Extremely slow harddrive read/write

[knutz]

Hey everybody!

I have a huge problem with my server!
I have installed Ubuntu Minimal 8.04.3 LTS on my small server.

My hardware specs are:

Mainboard: INTEL D945GCLF ATOM230 MINI-ITX
Harddrives:
- DELOCK INTERNAL SATA CF CARDREADER with Kingston ELITE PRO 133x 8GB CF car. (/dev/sdb)
- 1.5 TB WESTERN DIGITAL CAVIAR GREEN 32MB SATA2 (/dev/sda)
RAM: 2gb Kingston VALUE RAM

I have installed ubuntu on the CF card and my problem is the western digital harddrive, which was a surprise to me.
I run hellanzb as a daemon and after a few minutes a little writing and reading, my harddrive becomes inaccessible. I can see in htop/top, that the programs trying to access the harddrive is in status "D" (drive sleep), and i have tried running running 'hdparm -Tt' for both drives when it "freezes".

The hdparm result for both drives:
(/dev/sda is the Western Digital drive)
(/dev/sdb is the CF card mounted as /)

/dev/sda:
 Timing cached reads:     2 MB in  3.41 seconds = 599.72 kB/sec
 Timing buffered disk reads:    6 MB in  3.34 seconds =   1.80 MB/sec

/dev/sdb:
 Timing cached reads:   996 MB in  2.00 seconds = 498.04 MB/sec
 Timing buffered disk reads:  118 MB in  3.03 seconds =  38.93 MB/sec

I have also tried running the command hdparm -I for each drive and the ouput is:

/dev/sda (the slow drive)
ATA device, with non-removable media
        Model Number:       WDC WD15EADS-00P8B0
        Serial Number:      WD-WMAVU0121769
        Firmware Revision:  01.00A01
        Transport:          Serial, SATA 1.0a, SATA II Extensions, SATA Rev 2.5
Standards:
        Supported: 8 7 6 5
        Likely used: 8
Configuration:
        Logical         max     current
        cylinders       16383   16383
        heads           16      16
        sectors/track   63      63
        --
        CHS current addressable sectors:   16514064
        LBA    user addressable sectors:  268435455
        LBA48  user addressable sectors: 2930277168
        device size with M = 1024*1024:     1430799 MBytes
        device size with M = 1000*1000:     1500301 MBytes (1500 GB)
Capabilities:
        LBA, IORDY(can be disabled)
        Queue depth: 32
        Standby timer values: spec'd by Standard, with device specific minimum
        R/W multiple sector transfer: Max = 16  Current = 16
        Recommended acoustic management value: 128, 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
Commands/features:
        Enabled Supported:
           *    SMART feature set
                Security Mode feature set
           *    Power Management feature set
           *    Write cache
           *    Look-ahead
           *    Host Protected Area feature set
           *    WRITE_BUFFER command
           *    READ_BUFFER command
           *    NOP cmd
           *    DOWNLOAD_MICROCODE
                Power-Up In Standby feature set
           *    SET_FEATURES required to spinup after power up
                SET_MAX security extension
                Automatic Acoustic Management feature set
           *    48-bit Address feature set
           *    Device Configuration Overlay feature set
           *    Mandatory FLUSH_CACHE
           *    FLUSH_CACHE_EXT
           *    SMART error logging
           *    SMART self-test
           *    General Purpose Logging feature set
           *    64-bit World wide name
           *    WRITE_UNCORRECTABLE_EXT command
           *    {READ,WRITE}_DMA_EXT_GPL commands
           *    Segmented DOWNLOAD_MICROCODE
           *    SATA-I signaling speed (1.5Gb/s)
           *    SATA-II signaling speed (3.0Gb/s)
           *    Native Command Queueing (NCQ)
           *    Host-initiated interface power management
           *    Phy event counters
           *    unknown 76[12]
                DMA Setup Auto-Activate optimization
           *    Software settings preservation
           *    SMART Command Transport (SCT) feature set
           *    SCT Long Sector Access (AC1)
           *    SCT LBA Segment Access (AC2)
           *    SCT Error Recovery Control (AC3)
           *    SCT Features Control (AC4)
           *    SCT Data Tables (AC5)
                unknown 206[12] (vendor specific)
                unknown 206[13] (vendor specific)
Checksum: correct



/dev/sdb (the CF card mounted as /)

ATA device, with non-removable media
        Model Number:       ELITE PRO CF CARD 8GB
        Serial Number:      20081205    000066B3
        Firmware Revision:  20090216
Standards:
        Likely used: 6
Configuration:
        Logical         max     current
        cylinders       15538   15538
        heads           16      16
        sectors/track   63      63
        --
        CHS current addressable sectors:   15662304
        LBA    user addressable sectors:   15662304
        device size with M = 1024*1024:        7647 MBytes
        device size with M = 1000*1000:        8019 MBytes (8 GB)
Capabilities:
        LBA, IORDY(can be disabled)
        bytes avail on r/w long: 4
        Standby timer values: spec'd by Vendor
        R/W multiple sector transfer: Max = 1   Current = 0
        Advanced power management level: disabled
        DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 *udma5
             Cycle time: min=120ns recommended=120ns
        PIO: pio0 pio1 pio2 pio3 pio4
             Cycle time: no flow control=120ns  IORDY flow control=120ns
Commands/features:
        Enabled Supported:
           *    SMART feature set
                Security Mode feature set
                Power Management feature set
                Write cache
                WRITE_BUFFER command
                READ_BUFFER command
                NOP cmd
                CFA feature set
                Advanced Power Management feature set
                Mandatory FLUSH_CACHE
HW reset results:
        CBLID- above Vih
        Device num = 0
Integrity word not set (found 0x0000, expected 0x43a5)

The Western Digital drive is mounted as ext3 with default options.
The CF card i mounted as reiserfs with the options sync and noatime.
I have also tried installing Ubuntu Server 9.04. SAME PROBLEM!?!

I have no idea what is wrong and what causes the Western Digital drive to be so slow when there is r/w activity on it.
Please help?!

/knutz

[zmagnet]

Same problem here. Tried everything I could think of including a new motherboard. It has to be something with the drive itself. I also know another person with the exact same drive and the same problem.

[knutz]

Thats weird! I shure hope not, that the drive is the problem. Have you tried other OS's than ubuntu?

[zmagnet]

I'm using it for mythtv, so no. But I have tried several Ubuntu versions. I have an older Western Digital SATA drive in the same system that has always worked perfectly. It really seems like something with this specific drive and revision (WD15EADS-00P8B0).

[ian dobson]

Hi,

Try disabling NCQ for the drive:-

echo 1 > /sys/block/sdb/device/queue_depth

Some WD drives don't work correctly with NCQ. It worked for me on a 500Gb WD drive.

Regards
Ian Dobson

[knutz]

I have tried running the command, but I don't have the permission to do it, not even as root.
But if I read the /sys/block/sda/device/queue_depth in 'nano' the contents of that file is "1".

Does that mean that NCQ is already disabled?

[zmagnet]

I talked to a 2nd level support tech at Western Digital and they won't acknowledge a problem with the drive under Linux. I was advised by the tech to install Windows XP or Vista. They did offer to RMA the drive, but they will return the exact same model, likely with the same issue.

[kbrunsting]

to try running that command to disable ncq, I googled and found you need to edit the /etc/rc.local file and add

sh -c "echo 1 > /sys/block/sda/device/queue_depth"

before the exit 0 line.

[dragos2]

Boot with a live cd then mount and test the drive again.

Also: check the cables ! I had some problems with some faulty SATA II cables.

Switch their position, plug them in different holes on to motherboard.

[knutz]

to try running that command to disable ncq, I googled and found you need to edit the /etc/rc.local file and add

sh -c "echo 1 > /sys/block/sda/device/queue_depth"

before the exit 0 line.

Tried this and it didn't work. It still gives me a message that i permission is denied.

I have no idea what to do with this anymore..
I will try switching some SATA cables... See if that works.