RE: stipe size

From: Ruth Gramolini <rgramolini_at_tax.state.vt.us>
Date: Mon, 23 Feb 2004 14:33:52 -0500
Message-ID: <006901c3fa43$f813b5e0$8459699f@vttaxnet.tax.state.vt.us>

We are running AIX5.2 with Oracle 9.2.0.4, 64 bit. The DB block size in 8192. I am copying the specs my SA gave me to answer such questions. Thanks Paul! (I hear that you will be coming to my Birthday Bash in October, I am so glad!)

Ruth

>From my SA:

And just to give you some the answers to some of the questions that poster asked:
We have 1GB of cache and all logical devices are configured with write back cache. The cache is also used for read ahead so every read request actually reads at least 64KB from disk and then keeps it in cache. Our "weighted average" I/O size is in the 20-50KB range (depending on what LV you look at).

  -----Original Message-----
  From: oracle-l-bounce_at_freelists.org
  [mailto:oracle-l-bounce_at_freelists.org]On Behalf Of Paul Drake   Sent: Friday, February 20, 2004 3:09 PM   To: oracle-l_at_freelists.org
  Subject: Re: stipe size

• Ruth Gramolini <rgramolini_at_tax.state.vt.us> wrote:
  > Good morning all,
  > We just installed a new fast disk farm with fiber
  > channels. For production
  > we are using raid 10. My SA set in up with a stipe
  > size of 64K based on the
  > size of most of the transactions. He wants to know
  > if this will be OK. I
  > don't know so I told him I would ask the experts.
  > What do you think?
  >
  > Thanks,
  > Ruth Gramolini
  > Oracle DBA
  > Vermont Department of Taxes
  

  Hi Ruth.

  I'm not claiming to be an export, but I'll chime in   anyways. :)

  What operating system and version are you running   Oracle Server on?
  What is the database block size?
  What filesystem are you using, or are raw volumes in   use?
  Does the storage unit have a cache that is used for   pre-fetching, and does it also support write-back   cacheing?
  How many drives comprise the striped volume?

  In an average statspack report, what is the average   number of blocks fetched per request in your data,   index and temp tablespaces?

  If you're performing mostly single block accesses,   then a smaller stripe size will carry the least   overhead, but may make maintenance operations take   longer.

  It will be a tradeoff of optimizing performance of   daily oltp activity (single block requests), vs. your   monthly batch jobs which are likely more   batch-oriented, which may favor a largish stripe size,   say 512KB.

  I'd highly recommend that he short-stroke the drives,   and only throw a filesystem on the outer half of the   disks for datafiles, and throw a filesystem on the   inner half for storing backups, archlogs, etc.

  Paul

  token reference to Juan Loiza's paper on SAME up on   the BAARF.net site

---

  Do you Yahoo!?
  Yahoo! Mail SpamGuard - Read only the mail you want.   http://antispam.yahoo.com/tools

---

  Please see the official ORACLE-L FAQ: http://www.orafaq.com

---

  To unsubscribe send email to: oracle-l-request_at_freelists.org   put 'unsubscribe' in the subject line.   --
  Archives are at http://www.freelists.org/archives/oracle-l/   FAQ is at http://www.freelists.org/help/fom-serve/cache/1.html

---

---

Please see the official ORACLE-L FAQ: http://www.orafaq.com

---

To unsubscribe send email to: oracle-l-request_at_freelists.org put 'unsubscribe' in the subject line.

--
Archives are at http://www.freelists.org/archives/oracle-l/
FAQ is at http://www.freelists.org/help/fom-serve/cache/1.html
-----------------------------------------------------------------

Received on Mon Feb 23 2004 - 13:30:14 CST