-   Linux - Hardware (
-   -   High system load while reading from HDD on nforce2 (

qQsh 01-30-2005 05:27 AM

High system load while reading from HDD on nforce2
I think it`s a global problem on some nforce2 chipsets, but i cant find solution.

Loading any software or searching from hdd is very slow and "top" shows "WA" time (waste/waiting or somehtink like that) up to 99%. As i know, that WA must be 0 always.

I have DMA turned on, i have my IDE drives kompiled in kernel and i dont have any errors. For this time i tried a lots of kernels with different versions, patchsets and configuration, different gcc/glibc versions, different udma modes, but it doesn`t help.

Some info:

hdparm -tT /dev/hda
Timing cached reads:  2124 MB in  2.00 seconds = 1060.57 MB/sec
Timing buffered disk reads: 172 MB in 3.01 seconds = 57.09 MB/sec


USE="ac3 a52 a53dec mp3 arts -java -gdbm lame -samba gd libgd gd-external gphoto2 xml X -gtk opengl avi gpm mpeg xv videos 3dnow mmxjpeg usb xmms quicktime cups sse postgres gtk2 -gnome2 -gnome kde -ipv6 -cdr mysql truetype -doc qt xft qt-mt oss pic alsa chroot"
CFLAGS="-O2 -march=athlon-xp -pipe -fomit-frame-pointer -ffast-math -funroll-loops"


ide: Assuming 33MHz system bus speed for PIO modes; override with idebus=xx
    ide0: BM-DMA at 0xf000-0xf007, BIOS settings: hda:DMA, hdb:DMA
    ide1: BM-DMA at 0xf008-0xf00f, BIOS settings: hdc:DMA, hdd:DMA


root@sh root # hdparm -I /dev/hda


ATA device, with non-removable media
        Model Number:      Maxtor 6Y080L0
        Serial Number:      Y22EBR6E
        Firmware Revision:  YAR41BW0
        Supported: 7 6 5 4
        Likely used: 7
        Logical        max    current
        cylinders      16383  16383
        heads          16      16
        sectors/track  63      63
        CHS current addressable sectors:  16514064
        LBA    user addressable sectors:  160086528
        device size with M = 1024*1024:      78167 MBytes
        device size with M = 1000*1000:      81964 MBytes (81 GB)
        LBA, IORDY(can be disabled)
        Queue depth: 1
        Standby timer values: spec'd by Standard, no device specific minimum
        R/W multiple sector transfer: Max = 16  Current = 16
        Advanced power management level: unknown setting (0x0000)
        Recommended acoustic management value: 192, current value: 254
        DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 udma5 *udma6
            Cycle time: min=120ns recommended=120ns
        PIO: pio0 pio1 pio2 pio3 pio4
            Cycle time: no flow control=120ns  IORDY flow control=120ns
        Enabled Supported:
          *    NOP cmd
          *    READ BUFFER cmd
          *    WRITE BUFFER cmd
          *    Host Protected Area feature set
          *    Look-ahead
          *    Write cache
          *    Power Management feature set
                Security Mode feature set
          *    SMART feature set
          *    FLUSH CACHE EXT command
          *    Mandatory FLUSH CACHE command
          *    Device Configuration Overlay feature set
          *    Automatic Acoustic Management feature set
                SET MAX security extension
                Advanced Power Management feature set
          *    DOWNLOAD MICROCODE cmd
          *    SMART self-test
          *    SMART error logging
        Master password revision code = 65534
        not    enabled
        not    locked
        not    frozen
        not    expired: security count
        not    supported: enhanced erase
HW reset results:
        CBLID- above Vih
        Device num = 0 determined by the jumper
Checksum: correct

Matir 01-30-2005 09:27 AM

Re: High system load while reading from HDD on nforce2

Originally posted by qQsh
As i know, that WA must be 0 always.
Why do you feel that must 'always' be 0?

qQsh 01-30-2005 01:42 PM

Re: Re: High system load while reading from HDD on nforce2

Originally posted by Matir
Why do you feel that must 'always' be 0?
If you cant answer anythink useless, please dont answer... That number never must be about 95% and normally it must be 0%.

Electro 01-30-2005 02:21 PM

What services are you running?

What does hdparm -v /dev/hda show?

Maxtor hard drives are know to use a lot of processor usage when being in use. IBM/Hitachi and Western Digital uses a lot less processor usage during use.

Loading or searching changes WA, so again why do you think that it should be 0.

Matir 01-30-2005 06:50 PM

For my own curiousity, why do maxtor drives generate more cpu? I would've figured they were all about the same, if they conform to the same IDE/ATA standards.

You know, I also have to wonder if your system is trying to correct CRC errors or anything of that sort. Do you have smartmontools installed?

qQsh 01-31-2005 04:37 AM


# hdparm -v /dev/hda

 multcount    = 16 (on)
 IO_support  =  1 (32-bit)
 unmaskirq    =  1 (on)
 using_dma    =  1 (on)
 keepsettings =  0 (off)
 readonly    =  0 (off)
 readahead    = 256 (on)
 geometry    = 65535/16/63, sectors = 81964302336, start = 0

BTW, same problem on other PC with same motherboard, but another HDD and linux distro.

All times are GMT -5. The time now is 02:21 PM.