- Community Home
- >
- Servers and Operating Systems
- >
- Legacy
- >
- HPE 9000 and HPE e3000 Servers
- >
- Re: rp3410/rp3440 scsi upgrade
HPE 9000 and HPE e3000 Servers
1752588
Members
4395
Online
108788
Solutions
Forums
Categories
Company
Local Language
юдл
back
Forums
Discussions
Forums
- Data Protection and Retention
- Entry Storage Systems
- Legacy
- Midrange and Enterprise Storage
- Storage Networking
- HPE Nimble Storage
Discussions
Discussions
Discussions
Forums
Forums
Discussions
юдл
back
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
- BladeSystem Infrastructure and Application Solutions
- Appliance Servers
- Alpha Servers
- BackOffice Products
- Internet Products
- HPE 9000 and HPE e3000 Servers
- Networking
- Netservers
- Secure OS Software for Linux
- Server Management (Insight Manager 7)
- Windows Server 2003
- Operating System - Tru64 Unix
- ProLiant Deployment and Provisioning
- Linux-Based Community / Regional
- Microsoft System Center Integration
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Blogs
Information
Community
Resources
Community Language
Language
Forums
Blogs
Go to solution
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
тАО06-12-2006 03:14 AM
тАО06-12-2006 03:14 AM
I have 3 servers 2 rp3410 and 1 rp3440 , They have 2xUltra 320 15k Disks installed,
We are hitting an I/O bottleneck which seams to be related to the fact that these machines only have Ultra 160 SCSI Contollers. I have asked HP for an upgrade , But they are saying that I can only have an Ultra 320 contoller with PA8900 CPU module and Not PA8800, I cannot get an explaination why , Does anybody know.
We are hitting an I/O bottleneck which seams to be related to the fact that these machines only have Ultra 160 SCSI Contollers. I have asked HP for an upgrade , But they are saying that I can only have an Ultra 320 contoller with PA8900 CPU module and Not PA8800, I cannot get an explaination why , Does anybody know.
Divide and Conquer
Solved! Go to Solution.
2 REPLIES 2
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
тАО06-12-2006 12:42 PM
тАО06-12-2006 12:42 PM
Solution
The explanation is that HP chose to design the Ultra 320 controller to work with the newer 8900 series of computers. Without accurate details, I can guess that the older architecture (memory bus, I/O channel adapters, etc) can't keep up with the 320 card, especially when the system is fully loaded with 320 cards and high speed disks.
It's easy to assume that going from 160 to 320 will double the throughput, and improve overall performance. However, the interface speed is only a small part of the total I/O throughput. If the disk has very limited cache space (JBOD disks usually have just a few megs), then seek time and rotation rate are much more important. And of course, the access patterns caused by your application programs can rfeduce the overall throughput to much less than 160 SCSI performance.
And as stated many times here in the Forums, there are a lot of bad applications, bad SQL code, and simply poor design (a very large disk for everything). Rather than hide poor design with a faster I/O card, you may find 5 x to 10x improvement by examining the data layout and look at additional smaller disks to separate conflicting access. top and sar will help with the analysis but you really need to purchase Glance to see the big picture.
Bill Hassell, sysadmin
It's easy to assume that going from 160 to 320 will double the throughput, and improve overall performance. However, the interface speed is only a small part of the total I/O throughput. If the disk has very limited cache space (JBOD disks usually have just a few megs), then seek time and rotation rate are much more important. And of course, the access patterns caused by your application programs can rfeduce the overall throughput to much less than 160 SCSI performance.
And as stated many times here in the Forums, there are a lot of bad applications, bad SQL code, and simply poor design (a very large disk for everything). Rather than hide poor design with a faster I/O card, you may find 5 x to 10x improvement by examining the data layout and look at additional smaller disks to separate conflicting access. top and sar will help with the analysis but you really need to purchase Glance to see the big picture.
Bill Hassell, sysadmin
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
тАО07-20-2006 02:11 AM
тАО07-20-2006 02:11 AM
Re: rp3410/rp3440 scsi upgrade
Used an external array
Divide and Conquer
The opinions expressed above are the personal opinions of the authors, not of Hewlett Packard Enterprise. By using this site, you accept the Terms of Use and Rules of Participation.
News and Events
Support
© Copyright 2024 Hewlett Packard Enterprise Development LP