[1.] One line summary of the problem:
Slow writes with dd on Lexar JumpDrive P20 64GB flash drives connected
via Intel USB 3.0 host controllers.
[2.] Full description of the problem/report:
Writes on Lexar JumpDrive P20 64GB flash drives are unexpectedly slow.
With dd we are seeing 45 MB/s while
Is there anything else I can do to debug this issue further?
Are there any quirks I could try?
On Wed, May 18, 2016 at 3:41 PM, Michael Schaller wrote:
> [1.] One line summary of the problem:
> Slow writes with dd on Lexar JumpDrive P20 64GB flash drives connected
> via Intel USB
records out
268435456 bytes (268 MB, 256 MiB) copied, 5,84305 s, 45,9 MB/s
On Tue, May 31, 2016 at 5:15 PM, Alan Stern wrote:
> On Tue, 31 May 2016, Michael Schaller wrote:
>
>> Is there anything else I can do to debug this issue further?
>> Are there any quirks I could try?
&
:
> On Fri, 17 Jun 2016, Michael Schaller wrote:
>
>> Alan, here is the requested information. Sorry for the delay.
>>
>> Started usbmon log with no connected USB devices:
>> $ sudo cat /sys/kernel/debug/usb/usbmon/0u | tee usbmon.txt
>> ...
>>
>> S
MB/s (~1/6th).
If someone is interested into digging deeper into this issue I can
look into shipping one of these flash drives...
On Fri, Jun 17, 2016 at 8:30 PM, Michael Schaller wrote:
> Greg, for my initial tests I did a sync afterwards and it finished
> immediately on Linux and Mac OS X.
:30:47PM +0200, Michael Schaller wrote:
>> Greg, for my initial tests I did a sync afterwards and it finished
>> immediately on Linux and Mac OS X. Sorry for not mentioning that
>> earlier.
>
> That's really odd, and is not normal for either OS.
>
>> Furthermor
Great tip, Alan. I'll look into capturing USB traffic with Wireshark
as well. Both fio and Wireshark should be available for Linux and
Windows.
On Fri, Jun 17, 2016 at 10:11 PM, Alan Stern wrote:
> On Fri, 17 Jun 2016, Michael Schaller wrote:
>
>> Alan, thank you for the ana
