- Community Home
- >
- Storage
- >
- Entry Storage Systems
- >
- Disk Enclosures
- >
- Attn: Peter Jansen
Disk Enclosures
1757127
Members
2691
Online
108858
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
тАО01-29-2001 01:29 PM
тАО01-29-2001 01:29 PM
Hi Peter -
I was reading your response to a question regard performance problems on a autoraid 12H array (see below).
Would you mind expanding on this a bit? How could it be a performance problem to have the cache enabled? I just bought an autoraid and had dual 96mb controllers installed specifically so I could take advantage of the cache.
Thanks in advance!
Tim
timmed@saif.com
----------------------------------
Another big performancehit can be suffered if the AutoRaid "automatically" sets the "Write Cache" to "Enabled".
Please check if this is true for your AutoRaid (i think the command is. If so, please let me know to supply you with further information on this subject.
Best regards,
Peter Jansen
ITchallenge
I was reading your response to a question regard performance problems on a autoraid 12H array (see below).
Would you mind expanding on this a bit? How could it be a performance problem to have the cache enabled? I just bought an autoraid and had dual 96mb controllers installed specifically so I could take advantage of the cache.
Thanks in advance!
Tim
timmed@saif.com
----------------------------------
Another big performancehit can be suffered if the AutoRaid "automatically" sets the "Write Cache" to "Enabled".
Please check if this is true for your AutoRaid (i think the command is
Best regards,
Peter Jansen
ITchallenge
Solved! Go to Solution.
2 REPLIES 2
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
тАО01-29-2001 10:34 PM
тАО01-29-2001 10:34 PM
Re: Attn: Peter Jansen
Hi Peter,
the Write Cache and Read Cache enable is a bit which have nothing to do with the cache of the diskarray itself. These bit are for the Host interface which could set there interal performance to a higher level. These could be a performance inrease because of the Host interface setting.
Best regards
Frank Skibbe
the Write Cache and Read Cache enable is a bit which have nothing to do with the cache of the diskarray itself. These bit are for the Host interface which could set there interal performance to a higher level. These could be a performance inrease because of the Host interface setting.
Best regards
Frank Skibbe
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
тАО01-30-2001 05:57 AM
тАО01-30-2001 05:57 AM
Solution
Gents,
Some explanation about the READ & Write Cache settings:
Change the apparent state of write cache on or
off. This switch only changes the write cache
setting presented to the operating system and does not affect the operation of the disk array, which always has write cache enabled. The disk array write cache is stored in NVRAM which eliminates the need to disable write cache for protection against power loss. This switch is provided for interoperability with those operating systems that require write cache be turned off.
However arraymgr -w off $ARRAYID will return an error message to you, you are not able to change this setting (allthough the man page says so).
The setting of the write cache is directly related to the resiliency mode settings and therefore cannot be changed manually with the
'arraymgr -w off' command. The write cache flag setting is as follows:
- Resiliency Setting = SingleController -> Write Cache = DISABLED
Force Unit Access Response = 2
- Resiliency Setting = Secure -> Write Cache = DISABLED
Force Unit Access Response = 2
- Resiliency Setting = Normal -> Write Cache = ENABLED
Force Unit Access Response = 2
- Resiliency Setting = HighPerformance -> Write Cache = ENABLED
Force Unit Access Response = 0
The 'Force Unit Access Response' parameter depends on the resiliency mode settings. In 'SingleController', 'Normal' and 'Secure' mode the FUA parameter is 2. In 'HighPerformance' mode the FUA parameter is 0.
The FUA parameter controls the array's response to the FUA bit. The FUA bit is a command from the host when Write Cache is enabled. It gives the host an opportunity to flush write cache on command:
- if this field is 0, then the FUA bit is ignored.
- If this field is 1, then the FUA bit in a write command disables immediate report on the write and all write cache data for the involved LUN will be flushed.
- If this field is 2, then the FUA bit in a write command disables immediate report on the write and all write cache data for the involved LUN will be flushed along with the map journal before completing the write request.
- If NVRAM use is disabled due to the chosen map resiliency mode, then this field is ignored.
Regards,
Mark
Some explanation about the READ & Write Cache settings:
Change the apparent state of write cache on or
off. This switch only changes the write cache
setting presented to the operating system and does not affect the operation of the disk array, which always has write cache enabled. The disk array write cache is stored in NVRAM which eliminates the need to disable write cache for protection against power loss. This switch is provided for interoperability with those operating systems that require write cache be turned off.
However arraymgr -w off $ARRAYID will return an error message to you, you are not able to change this setting (allthough the man page says so).
The setting of the write cache is directly related to the resiliency mode settings and therefore cannot be changed manually with the
'arraymgr -w off' command. The write cache flag setting is as follows:
- Resiliency Setting = SingleController -> Write Cache = DISABLED
Force Unit Access Response = 2
- Resiliency Setting = Secure -> Write Cache = DISABLED
Force Unit Access Response = 2
- Resiliency Setting = Normal -> Write Cache = ENABLED
Force Unit Access Response = 2
- Resiliency Setting = HighPerformance -> Write Cache = ENABLED
Force Unit Access Response = 0
The 'Force Unit Access Response' parameter depends on the resiliency mode settings. In 'SingleController', 'Normal' and 'Secure' mode the FUA parameter is 2. In 'HighPerformance' mode the FUA parameter is 0.
The FUA parameter controls the array's response to the FUA bit. The FUA bit is a command from the host when Write Cache is enabled. It gives the host an opportunity to flush write cache on command:
- if this field is 0, then the FUA bit is ignored.
- If this field is 1, then the FUA bit in a write command disables immediate report on the write and all write cache data for the involved LUN will be flushed.
- If this field is 2, then the FUA bit in a write command disables immediate report on the write and all write cache data for the involved LUN will be flushed along with the map journal before completing the write request.
- If NVRAM use is disabled due to the chosen map resiliency mode, then this field is ignored.
Regards,
Mark
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