Re: SSD vs HDD

Rob,

Not journalling the files on the SSDs is really going to skew the
results. Particularly as you are apparently not using commitment
control.

Unless you have the optional HA Journal Performance LICPGM installed
(and you being you, you might :) Each write to a journal file without
commitment control forces a sync write for the journal entry.

In some prior test:
1) non journaled file, 1min
2) journaled file w/o commit, 13min
3) journaled file w/commit, 4min

Charles


On Fri, Oct 16, 2009 at 10:59 AM, <rob@xxxxxxxxx> wrote:

Running some tests in Rochester MN on HDD (Hard Disk Drives) versus SSD
(Solid State Drives).  On eight 280GB drives (405CD) INV901C ran for 4
hours and 58 minutes.  On a three drive Raid 5 parity set composed of
SSD's it only ran for 1 hour and 57 minutes.

I think that's significant.

CST600C dropped from 78 minutes down to 30 minutes.

The files on HDD were journaled.  The data on the SSD was not because we
had our journals and receivers back on *SYSASP and it didn't link them up
when we restored the library on the SSDs.

Rob Berendt
--
Group Dekko Services, LLC
Dept 01.073
Dock 108
6928N 400E
Kendallville, IN 46755
http://www.dekko.com

--
This is the Midrange Systems Technical Discussion (MIDRANGE-L) mailing list
To post a message email: MIDRANGE-L@xxxxxxxxxxxx
To subscribe, unsubscribe, or change list options,
visit: http://lists.midrange.com/mailman/listinfo/midrange-l
or email: MIDRANGE-L-request@xxxxxxxxxxxx
Before posting, please take a moment to review the archives
at http://archive.midrange.com/midrange-l.