|
|Subject:
TED]
cc:
Subject:Re: RAW vs. JFS question
There are not any performance improvements when the TSM Recovery Log or
TSM Data Base is put on RAW volumes. It would be much easier to manage
if the environment is all JFS. There may also be a need in the future to
run multiple ins
several years ago (4?) I was working on TSM on Solaris, and working for a
VAR
we did some testing. Putting TSM files (everything) on a raw JBOD was
significantly
faster than using a big raid array.
for customers, we did use (in the old days, online disk suite) and a white
paper
from Sun, to use 4
Bill,
JFS journalling doesn't journal data changes, only changes to metadata. So in a
filesystem with lots of file and directory creates and deletes its useful. In the TSM
situation, such changes are rare, and so JFS doesn't buy you a lot in terms of
recoverability.
Steve
Steve Harris
AIX a
At 03:01 PM 1/22/2004 -0500, James Hunt wrote:
There are not any performance improvements when the TSM Recovery Log or
TSM Data Base is put on RAW volumes.
Moving from JFS to RAW (for DB and LOG vols) does in fact help performance
somewhat on larger systems. On smaller systems which are not resour
owski [mailto:[EMAIL PROTECTED]
Sent: Thursday, January 22, 2004 1:36 PM
To: [EMAIL PROTECTED]
Subject: Re: RAW vs. JFS question
At 06:24 PM 1/22/2004 +0100, you wrote:
>On Thursday 22 January 2004 15:38, Bill Boyer wrote:
> > The "new" TSM runing guide recommends using RAW volume
At 06:24 PM 1/22/2004 +0100, you wrote:
On Thursday 22 January 2004 15:38, Bill Boyer wrote:
> The "new" TSM runing guide recommends using RAW volumes for performance
> reasons.
I think IBM's recommendation is raw for DB and LOG, and JFS for stgpool
volumes (because of potential readahead benefits
On Thursday 22 January 2004 15:38, Bill Boyer wrote:
> The "new" TSM runing guide recommends using RAW volumes for performance
> reasons. I have a client that doesn't want to go RAW because the JFS
> logging goes away. I'm not that AIX savy to be able to argue one way or the
> other with him...
>
>
>I can't speak to AIX, I use Solaris but I just converted all of
>my volumes from mounted, VXFS ones to RAW and the performance difference
>has been huge. ...
This might be an indication that file system operations in that environment
- particulary, sync() - may be quite expensive. Many a
lly noticable) performance benefits from RAW.
"French, Michael" <[EMAIL PROTECTED]>
Sent by: "ADSM: Dist Stor Manager" <[EMAIL PROTECTED]>
01/22/2004 10:12 AM
Please respond to "ADSM: Dist Stor Manager"
To: [EMAIL PROTECTED]
cc:
.
Michael French
Savvis Communications
IDS01 Santa Clara, CA
(408)450-7812 -- desk
(408)239-9913 -- mobile
-Original Message-
From: ADSM: Dist Stor Manager [mailto:[EMAIL PROTECTED] On Behalf Of
Gerhard Rentschler
Sent: Thursday, January 22, 2004 9:05 AM
To: [EMAIL PROTECTED]
Subject: Re: R
ry 22, 2004 9:54 AM
To: [EMAIL PROTECTED]
Subject: Re: RAW vs. JFS question
>The "new" TSM runing guide recommends using RAW volumes for performance
>reasons. I have a client that doesn't want to go RAW because the JFS
logging
>goes away. I'm not that AIX savy to be a
I think the most interesting question is still unanswered: how much
performance do I gain with raw volumes? More exactly: how much less time
will an expiration take on a 100 GB TSM data base? I don't think raw volumes
would make sense for disk caches.
Does anyone have experience in this area?
Bes
>The "new" TSM runing guide recommends using RAW volumes for performance
>reasons. I have a client that doesn't want to go RAW because the JFS logging
>goes away. I'm not that AIX savy to be able to argue one way or the other
>with him...
Bill -
See "The Advantages of Using Journal File System Fi
The "new" TSM runing guide recommends using RAW volumes for performance
reasons. I have a client that doesn't want to go RAW because the JFS logging
goes away. I'm not that AIX savy to be able to argue one way or the other
with him...
Going RAW for performance, does that take away from recoverabil
15 matches
Mail list logo
