Thanks for all your tips. I will contact my CE to see if we have the latest
microcode update (we just installed the device in late February). I ran the
test suggested as follows:
timex dd if=/dev/zero of=/dev/rmt1 bs=1024 count=1000
The result was real 21.06 seconds. This falls way short of what I would
expect when the advertised sustained transfer rate is supposed to be
15MB/sec native (30MB/sec compressed). The advertised transfer rates are
double what we had previously with the 3575 library, which is why we were
suprised by the poor performance. We expected the 3584 to be faster, other
than the initial locate of the data on the tape.
-----Original Message-----
From: Nathan E King [mailto:[EMAIL PROTECTED]]
Sent: Friday, April 20, 2001 1:50 PM
To: [EMAIL PROTECTED]
Subject: LTO performance
Debbie,
I saw your post regarding poor LTO performance in the TSM forum. While this
may not be the cause of your problems I did want to make you aware of one
known performance problem with LTO/TSM.
LTO can perform rather poorly with small files. This is because TSM does a
buffer flush at the end of every transaction. With smaller files there are
going to be more transactions and therefore more buffer flushes encountered
more frequently. Frequent buffer flushes cause the tape drive to backhitch
excessively slowing performance. This is less noticeable with tape drives
which are less susceptible to backhitch ie. 3575 and 3590. These drives
backhitch less because their motors are much more powerful. LTO is intended
as a high capacity, high performance drive, but people often forget that it
is pitched at the midrange tape market. If you require cadillac performance
then you have to go with 3590.
Engineering did however release a microcode update for the LTO drives. 0CE1
is the latest release. The previous release was 0BN1. Get your CE to
install the latest release, it does improve performance quite significantly
with small files on LTO/TSM. It doesn't eliminate performance problems with
small files but we have seen a 30-50% performance improvement in some
cases.
You can download the firmware update at:
ftp://service.boulder.ibm.com/storage/358x
The microcode is 0CE1.fmr
You can also find instructions for verifying the microcode at
ftp://ftp.software.ibm.com/storage/devdrvr/ in the LTO Ultrium user guide.
This may not be the true source of your problems however!!! I'm only
eliminating a known performance problem that I am aware of. Your case may
be adapter related or it could be a problem with the drives themselves. I
would definitely consider opening up a problem with IBM/Tivoli.
I hope this helps and that you reach a resolution quickly.
Regards,
Nathan King
IBM Corporation
