Where is the bottleneck?

  • Hi!


    Here are the specs of my nas build:

    Motherboard: ASRock J3455B-ITX (Bios version P1.20)

    RAM: 8GB DDR3 Synchronous 1600MHz (0.6 ns) (2 x 4GB)

    CPU: Celeron J3455 (Quadcore, 1.5GHz)

    System Drive: Samsung SSD 830 (64GB)

    Expansion Slot: DeLock PCIe x2 SATA controller (10 SATA Ports) (https://www.delock.de/produkte…kmale.html?setLanguage=en)

    - 2 x 2TB SSD (SanDisk SDSSDA-2): RAID 1

    - 3 x 5TB HDD (TOSHIBA HDWE150): RAID 5

    - 3 x 8TB HDD (TOSHIBA HDWG180): RAID 5

    OS: Debian 9.13

    OMV-Version: 4.1.36-1

    See full system-report attached.


    Currently both RAID 5 RAIDs are degraded running with only 2 out of 3 disks:

    When writing large amounts of data to one of the RAID 5 devices I experience a huge IO/wait load, load average goes up somewhere between 5 and 10 (see output of top below). Copying large files from one RAID 5 to the other RAID 5 is very slow - about 25 MB/s.


    dmesg shows repeating errors:

    Code
    [37013.334123] ata3.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen
    [37013.338796] ata3.00: failed command: WRITE DMA EXT
    [37013.340925] ata3.00: cmd 35/00:40:80:d2:35/00:05:28:00:00/e0 tag 7 dma 688128 out
    res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
    [37013.345242] ata3.00: status: { DRDY }
    [37013.346315] ata3: hard resetting link
    [37013.661354] ata3: SATA link up 1.5 Gbps (SStatus 113 SControl 310)
    [37013.664382] ata3.00: configured for UDMA/33
    [37013.664392] ata3.00: device reported invalid CHS sector 0
    [37013.664405] ata3: EH complete

    I don't know if these errors are because of some bottleneck or if it is a hardware error.


    Can someone point me to where the bottleneck most likely is? Is it

    - the CPU (computing the parity data)

    - the SATA controller card

    - the HDDs themself

    - something else?


    Thanks for your advice,

    Mike

  • mfischer

    Added the Label OMV 4.x
  • votdev

    Approved the thread.
  • OMV-Version: 4.1.36-1

    is unsupported since some time and OS: Debian 9.13 doesn't look up-to-date either.

    I'm not a RAID expert, but 'Currently both RAID 5 RAIDs are degraded running with only 2 out of 3 disks' sounds like the biggest issue to fix first.

    Is this a software or HW RAID configuration?

    Relevant may this comment https://github.com/geerlingguy…/1#issuecomment-724822718

    omv 5.6.3-1 (usul) on RPi4/4GB with Kernel 5.10.x and WittyPi 3 V2 RTC HAT

    2x 6TB HDD formatted with ext4 in Icy Box IB-RD3662-C31 / hardware supported RAID1

    For Read/Write performance of SMB shares hosted on this hardware see forum here

Participate now!

Don’t have an account yet? Register yourself now and be a part of our community!