• [6.9.2] Odd performance issue with LSI-2308 (SAS9206-16e) HBA

    ken-ji

    By ken-ji

      • Minor

    There seems to be a really odd performance issue with LSI-2308 based controllers

    When all the drives on the controller are spun down (I only have eight) and you attempt to access them for parity checking, benchmarking a single drive

    We get the following speed results from

    Parity tests: 

    2021-04-27, 03:06:09	1 day, 4 hr, 36 min, 29 sec	77.7 MB/s	OK	0
2021-03-15, 14:44:59	15 hr, 14 min, 58 sec	145.8 MB/s	OK	0
2021-02-15, 15:16:28	15 hr, 46 min, 27 sec	140.9 MB/s	OK	0
2021-01-11, 15:39:25	16 hr, 9 min, 24 sec	137.6 MB/s	OK	0
2020-12-14, 15:40:07	16 hr, 10 min, 5 sec	137.5 MB/s	OK	0
2020-11-09, 14:42:48	15 hr, 12 min, 47 sec	146.1 MB/s	OK	0
2020-10-12, 14:54:37	14 hr, 57 min, 53 sec	148.5 MB/s	OK	0

     

    As you can see my typical speed for parity tests should be about 140MB/s on average

     

    Drive benchmarks:

    controller-benchmark-6.9.2-2.thumb.png.438700f810def8bfb3f7aad5f86953b9.png

     

     

    controller-benchmark-6.9.2.thumb.png.8f50fa2b88f1049bd85262de9ae3116b.png

    The benchmarks are also weird in that I got the second results by simplying spinning down and spinning up all the drives prior to just blindly benchmarking all my drives.

    Testing this condition with the parity check also produces the same result - starting the parity check while the drives are spun down results in a prity check that runs at 777MB/s max, whereas spinning up all the drives first allows them hit the max speed of about 200MB/s

     

    Also it seems only my Toshiba N300 drives are affected, and none of my Seagate Archive drives or drives on the onboard SATA controller seems to be affected (or I haven't noticed)

     

    Any suggestions or ideas?

     

    mediastore-diagnostics-20210424-1011.zip

    Go to reports Stable Releases

    User Feedback

    Recommended Comments

    JorgeB

    Looks more like an LSI driver issue, especially if doesn't happens with all the disk models, a future kernel may include a fix for that.

    Link to comment


    Join the conversation

    You can post now and register later. If you have an account, sign in now to post with your account.
    Note: Your post will require moderator approval before it will be visible.

    Guest
    Add a comment...

    ×   Pasted as rich text.   Restore formatting

      Only 75 emoji are allowed.

    ×   Your link has been automatically embedded.   Display as a link instead

    ×   Your previous content has been restored.   Clear editor

    ×   You cannot paste images directly. Upload or insert images from URL.

    ×

  • Status Definitions

     

    Open = Under consideration.

     

    Solved = The issue has been resolved.

     

    Solved version = The issue has been resolved in the indicated release version.

     

    Closed = Feedback or opinion better posted on our forum for discussion. Also for reports we cannot reproduce or need more information. In this case just add a comment and we will review it again.

     

    Retest = Please retest in latest release.

    Priority Definitions

     

    Minor = Something not working correctly.

     

    Urgent = Server crash, data loss, or other showstopper.

     

    Annoyance = Doesn't affect functionality but should be fixed.

     

    Other = Announcement or other non-issue.