Hi Guys
I *think* this card is not that bad.
********************************************** **** Lexar mobile microSDHC class 6, 8 GB **** **********************************************
==> /sys/block/mmcblk0/device/cid <== 0941502020202020102180020900b400
==> /sys/block/mmcblk0/device/csd <== 400e00325b5900003bad7f800a400000
==> /sys/block/mmcblk0/device/scr <== 0235800000000000
==> /sys/block/mmcblk0/device/fwrev <== 0x0
==> /sys/block/mmcblk0/device/hwrev <== 0x1
==> /sys/block/mmcblk0/device/cid <== 0941502020202020102180020900b400
==> /sys/block/mmcblk0/device/manfid <== 0x000009
==> /sys/block/mmcblk0/device/oemid <== 0x4150
==> /sys/block/mmcblk0/device/serial <== 0x21800209
==> /sys/block/mmcblk0/device/erase_size <== 512
==> /sys/block/mmcblk0/device/preferred_erase_size <== 4194304
==> /sys/block/mmcblk0/device/name <==
==> /sys/block/mmcblk0/device/date <== 04/2011 clock: 33000000 Hz vdd: 20 (3.2 ~ 3.3 V) bus mode: 2 (push-pull) chip select: 0 (don't care) power mode: 2 (on) bus width: 2 (4 bits) timing spec: 2 (sd high-speed)
./flashbench -a /dev/sda3 --count=100 --blocksize=2048 align 134217728 pre 744µs on 982µs post 863µs diff 178µs align 67108864 pre 744µs on 981µs post 861µs diff 178µs align 33554432 pre 743µs on 967µs post 862µs diff 165µs align 16777216 pre 742µs on 970µs post 866µs diff 166µs align 8388608 pre 744µs on 974µs post 862µs diff 171µs align 4194304 pre 746µs on 961µs post 865µs diff 156µs align 2097152 pre 744µs on 855µs post 863µs diff 51.3µs align 1048576 pre 744µs on 854µs post 867µs diff 48.1µs align 524288 pre 743µs on 855µs post 868µs diff 50.1µs align 262144 pre 744µs on 855µs post 867µs diff 49.6µs align 131072 pre 744µs on 862µs post 865µs diff 57.1µs align 65536 pre 745µs on 867µs post 860µs diff 64.9µs align 32768 pre 744µs on 870µs post 867µs diff 64.3µs align 16384 pre 743µs on 868µs post 863µs diff 64.5µs align 8192 pre 742µs on 868µs post 864µs diff 64.8µs align 4096 pre 744µs on 865µs post 867µs diff 59.3µs
-> 4MiB erase block
./flashbench /dev/sda3 --open-au-nr=5 -O --blocksize=2048 4MiB 8.69M/s 2MiB 5.31M/s 1MiB 11M/s 512KiB 11M/s 256KiB 10.8M/s 128KiB 10.5M/s 64KiB 10.4M/s 32KiB 9.19M/s 16KiB 7.25M/s 8KiB 4.43M/s 4KiB 2.26M/s 2KiB 1.16M/s
./flashbench /dev/sda3 --open-au-nr=6 -O --blocksize=2048 4MiB 8.78M/s 2MiB 3.95M/s 1MiB 1.71M/s 512KiB 969K/s 256KiB 487K/s
-> deals well with 5 blocks
./flashbench /dev/sda3 --open-au-nr=5 -O --blocksize=2048 --random 4MiB 8.09M/s 2MiB 8.24M/s 1MiB 10.1M/s 512KiB 9.9M/s 256KiB 9.34M/s 128KiB 8.49M/s 64KiB 9.02M/s 32KiB 7.27M/s 16KiB 5.2M/s 8KiB 3.02M/s 4KiB 1.19M/s 2KiB 582K/s
./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
-> looks quite fair enough also on random access
./flashbench /dev/sda3 --open-au-nr=5 -O --blocksize=2048 --random --offset=$[123 * 512] 4MiB 4.49M/s 2MiB 2.28M/s 1MiB 2.27M/s 512KiB 2.23M/s 256KiB 2.19M/s 128KiB 2.13M/s 64KiB 2.1M/s 32KiB 1.34M/s 16KiB 756K/s 8KiB 398K/s 4KiB 206K/s
-> unaligned quite slow
peter
On Tuesday 12 July 2011, Peter Warasin wrote:
Hi Guys
I *think* this card is not that bad.
Yes, looks pretty good. For completeness, please also
* list size in KB (from /proc/partitions/ or fdisk -lu) * make sure that the cutoff number for --random is the same * for cards that don't do --random (not this one), also check if there is a FAT optimization (--find-fat --erasesize=xxx)
==> /sys/block/mmcblk0/device/manfid <== 0x000009
==> /sys/block/mmcblk0/device/oemid <== 0x4150
Ok, so the manufacturer id is '9', haven't seen that before. Oemid 'AP' does not remind me of any name I've heard before either, I wonder what it means. In most cards, the ASCII value of the OEMID is whoever made the controller (SD - sandisk, SM - samsung, AD - adata, PA - panasonic, ...)
./flashbench /dev/sda3 --open-au-nr=5 -O --blocksize=2048 4MiB 8.69M/s 2MiB 5.31M/s 1MiB 11M/s 512KiB 11M/s 256KiB 10.8M/s 128KiB 10.5M/s 64KiB 10.4M/s 32KiB 9.19M/s 16KiB 7.25M/s 8KiB 4.43M/s 4KiB 2.26M/s 2KiB 1.16M/s
I would guess that the page size for this is 8KB based on these numbers.
./flashbench /dev/sda3 --open-au-nr=6 -O --blocksize=2048 4MiB 8.78M/s 2MiB 3.95M/s 1MiB 1.71M/s 512KiB 969K/s 256KiB 487K/s
-> deals well with 5 blocks
Ok.
./flashbench /dev/sda3 --open-au-nr=5 -O --blocksize=2048 --random 4MiB 8.09M/s 2MiB 8.24M/s 1MiB 10.1M/s 512KiB 9.9M/s 256KiB 9.34M/s 128KiB 8.49M/s 64KiB 9.02M/s 32KiB 7.27M/s 16KiB 5.2M/s 8KiB 3.02M/s 4KiB 1.19M/s 2KiB 582K/s
./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
-> looks quite fair enough also on random access
Yes, very good in fact.
./flashbench /dev/sda3 --open-au-nr=5 -O --blocksize=2048 --random --offset=$[123 * 512] 4MiB 4.49M/s 2MiB 2.28M/s 1MiB 2.27M/s 512KiB 2.23M/s 256KiB 2.19M/s 128KiB 2.13M/s 64KiB 2.1M/s 32KiB 1.34M/s 16KiB 756K/s 8KiB 398K/s 4KiB 206K/s
-> unaligned quite slow
The 123*512 is extremely unaligned. In general you can also try half the erasesize as an offset here, i.e. '--offset=$[2048 * 1024]'. If the erasesize is correct, it should be slower.
Arnd
hi
On 12/07/11 17:45, Arnd Bergmann wrote:
Yes, looks pretty good. For completeness, please also
- list size in KB (from /proc/partitions/ or fdisk -lu)
i dd'd first 512bytes from my sd card in mmc reader where i have /var and swap of the running system to this test card which i tested with a usb-adapter, so i did not use the entire size, because the mmc card is only 4GB and test card 8GB. but i guess this makes no difference, since i only use the 3rd partition for tests.
root@host-3u9ak0vmgb:~ # fdisk -lu /dev/sda You must set cylinders. You can do this from the extra functions menu.
Disk /dev/sda: 0 MB, 0 bytes 128 heads, 32 sectors/track, 0 cylinders, total 0 sectors Units = sectors of 1 * 512 = 512 bytes Disk identifier: 0x00000000
Device Boot Start End Blocks Id System /dev/sda1 1 614399 307199+ 83 Linux /dev/sda2 614400 819199 102400 83 Linux /dev/sda3 819200 1851391 516096 82 Linux swap / Solaris /dev/sda4 1851392 7364607 2756608 83 Linux Partition 4 has different physical/logical endings: phys=(1023, 127, 32) logical=(1797, 127, 32)
- make sure that the cutoff number for --random is the same
you mean where the throughput starts to begin worse, that this is the same for linear and random?
- for cards that don't do --random (not this one), also check if there is a FAT optimization (--find-fat --erasesize=xxx)
ok.
peter
On Tuesday 12 July 2011, Peter Warasin wrote:
hi
On 12/07/11 17:45, Arnd Bergmann wrote:
Yes, looks pretty good. For completeness, please also
- list size in KB (from /proc/partitions/ or fdisk -lu)
i dd'd first 512bytes from my sd card in mmc reader where i have /var and swap of the running system to this test card which i tested with a usb-adapter, so i did not use the entire size, because the mmc card is only 4GB and test card 8GB. but i guess this makes no difference, since i only use the 3rd partition for tests.
root@host-3u9ak0vmgb:~ # fdisk -lu /dev/sda You must set cylinders. You can do this from the extra functions menu.
Disk /dev/sda: 0 MB, 0 bytes 128 heads, 32 sectors/track, 0 cylinders, total 0 sectors Units = sectors of 1 * 512 = 512 bytes Disk identifier: 0x00000000
Device Boot Start End Blocks Id System /dev/sda1 1 614399 307199+ 83 Linux /dev/sda2 614400 819199 102400 83 Linux /dev/sda3 819200 1851391 516096 82 Linux swap / Solaris /dev/sda4 1851392 7364607 2756608 83 Linux Partition 4 has different physical/logical endings: phys=(1023, 127, 32) logical=(1797, 127, 32)
This looks strange, it has not actually reported the size, just '0 sectors' above, and as you mentioned the last partition does not end at the end of the drive.
- make sure that the cutoff number for --random is the same
you mean where the throughput starts to begin worse, that this is the same for linear and random?
For most cards it's the same number for linear and random, but for some cards, one of the two is larger. The FlashCardSurvey lists both numbers, so you can see the few exceptions.
Arnd
hi
On 12/07/11 18:20, Arnd Bergmann wrote:
This looks strange, it has not actually reported the size, just '0 sectors' above, and as you mentioned the last partition does not end at the end of the drive.
sorry, that's my fault i already used the card for testing our platform when you asked for the partition table, so i copied (dd) it over again but did no re-sync removed/readded usb adapter and it is fine now:
fdisk -lu /dev/sda
Disk /dev/sda: 8010 MB, 8010072064 bytes 128 heads, 32 sectors/track, 3819 cylinders, total 15644672 sectors Units = sectors of 1 * 512 = 512 bytes Disk identifier: 0x00000000
Device Boot Start End Blocks Id System /dev/sda1 1 1368063 684031+ 83 Linux /dev/sda2 1368064 1572863 102400 83 Linux /dev/sda3 1572864 2605055 516096 82 Linux swap / Solaris /dev/sda4 2605056 14868479 6131712 83 Linux
last partition does not end at end of the device because i always copy the same partition table on the various sticks.
do you prefer actually to partition from scratch? should not make any difference, does it?
peter
On Wednesday 13 July 2011, Peter Warasin wrote:
fdisk -lu /dev/sda
Disk /dev/sda: 8010 MB, 8010072064 bytes 128 heads, 32 sectors/track, 3819 cylinders, total 15644672 sectors Units = sectors of 1 * 512 = 512 bytes Disk identifier: 0x00000000
Device Boot Start End Blocks Id System /dev/sda1 1 1368063 684031+ 83 Linux /dev/sda2 1368064 1572863 102400 83 Linux /dev/sda3 1572864 2605055 516096 82 Linux swap / Solaris /dev/sda4 2605056 14868479 6131712 83 Linux
last partition does not end at end of the device because i always copy the same partition table on the various sticks.
do you prefer actually to partition from scratch? should not make any difference, does it?
I', not so much interested in the actual partition data, as in the total size in sectors, for putting it into the wiki.
Note however that the partition table you are showing above does not align the first partition, it starts at sector 1 when it should start at sector 8192.
Arnd
hi arnd
On 13/07/11 15:05, Arnd Bergmann wrote:
I', not so much interested in the actual partition data, as in the total size in sectors, for putting it into the wiki.
ok, then it should do :)
Note however that the partition table you are showing above does not align the first partition, it starts at sector 1 when it should start at sector 8192.
ouch. didn't know how to handle the first one. in theory it should start at 0, but that's not possible because of mbr.. ok, so i have to fix the partitioning then. thank you!
it does not affect these tests however, since i use the 3rd partition which is aligned.. right?
peter
flashbench-results@lists.linaro.org
-
Arnd Bergmann -
Peter Warasin