Comments for The Pythian Blog http://www.pythian.com/news News and views from Pythian DBAs Thu, 17 May 2012 00:05:51 +0000 hourly 1 http://wordpress.org/?v=3.0.4 Comment on Installing Oracle VM Manager 3.1.1 under Dom0 host, or How to save resources on your sandbox by Oracle VM Manager: OVMAPI_6000E Internal Error: Connection refused Connection refused | The Pythian Blog http://www.pythian.com/news/32965/installing-oracle-vm-manager-3-1-1-under-dom0-host-or-how-to-save-resources-on-your-sandbox/#comment-792693 Oracle VM Manager: OVMAPI_6000E Internal Error: Connection refused Connection refused | The Pythian Blog Thu, 17 May 2012 00:05:51 +0000 http://www.pythian.com/news/?p=32965#comment-792693 [...] is just a quick post to share my first 3.1.1 Oracle VM Manager (OVMM) [...] [...] is just a quick post to share my first 3.1.1 Oracle VM Manager (OVMM) [...]

]]> Comment on Announcement: Release 1.1.2 of MySQL Plug-in for Oracle Enterprise Manager 10g/11g by Michael Wehrle http://www.pythian.com/news/30791/announcement-release-1-1-2-of-mysql-plug-in-for-oracle-enterprise-manager-10g11g/#comment-792423 Michael Wehrle Wed, 16 May 2012 17:28:37 +0000 http://www.pythian.com/news/?p=30791#comment-792423 I would love to be an aplha tester... please sign me up. woo-hoo! I would love to be an aplha tester… please sign me up. woo-hoo!

]]> Comment on Installing Oracle VM Manager 3.0.3 under Dom0 host, or How to save resources on your sandbox by Installing Oracle VM Manager 3.1.1 under Dom0 host, or How to save resources on your sandbox | The Pythian Blog http://www.pythian.com/news/30197/installing-oracle-vm-manager-3-0-3-under-dom0-host-or-how-to-save-resources-on-your-sandbox/#comment-792251 Installing Oracle VM Manager 3.1.1 under Dom0 host, or How to save resources on your sandbox | The Pythian Blog Wed, 16 May 2012 13:27:00 +0000 http://www.pythian.com/news/?p=30197#comment-792251 [...] installing the previous version. For all tricks that you need to use please see my Oracle VM Manager 3.0.3 under Dom0 [...] [...] installing the previous version. For all tricks that you need to use please see my Oracle VM Manager 3.0.3 under Dom0 [...]

]]> Comment on Oracle Database Appliance as a Consolidation Platform by Yury Velikanov http://www.pythian.com/news/32835/oracle-database-appliance-as-a-consolidation-platform/#comment-791715 Yury Velikanov Tue, 15 May 2012 23:30:55 +0000 http://www.pythian.com/news/?p=32835#comment-791715 +1. Loven the post Marc. Good summary. +1. Loven the post Marc. Good summary.

]]> Comment on Log Buffer #271, A Carnival of the Vanities for DBAs by Amardeep Sidhu http://www.pythian.com/news/32801/log-buffer-271-a-carnival-of-the-vanities-for-dbas/#comment-791511 Amardeep Sidhu Tue, 15 May 2012 18:02:53 +0000 http://www.pythian.com/news/?p=32801#comment-791511 I obviously know :) I obviously know :)

]]> Comment on My First Experience Running SLOB – Status Update 2 (first results) by Kevin Closson http://www.pythian.com/news/32907/my-first-experience-running-slob-status-update-2-first-results/#comment-791433 Kevin Closson Tue, 15 May 2012 15:30:01 +0000 http://www.pythian.com/news/?p=32907#comment-791433 Sorry, Yury, one more comment. Do you intend to analyze the behavior difference between SLOB and Orion for writes? I've been pointing out the difference in CPU profile for the two kits. DBWR is different than Orion. Perhaps some runit.sh N 0 ? Sorry, Yury, one more comment. Do you intend to analyze the behavior difference between SLOB and Orion for writes? I’ve been pointing out the difference in CPU profile for the two kits. DBWR is different than Orion. Perhaps some runit.sh N 0 ?

]]> Comment on My First Experience Running SLOB – Status Update 2 (first results) by Kevin Closson http://www.pythian.com/news/32907/my-first-experience-running-slob-status-update-2-first-results/#comment-791429 Kevin Closson Tue, 15 May 2012 15:27:18 +0000 http://www.pythian.com/news/?p=32907#comment-791429 Yury, Orion gets raw disks. How does SLOB access disk? Is it through a file system with direct I/O? Yury,

Orion gets raw disks. How does SLOB access disk? Is it through a file system with direct I/O?

]]> Comment on My First Experience Running SLOB – Status Update 2 (first results) by Kevin Closson http://www.pythian.com/news/32907/my-first-experience-running-slob-status-update-2-first-results/#comment-791427 Kevin Closson Tue, 15 May 2012 15:25:43 +0000 http://www.pythian.com/news/?p=32907#comment-791427 Love the testing, Yury..your work will help others so thanks. A couple of comments: 1. Regarding the HDD cache hypothesis. You have 12 disks atached to your server so I'll just presume you have an LSI controller. Depending on the vintage that will provide either 256 or 512MB cache on the PCI card. If you run more than 8 reader.sql users you will blow out that cache. The cache on an LSI card is generally a <200us service time PIO. You are seeing 5ms which is physically acceptable for fast drives with short seeks. You cite the capacity and count of your disks but not the performance attributes (e.g., RPM, track buffer size). Your 5ms I/O is quite likely due to short stroke seeks because you are in the neighborhood of 370 IOPS/drive which is quite possible with short seeks. 2. I'll be gentle on this comment. Your testing is at the extreme low end. Modern Xeons (e.g., WSM, SNB) can handle on the order of 20,000 IOPS/core. Since Orion uses no user-mode CPU it has the propensity to get to high-performance numbers easier than SLOB. SLOB has Oracle latches to contend with. Modern QPI servers handle that better, sure, but at your PIO rate there simply is no contention. All that aside, nice work. Thanks for posting for us too. Love the testing, Yury..your work will help others so thanks.

A couple of comments:

1. Regarding the HDD cache hypothesis. You have 12 disks atached to your server so I’ll just presume you have an LSI controller. Depending on the vintage that will provide either 256 or 512MB cache on the PCI card. If you run more than 8 reader.sql users you will blow out that cache. The cache on an LSI card is generally a <200us service time PIO. You are seeing 5ms which is physically acceptable for fast drives with short seeks. You cite the capacity and count of your disks but not the performance attributes (e.g., RPM, track buffer size). Your 5ms I/O is quite likely due to short stroke seeks because you are in the neighborhood of 370 IOPS/drive which is quite possible with short seeks.

2. I'll be gentle on this comment. Your testing is at the extreme low end. Modern Xeons (e.g., WSM, SNB) can handle on the order of 20,000 IOPS/core. Since Orion uses no user-mode CPU it has the propensity to get to high-performance numbers easier than SLOB. SLOB has Oracle latches to contend with. Modern QPI servers handle that better, sure, but at your PIO rate there simply is no contention.

All that aside, nice work. Thanks for posting for us too.

]]> Comment on My First Experience Running SLOB – Status Update 2 (first results) by Yury Velikanov http://www.pythian.com/news/32907/my-first-experience-running-slob-status-update-2-first-results/#comment-791323 Yury Velikanov Tue, 15 May 2012 13:15:31 +0000 http://www.pythian.com/news/?p=32907#comment-791323 Sure I can :) nohup time ./run_orion_oltp.sh 2>&1 1>./run_orion_oltp.01.log & [grid@host2 orion]$ cat ./run_orion_oltp.sh ./orion_linux_x86-64 -run oltp -testname data_dg -num_disks 12 -write 0 [grid@host2 orion]$ [grid@host2 orion]$ cat data_dg.lun /dev/mapper/disk_0_y00_532421940p1 /dev/mapper/disk_0_y01_532341712p1 /dev/mapper/disk_0_y04_532337776p1 /dev/mapper/disk_0_y05_532378236p1 /dev/mapper/disk_0_y08_532384844p1 /dev/mapper/disk_0_y09_532341692p1 /dev/mapper/disk_1_y02_532253988p1 /dev/mapper/disk_1_y03_532384572p1 /dev/mapper/disk_1_y06_532385008p1 /dev/mapper/disk_1_y07_532341764p1 /dev/mapper/disk_1_y10_532385560p1 /dev/mapper/disk_1_y11_531870356p1 [grid@host2 orion]$ Sure I can :)

nohup time ./run_orion_oltp.sh 2>&1 1>./run_orion_oltp.01.log &

[grid@host2 orion]$ cat ./run_orion_oltp.sh
./orion_linux_x86-64 -run oltp -testname data_dg -num_disks 12 -write 0
[grid@host2 orion]$

[grid@host2 orion]$ cat data_dg.lun
/dev/mapper/disk_0_y00_532421940p1
/dev/mapper/disk_0_y01_532341712p1
/dev/mapper/disk_0_y04_532337776p1
/dev/mapper/disk_0_y05_532378236p1
/dev/mapper/disk_0_y08_532384844p1
/dev/mapper/disk_0_y09_532341692p1
/dev/mapper/disk_1_y02_532253988p1
/dev/mapper/disk_1_y03_532384572p1
/dev/mapper/disk_1_y06_532385008p1
/dev/mapper/disk_1_y07_532341764p1
/dev/mapper/disk_1_y10_532385560p1
/dev/mapper/disk_1_y11_531870356p1
[grid@host2 orion]$

]]> Comment on My First Experience Running SLOB – Status Update 2 (first results) by GregG http://www.pythian.com/news/32907/my-first-experience-running-slob-status-update-2-first-results/#comment-791315 GregG Tue, 15 May 2012 13:08:20 +0000 http://www.pythian.com/news/?p=32907#comment-791315 Great post, could You please post Orion command line related parameters as well ? Regards GregG Great post, could You please post Orion command line related parameters as well ?
Regards
GregG

]]>