linaro-release team mailing list archive

[mahmoh <709245@xxxxxxxxxxxxxxxxxx>]

Ran a quick benchmark with and without ping -f and 20x performance
increase with ping vs. without (below); I'd like to see this bumped up
to High since this poor performance is impacting testing using these
boards.  I also came across a similar problem on another board that may
help with a fix (or not -
https://lists.yoctoproject.org/pipermail/poky/2011-June/006649.html).

Linux panda-qa1 2.6.38-1309-omap4 #14-Ubuntu SMP PREEMPT Wed Jul 6
09:42:21 UTC 2011 armv7l armv7l armv7l GNU/Linux

Description:    Ubuntu oneiric (development branch)
Release:        11.10

<NO PING>

# phoronix-test-suite run pts/tiobench

Phoronix Test Suite v3.2.0
Threaded I/O Tester Test Configuration


Test:

1: Write
2: Random Write
3: Read
4: Random Read
5: Test All Options

Enter Your Choice: 5

Size Per Thread:

1: 32MB
2: 64MB
3: 128MB
4: 256MB
5: Test All Options

Enter Your Choice: 1

Thread Count:

1: 4
2: 8
3: 16
4: 32
5: Test All Options

Enter Your Choice: 1
    Would you like to save these test results (Y/n): n

Estimated Run-Time: 2 Hours, 31 Minutes


Threaded I/O Tester:
    pts/tiobench-1.1.0 [Test: Write - Size Per Thread: 32MB - Thread Count: 4]
    Test 1 of 4
    Estimated Time Remaining: 2 Hours, 31 Minutes
    Estimated Test Run-Time: 38 Minutes
    Expected Trial Run Count: 4
        Started Run 1 @ 17:28:21
        Started Run 2 @ 17:28:45
        Started Run 3 @ 17:29:09
        Started Run 4 @ 17:29:32  [Std. Dev: 2.16%]

    Test Results:
        6.273
        6.195
        6.388
        6.508

    Average: 6.34 MB/s


Threaded I/O Tester:
    pts/tiobench-1.1.0 [Test: Random Write - Size Per Thread: 32MB - Thread Count: 4]
    Test 2 of 4
    Estimated Time Remaining: 1 Hour, 53 Minutes
    Estimated Test Run-Time: 38 Minutes
    Expected Trial Run Count: 4
        Started Run 1 @ 17:29:59
        Started Run 2 @ 17:31:40
        Started Run 3 @ 17:33:08

<START PING>

        Started Run 4 @ 17:33:26  [Std. Dev: 104.51%]
        Started Run 5 @ 17:33:40  [Std. Dev: 84.05%]
        Started Run 6 @ 17:33:55  [Std. Dev: 71.87%]
        Started Run 7 @ 17:34:09  [Std. Dev: 63.69%]
        Started Run 8 @ 17:34:24  [Std. Dev: 61.29%]

    Test Results:
        0.206
        0.241
        4.493
        4.476
        4.623
        4.461
        4.534
        2.534

    Average: 3.20 MB/s

^C
# uname -a
Linux panda-qa1 2.6.38-1309-omap4 #14-Ubuntu SMP PREEMPT Wed Jul 6 09:42:21 UTC 2011 armv7l armv7l armv7l GNU/Linux
root@panda-qa1:/home/u# phoronix-test-suite run pts/tiobench

Phoronix Test Suite v3.2.0
Threaded I/O Tester Test Configuration


Test:

1: Write
2: Random Write
3: Read
4: Random Read
5: Test All Options

Enter Your Choice: 5

Size Per Thread:

1: 32MB
2: 64MB
3: 128MB
4: 256MB
5: Test All Options

Enter Your Choice: 1

Thread Count:

1: 4
2: 8
3: 16
4: 32
5: Test All Options

Enter Your Choice: 1
    Would you like to save these test results (Y/n): n

Estimated Run-Time: 2 Hours, 9 Minutes


Threaded I/O Tester:
    pts/tiobench-1.1.0 [Test: Write - Size Per Thread: 32MB - Thread Count: 4]
    Test 1 of 4
    Estimated Time Remaining: 2 Hours, 9 Minutes
    Estimated Test Run-Time: 33 Minutes
    Expected Trial Run Count: 4
        Started Run 1 @ 17:46:16
        Started Run 2 @ 17:46:26
        Started Run 3 @ 17:46:36
        Started Run 4 @ 17:46:46  [Std. Dev: 0.58%]

    Test Results:
        19.276
        19.526
        19.311
        19.323

    Average: 19.36 MB/s


Threaded I/O Tester:
    pts/tiobench-1.1.0 [Test: Random Write - Size Per Thread: 32MB - Thread Count: 4]
    Test 2 of 4
    Estimated Time Remaining: 1 Hour, 37 Minutes
    Estimated Test Run-Time: 33 Minutes
    Expected Trial Run Count: 4
        Started Run 1 @ 17:47:00
        Started Run 2 @ 17:47:14
        Started Run 3 @ 17:47:28
        Started Run 4 @ 17:47:42  [Std. Dev: 1.58%]

    Test Results:
        4.905
        4.72
        4.815
        4.799

    Average: 4.81 MB/s

-- 
You received this bug notification because you are a member of Linaro
Release Team, which is subscribed to the bug report.
https://bugs.launchpad.net/bugs/709245

Title:
  panda: USB disk IO slow

Status in Linaro Linux:
  Confirmed
Status in “linux-ti-omap4” package in Ubuntu:
  Confirmed

Bug description:
  My Panda's USB seems to be significantly slower than a Beagle C4.

  hdparm shows buffered reads as ~12MB/s on the Panda, and about ~20-25MB/s on a Beagle C4 from the same
  external Lacie USB disk.

  Kernel is 2.6.37-1002-linaro-omap

  Disk shows as:

  [    5.170440] scsi 0:0:0:0: Direct-Access     LaCie    d2 quadra             PQ: 0 ANSI: 4
  [    5.172546] sd 0:0:0:0: Attached scsi generic sg0 type 0
  [    5.175415] sd 0:0:0:0: [sda] 976773168 512-byte logical blocks: (500 GB/465 GiB)

  The board is otherwise idle during the test.

  Doing perf_2.6.37-12 record -a dd if=/dev/sda of=/dev/null bs=4096
  count=100000

  shows :
      81.41%         swapper  [kernel.kallsyms]     [k] default_idle
       6.33%              dd  [kernel.kallsyms]     [k] __copy_to_user
       0.94%         swapper  [kernel.kallsyms]     [k] cpu_idle
       0.51%              dd  [kernel.kallsyms]     [k] __make_request
       0.51%  perf_2.6.37-12  [kernel.kallsyms]     [k] __copy_from_user

  
  which suggests it's not CPU constrained.

  Dave

To manage notifications about this bug go to:
https://bugs.launchpad.net/linux-linaro/+bug/709245/+subscriptions