DATA_BUFFERS.
When testing I took backups before
and after the SIZE_DATA_BUFFERS implementation. I
then proceeded to test restores from both images written with different Buffer
sizes.
All
where successful however could you shed a little more light on this as we
obviously have all our backed up data written in the current SIZE_DATA_BUFFER
and it would be a shame not to achieve the throughput we saw when testing.
What
Brenton is referring to, isn't so much a performance issue as a function
issue....if you change the values you're using for SIZE_DATA_BUFFER, you will
want to thoroughly test restores from backups written at a different number to
ensure
functionality.
Paul
====================================================================================
La version française suit le texte anglais. ------------------------------------------------------------------------------------ This email may contain privileged and/or confidential information, and the Bank of Canada does not waive any related rights. Any distribution, use, or copying of this email or the information it contains by other than the intended recipient is unauthorized. If you received this email in error please delete it immediately from your system and notify the sender promptly by email that you have done so. ------------------------------------------------------------------------------------ Le présent courriel peut contenir de l'information privilégiée ou confidentielle. La Banque du Canada ne renonce pas aux droits qui s'y rapportent. Toute diffusion, utilisation ou copie de ce courriel ou des renseignements qu'il contient par une personne autre que le ou les destinataires désignés est interdite. Si vous recevez ce courriel par erreur, veuillez le supprimer immédiatement et envoyer sans délai à l'expéditeur un message électronique pour l'aviser que vous avez éliminé de votre ordinateur toute copie du courriel reçu.
_______________________________________________ Veritas-bu maillist - Veritas-bu@mailman.eng.auburn.edu http://mailman.eng.auburn.edu/mailman/listinfo/veritas-bu
