Author: Zoltan Forray/AC/VCU <zforray AT VCU DOT EDU>
Date: Tue, 19 Oct 2010 09:14:46 -0400
Now that I have ventured into new territory with this new server (Linux 6.2.1.1), I am experiencing terrible performance when it comes to moving data from disk (FILEDEVCLASS on EMC/SAN storage) vs my
Author: "Strand, Neil B." <NBStrand AT LEGGMASON DOT COM>
Date: Tue, 19 Oct 2010 13:50:37 -0400
Zoltan, You may need to increase the queue depth for the individual disks and/or the HBA attached to the disks. Monitor both the server (iostat/vmstat) and the storage (EMC voodoo application) for la
Author: Zoltan Forray/AC/VCU <zforray AT VCU DOT EDU>
Date: Tue, 19 Oct 2010 15:41:07 -0400
Neil, Thanks for the info. I have passed this on to my SAN guys since I know nothing about this aspect of the configuration nor if we can make these tweaks. I am still wondering if I should go back t
Author: Zoltan Forray/AC/VCU <zforray AT VCU DOT EDU>
Date: Wed, 20 Oct 2010 08:49:21 -0400
Huh? Please explain further. I thought the whole idea was you didn't need to pre-create volumes....they are automatically created and deleted as needed? From: Remco Post <r.post AT PLCS DOT NL> To: A
Author: Markus Engelhard <markus.engelhard AT BUNDESBANK DOT DE>
Date: Wed, 20 Oct 2010 15:19:56 +0200
Hi Zoltan, my experience has been: use fixed size preformatted volumes, and be sure to format them sequentially, even if it seems to take a hell of a time. But then, itīs a one-time action and highly
Author: Zoltan Forray/AC/VCU <zforray AT VCU DOT EDU>
Date: Wed, 20 Oct 2010 14:02:12 -0400
Thanks for the affirmation. This is what I have been seeing/experiencing. As soon as I can empty the stgpool (5TB), I will define fixed volumes and see how much difference that makes. I am aware of t
How you connect to the disk storage (i.e., SCSI or SAN) doesn't matter. This goes more to the issue of how blocks within the volumes are laid out on the spindles. formatting them one at a time will c
Author: "Hart, Charles A" <charles_hart AT UHC DOT COM>
Date: Wed, 20 Oct 2010 13:11:39 -0500
Dumb statement, but isn't the whole Idea of the File Devclass is it is sequential. Can one be more sequential than the other? If its not then its random. --Original Message-- From: ADSM: Dist Stor Ma
I/O to devclass file volumes will be inherently sequential, yes. It's not an absolute, however. There are varying degrees of "sequentialness". Think about it this way. When you are writing these volu
It is. But, if the blocks that make up a devtype file volume are scattered all over your disk, they don't occupy a sequential series of blocks on the disk. This means that the disk controller will no
Author: Richard Rhodes <rrhodes AT FIRSTENERGYCORP DOT COM>
Date: Wed, 20 Oct 2010 15:01:04 -0400
This can get complicated. File devices, as Paul states, are mostly accessed sequentially. But, as has been also said, the actual file volumes may be fragmented on the filesystem, resulting is effecti
yes, this can get complicated... Yes, multiple threads accessing different volumes on the same spindles can create head contention, even with volumes formatted serially. But I think you can still rea
Hmmm, that's interesting, jfs2 read-ahead. I know it exists, but recent TSM servers by default use direct I/O on jfs2, bypassing the buffer cache, and I assume the read-ahead as well... Or am I wrong
Hmm... I thought perhaps the Performance Tuning Guide would help clarify, which is where I thought I read this. But it seems somewhat ambiguous. Here are some snippets (for AIX): then later on the sa
Hi, I guess (just guess) that the performance tuning guide has been updated to reflect the fact that we can no longer disable directio (in a supported manner) on jfs2 in recent TSM releases, but that
Author: robert_clark <robert_clark AT MAC DOT COM>
Date: Wed, 20 Oct 2010 20:28:49 +0000
I like to divide the disk storage pool space into at least two file systems, on at least two volume groups. This provides a few benefits: First, you can set the two file systems up with different con
Being as our group in IBM is at least partially responsible for having written parts of the performance and tuning guide, let me make some clarifications here. I agree that some of this has not been
Author: Zoltan Forray/AC/VCU <zforray AT VCU DOT EDU>
Date: Thu, 21 Oct 2010 08:40:39 -0400
Speaking of this book, I found the paragraph titled: Mitigating performance degradation when backing up or archiving to FILE volumes Yes, I did follow their recommendations plus other recommendations
Author: "Strand, Neil B." <NBStrand AT LEGGMASON DOT COM>
Date: Thu, 21 Oct 2010 10:58:52 -0400
Zoltan, Is your database/logs on separate disks and separate HBAs from your filedevclass disks and are the disk HBAs separate from tape HBAs? Neil Strand Storage Engineer - Legg Mason Baltimore, MD.