John Carter wrote, On 02/03/09 13:29:
1) Is that on a EEE 901 or an Acer Aspire?

An eee 901, originally an XP model so it has 12 GB total not 20 GB.

2) Flash write speeds are (I believe) lot slower than reads... but for
flash wear reasons it's probably not a Good Idea to do extensive
testing. :-) ie. The write speed may dominate. Flash devices are
weird, they tend to have odd size pages and different size pages in
different parts of their address range.

Well this is bizarre....

time dd if=/dev/zero of=/file.dd  bs=16k count=16k
produces a 256 MB file.

onto sda (4GB) that took 11.34 seconds (27.9 MB/sec)
However onto sdb it took 55.93 seconds (4.8 MB/sec)
So you might be onto something here.

time dd if=/dev/zero of=/file.dd  bs=8k count=64k
sda     39.2 sec   13.7 MB/sec
sdb     77.2 sec    6.9 MB/sec

Weird.

3) You're doing buffered testing, you probably want "hdparm -t" not
"hdparm -T".

I actually did hdparm -Tt then got rid of the other line, because its not really relevant. Just edited out the wrong parameter :)

4) I can't think where I got the notion that the 4gb was faster... but
I got the impression the author knew something about it. I'll post the
link if I find it again.

Yes, I remember that info too... maybe the first gen 900 etc had slower flash on the second SSD.




--
Craig Falconer

Reply via email to