Re: mismatch_cnt questions

2007-03-13 Thread Andre Noll
On 00:21, H. Peter Anvin wrote: I have just updated the paper at: http://www.kernel.org/pub/linux/kernel/people/hpa/raid6.pdf ... with this information (in slightly different notation and with a bit more detail.) There's a typo in the new section: s/By assumption, X_z != D_n/By

Issue with Adaptec AIC-7899P using MD on Dell PE 2650

2007-03-13 Thread Laurent CARON
Hi, I'm happily using MD on one of our fileservers. This fileserver is basically a Dell PowerEdge 2650 loaded with 5x300GB HDDs. A 1TB Raid5 partition is defined over the 5 disks md1 : active raid5 sdb3[5] sde3[4] sdd3[3] sdc3[2] sda3[0] 1170238464 blocks level 5, 64k chunk, algorithm 2

sw raid0 read bottleneck

2007-03-13 Thread Tomka Gergely
Hi! I am currently testing 3ware raid cards. Now i have 15 disks, and on these a swraid0. The write speed seems good (700 MBps), but the read performance only 350 MBps. Another problem when i try to read with two process, then the _sum_ of the read speeds fall back to 200 MBps. So there is a

Re: sw raid0 read bottleneck

2007-03-13 Thread Justin Piszcz
On Tue, 13 Mar 2007, Tomka Gergely wrote: Hi! I am currently testing 3ware raid cards. Now i have 15 disks, and on these a swraid0. The write speed seems good (700 MBps), but the read performance only 350 MBps. Another problem when i try to read with two process, then the _sum_ of the read

Re: sw raid0 read bottleneck

2007-03-13 Thread Tomka Gergely
On Tue, 13 Mar 2007, Justin Piszcz wrote: Have you tried increasing your readahead values for the md device? Yes. No real change. According to my humble mental image, readahead not a too useful thing, when we read 1-4 thread with sdd. The io subsystem already reading with the possible maximum

Re: sw raid0 read bottleneck

2007-03-13 Thread Tomka Gergely
On Tue, 13 Mar 2007, Tomka Gergely wrote: On Tue, 13 Mar 2007, Justin Piszcz wrote: Have you tried increasing your readahead values for the md device? Yes. No real change. According to my humble mental image, readahead not a too useful thing, when we read 1-4 thread with sdd. The io

Re: sw raid0 read bottleneck

2007-03-13 Thread Justin Piszcz
Nice. On Tue, 13 Mar 2007, Tomka Gergely wrote: On Tue, 13 Mar 2007, Tomka Gergely wrote: On Tue, 13 Mar 2007, Justin Piszcz wrote: Have you tried increasing your readahead values for the md device? Yes. No real change. According to my humble mental image, readahead not a too useful

Re: sw raid0 read bottleneck

2007-03-13 Thread Neil Brown
On Tuesday March 13, [EMAIL PROTECTED] wrote: On Tue, 13 Mar 2007, Tomka Gergely wrote: On Tue, 13 Mar 2007, Justin Piszcz wrote: Have you tried increasing your readahead values for the md device? Yes. No real change. According to my humble mental image, readahead not a too

Re: sw raid0 read bottleneck

2007-03-13 Thread Tomka Gergely
On Wed, 14 Mar 2007, Neil Brown wrote: On Tuesday March 13, [EMAIL PROTECTED] wrote: On Tue, 13 Mar 2007, Tomka Gergely wrote: On Tue, 13 Mar 2007, Justin Piszcz wrote: Have you tried increasing your readahead values for the md device? Yes. No real change. According to my

Re: mismatch_cnt questions

2007-03-13 Thread H. Peter Anvin
Andre Noll wrote: On 00:21, H. Peter Anvin wrote: I have just updated the paper at: http://www.kernel.org/pub/linux/kernel/people/hpa/raid6.pdf ... with this information (in slightly different notation and with a bit more detail.) There's a typo in the new section: s/By assumption, X_z !=