On Jun 02 2015, Motomura Shinichi <[email protected]> wrote:
> Before a thread (in May 2015), below strange output.
>
>>dd if=/dev/zero of=/some/path/speed_test.dat bs=2M count=1
> 1+0 records in
> 1+0 records out
> 2097152 bytes (2.1 MB) copied, 33.6993 s, 62.2 kB/s
>
>
> I try a check the suggestions.
>
> Check same condtions.
>
>>dd if=/dev/zero of=/mnt/data1 bs=2M count=1
> 1+0 records in
> 1+0 records out
> 2097152 bytes (2.1 MB) copied, 192.439 s, 10.9 kB/s
>
> Increase cachesize.
>
>>dd if=/dev/zero of=/mnt/data1 bs=2M count=1
> 1+0 records in
> 1+0 records out
> 2097152 bytes (2.1 MB) copied, 0.0736621 s, 28.5 MB/s
>
> Decrease bs (cacheseize 1024k).
>
>>dd if=/dev/zero of=/mnt/data1 bs=128k count=16
> 16+0 records in
> 16+0 records out
> 2097152 bytes (2.1 MB) copied, 123.385 s, 17.0 kB/s
>
> In samll cachesize, s3ql requests a number of PUT/DELETE methods to backend.
> This is not might it be slow cause?
Sorry, I do not understand the question. Could you rephrase?
Best,
-Nikolaus
--
GPG encrypted emails preferred. Key id: 0xD113FCAC3C4E599F
Fingerprint: ED31 791B 2C5C 1613 AF38 8B8A D113 FCAC 3C4E 599F
»Time flies like an arrow, fruit flies like a Banana.«
--
You received this message because you are subscribed to the Google Groups
"s3ql" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
