Re: SW-RAID0 Performance problems

2001-04-15 Thread Mike Castle
On Sun, Apr 15, 2001 at 07:38:00AM -0700, Gregory Leblanc wrote: > On 15 Apr 2001 10:37:15 -0400, ritz wrote: > > swap on RAID0 device? In that case, if ANY of the disks on the RAID > > 0 device dies, you lose access to all your swap on that device. > > Yes, they may have been, but I don't keep

Re: SW-RAID0 Performance problems

2001-04-15 Thread Michael Robinton
Never mind, didn't notice the subject said RAID 0, I took the body of the message to mean raid 1 or 5 On Sun, 15 Apr 2001, Per Jessen wrote: > On Thu, 12 Apr 2001 18:31:36 -, Craig Servin wrote: > > >I am curious if swap on raid works in the 2.4 kernels. If anyone could let me > >know I

Re: SW-RAID0 Performance problems

2001-04-15 Thread Michael Robinton
On Sun, 15 Apr 2001, Per Jessen wrote: > On Thu, 12 Apr 2001 18:31:36 -, Craig Servin wrote: > > >I am curious if swap on raid works in the 2.4 kernels. If anyone could let me > >know I would appreciate it. > > But would it - necessarily - make sense ? if you use multiple swap-paritions,

Re: SW-RAID0 Performance problems

2001-04-15 Thread Gregory Leblanc
On 15 Apr 2001 10:37:15 -0400, ritz wrote: > > From [EMAIL PROTECTED] Sun Apr 15 10:06:55 2001 > > > > On 15 Apr 2001 12:35:38 +0100, Per Jessen wrote: > > > On Thu, 12 Apr 2001 18:31:36 -, Craig Servin wrote: > > > > > > >I am curious if swap on raid works in the 2.4 kernels. If anyone co

Re: SW-RAID0 Performance problems

2001-04-15 Thread ritz
> From [EMAIL PROTECTED] Sun Apr 15 10:06:55 2001 > > On 15 Apr 2001 12:35:38 +0100, Per Jessen wrote: > > On Thu, 12 Apr 2001 18:31:36 -, Craig Servin wrote: > > > > >I am curious if swap on raid works in the 2.4 kernels. If anyone could let me > > >know I would appreciate it. > > > > Bu

Re: SW-RAID0 Performance problems

2001-04-15 Thread Gregory Leblanc
On 15 Apr 2001 12:35:38 +0100, Per Jessen wrote: > On Thu, 12 Apr 2001 18:31:36 -, Craig Servin wrote: > > >I am curious if swap on raid works in the 2.4 kernels. If anyone could let me > >know I would appreciate it. > > But would it - necessarily - make sense ? if you use multiple swap-par

Re: SW-RAID0 Performance problems

2001-04-15 Thread Per Jessen
On Thu, 12 Apr 2001 18:31:36 -, Craig Servin wrote: >I am curious if swap on raid works in the 2.4 kernels. If anyone could let me >know I would appreciate it. But would it - necessarily - make sense ? if you use multiple swap-paritions, Linux will alternate between them, provided you give

Re: SW-RAID0 Performance problems

2001-04-12 Thread Neil Brown
On Thursday April 12, [EMAIL PROTECTED] wrote: > > I am curious if swap on raid works in the 2.4 kernels. If anyone could let me > know I would appreciate it. Yes, it does. NeilBrown - To unsubscribe from this list: send the line "unsubscribe linux-raid" in the body of a message to [EMAIL PROT

Re: SW-RAID0 Performance problems

2001-04-12 Thread Andreas Peter
Am Donnerstag, 12. April 2001 18:48 schrieb Gregory Leblanc: > No offense, but you haven't benchmarked yet, so how do you know? hdparm > is very often on crack when it comes to benchmarking numbers. Bonnie++ > isn't that great at measuring RAID throughput (although it's very nice > on single dri

Re: SW-RAID0 Performance problems

2001-04-12 Thread Craig Servin
You are right -- I have not benchmarked yet. Speed is not that important to me. I am really only concerned with the redundancy. I just thought that hdparm would be a good test of single threaded sequential reads( but I have no idea if that is true ). A few kernels ago I tried the raid-1 read b

Re: SW-RAID0 Performance problems

2001-04-12 Thread Jeff Golds
Gregory Leblanc wrote: > > On 12 Apr 2001 15:55:51 +, Craig Servin wrote: > > I have often had the same question. > > > > I run in a raid-1 configuration and my read performance( mesured with hdparm > > -t ) on the md devices is about half of that of the ha[a-z] devices. I had > > always ass

Re: SW-RAID0 Performance problems

2001-04-12 Thread Andreas Peter
Am Donnerstag, 12. April 2001 18:48 schrieb Gregory Leblanc: > No offense, but you haven't benchmarked yet, so how do you know? hdparm > is very often on crack when it comes to benchmarking numbers. Bonnie++ > isn't that great at measuring RAID throughput (although it's very nice > on single dri

Re: SW-RAID0 Performance problems

2001-04-12 Thread Gregory Leblanc
On 12 Apr 2001 15:55:51 +, Craig Servin wrote: > I have often had the same question. > > I run in a raid-1 configuration and my read performance( mesured with hdparm > -t ) on the md devices is about half of that of the ha[a-z] devices. I had > always assumed that reads where ballanced among

Re: SW-RAID0 Performance problems

2001-04-12 Thread Andreas Peter
Am Donnerstag, 12. April 2001 17:59 schrieb C. R. Oldham: > Craig Servin wrote: > > I have often had the same question. > > What does bonnie say? Here are my bonnie results: -- RAID-0 -- -- chunk-size=16 -- Version 1.01--Sequential Output-- --Sequential Input- --Random-

RE: SW-RAID0 Performance problems

2001-04-12 Thread C. R. Oldham
Craig Servin wrote: > I have often had the same question. What does bonnie say? -- / C. R. (Charles) Oldham | NCA-CASI \ / Director of Technology | Arizona State University \ / [EMAIL PROTECTED] | V:480-965-8703 F:480-965-9423 \ - To unsubscribe from th

Re: SW-RAID0 Performance problems

2001-04-12 Thread Craig Servin
I have often had the same question. I run in a raid-1 configuration and my read performance( mesured with hdparm -t ) on the md devices is about half of that of the ha[a-z] devices. I had always assumed that reads where ballanced among the devices that made up the raid-1 volume and that reads wo

SW-RAID0 Performance problems

2001-04-12 Thread Andreas Peter
Hi, I've successfully set up SW-RAID0 with Kernel 2.4.3 and Raidtools 0.9. I did this to increase the performance of my HD, but nothig happens. hdparm -t /dev/md0 : 20.25 MB/sec hdparm -t /dev/hda : 20.51 MB/sec hdaprm -t /dev/hdc : 20.71 MB/sec I thougt the performnace of RAID0 should near 40MB/s