Question about rac: http://asktom.oracle.com/~tkyte/9iSeminar/img17.html

From: chao_ping <chao_ping_at_vip.163.com>
Date: Wed, 13 Nov 2002 16:09:04 -0800
Message-ID: <F001.00502D95.20021113160904@fatcity.com>

hi,list friends

         I am looking at rac performance and see tomas' paper, and i did a test: http://asktom.oracle.com/~tkyte/9iSeminar/img17.html

	My platform:
	Dell 6650 with 4*1.4G cpu and 4G memory on both nodes with 9.2 RAC and RDAS 2.1 OS.During this time, the server is quite idle.
	
	First i did a full table scan of some table in node1:

08:02:12 SQL> select count(*) from pdtviewcount;

  COUNT(*)

---

    808550

Elapsed: 00:00:01.09

Execution Plan

---

   0 SELECT STATEMENT Optimizer=CHOOSE (Cost=4 Card=1)    1 0 SORT (AGGREGATE)

   2    1     INDEX (FAST FULL SCAN) OF 'PK_COUNT' (UNIQUE) (Cost=4 Ca
          rd=8168)

Statistics

---

        193  recursive calls
          2  db block gets
       1792  consistent gets
       1728  physical reads
        188  redo size
        381  bytes sent via SQL*Net to client
        503  bytes received via SQL*Net from client
          2  SQL*Net roundtrips to/from client
          6  sorts (memory)
          0  sorts (disk)
          1  rows processed

	As you see, the full index scan is nearly all physical read, and it takes about 1 second.
	And now i did a second count from the second node 2:

08:08:54 SQL> select count(*) from pdtviewcount;

  COUNT(*)

---

    808550

Elapsed: 00:00:06.32

Execution Plan

---

   0 SELECT STATEMENT Optimizer=CHOOSE (Cost=4 Card=1)    1 0 SORT (AGGREGATE)

   2    1     INDEX (FAST FULL SCAN) OF 'PK_COUNT' (UNIQUE) (Cost=4 Ca
          rd=8168)

Statistics

---

        192  recursive calls
          0  db block gets
       1735  consistent gets
       1056  physical reads
          0  redo size
        381  bytes sent via SQL*Net to client
        503  bytes received via SQL*Net from client
          2  SQL*Net roundtrips to/from client
          6  sorts (memory)
          0  sorts (disk)
          1  rows processed
	As you see, it is mostly get from the physical disk, not the interconnect, and in the first node, it takes about 1 second while doing physical read, but in the second case, less physical io, but much slower(as you see ,it is 6.5 second!).
	So how about RAC advantage?  Please share your opinion.
	

Regards
zhu chao
Eachnet DBA
86-21-32174588-667
chao_ping_at_vip.163.com
www.happyit.net
www.cnoug.org(Chinese Oracle User Group)

-- 
Please see the official ORACLE-L FAQ: http://www.orafaq.com
-- 
Author: chao_ping
  INET: chao_ping_at_vip.163.com

Fat City Network Services    -- 858-538-5051 http://www.fatcity.com
San Diego, California        -- Mailing list and web hosting services


---------------------------------------------------------------------

To REMOVE yourself from this mailing list, send an E-Mail message
to: ListGuru_at_fatcity.com (note EXACT spelling of 'ListGuru') and in
the message BODY, include a line containing: UNSUB ORACLE-L
(or the name of mailing list you want to be removed from).  You may
also send the HELP command for other information (like subscribing).

Received on Wed Nov 13 2002 - 18:09:04 CST