Search String: Display: Description: Sort:

Results:

References: [ +subject:/^(?:^\s*(re|sv|fwd|fw)[\[\]\d]*[:>-]+\s*)*U320\s+Large\s+Array\s+Performance\s*$/: 27 ]

Total 27 documents matching your query.

1. U320 Large Array Performance (score: 1)
Author: "Rick Smith" <rgsmith72@xxxxxxxxxxx>
Date: Tue, 04 Feb 2003 14:09:40 -0800
I am constructing a large, high performance U320 raid0 array with XFS using the 2.4.20-rc1-xfs kernel and linux software raid. I am pleased with the performance, but it seems that when I exceed 14 di
/archives/xfs/2003-02/msg00030.html (8,815 bytes)

2. Re: U320 Large Array Performance (score: 1)
Author: Steve Lord <lord@xxxxxxx>
Date: 04 Feb 2003 16:16:05 -0600
Sounds like you need to play with mkfs options on XFS. Can you send the output of xfs_info /mnt where /mnt is the mounted filesystem. Steve -- Steve Lord voice: +1-651-683-3511 Principal Engineer, Fi
/archives/xfs/2003-02/msg00031.html (9,634 bytes)

3. Re: U320 Large Array Performance (score: 1)
Author: "Rick Smith" <rgsmith72@xxxxxxxxxxx>
Date: Tue, 04 Feb 2003 14:47:34 -0800
Here is the output from xfs_info, please excuse the formatting. I am using a chunk size of 4K in the raid. Larger sizes seem to degrade performance. Thanks for your help. With 14 disks in the array:
/archives/xfs/2003-02/msg00032.html (11,170 bytes)

4. Re: U320 Large Array Performance (score: 1)
Author: Steve Lord <lord@xxxxxxx>
Date: 04 Feb 2003 17:45:18 -0600
I was going to have a chat with someone about this, but they are gone for the day, so stripe suggestions will have to wait a while. Do you have any way of measuring the I/O going on to each drive? Th
/archives/xfs/2003-02/msg00033.html (13,681 bytes)

5. Re: U320 Large Array Performance (score: 1)
Author: Steve Lord <lord@xxxxxxx>
Date: 05 Feb 2003 12:02:08 -0600
Can you do one more thing for me, with these configurations send me the xfs_bmap -v output for a file on each filesystem. Thanks, Steve -- Steve Lord voice: +1-651-683-3511 Principal Engineer, Filesy
/archives/xfs/2003-02/msg00048.html (8,384 bytes)

6. Re: U320 Large Array Performance (score: 1)
Author: "Rick Smith" <rgsmith72@xxxxxxxxxxx>
Date: Wed, 05 Feb 2003 12:33:40 -0800
After examining the output of the xfs_bmap that I sent you it looks like each file has a different allocation group for the 15 disk case. With 14 disks (73GB each) there are 240 allocation groups wh
/archives/xfs/2003-02/msg00051.html (9,084 bytes)

7. Re: U320 Large Array Performance (score: 1)
Author: "Rick Smith" <rgsmith72@xxxxxxxxxxx>
Date: Wed, 05 Feb 2003 11:53:23 -0800
Here is the data you requested. By the way, I experimented with agsize as you suggested and it didn't have any affect. In fact (as you probably know), the tool mkfs.xfs produces a warning when agsiz
/archives/xfs/2003-02/msg00052.html (10,502 bytes)

8. Re: U320 Large Array Performance (score: 1)
Author: "Rick Smith" <rgsmith72@xxxxxxxxxxx>
Date: Wed, 05 Feb 2003 12:48:06 -0800
As a test, I shortened the size of one of the 15 disks in the array (using fdisk) in order to create a slightly smaller filesystem and thus requiring a smaller number of allocation groups. The resul
/archives/xfs/2003-02/msg00053.html (9,344 bytes)

9. Re: U320 Large Array Performance (score: 1)
Author: "Rick Smith" <rgsmith72@xxxxxxxxxxx>
Date: Wed, 05 Feb 2003 11:53:23 -0800
Here is the data you requested. By the way, I experimented with agsize as you suggested and it didn't have any affect. In fact (as you probably know), the tool mkfs.xfs produces a warning when agsiz
/archives/xfs/2003-02/msg00056.html (10,524 bytes)

10. U320 Large Array Performance (score: 1)
Author: "Rick Smith" <rgsmith72@xxxxxxxxxxx>
Date: Tue, 04 Feb 2003 14:09:40 -0800
I am constructing a large, high performance U320 raid0 array with XFS using the 2.4.20-rc1-xfs kernel and linux software raid. I am pleased with the performance, but it seems that when I exceed 14 di
/archives/xfs/2003-02/msg00514.html (8,815 bytes)

11. Re: U320 Large Array Performance (score: 1)
Author: Steve Lord <lord@xxxxxxx>
Date: 04 Feb 2003 16:16:05 -0600
Sounds like you need to play with mkfs options on XFS. Can you send the output of xfs_info /mnt where /mnt is the mounted filesystem. Steve -- Steve Lord voice: +1-651-683-3511 Principal Engineer, Fi
/archives/xfs/2003-02/msg00515.html (9,634 bytes)

12. Re: U320 Large Array Performance (score: 1)
Author: "Rick Smith" <rgsmith72@xxxxxxxxxxx>
Date: Tue, 04 Feb 2003 14:47:34 -0800
Here is the output from xfs_info, please excuse the formatting. I am using a chunk size of 4K in the raid. Larger sizes seem to degrade performance. Thanks for your help. With 14 disks in the array:
/archives/xfs/2003-02/msg00516.html (11,170 bytes)

13. Re: U320 Large Array Performance (score: 1)
Author: Steve Lord <lord@xxxxxxx>
Date: 04 Feb 2003 17:45:18 -0600
I was going to have a chat with someone about this, but they are gone for the day, so stripe suggestions will have to wait a while. Do you have any way of measuring the I/O going on to each drive? Th
/archives/xfs/2003-02/msg00517.html (13,681 bytes)

14. Re: U320 Large Array Performance (score: 1)
Author: Steve Lord <lord@xxxxxxx>
Date: 05 Feb 2003 12:02:08 -0600
Can you do one more thing for me, with these configurations send me the xfs_bmap -v output for a file on each filesystem. Thanks, Steve -- Steve Lord voice: +1-651-683-3511 Principal Engineer, Filesy
/archives/xfs/2003-02/msg00532.html (8,384 bytes)

15. Re: U320 Large Array Performance (score: 1)
Author: "Rick Smith" <rgsmith72@xxxxxxxxxxx>
Date: Wed, 05 Feb 2003 12:33:40 -0800
After examining the output of the xfs_bmap that I sent you it looks like each file has a different allocation group for the 15 disk case. With 14 disks (73GB each) there are 240 allocation groups wh
/archives/xfs/2003-02/msg00535.html (9,084 bytes)

16. Re: U320 Large Array Performance (score: 1)
Author: "Rick Smith" <rgsmith72@xxxxxxxxxxx>
Date: Wed, 05 Feb 2003 11:53:23 -0800
Here is the data you requested. By the way, I experimented with agsize as you suggested and it didn't have any affect. In fact (as you probably know), the tool mkfs.xfs produces a warning when agsiz
/archives/xfs/2003-02/msg00536.html (10,502 bytes)

17. Re: U320 Large Array Performance (score: 1)
Author: "Rick Smith" <rgsmith72@xxxxxxxxxxx>
Date: Wed, 05 Feb 2003 12:48:06 -0800
As a test, I shortened the size of one of the 15 disks in the array (using fdisk) in order to create a slightly smaller filesystem and thus requiring a smaller number of allocation groups. The resul
/archives/xfs/2003-02/msg00537.html (9,344 bytes)

18. Re: U320 Large Array Performance (score: 1)
Author: "Rick Smith" <rgsmith72@xxxxxxxxxxx>
Date: Wed, 05 Feb 2003 11:53:23 -0800
Here is the data you requested. By the way, I experimented with agsize as you suggested and it didn't have any affect. In fact (as you probably know), the tool mkfs.xfs produces a warning when agsiz
/archives/xfs/2003-02/msg00540.html (10,524 bytes)

19. U320 Large Array Performance (score: 1)
Author: "Rick Smith" <rgsmith72@xxxxxxxxxxx>
Date: Tue, 04 Feb 2003 14:09:40 -0800
I am constructing a large, high performance U320 raid0 array with XFS using the 2.4.20-rc1-xfs kernel and linux software raid. I am pleased with the performance, but it seems that when I exceed 14 di
/archives/xfs/2003-02/msg00998.html (8,867 bytes)

20. Re: U320 Large Array Performance (score: 1)
Author: Steve Lord <lord@xxxxxxx>
Date: 04 Feb 2003 16:16:05 -0600
Sounds like you need to play with mkfs options on XFS. Can you send the output of xfs_info /mnt where /mnt is the mounted filesystem. Steve -- Steve Lord voice: +1-651-683-3511 Principal Engineer, Fi
/archives/xfs/2003-02/msg00999.html (9,704 bytes)


This search system is powered by Namazu