1 |
On Sun, Dec 27, 2009 at 1:57 PM, Paul Hartman |
2 |
<paul.hartman+gentoo@×××××.com> wrote: |
3 |
> On Sun, Dec 27, 2009 at 1:46 PM, Paul Hartman |
4 |
> <paul.hartman+gentoo@×××××.com> wrote: |
5 |
>> On Sun, Dec 27, 2009 at 12:10 PM, Paul Hartman |
6 |
>> <paul.hartman+gentoo@×××××.com> wrote: |
7 |
>>> On Sun, Dec 27, 2009 at 12:01 AM, Michael Holmes |
8 |
>>> <holmesmich@××××××××××.com> wrote: |
9 |
>>>> 2009/12/27 Paul Hartman <paul.hartman+gentoo@×××××.com>: |
10 |
>>>>> On Sat, Dec 26, 2009 at 7:00 PM, Hung Dang <hungptit@×××××.com> wrote: |
11 |
>>>>>> On 12/26/09 15:54, Paul Hartman wrote: |
12 |
>>>>>>> Hi, |
13 |
>>>>>>> |
14 |
>>>>>>> I got a Nokia N900 linux internet tablet/phone a few days ago, and |
15 |
>>>>>>> when I connect it in USB Mass Storage mode to a Windows Vista computer |
16 |
>>>>>>> I can write at 17MB/sec, but when I connect it to my Gentoo box my |
17 |
>>>>>>> writes are really slow, between 500-900kb/sec depending on if I mount |
18 |
>>>>>>> in "sync" mode or not. As far as I know it should be just a totally |
19 |
>>>>>>> standard/generic mass storage device. (there were no drivers or |
20 |
>>>>>>> software install needed in windows, it just worked) |
21 |
>>>>>>> |
22 |
>>>>>>> Other USB devices plugged into the same port go full speed, and AFAIK |
23 |
>>>>>>> everything appears as if it should be high speed USB 2.0. Has anyone |
24 |
>>>>>>> seen something like this before? I'm not sure what the deal is. It |
25 |
>>>>>>> takes 20 minutes to copy 1 gigabyte from Linux and takes just under 1 |
26 |
>>>>>>> minute to do the same in Windows. |
27 |
>>>>>>> |
28 |
>>>>>>> I'm not sure about debugging USB or what the options are. Everything |
29 |
>>>>>>> I've used previously has worked without any hassle. |
30 |
>>>>>> Have you received a lot of debugging messages at the output of dmesg |
31 |
>>>>>> when copying files? |
32 |
>>>>>> |
33 |
>>>>>> Hung |
34 |
>>>>> |
35 |
>>>>> No errors, no strange messages at all, it seems normal (only slow). I |
36 |
>>>>> have other USB devices like SD card reader, external HDD, and they |
37 |
>>>>> perform at full speed when plugged into the same port, so it's weird |
38 |
>>>>> to me. |
39 |
>>>>> |
40 |
>>>>> Thanks |
41 |
>>>>> Paul |
42 |
>>>>> |
43 |
>>>>> |
44 |
>>>> |
45 |
>>>> This isn't that helpful, but in Windows I get good thoroughputs in |
46 |
>>>> mass storage mode, but compartively weak ones in sync mode. But this |
47 |
>>>> shouldn't be the problem because as far as I know, there are no |
48 |
>>>> ync-mode drivers for good old Linux (which is ironic if you consider |
49 |
>>>> it). |
50 |
>>> |
51 |
>>> When I said "sync" mode I mean mounting the device in mass storage |
52 |
>>> mode with with "-o sync" (as opposed to the default cached/async |
53 |
>>> mode), which I believe is the default in Windows Vista & Win7 (because |
54 |
>>> most windows users cannot be bothered to unmount before pulling the |
55 |
>>> plug). |
56 |
>>> |
57 |
>>> Thanks |
58 |
>> |
59 |
>> Well, after a bit more plugging/unplugging of all my USB devices into |
60 |
>> various ports in different orders, it seems to be going fast now. I |
61 |
>> hate USB :) |
62 |
>> |
63 |
>> Thanks for the help |
64 |
> |
65 |
> Maybe I spoke too soon. It seems what's happening is when I write a |
66 |
> large amount of data, there are several "pdflush" threads at near 100% |
67 |
> i/o wait. I'm thinking it's writing multiple streams over USB which is |
68 |
> causing the massive slow-down. |
69 |
> |
70 |
> I'm using 2.6.31, and I see in 2.6.32 there is something called |
71 |
> "Per-backing-device based writeback" which may help me here... I'll |
72 |
> try the new kernel and report back :) |
73 |
|
74 |
There is a slight improvement but it's still very slow (less than |
75 |
2MB/sec). It seems the problem happens if I try to copy more than 1 |
76 |
file to the device. If I copy/sync/copy/sync/copy/sync etc it goes |
77 |
faster, but that's extremely annoying! |