* Bug in 2.4.x??
@ 2001-02-14 4:08 Ashwin D
2001-02-14 21:28 ` Eugene Danilchenko
0 siblings, 1 reply; 2+ messages in thread
From: Ashwin D @ 2001-02-14 4:08 UTC (permalink / raw)
To: linux-kernel
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain, Size: 2076 bytes --]
Hi
Well, it may not be a bug, but it sure is bugging me - i have been on this
for more than a week. Well, here goes;
Why is it that my DMA performance under the kernel 2.4.x is worse than the
one under 2.2? I have attached the stats below the mail- information and test
results under both kernels.
I use the following option under rc.local to set dma ;
/sbin/hdparm -c1 -d1 -m16 -X66 /dev/hda
I use resierfs, Iam disappointed that 2.4 results are about 1/3rd and need to
know what to do.
I use a i810 mobo and seagate 8.4 gb hdd
I have tried recompiling the kernel - iam informed a broken .config could
have caused this, but no change.
I have tried random settings with hdparm to tune /dev/hda.
Thanks for your time.
Ashwin
(Iam not on the list yet, so please cc me personally)
-------------------------
TEST RESULTS
___________________________
a) Kernel 2.2.17 (mandrake)
(i) hdpartm -i:
/dev/hda:
Model=ST38420A, FwRev=3.07, SerialNo=7AZ0PTZT
Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs RotSpdTol>.5% }
RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=0
BuffType=unknown, BuffSize=512kB, MaxMultSect=16, MultSect=16
CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=16841664
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 udma0 udma1 *udma2
(ii) hdpartm -t:
/dev/hda:
Timing buffered disk reads: 64 MB in 4.38 seconds = 14.61 MB/sec
b) Kernel 2.4.1 (linux )
(i) hdparm -i
/dev/hda:
Model=ST38420A, FwRev=3.07, SerialNo=7AZ0PTZT
Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs RotSpdTol>.5% }
RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=0
BuffType=unknown, BuffSize=512kB, MaxMultSect=16, MultSect=16
CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=16841664
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 udma0 udma1 *udma2
(ii) hdparm -t
/dev/hda:
Timing buffered disk reads: 64 MB in 11.61 seconds = 5.51 MB/sec
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: Bug in 2.4.x??
2001-02-14 4:08 Bug in 2.4.x?? Ashwin D
@ 2001-02-14 21:28 ` Eugene Danilchenko
0 siblings, 0 replies; 2+ messages in thread
From: Eugene Danilchenko @ 2001-02-14 21:28 UTC (permalink / raw)
To: Ashwin D; +Cc: linux-kernel
Hello
the same behavior I have :
[root@localhost eugene]# uname -a
Linux localhost.localdomain 2.4.1 #1 Пнд Фев 12 23:19:20 /etc/localtime 2001 i686 unknown
[root@localhost eugene]# hdparm -i /dev/hdb
/dev/hdb:
Model=ST38410A, FwRev=3.32, SerialNo=7EG23EXT
Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs RotSpdTol>.5% }
RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=4
BuffType=unknown, BuffSize=512kB, MaxMultSect=32, MultSect=32
CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=16841664
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 udma0 udma1 *udma2 udma3 udma4
[root@localhost eugene]# hdparm /dev/hdb
/dev/hdb:
multcount = 32 (on)
I/O support = 1 (32-bit)
unmaskirq = 0 (off)
using_dma = 1 (on)
keepsettings = 0 (off)
nowerr = 0 (off)
readonly = 0 (off)
readahead = 8 (on)
geometry = 1048/255/63, sectors = 16841664, start = 0
[root@localhost eugene]# hdparm -t /dev/hdb
/dev/hdb:
Timing buffered disk reads: 64 MB in 8.00 seconds = 8.00 MB/sec
On Wed, 14 Feb 2001 09:38:18 +0530
Ashwin D <ashwinds@yahoo.com> (by way of Ashwin D <ashwinds@yahoo.com>) wrote:
ADAYCBWOAD> Hi
ADAYCBWOAD>
ADAYCBWOAD> Well, it may not be a bug, but it sure is bugging me - i have been on this
ADAYCBWOAD> for more than a week. Well, here goes;
ADAYCBWOAD>
ADAYCBWOAD> Why is it that my DMA performance under the kernel 2.4.x is worse than the
ADAYCBWOAD> one under 2.2? I have attached the stats below the mail- information and test
ADAYCBWOAD> results under both kernels.
ADAYCBWOAD>
ADAYCBWOAD> I use the following option under rc.local to set dma ;
ADAYCBWOAD> ════════ /sbin/hdparm -c1 -d1 -m16 -X66 /dev/hda
ADAYCBWOAD>
ADAYCBWOAD> I use resierfs, Iam disappointed that 2.4 results are about 1/3rd and need to
ADAYCBWOAD> know what to do.
ADAYCBWOAD>
ADAYCBWOAD> I use a i810 mobo and seagate 8.4 gb hdd
ADAYCBWOAD>
ADAYCBWOAD> I have tried recompiling the kernel - iam informed a broken .config could
ADAYCBWOAD> have caused this, but no change.
ADAYCBWOAD> I have tried random settings with hdparm to tune /dev/hda.
ADAYCBWOAD>
ADAYCBWOAD> Thanks for your time.
ADAYCBWOAD> Ashwin
ADAYCBWOAD> (Iam not on the list yet, so please cc me personally)
ADAYCBWOAD>
ADAYCBWOAD> -------------------------
ADAYCBWOAD> TEST RESULTS
ADAYCBWOAD> ___________________________
ADAYCBWOAD>
ADAYCBWOAD> a) Kernel 2.2.17 (mandrake)
ADAYCBWOAD>
ADAYCBWOAD> (i) hdpartm -i:
ADAYCBWOAD> /dev/hda:
ADAYCBWOAD>
ADAYCBWOAD> ═Model=ST38420A, FwRev=3.07, SerialNo=7AZ0PTZT
ADAYCBWOAD> ═Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs RotSpdTol>.5% }
ADAYCBWOAD> ═RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=0
ADAYCBWOAD> ═BuffType=unknown, BuffSize=512kB, MaxMultSect=16, MultSect=16
ADAYCBWOAD> ═CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=16841664
ADAYCBWOAD> ═IORDY=on/off, tPIO={min:240,w/IORDY:120}, tDMA={min:120,rec:120}
ADAYCBWOAD> ═PIO modes: pio0 pio1 pio2 pio3 pio4
ADAYCBWOAD> ═DMA modes: mdma0 mdma1 mdma2 udma0 udma1 *udma2
ADAYCBWOAD>
ADAYCBWOAD> (ii) hdpartm -t:
ADAYCBWOAD> /dev/hda:
ADAYCBWOAD> ═Timing buffered disk reads: ═64 MB in ═4.38 seconds = 14.61 MB/sec
ADAYCBWOAD>
ADAYCBWOAD>
ADAYCBWOAD> b) Kernel 2.4.1 (linux )
ADAYCBWOAD>
ADAYCBWOAD> (i) hdparm -i
ADAYCBWOAD> /dev/hda:
ADAYCBWOAD>
ADAYCBWOAD> ═Model=ST38420A, FwRev=3.07, SerialNo=7AZ0PTZT
ADAYCBWOAD> ═Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs RotSpdTol>.5% }
ADAYCBWOAD> ═RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=0
ADAYCBWOAD> ═BuffType=unknown, BuffSize=512kB, MaxMultSect=16, MultSect=16
ADAYCBWOAD> ═CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=16841664
ADAYCBWOAD> ═IORDY=on/off, tPIO={min:240,w/IORDY:120}, tDMA={min:120,rec:120}
ADAYCBWOAD> ═PIO modes: pio0 pio1 pio2 pio3 pio4
ADAYCBWOAD> ═DMA modes: mdma0 mdma1 mdma2 udma0 udma1 *udma2
ADAYCBWOAD>
ADAYCBWOAD> (ii) hdparm -t
ADAYCBWOAD>
ADAYCBWOAD> /dev/hda:
ADAYCBWOAD> ═Timing buffered disk reads: ═64 MB in 11.61 seconds = ═5.51 MB/sec
ADAYCBWOAD> -
ADAYCBWOAD> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
ADAYCBWOAD> the body of a message to majordomo@vger.kernel.org
ADAYCBWOAD> More majordomo info at http://vger.kernel.org/majordomo-info.html
ADAYCBWOAD> Please read the FAQ at http://www.tux.org/lkml/
--
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2001-02-14 11:33 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2001-02-14 4:08 Bug in 2.4.x?? Ashwin D
2001-02-14 21:28 ` Eugene Danilchenko
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox