[RE] Poorer performance with Raid0 then without?
Listbox
listbox at hymerfania.com
Tue Jan 2 01:36:13 UTC 2007
Yeah, that's what I did that I described as
"I tried removing the third drive on the board (primary slave), no effect. "
This smells like a driver/software problem. I'd like to try a different
setup.
Is there some way to use "md type" RAID that uses /dev/md? instead of "dm
type" RAID that uses /dev/mapper/*?
Thanks!
Listbox
_____
From: James Olson [mailto:big_spender12 at lycos.com]
Sent: Monday, January 01, 2007 5:15 PM
To: ATARAID (eg, Promise Fasttrak, Highpoint 370) related discussions
Subject: [RE] Poorer performance with Raid0 then without?
So the dma settings are normal. My only other thought is what do you have on
/dev/hdf? Is that drive a slave with /dev/hde as the master? Can you run the
system with hde and hdg but without hdf and see if the raid0 performance
improves?
---------[ Received Mail Content ]----------
Subject : [RE] Poorer performance with Raid0 then without?
Date : Mon, 1 Jan 2007 11:24:31 -0800
>From : "Listbox" <listbox at hymerfania.com>
To : <ataraid-list at redhat.com>
Here is more hdparm data. It looks like bad news.
Note: for whatever reason, /dev/md0 does not seem to be my RAID device. I
set up my raid (via trial and error) with dmraid, and it gave me
/dev/mapper/sil_agbgdgbjfhei. I have always felt there was something
not-right about that.
Second, the errors hdparm reports from -tT look significant.
Finally, "Timing cached reads" are much lower then single drives. I don't
know what this really means in a RAID context.
I tried removing the third drive on the board (primary slave), no effect.
Anyway, given the errors, is this a RAID software problem, or a piece of
junk RAID adapter card?
Thanks so much, folks.
Listbox
* * * * * * * * * * *
* * * * * * * * * * *
/dev/hde:
multcount = 16 (on)
IO_support = 0 (default 16-bit)
unmaskirq = 0 (off)
using_dma = 1 (on)
keepsettings = 0 (off)
readonly = 0 (off)
readahead = 256 (on)
geometry = 19457/255/63, sectors = 312581808, start = 0
/dev/hdg:
multcount = 16 (on)
IO_support = 0 (default 16-bit)
unmaskirq = 0 (off)
using_dma = 1 (on)
keepsettings = 0 (off)
readonly = 0 (off)
readahead = 256 (on)
geometry = 19457/255/63, sectors = 312581808, start = 0
* * * * * * * * * * *
* * * * * * * * * * *
hprarm -tT /dev/md0
read() hit EOF - device too small
/dev/md0:
Timing buffered disk reads: read() hit EOF - device too small
BLKFLSBUF failed: No such device
HDIO_DRIVE_CMD(null) (wait for flush complete) failed: No such device
hprarm -tT /dev/mapper/sil_agbgdgbjfhei
/dev/mapper/sil_agbgdgbjfhei:
Timing cached reads: HDIO_DRIVE_CMD(null) (wait for flush complete)
failed: Inappropriate ioctl for device
1288 MB in 2.00 seconds = 643.22 MB/sec
Timing buffered disk reads: HDIO_DRIVE_CMD(null) (wait for flush complete)
failed: Inappropriate ioctl for device
284 MB in 3.01 seconds = 94.27 MB/sec
* * * * * * * * * * *
* * * * * * * * * * *
* * * * * * * * * * *
* * * * * * * * * * *
dev/hda:
Timing cached reads: 1668 MB in 2.00 seconds = 834.10 MB/sec
Timing buffered disk reads: 88 MB in 3.05 seconds = 28.87 MB/sec
/dev/hdb:
Timing buffered disk reads:
/dev/hdc:
Timing cached reads: 1696 MB in 2.00 seconds = 847.36 MB/sec
Timing buffered disk reads: 88 MB in 3.05 seconds = 28.82 MB/sec
/dev/hde:
Timing cached reads: 1680 MB in 2.00 seconds = 838.49 MB/sec
Timing buffered disk reads: 168 MB in 3.03 seconds = 55.46 MB/sec
/dev/hdf:
Timing cached reads: 1688 MB in 2.00 seconds = 843.57 MB/sec
Timing buffered disk reads: 164 MB in 3.00 seconds = 54.59 MB/sec
/dev/hdg:
Timing cached reads: 1696 MB in 2.00 seconds = 846.68 MB/sec
Timing buffered disk reads: 162 MB in 3.03 seconds = 53.45 MB/sec
_______________________________________________
Ataraid-list mailing list
Ataraid-list at redhat.com
https://www.redhat.com/mailman/listinfo/ataraid-list
_____
<http://cinema.lycos.com/?if_Event=mail> Free Movies 100's of Free Feature
Length Films - Meet Friends, Watch Movies & Win!
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listman.redhat.com/archives/ataraid-list/attachments/20070101/0daf96eb/attachment.htm>
More information about the Ataraid-list
mailing list