Comments on: What Are Your System Statistics? http://structureddata.org/2008/01/02/what-are-your-system-statistics/ Oracle Database Performance And Scalability Blog Mon, 01 Mar 2010 22:11:26 +0000 http://wordpress.org/?v=2.9.2 hourly 1 By: Leigh Riffel http://structureddata.org/2008/01/02/what-are-your-system-statistics/comment-page-1/#comment-133 Leigh Riffel Fri, 04 Sep 2009 16:05:43 +0000 http://structureddata.org/2008/01/02/what-are-your-system-statistics/#comment-133 SQL > SELECT version FROM v$instance; VERSION ----------------- 11.1.0.7.0 SQL > select pname, pval1 from sys.aux_stats$ where sname = 'SYSSTATS_MAIN'; PNAME PVAL1 ------------------------------ ---------- CPUSPEEDNW 2138.081 IOSEEKTIM 5.776 IOTFRSPEED 36145.224 SREADTIM 2.724 MREADTIM 3.547 CPUSPEED 2081 MBRC 31 MAXTHR 176668672 SLAVETHR 764928 9 rows selected. Windows 2008 on VMware ESX 3.5 on a two node cluster with 6 DBs. Each node has two dual core 2.66 GHz processors. The storage is an HP EVA with 35 disks shared among about two dozen systems. SQL > SELECT version FROM v$instance;
VERSION
—————–
11.1.0.7.0

SQL > select pname, pval1 from sys.aux_stats$ where sname = ‘SYSSTATS_MAIN’;
PNAME PVAL1
—————————— ———-
CPUSPEEDNW 2138.081
IOSEEKTIM 5.776
IOTFRSPEED 36145.224
SREADTIM 2.724
MREADTIM 3.547
CPUSPEED 2081
MBRC 31
MAXTHR 176668672
SLAVETHR 764928
9 rows selected.

Windows 2008 on VMware ESX 3.5 on a two node cluster with 6 DBs. Each node has two dual core 2.66 GHz processors. The storage is an HP EVA with 35 disks shared among about two dozen systems.

]]> By: Nir Carasso http://structureddata.org/2008/01/02/what-are-your-system-statistics/comment-page-1/#comment-120 Nir Carasso Mon, 23 Mar 2009 12:38:25 +0000 http://structureddata.org/2008/01/02/what-are-your-system-statistics/#comment-120 <a href="#comment-793" rel="nofollow">@Richa</a> I Richa's IOSEEKTIM parameter is very interesting -is it possible to know what type of storage is being used ? @Richa
I Richa’s IOSEEKTIM parameter is very interesting -is it possible to know what type of storage is being used ?

]]> By: Nir Carasso http://structureddata.org/2008/01/02/what-are-your-system-statistics/comment-page-1/#comment-132 Nir Carasso Mon, 23 Mar 2009 12:32:22 +0000 http://structureddata.org/2008/01/02/what-are-your-system-statistics/#comment-132 <pre> SQL> select version from v$instance; VERSION ----------------- 10.2.0.1.0 SQL> select pname, pval1 from sys.aux_stats$ where sname = 'SYSSTATS_MAIN'; PNAME PVAL1 ------------------------------ ---------- CPUSPEED 1985 CPUSPEEDNW 1588.616 IOSEEKTIM 4.876 IOTFRSPEED 67665.085 MAXTHR 152200192 MBRC 33 MREADTIM 1.747 SLAVETHR 32113664 SREADTIM 2.021 9 rows selected. </pre> SQL> select version from v$instance; VERSION ----------------- 10.2.0.1.0 SQL> select pname, pval1 from sys.aux_stats$ where sname = 'SYSSTATS_MAIN'; PNAME PVAL1 ------------------------------ ---------- CPUSPEED 1985 CPUSPEEDNW 1588.616 IOSEEKTIM 4.876 IOTFRSPEED 67665.085 MAXTHR 152200192 MBRC 33 MREADTIM 1.747 SLAVETHR 32113664 SREADTIM 2.021 9 rows selected. ]]> By: Greg Rahn http://structureddata.org/2008/01/02/what-are-your-system-statistics/comment-page-1/#comment-128 Greg Rahn Wed, 28 May 2008 21:39:30 +0000 http://structureddata.org/2008/01/02/what-are-your-system-statistics/#comment-128 Chris- The largest I/O that Oracle can currently issue is 1MB. All modern operating systems support this (as far as I know) and some support even larger, though Oracle does not currently. The size of MBRC will depend mostly on the type of workload. If it is mostly index access, then it is likely to be on the smaller side (16 * 8k). If it is a data warehouse, then it very well may be on the upper bound, 1MB (128 * 8k). On a hybrid system, probably somewhere in between. I would be less concerned with the just MBRC size, and more concerned with the single and multi block read times (SREADTIM & MREADTIM), in relationship to a single block and the MBRC size. If these times are too close, and MBRC is on the larger side, it could possible cause the cost of a FTS to be artificially cheap. Chris-

The largest I/O that Oracle can currently issue is 1MB. All modern operating systems support this (as far as I know) and some support even larger, though Oracle does not currently.

The size of MBRC will depend mostly on the type of workload. If it is mostly index access, then it is likely to be on the smaller side (16 * 8k). If it is a data warehouse, then it very well may be on the upper bound, 1MB (128 * 8k). On a hybrid system, probably somewhere in between.

I would be less concerned with the just MBRC size, and more concerned with the single and multi block read times (SREADTIM & MREADTIM), in relationship to a single block and the MBRC size. If these times are too close, and MBRC is on the larger side, it could possible cause the cost of a FTS to be artificially cheap.

]]> By: Chris Adkin http://structureddata.org/2008/01/02/what-are-your-system-statistics/comment-page-1/#comment-131 Chris Adkin Sun, 25 May 2008 18:25:44 +0000 http://structureddata.org/2008/01/02/what-are-your-system-statistics/#comment-131 Hi Greg, I've been tuning some queries and it appears that I'm getting a lot more full table scans than I would expect. I've noticed from sys_auxstats$ that my MBRC is 21, considering the block size of my database is 16K, this equates to a whopping multiblock read of 336K, when I thought the max i/o size of most Unix platforms is 64K (give or take a bit). I was careful to gather sys stats first thing in the morning after the batch jobs that run where I work have completed (against databases I'm not using for my work), so as to make sure that I was getting stats for the disk rather than the SAN cache. However, I can't help feel that some sort of read ahead optimization has kicked in, giving an artificialy high MRBC value. The MRBCs of 82 and 105 that some of your respondants have given are quite interesting. What is your view of this and what sort of bounds a reasonable MRBC should be within ?. Chris Hi Greg,

I’ve been tuning some queries and it appears that I’m getting a lot more full table scans than I would expect. I’ve noticed from sys_auxstats$ that my MBRC is 21, considering the block size of my database is 16K, this equates to a whopping multiblock read of 336K, when I thought the max i/o size of most Unix platforms is 64K (give or take a bit). I was careful to gather sys stats first thing in the morning after the batch jobs that run where I work have completed (against databases I’m not using for my work), so as to make sure that I was getting stats for the disk rather than the SAN cache. However, I can’t help feel that some sort of read ahead optimization has kicked in, giving an artificialy high MRBC value. The MRBCs of 82 and 105 that some of your respondants have given are quite interesting. What is your view of this and what sort of bounds a reasonable MRBC should be within ?.

Chris

]]> By: RJarertt http://structureddata.org/2008/01/02/what-are-your-system-statistics/comment-page-1/#comment-129 RJarertt Mon, 19 May 2008 02:00:31 +0000 http://structureddata.org/2008/01/02/what-are-your-system-statistics/#comment-129 <pre> SQL> select version from v$instance; VERSION ----------------- 10.2.0.1.0 SQL> select pname, pval1 from sys.aux_stats$ where sname = 'SYSSTATS_MAIN'; PNAME PVAL1 ------------------------------ ---------- CPUSPEED 1071 CPUSPEEDNW 713.905386 IOSEEKTIM 10 IOTFRSPEED 4096 MAXTHR 61631488 MBRC 105 MREADTIM 34.52 SLAVETHR 7168 SREADTIM 18.006 </pre> Sun v40x w/ 4x Single-core opterons. 32gb ram connected via 4 2gb PCIx FC HBAs to a small HDS SAN. Probably will be upgrading to a 4x quad-core opteron w/ 64gb ram. Either a Sun x4400 or HP dl585 SQL> select version from v$instance; VERSION ----------------- 10.2.0.1.0 SQL> select pname, pval1 from sys.aux_stats$ where sname = 'SYSSTATS_MAIN'; PNAME PVAL1 ------------------------------ ---------- CPUSPEED 1071 CPUSPEEDNW 713.905386 IOSEEKTIM 10 IOTFRSPEED 4096 MAXTHR 61631488 MBRC 105 MREADTIM 34.52 SLAVETHR 7168 SREADTIM 18.006

Sun v40x w/ 4x Single-core opterons. 32gb ram connected via 4 2gb PCIx FC HBAs to a small HDS SAN.

Probably will be upgrading to a 4x quad-core opteron w/ 64gb ram. Either a Sun x4400 or HP dl585

]]> By: ajayy http://structureddata.org/2008/01/02/what-are-your-system-statistics/comment-page-1/#comment-102 ajayy Tue, 25 Mar 2008 00:40:39 +0000 http://structureddata.org/2008/01/02/what-are-your-system-statistics/#comment-102 <pre> SQL> select version from v$instance; VERSION ----------------- 10.2.0.3.0 SQL> select pname, pval1 from sys.aux_stats$ where sname = 'SYSSTATS_MAIN'; PNAME PVAL1 ------------------------------ ---------- CPUSPEED CPUSPEEDNW 607.475821 IOSEEKTIM 10 IOTFRSPEED 4096 MAXTHR MBRC MREADTIM SLAVETHR SREADTIM </pre> SQL> select version from v$instance; VERSION ----------------- 10.2.0.3.0 SQL> select pname, pval1 from sys.aux_stats$ where sname = 'SYSSTATS_MAIN'; PNAME PVAL1 ------------------------------ ---------- CPUSPEED CPUSPEEDNW 607.475821 IOSEEKTIM 10 IOTFRSPEED 4096 MAXTHR MBRC MREADTIM SLAVETHR SREADTIM ]]> By: Jimmy Green http://structureddata.org/2008/01/02/what-are-your-system-statistics/comment-page-1/#comment-130 Jimmy Green Thu, 20 Mar 2008 14:24:30 +0000 http://structureddata.org/2008/01/02/what-are-your-system-statistics/#comment-130 <pre> SQL> select version from v$instance; VERSION ---------------------------------------- 10.2.0.3.0 SQL> select pname, pval1 from sys.aux_stats$ where sname = 'SYSSTATS_MAIN'; PNAME PVAL1 ------------------------------ ---------- CPUSPEED 2063 CPUSPEEDNW 2091.18176 IOSEEKTIM 10 IOTFRSPEED 4096 MAXTHR 13312 MBRC MREADTIM SLAVETHR SREADTIM 1 </pre> SQL> select version from v$instance; VERSION ---------------------------------------- 10.2.0.3.0 SQL> select pname, pval1 from sys.aux_stats$ where sname = 'SYSSTATS_MAIN'; PNAME PVAL1 ------------------------------ ---------- CPUSPEED 2063 CPUSPEEDNW 2091.18176 IOSEEKTIM 10 IOTFRSPEED 4096 MAXTHR 13312 MBRC MREADTIM SLAVETHR SREADTIM 1 ]]> By: Michael Seiwert http://structureddata.org/2008/01/02/what-are-your-system-statistics/comment-page-1/#comment-115 Michael Seiwert Mon, 03 Mar 2008 12:35:23 +0000 http://structureddata.org/2008/01/02/what-are-your-system-statistics/#comment-115 <pre> SQL> select version from v$instance; VERSION ----------------- 11.1.0.6.0 SQL> select pname, pval1 from sys.aux_stats$ where sname='SYSSTATS_MAIN'; PNAME PVAL1 ------------------------------ ---------- CPUSPEED CPUSPEEDNW 1764,61655 IOSEEKTIM 10 IOTFRSPEED 4096 MAXTHR MBRC MREADTIM SLAVETHR SREADTIM </pre> SQL> select version from v$instance; VERSION ----------------- 11.1.0.6.0 SQL> select pname, pval1 from sys.aux_stats$ where sname='SYSSTATS_MAIN'; PNAME PVAL1 ------------------------------ ---------- CPUSPEED CPUSPEEDNW 1764,61655 IOSEEKTIM 10 IOTFRSPEED 4096 MAXTHR MBRC MREADTIM SLAVETHR SREADTIM ]]> By: Jeroen http://structureddata.org/2008/01/02/what-are-your-system-statistics/comment-page-1/#comment-126 Jeroen Mon, 28 Jan 2008 00:19:42 +0000 http://structureddata.org/2008/01/02/what-are-your-system-statistics/#comment-126 <pre> VERSION ----------------- 11.1.0.6.0 SQL> select pname, pval1 from sys.aux_stats$ where sname = 'SYSSTATS_MAIN'; PNAME PVAL1 ------------------------------ ---------- CPUSPEEDNW 324.838093 IOSEEKTIM 10 IOTFRSPEED 4096 SREADTIM MREADTIM CPUSPEED MBRC MAXTHR SLAVETHR </pre> VERSION ----------------- 11.1.0.6.0 SQL> select pname, pval1 from sys.aux_stats$ where sname = 'SYSSTATS_MAIN'; PNAME PVAL1 ------------------------------ ---------- CPUSPEEDNW 324.838093 IOSEEKTIM 10 IOTFRSPEED 4096 SREADTIM MREADTIM CPUSPEED MBRC MAXTHR SLAVETHR ]]>