On Monday 18 July 2011, Peter Warasin wrote:
On 14/07/11 14:06, Arnd Bergmann wrote:
To follow up on this, the two tests you posted from the Lexar 8 GB cards (class 4 and 6) show almost identical results, which is highly unusual.
really those 2 cards? or do you mean class 6 8Gb and 16Gb? because on higher nr of blocks numbers vary much on these 2. class6 is imho way better than class4.
The 16GB class 6 has the same manfid as the 8GB class 4, I expect them to be quite similar.
For the class4 card, you have listed
$ ./flashbench /dev/sda3 --open-au-nr=5 -O --blocksize=2048 --random 4MiB 10.7M/s 2MiB 10.5M/s 1MiB 10.5M/s 512KiB 10.2M/s 256KiB 9.75M/s 128KiB 9.67M/s 64KiB 9.54M/s 32KiB 7.59M/s 16KiB 5.5M/s 8KiB 3.19M/s 4KiB 1.25M/s 2KiB 613K/s
and for the class 6 card
./flashbench /dev/sda3 --open-au-nr=5 -O --blocksize=2048 --random 4MiB 10.2M/s 2MiB 9.95M/s 1MiB 10.1M/s 512KiB 9.89M/s 256KiB 9.7M/s 128KiB 9.3M/s 64KiB 9.07M/s 32KiB 7.31M/s 16KiB 5.21M/s 8KiB 3.02M/s 4KiB 1.2M/s 2KiB 584K/s
The numbers are all very close. If anything, the class 4 performs slightly better except that it hangs at some point, but that might not be an unrelated problem.
- You accidentally measured the same card twice and one of the two test runs you posted does not match the card. Can you look again to be sure that the results are matching up? In particular, the size is normally different for every new controller.
the number of sector are really the same on both cards. re-did a test with class4 card and those numbers are correct. the class6 card was the best so far, we do product tests with it, so i can't redo the tests, only thing i can tell now is that fdisk tells the same size
ok.
Arnd