Jim Colton wrote:
Hi Mike,
I looked at the code your wrote. It doesn't do anything that 'time dd'
already can do.
It includes an fsync() in the timing measurement when writing the file,
and does a posix_fadvise() before reading it back (both intended to make
sure that the I/O is going to
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Somebody in the thread at some point said:
|
| Oh well, I should have bought a slower card. At least it won't be a
| limiting factor.
| I'll compare speeds I get with your 3M bytes/sec. anyway.
|
| I was meaning 12 megabits /sec
| By 12MB/s I was
Oh, I see. Good thought about flushing cache.
The speeds for read and write are different on a SD card with read being
always faster and so I was thinking to do only the read test and to have
dd(1) read directly from the device rather than going through the file
system - taking the file system
On Thu, Jul 31, 2008 at 4:11 PM, Esben Stien [EMAIL PROTECTED] wrote:
Jim Colton [EMAIL PROTECTED] writes:
in M bytes per second
Please use new SI convention, Mi (Mebi), Gi (Gibi), Ti (Tebi).
It's also a nice convention to use octects, o, instead of bytes, as
bytes are not always 8 bits.
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Somebody in the thread at some point said:
| Hey Tim,
|
| no it's not overkill or no is the glamo driver able to read that
fast?
| Are you involved with or knowledgeable of how the glamo drive works?
| I'm not.
I have that not very marketable
On 30 Jul 2008, at 20:05, Andy Green wrote:
...
We read from it at 16MHz / 4 bits, so not sure where this 12MBytes/sec
figure came from.
I think it's the figure printed on the SD card that the OP is
considering buying.
I think this is obvious if you read the subject line, but not if you
If anyone cares this is the card I have coming and will speed test by using
dd(1) from the device to dev/null. But as Tim said the bus speed the Glamo
willbe limiting.
http://www.memorysuppliers.com/atp-fmcs-atp-microsd-af4gud-ap-with-adapter.html
Jim
On Wed, Jul 30, 2008 at 3:07 PM, Jim Colton
Hi Mike,
I looked at the code your wrote. It doesn't do anything that 'time dd'
already can do.
Thanks anyway.
On Wed, Jul 30, 2008 at 8:10 PM, Mike Montour [EMAIL PROTECTED] wrote:
Jim Colton wrote:
If anyone cares this is the card I have coming and will speed test by
using dd(1) from