- Community Home
- >
- Servers and Operating Systems
- >
- Operating Systems
- >
- Operating System - HP-UX
- >
- Re: Immediate reporting error
Categories
Company
Local Language
Forums
Discussions
Forums
- Data Protection and Retention
- Entry Storage Systems
- Legacy
- Midrange and Enterprise Storage
- Storage Networking
- HPE Nimble Storage
Discussions
Forums
Discussions
Discussions
Forums
Discussions
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
Community
Resources
Forums
Blogs
- 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
01-29-2007 08:29 AM
01-29-2007 08:29 AM
I have an HP Smart Array controller with 512 MB cache upgrade installed in an Integrity rx4640 Itanium machine.
I am attempting to enable "immediate reporting" on that controller to measure the impact on performance. I use the command "sudo scsictl -a -m ir=1 -m ir /dev/rdsk/c5t0d0"
However, I see the error message:
"scsictl: Device ioctl (: Device ioctl () error: Invalid argument"
I don't know if it is relevant, but the disk is in use at the moment. I can't easily unmount the active filesystems.
Will someone give me a tip about how to resolve this error?
Thanks,
Rodney
Solved! Go to Solution.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
01-29-2007 08:34 AM
01-29-2007 08:34 AM
Re: Immediate reporting error
Seems reasonable to me.
The scsictl command is intended to control 'real disks'.
The Smart Array has its own management tools and 'smarts'. Therefor 'immmediate reporting' (switching on write behind caching) is an 'Invalid Argument'.
Please use the Smart Array tools to manage it.
hth,
Hein.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
01-29-2007 09:00 AM
01-29-2007 09:00 AM
Re: Immediate reporting error
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
01-29-2007 10:19 AM
01-29-2007 10:19 AM
Re: Immediate reporting error
It could be a terminology confusion.
The "immediate reporting" corresponds to enabling write caching which in turn corresponds to a non-100% read cache.
See:
http://docs.hp.com/en/J6369-90036/J6369-90036.pdf
http://docs.hp.com/en/J6369-90036/index.html
detail:
http://docs.hp.com/en/J6369-90036/ch04s02.html#chdggiab
Example:
saconfig /dev/ciss7 -C 50
Also:
http://h18004.www1.hp.com/products/servers/proliantstorage/arraycontrollers/smartarray6400/index.html
hth,
Hein.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
01-29-2007 10:39 AM
01-29-2007 10:39 AM
Re: Immediate reporting error
Currently the smart array cache is enabled, with 25% dedicated for read cache, 75% dedicated for write cache. I have changed no other setting.
In case I have misunderstood you or the documentation, please verify that this configuration will give write behind caching aka "immediate reporting" for the smart array. Thank you.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
01-29-2007 11:00 AM
01-29-2007 11:00 AM
SolutionWith memory available for write cache the smart array will immediatly report a write IO as completed as soon as the data is in its cache.
A battery protects it there for up to 4 days.
75% of cache dedicated to write cache sounds like a lot but may be justified when write happen in large bursts (sync).
If you have more then 128MB cache memory, then you might reduce to 50/50.
Ideally you would run a week (or day) one way, and an other period without and compare results (transaction response times, throughput, idle time).
hth,
Hein van den Heuvel
HvdH Performance Consulting
http://h18004.www1.hp.com/products/quickspecs/11587_div/11587_div.html#Technical%20Specifications
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
01-30-2007 01:23 AM
01-30-2007 01:23 AM