Intrepid kernel UDMA/33 (slow disk transfer rate)

[f3a97]

Hi,
       I've just upgraded to Intrepid and I've seen that a major performance slowdown is still existing.

I'm referring to the slow disk transfer rate, which I've already noticed in Hardy's kernel (https://bugs.launchpad.net/bugs/195221).

This is a major drawback since Gutsy, where I could reach a disk transfer rate almost double wrt Hardy and even Intrepid.

For example, with a recent WD disk I get the following:

ste@ste-ubuntu:~$ sudo hdparm -tT /dev/sdb

/dev/sdb:
 Timing cached reads: 436 MB in 2.01 seconds = 217.19 MB/sec
 Timing buffered disk reads: 88 MB in 3.04 seconds = 28.92 MB/sec

This is probably due to the fact that the DMA is set to DMA/33 (several years old!!!):

[ 4.628641] ata1.00: configured for UDMA/33
[ 4.645704] ata1.01: configured for UDMA/33

Can you fix that please?

[Jullian Gafar (jullian)]

I also would like to inform that there is already a workaround that worked, but only for the old kernet 2.6.24-19, which was outlined here: https://bugs.launchpad.net/ubuntu/+bug/195221/comments/38 - maybe you can tell me how to do this to the new Intrepid kernel?

I am adding some info:

cat /etc/issue
Ubuntu 8.10

uname -a
Linux zelda 2.6.27-7-generic #1 SMP Fri Oct 24 06:42:44 UTC 2008 i686 GNU/Linux

hdparm -tT /dev/sda:
/dev/sda:
 Timing cached reads: 434 MB in 2.00 seconds = 216.56 MB/sec
 Timing buffered disk reads: 68 MB in 3.06 seconds = 22.20 MB/sec

hdparm -i /dev/sda
/dev/sda:
 Model=FUJITSU MHV2080AH , FwRev=00000096, SerialNo= NT36T5C265B3
 Config={ HardSect NotMFM HdSw>15uSec Fixed DTR>10Mbs }
 RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=0
 BuffType=DualPortCache, BuffSize=8192kB, MaxMultSect=16, MultSect=?16?
 CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=156301488
 IORDY=yes, 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=yes: mode=0x80 (128) WriteCache=enabled
 Drive conforms to: ATA/ATAPI-6 T13 1410D revision 3a: ATA/ATAPI-2,3,4,5,6

lspci
00:00.0 Host bridge: Silicon Integrated Systems [SiS] 650/M650 Host (rev 01)
00:01.0 PCI bridge: Silicon Integrated Systems [SiS] Virtual PCI-to-PCI bridge (AGP)
00:02.0 ISA bridge: Silicon Integrated Systems [SiS] SiS961 [MuTIOL Media IO]
00:02.1 SMBus: Silicon Integrated Systems [SiS] SiS961/2 SMBus Controller
00:02.2 USB Controller: Silicon Integrated Systems [SiS] USB 1.1 Controller (rev 07)
00:02.3 USB Controller: Silicon Integrated Systems [SiS] USB 1.1 Controller (rev 07)
00:02.5 IDE interface: Silicon Integrated Systems [SiS] 5513 [IDE] (rev d0)
00:02.6 Modem: Silicon Integrated Systems [SiS] AC'97 Modem Controller (rev a0)
00:02.7 Multimedia audio controller: Silicon Integrated Systems [SiS] AC'97 Sound Controller (rev a0)
00:08.0 CardBus bridge: ENE Technology Inc CB1410 Cardbus Controller
01:00.0 VGA compatible controller: Silicon Integrated Systems [SiS] 65x/M650/740 PCI/AGP VGA Display Adapter

A portion of dmesg (full dmesg is attached):
[ 2.820532] scsi0 : pata_sis
[ 2.820971] scsi1 : pata_sis
[ 2.822495] ata1: PATA max UDMA/100 cmd 0x1f0 ctl 0x3f6 bmdma 0x1100 irq 14
[ 2.822549] ata2: PATA max UDMA/100 cmd 0x170 ctl 0x376 bmdma 0x1108 irq 15
[ 2.984633] ata1.00: ATA-6: FUJITSU MHV2080AH, 00000096, max UDMA/100
[ 2.984683] ata1.00: 156301488 sectors, multi 16: LBA
[ 2.984746] ata1.00: limited to UDMA/33 due to 40-wire cable
[ 3.000449] ata1.00: configured for UDMA/33
[ 3.164486] ata2.00: ATAPI: DV-28E-B, 1.2B, max UDMA/33
[ 3.180374] ata2.00: configured for UDMA/33

[David Burgess (apt-get)]

I didn't see this in 8.04, but upgrading to 8.10 a couple days ago initiated this bug on my system.

db

[David Burgess (apt-get)]

I'd like to retract my earlier posts, as I had DMA disabled in my BIOS for some reason. Reversing that resolved this problem for me.

db

[EricDHH (ericdhh)]

Ubuntu intrepid i386
Linux vishnu 2.6.27-10-generic

Hello

full confirm on that, my thinkpad t23 has no cable for detection. The disk connector is soldered to the mainboard. The controller can do udma100, has done this for 7.xx versions and does it when booting such old live cd. Kernel with hdX runs well, with sdX they are slow.

Board and controller can do:

[ 5.562716] scsi0 : ata_piix
[ 5.563078] scsi1 : ata_piix
[ 5.565677] ata1: PATA max UDMA/100 cmd 0x1f0 ctl 0x3f6 bmdma 0x1860 irq 14
[ 5.565685] ata2: PATA max UDMA/100 cmd 0x170 ctl 0x376 bmdma 0x1868 irq 15

But when detecting the disk (transcend ssd) it fails.

[ 5.728373] ata1.00: ATA-8: TS8GSSD25-S, FW0625, max UDMA/100
[ 5.728383] ata1.00: 15604848 sectors, multi 0: LBA
[ 5.728408] ata1.00: limited to UDMA/33 due to 40-wire cable
[ 5.736757] ata1.00: configured for UDMA/33

So the ssd runs slowdowned at not as fast as possible.

/dev/sda:

 Model=TS8GSSD25-S , FwRev=FW0625 , SerialNo=226311100010
 Config={ Fixed }
 RawCHS=15481/16/63, TrkSize=0, SectSize=0, ECCbytes=63
 BuffType=unknown, BuffSize=0kB, MaxMultSect=1, MultSect=?1?
 CurCHS=15481/16/63, CurSects=15604848, LBA=yes, LBAsects=15604848
 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

What to do? Use a very old kernel from 7.xx with lots of problems to fix this? I have no bios limitations in the machine that can be adjusted.

Eric

[Ganton (ganton)]

I confirm this bug, a computer I have a prior 8.04 installation in a partition and:

    $ sudo hdparm -Tt /dev/hdg

    /dev/hdg:
    Timing cached reads: 386 MB in 2.01 seconds = 192.38 MB/sec
    Timing buffered disk reads: 90 MB in 3.01 seconds = 29.88 MB/sec

but with the 8.10 installation in another partition... the udma100 mode is NOT activated, /dev/hdg becomes /dev/sda, hdparm can not change the dma mode, and working with the hard disk ends sinking the user into desperation:

   $ sudo hdparm -Tt /dev/sda

  /dev/sda:
  Timing cached reads: 274 MB in 2.00 seconds = 136.84 MB/sec
  Timing buffered disk reads: 14 MB in 3.08 seconds = 4.55 MB/sec

[Frans (frans0023)]

Hello,

I have this problem on an Thinkpad X40 and a Compact flash X233.
I use Ubuntu Jaunty 9.04 alpha 5 on the 2.6.28.8-generic kernel.
Can someone help me please ?

Thanks !

[Richard Driscoll (rjdriscoll)]

I have the same problem with Ubuntu 8.10 (latest updates). I have a CDROM writer/DVD reader attached with a 80 way cable. It is supposed to be able o do UDMA/100 but is being limited to UDMA/33 by an erroneous claim that the cable is 40 way.

I realise that in the case of a CDROM drive the loss of performance is pretty minimal but it's a bug just the same.

DMESG is enclosed.

Thanks,

Richard

[Davias (davias)]

I confirm this bug exists on 8.10 (mythbuntu)

BIOS is set to UDMA 100 and shows it at startup, but hdparm reports udma2 and dmesg the 40-wire cable - NOT!

I tried this solutions that worked for a guy:

Modified /etc/modules:
Code:

fuse
lp
#custom start
amd74xx
mousedev
psmouse
via82cxxx
piix
ide-core
#ide-generic
ide-disk
ide-cd
#custom end

Added to /etc/hdparm.conf:
Code:

/dev/sda {
 dma = on
 io32_support = 1
 write_cache = on
}

but it did nothing for me - any suggestions?

BTW: System is old but proven capable of running at udma5...

[Davias (davias)]

Just update the Jaunty partition with latest beta 9.04: same as intrepid 8.10 - UDMA2 is set instead of 5!!

Ubuntu, are we going backward?

Anyhelp? TIA

[Karl Martin (klein-km)]

Hi,

I had the same problem with my Thinkpad T61 and a hard disk Ultrabay adapter using Jaunty. Linux reported a 40-wire cable and used UDMA/33. However, adding libata.force=80c to the kernel boot options solved the problem and the Ultrabay adapter is now connected with UDMA/100.

Best wishes

Karl Martin

[kernel-janitor (kernel-janitor)]

Hi stek79,

Please be sure to confirm this issue exists with the latest development release of Ubuntu. ISO CD images are available from http://cdimage.ubuntu.com/releases/karmic . If the issue remains, please run the following command from a Terminal (Applications->Accessories->Terminal). It will automatically gather and attach updated debug information to this report.

apport-collect -p linux 285595

Also, if you could test the latest upstream kernel available that would be great. It will allow additional upstream developers to examine the issue. Refer to https://wiki.ubuntu.com/KernelMainlineBuilds . Once you've tested the upstream kernel, please remove the 'needs-upstream-testing' tag. This can be done by clicking on the yellow pencil icon next to the tag located at the bottom of the bug description and deleting the 'needs-upstream-testing' text. Please let us know your results.

Thanks in advance.

[This is an automated message. Apologies if it has reached you inappropriately; please just reply to this message indicating so.]

[Ganton (ganton)]

> adding libata.force=80c to the kernel boot options
At least in the case of the machine I report, with Ubuntu 9.04, that didn't work.

Several errors appear later and finally the system is configured for UDMA/33 instead of UDMA/100

$ dmesg | grep -i udma
[ 3.152722] ata1: PATA max UDMA/100 cmd 0x9000 ctl 0x8800 bmdma 0x7800 irq 10
[ 3.152730] ata2: PATA max UDMA/100 cmd 0x8400 ctl 0x8000 bmdma 0x7808 irq 10
[ 3.504481] ata2.00: ATA-4: ST340823A, 3.07, max UDMA/100
[ 3.504756] ata2.01: ATA-5: ST340016A, 3.75, max UDMA/100
[ 3.520344] ata2.00: configured for UDMA/100
[ 3.536423] ata2.01: configured for UDMA/100
[ 3.689467] ata3: PATA max UDMA/66 cmd 0x1f0 ctl 0x3f6 bmdma 0xd800 irq 14
[ 3.689475] ata4: PATA max UDMA/66 cmd 0x170 ctl 0x376 bmdma 0xd808 irq 15
[ 3.852347] ata3.00: ATAPI: HL-DT-ST DVDRAM GSA-4167B, DL11, max UDMA/33
[ 3.868297] ata3.00: configured for UDMA/33
[ 49.396341] ata2.00: configured for UDMA/100
[...]
[ 50.257375] ata2.01: limiting speed to UDMA/66:PIO4
[ 50.452348] ata2.00: configured for UDMA/100
[ 50.468406] ata2.01: configured for UDMA/66
[ 50.804321] ata2.00: configured for UDMA/100
[ 50.820416] ata2.01: configured for UDMA/66
[ 50.961387] ata2.01: limiting speed to UDMA/33:PIO4
[ 51.156359] ata2.00: configured for UDMA/100
[ 51.172431] ata2.01: configured for UDMA/33
[ 51.508362] ata2.00: configured for UDMA/100
[...]
[ 53.745084] ata2.00: limiting speed to UDMA/66:PIO4
[ 53.940358] ata2.00: configured for UDMA/66
[...]
[ 54.449026] ata2.00: limiting speed to UDMA/33:PIO4
[...]
[ 56.628336] ata2.00: configured for UDMA/33

[Ganton (ganton)]

Note: the system accepted the boot parameter:
   $ dmesg | grep -i cabl
   [ 3.318892] ata1: FORCE: cable set to 80c
   [...]
   [ 56.972410] ata2: FORCE: cable set to 80c

   $ cat /proc/cmdline
   root=UUID=bfd63b60-f8fb-405b-b695-749b138b68c4 libata.force=80c ro quiet splash

[Nick Twigg (nick-nick-web)]

Architecture: i386
AudioDevicesInUse:
 USER PID ACCESS COMMAND
 /dev/snd/controlC0: nick 20746 F.... Picasa3.exe
                      nick 20767 F.... explorer.exe
                      nick 28333 F.... pulseaudio
 /dev/snd/pcmC0D0p: nick 28333 F...m pulseaudio
CRDA: Error: [Errno 2] No such file or directory
Card0.Amixer.info:
 Card hw:0 'NVidia'/'HDA NVidia at 0xdfff8000 irq 21'
   Mixer name : 'Realtek ALC888'
   Components : 'HDA:10ec0888,18491e01,00100001'
   Controls : 34
   Simple ctrls : 19
DistroRelease: Ubuntu 9.10
HibernationDevice: RESUME=UUID=dba08f70-cfd6-463e-a9c2-3a0c4e24d5e3
IwConfig:
 lo no wireless extensions.

 eth0 no wireless extensions.
Lsusb:
 Bus 002 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
 Bus 001 Device 002: ID 0781:b6b7 SanDisk Corp.
 Bus 001 Device 001: ID 1d6b:0002 Linux Foundation 2.0 root hub
MachineType: To Be Filled By O.E.M. To Be Filled By O.E.M.
NonfreeKernelModules: nvidia
Package: linux (not installed)
ProcCmdLine: BOOT_IMAGE=/boot/vmlinuz-2.6.31-12-generic root=UUID=7d45c166-4251-45e3-9dc9-a51e85da49bc ro quiet splash
ProcEnviron:
 SHELL=/bin/bash
 LANG=en_GB.UTF-8
ProcVersionSignature: Ubuntu 2.6.31-12.41-generic
RelatedPackageVersions: linux-firmware 1.21
RfKill:

Uname: Linux 2.6.31-12-generic i686
UserGroups: adm admin cdrom dialout lpadmin plugdev sambashare
dmi.bios.date: 08/08/2007
dmi.bios.vendor: American Megatrends Inc.
dmi.bios.version: P2.20
dmi.board.name: ALiveNF6G-DVI
dmi.chassis.asset.tag: To Be Filled By O.E.M.
dmi.chassis.type: 3
dmi.chassis.vendor: To Be Filled By O.E.M.
dmi.chassis.version: To Be Filled By O.E.M.
dmi.modalias: dmi:bvnAmericanMegatrendsInc.:bvrP2.20:bd08/08/2007:svnToBeFilledByO.E.M.:pnToBeFilledByO.E.M.:pvrToBeFilledByO.E.M.:rvn:rnALiveNF6G-DVI:rvr:cvnToBeFilledByO.E.M.:ct3:cvrToBeFilledByO.E.M.:
dmi.product.name: To Be Filled By O.E.M.
dmi.product.version: To Be Filled By O.E.M.
dmi.sys.vendor: To Be Filled By O.E.M.

[Cloudlight (pnkellogg)]

AplayDevices:
 **** List of PLAYBACK Hardware Devices ****
 card 0: PCI [ESS Allegro PCI], device 0: Allegro [Allegro]
   Subdevices: 2/2
   Subdevice #0: subdevice #0
   Subdevice #1: subdevice #1
Architecture: i386
ArecordDevices:
 **** List of CAPTURE Hardware Devices ****
 card 0: PCI [ESS Allegro PCI], device 0: Allegro [Allegro]
   Subdevices: 1/1
   Subdevice #0: subdevice #0
AudioDevicesInUse:
 USER PID ACCESS COMMAND
 /dev/snd/controlC0: tina 1252 F.... pulseaudio
CRDA: Error: [Errno 2] No such file or directory
Card0.Amixer.info:
 Card hw:0 'PCI'/'ESS Allegro PCI at 0x3000, irq 11'
   Mixer name : 'ESS Technology ESS1988'
   Components : 'AC97a:45838308'
   Controls : 25
   Simple ctrls : 19
CurrentDmesg:
 [ 24.593278] IBM TrackPoint firmware: 0x0b, buttons: 3/3
 [ 24.619908] input: TPPS/2 IBM TrackPoint as /devices/platform/i8042/serio4/input/input6
 [ 24.816364] e100: eth0 NIC Link is Up 100 Mbps Full Duplex
 [ 24.816682] ADDRCONF(NETDEV_CHANGE): eth0: link becomes ready
 [ 35.304077] eth0: no IPv6 routers present
DistroRelease: Ubuntu 9.10
HibernationDevice: RESUME=UUID=3e5167ba-c5e1-4084-8261-e47eb067ea86
InstallationMedia: Ubuntu 9.10 "Karmic Koala" - Release i386 (20091028.5)
IwConfig:
 lo no wireless extensions.

 eth0 no wireless extensions.
Lsusb:
 Bus 001 Device 003: ID 0461:4d4c Primax Electronics, Ltd
 Bus 001 Device 002: ID 058f:9254 Alcor Micro Corp. Hub
 Bus 001 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
MachineType: Compaq Evo N400c
Package: linux (not installed)
PccardctlIdent:
 Socket 0:
   no product info available
PccardctlStatus:
 Socket 0:
   no card
ProcCmdLine: BOOT_IMAGE=/boot/vmlinuz-2.6.31-15-generic root=UUID=28f0b48e-8ee3-4419-a9c2-ac6439dcbd97 ro quiet splash
ProcEnviron:
 SHELL=/bin/bash
 LANG=en_CA.UTF-8
ProcVersionSignature: Ubuntu 2.6.31-15.50-generic
RelatedPackageVersions:
 linux-backports-modules-2.6.31-15-generic N/A
 linux-firmware 1.25
RfKill:

Uname: Linux 2.6.31-15-generic i686
UserGroups: adm admin cdrom dialout lpadmin plugdev sambashare
XsessionErrors:
 (gnome-settings-daemon:1310): GLib-CRITICAL **: g_propagate_error: assertion `src != NULL' failed
 (gnome-settings-daemon:1310): GLib-CRITICAL **: g_propagate_error: assertion `src != NULL' failed
 (nautilus:1400): Eel-CRITICAL **: eel_preferences_get_boolean: assertion `preferences_is_initialized ()' failed
 (polkit-gnome-authentication-agent-1:1419): GLib-CRITICAL **: g_once_init_leave: assertion `initialization_value != 0' failed
dmi.bios.date: 08/21/2001
dmi.bios.vendor: Compaq
dmi.bios.version: 686AW v2.47
dmi.board.name: 06F4
dmi.board.vendor: Compaq
dmi.chassis.type: 10
dmi.chassis.vendor: Compaq
dmi.modalias: dmi:bvnCompaq:bvr686AWv2.47:bd08/21/2001:svnCompaq:pnEvoN400c:pvr:rvnCompaq:rn06F4:rvr:cvnCompaq:ct10:cvr:
dmi.product.name: Evo N400c
dmi.sys.vendor: Compaq

[Cloudlight (pnkellogg)]

AplayDevices:
 **** List of PLAYBACK Hardware Devices ****
 card 0: PCI [ESS Allegro PCI], device 0: Allegro [Allegro]
   Subdevices: 2/2
   Subdevice #0: subdevice #0
   Subdevice #1: subdevice #1
Architecture: i386
ArecordDevices:
 **** List of CAPTURE Hardware Devices ****
 card 0: PCI [ESS Allegro PCI], device 0: Allegro [Allegro]
   Subdevices: 1/1
   Subdevice #0: subdevice #0
AudioDevicesInUse:
 USER PID ACCESS COMMAND
 /dev/snd/controlC0: tina 1252 F.... pulseaudio
CRDA: Error: [Errno 2] No such file or directory
Card0.Amixer.info:
 Card hw:0 'PCI'/'ESS Allegro PCI at 0x3000, irq 11'
   Mixer name : 'ESS Technology ESS1988'
   Components : 'AC97a:45838308'
   Controls : 25
   Simple ctrls : 19
CurrentDmesg:
 [ 24.593278] IBM TrackPoint firmware: 0x0b, buttons: 3/3
 [ 24.619908] input: TPPS/2 IBM TrackPoint as /devices/platform/i8042/serio4/input/input6
 [ 24.816364] e100: eth0 NIC Link is Up 100 Mbps Full Duplex
 [ 24.816682] ADDRCONF(NETDEV_CHANGE): eth0: link becomes ready
 [ 35.304077] eth0: no IPv6 routers present
DistroRelease: Ubuntu 9.10
HibernationDevice: RESUME=UUID=3e5167ba-c5e1-4084-8261-e47eb067ea86
InstallationMedia: Ubuntu 9.10 "Karmic Koala" - Release i386 (20091028.5)
IwConfig:
 lo no wireless extensions.

 eth0 no wireless extensions.
Lsusb:
 Bus 001 Device 003: ID 0461:4d4c Primax Electronics, Ltd
 Bus 001 Device 002: ID 058f:9254 Alcor Micro Corp. Hub
 Bus 001 Device 001: ID 1d6b:0001 Linux Foundation 1.1 root hub
MachineType: Compaq Evo N400c
Package: linux (not installed)
PccardctlIdent:
 Socket 0:
   no product info available
PccardctlStatus:
 Socket 0:
   no card
ProcCmdLine: BOOT_IMAGE=/boot/vmlinuz-2.6.31-15-generic root=UUID=28f0b48e-8ee3-4419-a9c2-ac6439dcbd97 ro quiet splash
ProcEnviron:
 SHELL=/bin/bash
 LANG=en_CA.UTF-8
ProcVersionSignature: Ubuntu 2.6.31-15.50-generic
RelatedPackageVersions:
 linux-backports-modules-2.6.31-15-generic N/A
 linux-firmware 1.25
RfKill:

Uname: Linux 2.6.31-15-generic i686
UserGroups: adm admin cdrom dialout lpadmin plugdev sambashare
XsessionErrors:
 (gnome-settings-daemon:1310): GLib-CRITICAL **: g_propagate_error: assertion `src != NULL' failed
 (gnome-settings-daemon:1310): GLib-CRITICAL **: g_propagate_error: assertion `src != NULL' failed
 (nautilus:1400): Eel-CRITICAL **: eel_preferences_get_boolean: assertion `preferences_is_initialized ()' failed
 (polkit-gnome-authentication-agent-1:1419): GLib-CRITICAL **: g_once_init_leave: assertion `initialization_value != 0' failed
dmi.bios.date: 08/21/2001
dmi.bios.vendor: Compaq
dmi.bios.version: 686AW v2.47
dmi.board.name: 06F4
dmi.board.vendor: Compaq
dmi.chassis.type: 10
dmi.chassis.vendor: Compaq
dmi.modalias: dmi:bvnCompaq:bvr686AWv2.47:bd08/21/2001:svnCompaq:pnEvoN400c:pvr:rvnCompaq:rn06F4:rvr:cvnCompaq:ct10:cvr:
dmi.product.name: Evo N400c
dmi.sys.vendor: Compaq

[Cloudlight (pnkellogg)]

Sorry sorry sorry, my apologies to all for the deluge of my (mainly) unwanted postings. This is what happens when a rookie doesn't do his homework. Again, please accept my apologies for my doing.

However, Bug #285595 does affect my girl friend's Compaq Evo N400c. Has there occurred a resolution yet?