* [gentoo-user] /dev/hdb performance really sucks ...
@ 2005-07-25 8:27 Richard Watson
2005-07-25 10:32 ` Tomas Bohata
` (3 more replies)
0 siblings, 4 replies; 5+ messages in thread
From: Richard Watson @ 2005-07-25 8:27 UTC (permalink / raw
To: gentoo-user
Hi - I'm getting vastly different performance results on hda (master) as
opposed to hdb (slave). Basically when my root partition mounts (/dev/hdb)
I'm warned that DMA is off, yet hdparm -i shows udma as active. Basically
/dev/hdb performance sucks ... I've bought both drives in the last few
months. The motherboard is quite old (3 years .. I think).
Any suggestions would be appreciated.
--
Thanks - Richard
=============================
/dev/hda:
Timing cached reads: 1360 MB in 2.00 seconds = 678.75 MB/sec
Timing buffered disk reads: 146 MB in 3.03 seconds = 48.22 MB/sec
/dev/hdb:
Timing cached reads: 1376 MB in 2.00 seconds = 687.42 MB/sec
Timing buffered disk reads: 10 MB in 3.51 seconds = 2.85 MB/sec
/dev/hda:
Model=Maxtor 6Y120P0, FwRev=YAR41BW0, SerialNo=Y36DHLVE
Config={ Fixed }
RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=57
BuffType=DualPortCache, BuffSize=7936kB, MaxMultSect=16, MultSect=16
CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=240121728
IORDY=on/off, tPIO={min:120,w/IORDY:120}, tDMA={min:120,rec:120}
PIO modes: pio0 pio1 pio2 pio3 pio4
DMA modes: mdma0 mdma1 mdma2
UDMA modes: udma0 udma1 udma2 udma3 udma4 *udma5 udma6
AdvancedPM=yes: disabled (255) WriteCache=enabled
Drive conforms to: (null):
* signifies the current active mode
/dev/hdb:
Model=ST3200826A, FwRev=3.03, SerialNo=5ND0CVYX
Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs RotSpdTol>.5% }
RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=4
BuffType=unknown, BuffSize=8192kB, MaxMultSect=16, MultSect=16
CurCHS=65535/1/63, CurSects=4128705, LBA=yes, LBAsects=268435455
IORDY=on/off, tPIO={min:240,w/IORDY:120}, tDMA={min:120,rec:120}
PIO modes: pio0 pio1 pio2 pio3 pio4
DMA modes: mdma0 mdma1 mdma2
UDMA modes: udma0 udma1 udma2 udma3 udma4 *udma5
AdvancedPM=no WriteCache=enabled
Drive conforms to: device does not report version:
* signifies the current active mode
--
No virus found in this outgoing message.
Checked by AVG Anti-Virus.
Version: 7.0.338 / Virus Database: 267.9.4/57 - Release Date: 22/07/2005
--
gentoo-user@gentoo.org mailing list
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [gentoo-user] /dev/hdb performance really sucks ...
2005-07-25 8:27 [gentoo-user] /dev/hdb performance really sucks Richard Watson
@ 2005-07-25 10:32 ` Tomas Bohata
2005-07-25 13:13 ` [gentoo-user] " James
` (2 subsequent siblings)
3 siblings, 0 replies; 5+ messages in thread
From: Tomas Bohata @ 2005-07-25 10:32 UTC (permalink / raw
To: gentoo-user
Richard Watson napsal(a):
> Hi - I'm getting vastly different performance results on hda (master) as
> opposed to hdb (slave). Basically when my root partition mounts (/dev/hdb)
> I'm warned that DMA is off, yet hdparm -i shows udma as active. Basically
> /dev/hdb performance sucks ... I've bought both drives in the last few
> months. The motherboard is quite old (3 years .. I think).
>
> Any suggestions would be appreciated.
> --
> Thanks - Richard
>
> =============================
>
> /dev/hda:
> Timing cached reads: 1360 MB in 2.00 seconds = 678.75 MB/sec
> Timing buffered disk reads: 146 MB in 3.03 seconds = 48.22 MB/sec
>
> /dev/hdb:
> Timing cached reads: 1376 MB in 2.00 seconds = 687.42 MB/sec
> Timing buffered disk reads: 10 MB in 3.51 seconds = 2.85 MB/sec
>
> /dev/hda:
>
> Model=Maxtor 6Y120P0, FwRev=YAR41BW0, SerialNo=Y36DHLVE
> Config={ Fixed }
> RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=57
> BuffType=DualPortCache, BuffSize=7936kB, MaxMultSect=16, MultSect=16
> CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=240121728
> IORDY=on/off, tPIO={min:120,w/IORDY:120}, tDMA={min:120,rec:120}
> PIO modes: pio0 pio1 pio2 pio3 pio4
> DMA modes: mdma0 mdma1 mdma2
> UDMA modes: udma0 udma1 udma2 udma3 udma4 *udma5 udma6
> AdvancedPM=yes: disabled (255) WriteCache=enabled
> Drive conforms to: (null):
>
> * signifies the current active mode
>
>
> /dev/hdb:
>
> Model=ST3200826A, FwRev=3.03, SerialNo=5ND0CVYX
> Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs RotSpdTol>.5% }
> RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=4
> BuffType=unknown, BuffSize=8192kB, MaxMultSect=16, MultSect=16
> CurCHS=65535/1/63, CurSects=4128705, LBA=yes, LBAsects=268435455
> IORDY=on/off, tPIO={min:240,w/IORDY:120}, tDMA={min:120,rec:120}
> PIO modes: pio0 pio1 pio2 pio3 pio4
> DMA modes: mdma0 mdma1 mdma2
> UDMA modes: udma0 udma1 udma2 udma3 udma4 *udma5
> AdvancedPM=no WriteCache=enabled
> Drive conforms to: device does not report version:
>
> * signifies the current active mode
>
>
maybe they dont like each other, try to plug second hd to another
controller (hdc/hdd)
T.B.
--
gentoo-user@gentoo.org mailing list
^ permalink raw reply [flat|nested] 5+ messages in thread
* [gentoo-user] Re: /dev/hdb performance really sucks ...
2005-07-25 8:27 [gentoo-user] /dev/hdb performance really sucks Richard Watson
2005-07-25 10:32 ` Tomas Bohata
@ 2005-07-25 13:13 ` James
2005-07-25 15:33 ` James
2005-07-25 18:29 ` [gentoo-user] " Richard Fish
3 siblings, 0 replies; 5+ messages in thread
From: James @ 2005-07-25 13:13 UTC (permalink / raw
To: gentoo-user
Richard Watson <waty <at> bigpond.net.au> writes:
> Hi - I'm getting vastly different performance results on hda (master) as
> opposed to hdb (slave).
> Any suggestions would be appreciated.
I'd make sure you read the man page on hdparm. Certain actions can kill hardware,
permanently.
That said, what I do is set the hdparms in /etc/conf.d/hdparm. I believe you
can test each drive, note the best (safe) parameters to adjust. Test the
adjustments, and then make an entry, per hard drive in the
/etc/conf.d/hdparm. Here's what works for me on one system:
all_args="-d1"
hda_args="-d1 -u1 -c1 -a256"
Remember, any device that is seen as a /dev/hd* will be affected by
settings like [all_args="-d1"]......
If get lesser performance when (2) different drives are on the same
(ide/ata/eide) controller, then try a second pci cotroller card.
or if both are on the same cable, and the MB or controller has a
second port, add a second cable and move one drive to the other
port/cable. This sort of performance degradation should effect both drives.
HTH
James
--
gentoo-user@gentoo.org mailing list
^ permalink raw reply [flat|nested] 5+ messages in thread
* [gentoo-user] Re: /dev/hdb performance really sucks ...
2005-07-25 8:27 [gentoo-user] /dev/hdb performance really sucks Richard Watson
2005-07-25 10:32 ` Tomas Bohata
2005-07-25 13:13 ` [gentoo-user] " James
@ 2005-07-25 15:33 ` James
2005-07-25 18:29 ` [gentoo-user] " Richard Fish
3 siblings, 0 replies; 5+ messages in thread
From: James @ 2005-07-25 15:33 UTC (permalink / raw
To: gentoo-user
Richard Watson <waty <at> bigpond.net.au> writes:
>
> Hi - I'm getting vastly different performance results on hda (master) as
> opposed to hdb (slave).
One more point. The drive tests via hdparm may not be conclusive.
A variety of I/O (drive) benchmark performance tests may be needed.
In portage there are other tools/tests to benchmark I/O (drive) performance:
bonnie
bonnie++
Other benchmark/diagnostic tools may exist for I/O drive testing.
HTH,
James
--
gentoo-user@gentoo.org mailing list
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [gentoo-user] /dev/hdb performance really sucks ...
2005-07-25 8:27 [gentoo-user] /dev/hdb performance really sucks Richard Watson
` (2 preceding siblings ...)
2005-07-25 15:33 ` James
@ 2005-07-25 18:29 ` Richard Fish
3 siblings, 0 replies; 5+ messages in thread
From: Richard Fish @ 2005-07-25 18:29 UTC (permalink / raw
To: gentoo-user
Richard Watson wrote:
>Hi - I'm getting vastly different performance results on hda (master) as
>opposed to hdb (slave). Basically when my root partition mounts (/dev/hdb)
>I'm warned that DMA is off, yet hdparm -i shows udma as active. Basically
>/dev/hdb performance sucks ... I've bought both drives in the last few
>months. The motherboard is quite old (3 years .. I think).
>
>Any suggestions would be appreciated.
>
>
Maybe double check the jumpers on both drives... the first one should be
"master w/slave" if that option is available.
-Richard (um, Fish that is)
--
gentoo-user@gentoo.org mailing list
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2005-07-25 18:34 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2005-07-25 8:27 [gentoo-user] /dev/hdb performance really sucks Richard Watson
2005-07-25 10:32 ` Tomas Bohata
2005-07-25 13:13 ` [gentoo-user] " James
2005-07-25 15:33 ` James
2005-07-25 18:29 ` [gentoo-user] " Richard Fish
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox