Gentoo Forums
Gentoo Forums
Gentoo Forums
Quick Search: in
my harddrive performance is sucking
View unanswered posts
View posts from last 24 hours

Goto page Previous  1, 2, 3, 4, 5, 6, 7, 8, 9  Next  
Reply to topic    Gentoo Forums Forum Index Kernel & Hardware
View previous topic :: View next topic  
Author Message
m00re
n00b
n00b


Joined: 17 Jun 2002
Posts: 65
Location: Germany

PostPosted: Sat Sep 21, 2002 1:15 pm    Post subject: vt8235 southbridge Reply with quote

For all of you out there who get
>> HDIO_SET_DMA failed: Operation not permitted
on your machine with a VIA VT8235 Southbridge: get the new VIA IDE drivers for your kernel (v3.35). It finally solved my hd speed problem.
Get it at VIA IDE Drivers v3.35 by Vojtech Pavlik. Replace your old via82xxx.c in drivers/ide and have fun.

Attention: On my system, I had to edit Line 520 from
>> } #endif /* CONFIG_BLK_DEV_IDEDMA */
to
>> }
>> #endif /* CONFIG_BLK_DEV_IDEDMA */

Hope I can help some of you with that.
_________________
"Fall seven times, stand up eight."
Back to top
View user's profile Send private message
idl
Retired Dev
Retired Dev


Joined: 24 Dec 2002
Posts: 1728
Location: Nottingham, UK

PostPosted: Thu Jan 02, 2003 10:49 pm    Post subject: Reply with quote

Code:
/dev/hdb:
 Timing buffer-cache reads:   128 MB in  0.61 seconds =210.18 MB/sec
 Timing buffered disk reads:  64 MB in  1.39 seconds = 46.18 MB/sec
:)
Back to top
View user's profile Send private message
Lefungus
n00b
n00b


Joined: 20 Jan 2003
Posts: 16

PostPosted: Thu Jan 23, 2003 3:51 pm    Post subject: Reply with quote

Before :

Timing buffer-cache reads: 128 MB in 0.22 seconds =581.82 MB/sec
Timing buffered disk reads: 64 MB in 16.09 seconds = 3.98 MB/sec

Then i do : hdparm -c 1 -d 1 -u 1 -m 16 -X 70 /dev/hda with my maxtor drive

Timing buffer-cache reads: 128 MB in 0.22 seconds =581.82 MB/sec
Timing buffered disk reads: 64 MB in 1.60 seconds = 40.00 MB/sec


I think the last one is better :)
Back to top
View user's profile Send private message
ragingwolf
n00b
n00b


Joined: 20 Jan 2003
Posts: 50
Location: Ontario - Canada

PostPosted: Thu Jan 23, 2003 6:43 pm    Post subject: :) Reply with quote

Sweet, my speeds were boosted by alot:

/dev/hda:
Timing buffer-cache reads: 128 MB in 0.68 seconds =188.24 MB/sec
Timing buffered disk reads: 64 MB in 2.28 seconds = 28.07 MB/sec

/dev/hde:
Timing buffer-cache reads: 128 MB in 0.66 seconds =193.94 MB/sec
Timing buffered disk reads: 64 MB in 1.33 seconds = 48.12 MB/sec

Both from ~3MB/sec and both are ide drives. Man, this post is a god send, before, doing anything in the background (compiling, copying etc) my music would stutter so bad, now it fixed :). btw I noticed that in my current kernel, dma isn't enabled by default, if i enabled and recompiled with the via82C... option, will it enable by default?
_________________
Gentoo Linux amd64 2004.2 --> updated
Amd 3000+
Asus K8N-E mobo
Geforce4 ti 4200
Back to top
View user's profile Send private message
heijs
Apprentice
Apprentice


Joined: 12 Jun 2002
Posts: 174
Location: Groningen

PostPosted: Fri Jan 24, 2003 12:30 pm    Post subject: Reply with quote

Before:
/dev/hdg:
Timing buffer-cache reads: 128 MB in 0.71 seconds =180.28 MB/sec
Timing buffered disk reads: 64 MB in 13.72 seconds = 4.66 MB/sec

After:
/dev/hdg:
Timing buffer-cache reads: 128 MB in 0.72 seconds =177.78 MB/sec
Timing buffered disk reads: 64 MB in 1.63 seconds = 39.26 MB/sec

I'm happy :D
Back to top
View user's profile Send private message
newky2000
n00b
n00b


Joined: 13 Jan 2003
Posts: 36

PostPosted: Sat Jan 25, 2003 6:03 pm    Post subject: Re: Can't get DMA on Reply with quote

I have the same problem with hdparm saying the same thing.

I know that dma works on these drives as it was enabled when using the livecd disk.

Is there anything that should be enabled in the kernel?


pr0vidence wrote:
wombat wrote:
This command: hdparm -c 1 -d 1 -k 1 /dev/hdc

Gives me this response:

/dev/hdc:
setting 32-bit I/O support flag to 1
setting using_dma to 1 (on)
HDIO_SET_DMA failed: Operation not permitted
setting keep_settings to 1 (on)
I/O support = 1 (32-bit)
using_dma = 0 (off)
keepsettings = 1 (on)

How can I get my DMA on ? Is it a missing kernel option ? I am only getting 2.1MB/S from my new Deskstar ! :cry:


I don't know if it has anything to do with it, but I don't tihnk you are supposed to have spaces between the "d" and the "1" so you like should look more like this:

hdparm -c1 -d1 -k1 /dev/hdc
NOT
hdparm -c 1 -d 1 -k 1 /dev/hdc

Try that.
Back to top
View user's profile Send private message
pablo_pita
n00b
n00b


Joined: 05 Jan 2003
Posts: 25
Location: Frankfurt

PostPosted: Sun Jan 26, 2003 3:09 pm    Post subject: Re: Can't get DMA on Reply with quote

newky2000 wrote:

Is there anything that should be enabled in the kernel?

I also have this problem ... I can not setup the DMA in a new HITACHI hard disk to on. So, I am stuck with poor hard disk performance. I have been compiling the kernel with different options but no luck yet.

The hard disk is :

ATA device, with non-removable media
Model Number: HITACHI_DK23DA-20
Serial Number: 115ENL
Firmware Revision: 00J2A0A1
Standards:
Used: ATA/ATAPI-5 T13 1321D revision 3
Supported: 5 4 3 2 & some of 6

The IDE controller is (from /proc/pci):

Bus 0, device 31, function 1:
IDE interface: Intel Corp. 82801CAM IDE U100 (rev 2).
IRQ 5.
I/O at 0x0 [0x7].
I/O at 0x0 [0x3].
I/O at 0x0 [0x7].
I/O at 0x0 [0x3].
I/O at 0x1860 [0x186f].
Non-prefetchable 32 bit memory at 0x20000000 [0x200003ff].

The options I have:
# ATA/IDE/MFM/RLL support
CONFIG_IDE=y
# IDE, ATA and ATAPI Block devices
CONFIG_BLK_DEV_IDE=y
# IDE, ATA and ATAPI Block devices
CONFIG_BLK_DEV_IDE=y
# CONFIG_BLK_DEV_HD_IDE is not set
CONFIG_BLK_DEV_IDEDISK=y
CONFIG_IDEDISK_MULTI_MODE=y
# CONFIG_IDEDISK_STROKE is not set
# CONFIG_BLK_DEV_IDEDISK_VENDOR is not set
# CONFIG_BLK_DEV_IDEDISK_FUJITSU is not set
# CONFIG_BLK_DEV_IDEDISK_IBM is not set
# CONFIG_BLK_DEV_IDEDISK_MAXTOR is not set
# CONFIG_BLK_DEV_IDEDISK_QUANTUM is not set
# CONFIG_BLK_DEV_IDEDISK_SEAGATE is not set
# CONFIG_BLK_DEV_IDEDISK_WD is not set
# CONFIG_BLK_DEV_IDECS is not set
CONFIG_BLK_DEV_IDECD=y
# CONFIG_BLK_DEV_IDETAPE is not set
# CONFIG_BLK_DEV_IDEFLOPPY is not set
CONFIG_BLK_DEV_IDESCSI=m
CONFIG_IDE_TASK_IOCTL=y
CONFIG_IDE_TASKFILE_IO=y
CONFIG_BLK_DEV_IDEPCI=y
CONFIG_IDEPCI_SHARE_IRQ=y
CONFIG_BLK_DEV_IDEDMA_PCI=y
# CONFIG_BLK_DEV_IDEDMA_FORCED is not set
CONFIG_IDEDMA_PCI_AUTO=y
# CONFIG_IDEDMA_ONLYDISK is not set
CONFIG_BLK_DEV_IDEDMA=y
# CONFIG_IDEDMA_PCI_WIP is not set
# CONFIG_BLK_DEV_IDEDMA_TIMEOUT is not set
# CONFIG_IDEDMA_NEW_DRIVE_LISTINGS is not set
# CONFIG_AMD74XX_OVERRIDE is not set
# CONFIG_IDE_CHIPSETS is not set
CONFIG_IDEDMA_AUTO=y
# CONFIG_IDEDMA_IVB is not set
CONFIG_BLK_DEV_IDE_MODES=y
Back to top
View user's profile Send private message
pablo_pita
n00b
n00b


Joined: 05 Jan 2003
Posts: 25
Location: Frankfurt

PostPosted: Mon Jan 27, 2003 1:00 pm    Post subject: Re: Can't get DMA on Reply with quote

Maybe I am getting a bit off topic here. I found the following information about my IDE controller (Intel's 82801CAM IDE U100 controller), which I barely understand but seems to be the reason of why hdparm -d 1 /dev/hda fails:

Mode Data Corruption

Problem:

DMA compatible mode on the secondary channel causes data corruption on primary channel. If a device on one of the IDE interfaces (e.g., the secondary channel), is operating in Multi-Word DMA Mode with compatible timings where the cycle time is 600 ns, while a device on the other interface (primary channel) is running in PIO mode), the IDE PIO pre-fetch buffer will inadvertently provide an extra piece of secondary channel data to the primary device resulting in data corruption. This happens when DMAREQ is deasserted and a DMA transaction is running while a PIO transaction
is outstanding on the other channel.

Implication:

Systems configured in this manner may experience a situation in which the DMA IDE controller transfers incorrect data from the PIO configured device. Exactly how this manifests itself in a system is dependent on the system activity at the time.

Workaround:

When BIOS is determining which mode(s) an IDE device is capable of, it must not set the DMA capable bits in the ICH3-M if that device only supports Mode-0 DMA or slower. That device should be configured for PIO instead.

Status:

There are no plans to fix this erratum.

Is this the really reason why "hdparm -d 1 /dev/hda" does not work ? Any enlightment about what is going on ?
Back to top
View user's profile Send private message
newky2000
n00b
n00b


Joined: 13 Jan 2003
Posts: 36

PostPosted: Mon Jan 27, 2003 6:50 pm    Post subject: Re: Can't get DMA on Reply with quote

I have since learned that DMA for the ICH4 chipset will not work in the 2.4.19 kernel. It does however wrok very well in the 2.4.20 kernel. This is the one that the livecd uses and it is also the version for the vanilla-sources aswell.

I compiled and tested the 2.4.20 and it worked great with the drives, i forgot to re-link /usr/src/linux the the new kernel and it caused problems with X.




pablo_pita wrote:
Maybe I am getting a bit off topic here. I found the following information about my IDE controller (Intel's 82801CAM IDE U100 controller), which I barely understand but seems to be the reason of why hdparm -d 1 /dev/hda fails:

Mode Data Corruption

Problem:

DMA compatible mode on the secondary channel causes data corruption on primary channel. If a device on one of the IDE interfaces (e.g., the secondary channel), is operating in Multi-Word DMA Mode with compatible timings where the cycle time is 600 ns, while a device on the other interface (primary channel) is running in PIO mode), the IDE PIO pre-fetch buffer will inadvertently provide an extra piece of secondary channel data to the primary device resulting in data corruption. This happens when DMAREQ is deasserted and a DMA transaction is running while a PIO transaction
is outstanding on the other channel.

Implication:

Systems configured in this manner may experience a situation in which the DMA IDE controller transfers incorrect data from the PIO configured device. Exactly how this manifests itself in a system is dependent on the system activity at the time.

Workaround:

When BIOS is determining which mode(s) an IDE device is capable of, it must not set the DMA capable bits in the ICH3-M if that device only supports Mode-0 DMA or slower. That device should be configured for PIO instead.

Status:

There are no plans to fix this erratum.

Is this the really reason why "hdparm -d 1 /dev/hda" does not work ? Any enlightment about what is going on ?
Back to top
View user's profile Send private message
Delphiki
Guru
Guru


Joined: 04 Oct 2002
Posts: 337
Location: A2

PostPosted: Thu Jan 30, 2003 12:51 am    Post subject: Reply with quote

From an 80gb 7200 rpm seagate, using udma5 I get

hdparm -tT /dev/hda wrote:
/dev/hda:
Timing buffer-cache reads: 128 MB in 0.58 seconds =219.18 MB/sec
Timing buffered disk reads: 64 MB in 3.66 seconds = 17.51 MB/sec


dma is turned on, I've tried

The options enabled are
hdparm /dev/hda wrote:
/dev/hda:
multcount = 16 (on)
IO_support = 1 (32-bit)
unmaskirq = 1 (on)
using_dma = 1 (on)
keepsettings = 0 (off)
readonly = 0 (off)
readahead = 8 (on)
geometry = 9729/255/63, sectors = 156301488, start = 0


I turned on multcount (it was 0). I also set UDMA to 5 like I said, but neither seems to have any effect at all on my transfer speed. This seems really low for a 7200 rpm hd on a 1533 mhz athlon system and in fact my second hd, a 5200 Maxtor gets the following.

hdparm -tT /dev/hdb wrote:

/dev/hdb:
Timing buffer-cache reads: 128 MB in 0.56 seconds =226.95 MB/sec
Timing buffered disk reads: 64 MB in 2.42 seconds = 26.41 MB/sec


The settings are the same as far as I can tell..

Any suggestions would be appreciated.
_________________
Excellent..
Back to top
View user's profile Send private message
pilla
Administrator
Administrator


Joined: 07 Aug 2002
Posts: 7212
Location: Pelotas, BR

PostPosted: Thu Jan 30, 2003 1:31 am    Post subject: Reply with quote

Delphiki, are you sure you have support for your specific chipset enabled in your kernel?
_________________
"I'm just very selective about the reality I choose to accept." -- Calvin
Back to top
View user's profile Send private message
Delphiki
Guru
Guru


Joined: 04 Oct 2002
Posts: 337
Location: A2

PostPosted: Thu Jan 30, 2003 3:01 am    Post subject: Reply with quote

I have VIA82 CXXX chipset support compiled in and according to dmesg it finds my VIA vt8233 (rev 00) IDE UDMA100 controller on pci00:11.1
_________________
Excellent..
Back to top
View user's profile Send private message
new2lin
n00b
n00b


Joined: 11 Jun 2002
Posts: 33

PostPosted: Sat Feb 01, 2003 11:12 am    Post subject: Reply with quote

Code:
/dev/hdb:
 Timing buffer-cache reads:   128 MB in  0.35 seconds =365.71 MB/sec
 Timing buffered disk reads:  64 MB in  1.39 seconds = 46.04 MB/sec


Not too bad ... thanks for the tip, oh and I have the Via 8235, 2.4.20 vanilla kernel patched to pre3. WD 7200 RPM (8MB buffer :D ).
_________________
- Dustin
- Gentoo, breakfast of champions...
Back to top
View user's profile Send private message
pablo_pita
n00b
n00b


Joined: 05 Jan 2003
Posts: 25
Location: Frankfurt

PostPosted: Sun Feb 02, 2003 1:37 am    Post subject: Re: Can't get DMA on Reply with quote

Quote:

Is this the really reason why "hdparm -d 1 /dev/hda" does not work ? Any enlightment about what is going on ?


I got hdparm to set up the DMA to on !

I had to compile some other options in the kernel to get the support.

I saw in the hdparm source that setting DMA failed on the call to ioctl. I downloaded the 2.4.20-r1 kernel, checked more flags, especially if they had something to do with ioctl or with DMA (and of course, the IDE drive) ... and voila.
Back to top
View user's profile Send private message
moonshade
n00b
n00b


Joined: 03 Dec 2002
Posts: 6

PostPosted: Mon Mar 03, 2003 3:57 am    Post subject: Reply with quote

60 Gb Maxtor 6Y060L0, i845G chipset
Code:

/dev/hda:
 Timing buffer-cache reads:   128 MB in  0.28 seconds =457.14 MB/sec
 Timing buffered disk reads:  64 MB in  1.36 seconds = 47.58 MB/sec

:D
Back to top
View user's profile Send private message
mxller
n00b
n00b


Joined: 21 Feb 2003
Posts: 24
Location: Denmark

PostPosted: Thu Mar 06, 2003 11:34 am    Post subject: Reply with quote

nice :D

Code:

bash-2.05b# hdparm -tT /dev/hdb
 
/dev/hdb:
 Timing buffer-cache reads:   128 MB in  0.45 seconds =284.44 MB/sec
 Timing buffered disk reads:  64 MB in 17.25 seconds =  3.71 MB/sec

bash-2.05b# hdparm -m 16 -c 1 -u 1 -d 1  /dev/hdb
 
/dev/hdb:
 setting 32-bit IO_support flag to 1
 setting multcount to 16
 setting unmaskirq to 1 (on)
 setting using_dma to 1 (on)
 multcount    = 16 (on)
 IO_support   =  1 (32-bit)
 unmaskirq    =  1 (on)
 using_dma    =  1 (on)

bash-2.05b# hdparm -tT /dev/hdb
 
/dev/hdb:
 Timing buffer-cache reads:   128 MB in  0.46 seconds =278.26 MB/sec
 Timing buffered disk reads:  64 MB in  1.60 seconds = 40.00 MB/sec
Back to top
View user's profile Send private message
Donovan
Tux's lil' helper
Tux's lil' helper


Joined: 08 Feb 2003
Posts: 97
Location: Halifax, NS, Canada

PostPosted: Fri Mar 07, 2003 6:37 am    Post subject: Reply with quote

Tried it here on two PCs, one ancient (Cyrix M200) another not so ancient Abit BH6 (440) + Celeron 466 Mendocino. Neither machine received any appreciable benefit from the settings change.

On the Celery based machine, does that have something to do with this?

Quote:

Uniform Multi-Platform E-IDE driver Revision: 6.31
ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
PIIX4: IDE controller on PCI bus 00 dev 39
PIIX4: chipset revision 1
PIIX4: not 100% native mode: will probe irqs later
ide0: BM-DMA at 0xf000-0xf007, BIOS settings: hda:DMA, hdb:DMA
ide1: BM-DMA at 0xf008-0xf00f, BIOS settings: hdc:DMA, hdd:pio
hda: Maxtor 5T030H3, ATA DISK drive
hdb: WDC WD800BB-32CCB0, ATA DISK drive
hdc: CR-4804TE, ATAPI CD/DVD-ROM drive
ide0 at 0x1f0-0x1f7,0x3f6 on irq 14
ide1 at 0x170-0x177,0x376 on irq 15
blk: queue c039a9a4, I/O limit 4095Mb (mask 0xffffffff)
hda: 60030432 sectors (30736 MB) w/2048KiB Cache, CHS=3736/255/63, UDMA(33)
blk: queue c039aae4, I/O limit 4095Mb (mask 0xffffffff)
hdb: 156301488 sectors (80026 MB) w/2048KiB Cache, CHS=9729/255/63, UDMA(33)
hdc: ATAPI 24X CD-ROM CD-R/RW drive, 2048kB Cache, DMA
Uniform CD-ROM driver Revision: 3.12
Partition check:
/dev/ide/host0/bus0/target0/lun0: p1 p2 p3
/dev/ide/host0/bus0/target1/lun0: p1 p2 p3


Curious... :) I have 440 support enabled in my kernel (and no others).
_________________
Gentoo Linux * DirecTivo * Who needs heaven?
Back to top
View user's profile Send private message
Forse
Apprentice
Apprentice


Joined: 26 Dec 2002
Posts: 260
Location: /dev/random

PostPosted: Fri Mar 14, 2003 11:42 pm    Post subject: hehe Reply with quote

Maxtor 120gig 7200rpm running in ATA133:
Code:
homer Sources # hdparm -vTt /dev/hdg

/dev/hdg:
 multcount    = 16 (on)
 IO_support   =  1 (32-bit)
 unmaskirq    =  1 (on)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 readonly     =  0 (off)
 readahead    = 80 (on)
 geometry     = 14946/255/63, sectors = 240121728, start = 0
 Timing buffer-cache reads:   128 MB in  1.42 seconds = 90.14 MB/sec
 Timing buffered disk reads:  64 MB in  1.34 seconds = 49.76 MB/sec

_________________
[ My sites ]: UnixTutorials : AniFIND : AnimeYume
Back to top
View user's profile Send private message
klausx
n00b
n00b


Joined: 31 Jul 2002
Posts: 22
Location: Germany

PostPosted: Mon Mar 17, 2003 9:15 pm    Post subject: new chipset, new probs Reply with quote

hy there,
gor an Asus P4G8X (Intel 7205). And get
Quote:

/dev/hda:
setting using_dma to 1 (on)
HDIO_SET_DMA failed: Operation not permitted
using_dma = 0 (off)

Anyone knows a fix ?

Thanks
Klausx
Back to top
View user's profile Send private message
Anubis
n00b
n00b


Joined: 09 Nov 2002
Posts: 68
Location: BYU

PostPosted: Tue Mar 18, 2003 10:34 pm    Post subject: Reply with quote

Got the same thing myself...:

HDIO_SET_DMA failed: Operation not permitted
setting xfermode to 70 (UltraDMA mode6)
multcount = 16 (on)
IO_support = 1 (32-bit)
unmaskirq = 1 (on)
using_dma = 0 (off)
bash-2.05b# hdparm -tT /dev/hda

/dev/hda:
Timing buffer-cache reads: 128 MB in 0.61 seconds =209.84 MB/sec
Timing buffered disk reads: 64 MB in 17.25 seconds = 3.71 MB/sec

on my IBM 60giger.
_________________
The one who says it cannot be done should never interrupt the one who is doing it.
Back to top
View user's profile Send private message
Anubis
n00b
n00b


Joined: 09 Nov 2002
Posts: 68
Location: BYU

PostPosted: Sun Mar 23, 2003 8:03 am    Post subject: Reply with quote

anyone have any idea on this?
_________________
The one who says it cannot be done should never interrupt the one who is doing it.
Back to top
View user's profile Send private message
dberkholz
Developer
Developer


Joined: 18 Mar 2003
Posts: 1008
Location: Minneapolis, MN, USA

PostPosted: Fri Apr 11, 2003 10:01 pm    Post subject: Reply with quote

Results of hdparm -vtT, representative of average of 3

Western Digital 120GB, 7200 RPM, Model 1200BB
Quote:
/dev/hda:
multcount = 16 (on)
IO_support = 0 (default 16-bit)
unmaskirq = 0 (off)
using_dma = 1 (on)
keepsettings = 0 (off)
readonly = 0 (off)
readahead = 8 (on)
geometry = 14593/255/63, sectors = 234441648, start = 0
Timing buffer-cache reads: 128 MB in 0.50 seconds =256.00 MB/sec
Timing buffered disk reads: 64 MB in 1.41 seconds = 45.39 MB/sec

40 GB, 7200 RPM
Quote:
/dev/hdb:
multcount = 16 (on)
IO_support = 0 (default 16-bit)
unmaskirq = 0 (off)
using_dma = 1 (on)
keepsettings = 0 (off)
readonly = 0 (off)
readahead = 8 (on)
geometry = 4867/255/63, sectors = 78198750, start = 0
Timing buffer-cache reads: 128 MB in 0.50 seconds =256.00 MB/sec
Timing buffered disk reads: 64 MB in 2.01 seconds = 31.84 MB/sec

20 GB laptop drive
Quote:
/dev/hda: multcount = 16 (on)
IO_support = 0 (default 16-bit)
unmaskirq = 0 (off)
using_dma = 1 (on)
keepsettings = 0 (off)
readonly = 0 (off)
readahead = 8 (on)
geometry = 2432/255/63, sectors = 39070080, start = 0
Timing buffer-cache reads: 128 MB in 0.58 seconds =220.69 MB/sec
Timing buffered disk reads: 64 MB in 3.74 seconds = 17.11 MB/sec
Back to top
View user's profile Send private message
3vilinside
n00b
n00b


Joined: 11 Apr 2003
Posts: 56
Location: Graz, Austria

PostPosted: Sat Apr 12, 2003 7:05 pm    Post subject: Reply with quote

tanksimpson wrote:


hdparm -qc 1 -qd 1 -qk 1 /dev/hda



What exactly is the -k tag in this command?
_________________
"To err lies in the nature of humans, but to really fool things up you need a computer"
Back to top
View user's profile Send private message
volospin
Apprentice
Apprentice


Joined: 06 Aug 2002
Posts: 156
Location: Hong Kong

PostPosted: Mon Apr 28, 2003 10:04 am    Post subject: Reply with quote

I don't know how I did it... I didn't set anything...

but my hdparm -Tt results on my
Maxtor 5400rpm 2MB Cache 20GB Harddisk is
Timing buffer-cache reads: 128 MB in 1.10 seconds =116.36 MB/sec
Timing buffered disk reads: 64 MB in 1.72 seconds = 37.21 MB/sec
with the following result from hdparm /dev/hda
multcount = 16 (on)
IO_support = 0 (default 16-bit)
unmaskirq = 0 (off)
using_dma = 1 (on)
keepsettings = 0 (off)
readonly = 0 (off)
readahead = 8 (on)
geometry = 2491/255/63, sectors = 40020624, start = 0

and my WD 7200rpm 8MB Cache 80GB Harddisk is
Timing buffer-cache reads: 128 MB in 1.10 seconds =116.36 MB/sec
Timing buffered disk reads: 64 MB in 1.38 seconds = 46.38 MB/sec
with the following result from hdparm /dev/hdb
multcount = 16 (on)
IO_support = 0 (default 16-bit)
unmaskirq = 0 (off)
using_dma = 1 (on)
keepsettings = 0 (off)
readonly = 0 (off)
readahead = 8 (on)
geometry = 9729/255/63, sectors = 156301488, start = 0

the DMA Mode is max out already... I am running on a i810e chipset
I wonder if I get squeeze more performance out of this chipset + HD?
Especially the low "timing buffer-cache reads" speed... since others
are getting something like 4xxMB/sec
_________________
PIII-S 1.4G / 512MB / TUSL2-M / 3C920 x 2 / Seagate Barracuda IV 40GB
Back to top
View user's profile Send private message
pilla
Administrator
Administrator


Joined: 07 Aug 2002
Posts: 7212
Location: Pelotas, BR

PostPosted: Mon Apr 28, 2003 12:56 pm    Post subject: Reply with quote

AFAIK, there is no IDE hard drive that can do 400MB/sec :)

You probably read wrong, it must be 40MB/sec. Your results are quite good and I don't think you can get much more than that.

volospin wrote:

the DMA Mode is max out already... I am running on a i810e chipset
I wonder if I get squeeze more performance out of this chipset + HD?
Especially the low "timing buffer-cache reads" speed... since others
are getting something like 4xxMB/sec

_________________
"I'm just very selective about the reality I choose to accept." -- Calvin
Back to top
View user's profile Send private message
Display posts from previous:   
Reply to topic    Gentoo Forums Forum Index Kernel & Hardware All times are GMT
Goto page Previous  1, 2, 3, 4, 5, 6, 7, 8, 9  Next
Page 4 of 9

 
Jump to:  
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum