Flashbench-results

flashbench-results@lists.linaro.org

3 participants
651 discussions

Kingston microSD 2 GB (2010 model)

by Arnd Bergmann

$ head /sys/block/mmcblk0/device/{c*,scr,*rev,*id,serial,*size,name,date} ==> /sys/block/mmcblk0/device/cid <== 02544d534130324705200a985700a700 ==> /sys/block/mmcblk0/device/csd <== 002e00325b5aa3acffffff800a800000 ==> /sys/block/mmcblk0/device/scr <== 0225800001000000 ==> /sys/block/mmcblk0/device/fwrev <== 0x5 ==> /sys/block/mmcblk0/device/hwrev <== 0x0 ==> /sys/block/mmcblk0/device/cid <== 02544d534130324705200a985700a700 ==> /sys/block/mmcblk0/device/manfid <== 0x000002 ==> /sys/block/mmcblk0/device/oemid <== 0x544d ==> /sys/block/mmcblk0/device/serial <== 0x200a9857 ==> /sys/block/mmcblk0/device/erase_size <== 512 ==> /sys/block/mmcblk0/device/preferred_erase_size <== 4194304 ==> /sys/block/mmcblk0/device/name <== SA02G ==> /sys/block/mmcblk0/device/date <== 07/2010 $ sudo ./flashbench -a /dev/mmcblk0 --blocksize 1024 --count=50 [sudo] password for arnd: align 268435456 pre 1.45ms on 2.14ms post 1.19ms diff 819µs align 134217728 pre 1.77ms on 2.39ms post 1.26ms diff 874µs align 67108864 pre 1.78ms on 2.16ms post 1.19ms diff 677µs align 33554432 pre 1.77ms on 2.17ms post 1.21ms diff 680µs align 16777216 pre 1.58ms on 2.18ms post 1.21ms diff 788µs align 8388608 pre 1.26ms on 2.13ms post 1.21ms diff 900µs align 4194304 pre 1.3ms on 2.16ms post 1.21ms diff 911µs align 2097152 pre 1.5ms on 2.16ms post 1.18ms diff 822µs align 1048576 pre 1.21ms on 1.41ms post 1.24ms diff 186µs align 524288 pre 1.21ms on 1.27ms post 1.21ms diff 60.4µs align 262144 pre 1.21ms on 1.27ms post 1.21ms diff 59.3µs align 131072 pre 1.21ms on 1.27ms post 1.21ms diff 59.2µs align 65536 pre 1.21ms on 1.27ms post 1.21ms diff 59.2µs align 32768 pre 1.21ms on 1.27ms post 1.21ms diff 60.3µs align 16384 pre 1.22ms on 1.27ms post 1.21ms diff 57.8µs align 8192 pre 1.21ms on 1.28ms post 1.21ms diff 61.7µs align 4096 pre 1.21ms on 1.26ms post 1.21ms diff 41.6µs align 2048 pre 1.21ms on 1.26ms post 1.21ms diff 41.1µs $ sudo ./flashbench --findfat --fat-nr=4 /dev/mmcblk0 --blocksize=1024 --erasesize=$[2* 1024 * 1024] 2MiB 2.33M/s 4.67M/s 9.32M/s 9.57M/s 1MiB 3.4M/s 9.49M/s 9.31M/s 9.59M/s 512KiB 3.41M/s 9.54M/s 9.57M/s 9.51M/s 256KiB 4.95M/s 9.73M/s 9.63M/s 9.62M/s 128KiB 5.79M/s 9.76M/s 9.64M/s 9.72M/s 64KiB 6.04M/s 9.59M/s 9.9M/s 9.85M/s 32KiB 4.35M/s 8.92M/s 8.82M/s 8.87M/s 16KiB 2.98M/s 7.23M/s 7.25M/s 7.31M/s 8KiB 1.68M/s 4.67M/s 4.59M/s 4.62M/s 4KiB 847K/s 1.45M/s 1.56M/s 1.55M/s 2KiB 431K/s 726K/s 715K/s 736K/s 1KiB 218K/s 137K/s 137K/s 126K/s $ sudo ./flashbench --findfat --fat-nr=4 /dev/mmcblk0 --blocksize=4096 --erasesize=$[2* 1024 * 1024] --random 2MiB 2.3M/s 9.48M/s 9.29M/s 9.22M/s 1MiB 3.42M/s 5.89M/s 3.01M/s 3M/s 512KiB 4.51M/s 2.03M/s 1.85M/s 1.82M/s 256KiB 4.89M/s 1.32M/s 1.31M/s 1.31M/s 128KiB 4.93M/s 696K/s 696K/s 694K/s 64KiB 5.58M/s 850K/s 853K/s 849K/s 32KiB 4.56M/s 325K/s 326K/s 327K/s ^C $ sudo ./flashbench --open-au --open-au-nr=1 /dev/mmcblk0 --erasesize=$[2 * 1024 * 1024] --blocksize=1024 2MiB 8.25M/s 1MiB 2.65M/s 512KiB 2.67M/s 256KiB 2.67M/s 128KiB 4.16M/s 64KiB 9.48M/s 32KiB 8.56M/s 16KiB 6.59M/s 8KiB 4M/s 4KiB 1.32M/s 2KiB 544K/s 1KiB 14.1K/s (!!!) $ sudo ./flashbench --open-au --open-au-nr=1 /dev/mmcblk0 --erasesize=$[4 * 1024 * 1024] --blocksize=1024 4MiB 9.37M/s 2MiB 4.17M/s 1MiB 4.17M/s 512KiB 4.17M/s 256KiB 4.17M/s 128KiB 5.8M/s 64KiB 9.54M/s 32KiB 8.47M/s 16KiB 6.5M/s 8KiB 3.94M/s 4KiB 1.26M/s 2KiB 538K/s ^C $ sudo ./flashbench --open-au --open-au-nr=2 /dev/mmcblk0 --erasesize=$[2 * 1024 * 1024] --blocksize=1024 2MiB 5.82M/s 1MiB 3.62M/s 512KiB 1.43M/s 256KiB 658K/s 128KiB 318K/s 64KiB 232K/s ^C $ sudo ./flashbench --open-au --open-au-nr=2 /dev/mmcblk0 --erasesize=$[4 * 1024 * 1024] --blocksize=1024 4MiB 8.52M/s 2MiB 5.78M/s 1MiB 2.79M/s 512KiB 1.34M/s 256KiB 639K/s 128KiB 314K/s 64KiB 233K/s 32KiB 116K/s ^C

15 years

Sandisk white label 2GB (from Versatile Express board)

by Arnd Bergmann

This is the first Sandisk Card that I've seen that does not have any optimizations for random access. It's particularly bad since this card was specifically shipped with a Linux box for the purpose of installing Debian on it. The label says "15 MB/s read, 7 MB/s write". Arnd --- $ head /sys/block/mmcblk0/device/{c*,scr,*rev,*id,serial,*size} ==> /sys/block/mmcblk0/device/cid <== 035344534430324780019b8975009b00 ==> /sys/block/mmcblk0/device/csd <== 002600325f5a83aefefbcfff92804000 ==> /sys/block/mmcblk0/device/scr <== 0225000000000000 ==> /sys/block/mmcblk0/device/fwrev <== 0x0 ==> /sys/block/mmcblk0/device/hwrev <== 0x8 ==> /sys/block/mmcblk0/device/cid <== 035344534430324780019b8975009b00 ==> /sys/block/mmcblk0/device/manfid <== 0x000003 ==> /sys/block/mmcblk0/device/oemid <== 0x5344 ==> /sys/block/mmcblk0/device/serial <== 0x019b8975 ==> /sys/block/mmcblk0/device/erase_size <== 512 ==> /sys/block/mmcblk0/device/preferred_erase_size <== 4194304 $ sudo ./flashbench -a /dev/mmcblk0 --blocksize 1024 --count=50 align 268435456 pre 896µs on 1.14ms post 697µs diff 345µs align 134217728 pre 671µs on 983µs post 641µs diff 327µs align 67108864 pre 748µs on 1.02ms post 615µs diff 336µs align 33554432 pre 615µs on 699µs post 582µs diff 99.9µs align 16777216 pre 671µs on 807µs post 634µs diff 154µs align 8388608 pre 759µs on 822µs post 698µs diff 93.2µs align 4194304 pre 716µs on 822µs post 692µs diff 118µs align 2097152 pre 745µs on 824µs post 701µs diff 101µs align 1048576 pre 633µs on 662µs post 669µs diff 11.5µs align 524288 pre 636µs on 668µs post 656µs diff 22µs align 262144 pre 630µs on 673µs post 657µs diff 29.6µs align 131072 pre 629µs on 673µs post 661µs diff 28.4µs align 65536 pre 640µs on 670µs post 665µs diff 17.2µs align 32768 pre 629µs on 671µs post 667µs diff 23.1µs align 16384 pre 618µs on 664µs post 658µs diff 25.5µs align 8192 pre 643µs on 643µs post 637µs diff 3.5µs align 4096 pre 657µs on 661µs post 645µs diff 10.1µs align 2048 pre 661µs on 669µs post 656µs diff 10.8µs $ sudo ./flashbench --open-au --open-au-nr=1 /dev/mmcblk0 --erasesize=$[2 * 1024 * 1024] --blocksize=1024 --random 2MiB 11.1M/s 1MiB 3.72M/s 512KiB 3.26M/s 256KiB 1.38M/s 128KiB 1.89M/s 64KiB 1.43M/s 32KiB 918K/s 16KiB 350K/s 8KiB 1.16M/s 4KiB 542K/s 2KiB 254K/s 1KiB 121K/s sudo ./flashbench --open-au --open-au-nr=1 /dev/mmcblk0 --erasesize=$[2 * 1024 * 1024] --blocksize=1024 2MiB 6.91M/s 1MiB 6.1M/s 512KiB 6.06M/s 256KiB 6.11M/s 128KiB 6.39M/s 64KiB 12.1M/s 32KiB 9.97M/s 16KiB 6.74M/s 8KiB 3.66M/s 4KiB 2.04M/s 2KiB 945K/s 1KiB 461K/s $ sudo ./flashbench --open-au --open-au-nr=6 /dev/mmcblk0 --erasesize=$[2 * 1024 * 1024] --blocksize=1024 --random 2MiB 11.5M/s 1MiB 10.1M/s 512KiB 7.91M/s 256KiB 3M/s 128KiB 2.2M/s 64KiB 1.21M/s 32KiB 645K/s 16KiB 310K/s 8KiB 176K/s 4KiB 86.8K/s ^C $ sudo ./flashbench --open-au --open-au-nr=6 /dev/mmcblk0 --erasesize=$[2 * 1024 * 1024] --blocksize=1024 2MiB 9.79M/s 1MiB 11.7M/s 512KiB 11.9M/s 256KiB 11.8M/s 128KiB 11.7M/s 64KiB 11.8M/s 32KiB 9.77M/s 16KiB 6.64M/s 8KiB 4.13M/s 4KiB 2M/s 2KiB 929K/s 1KiB 445K/s $ sudo ./flashbench --open-au --open-au-nr=7 /dev/mmcblk0 --erasesize=$[2 * 1024 * 1024] --blocksize=1024 --random 2MiB 12M/s 1MiB 6.1M/s 512KiB 3.23M/s 256KiB 1.55M/s 128KiB 772K/s 64KiB 384K/s 32KiB 192K/s 16KiB 95.8K/s 8KiB 47.7K/s ^C $ sudo ./flashbench --open-au --open-au-nr=7 /dev/mmcblk0 --erasesize=$[2 * 1024 * 1024] --blocksize=1024 2MiB 11M/s 1MiB 7.75M/s 512KiB 3.2M/s 256KiB 1.54M/s 128KiB 768K/s 64KiB 384K/s ^C $ sudo ./flashbench --findfat --fat-nr=4 /dev/mmcblk0 --blocksize=1024 --erasesize=$[2* 1024 * 1024] --random 2MiB 11.9M/s 12M/s 11.7M/s 12M/s 1MiB 5.54M/s 5.69M/s 5.11M/s 7.73M/s 512KiB 7.08M/s 4.65M/s 4.35M/s 4.35M/s 256KiB 6.98M/s 2.26M/s 2.27M/s 2.26M/s 128KiB 7.98M/s 5.47M/s 5.48M/s 5.47M/s 64KiB 8.4M/s 5.62M/s 5.57M/s 5.45M/s 32KiB 7.16M/s 4.89M/s 4.94M/s 4.83M/s 16KiB 5.3M/s 2.32M/s 2.32M/s 2.27M/s 8KiB 2.31M/s 2.33M/s 2.33M/s 2.33M/s 4KiB 943K/s 945K/s 942K/s 944K/s 2KiB 411K/s 408K/s 410K/s 410K/s 1KiB 190K/s 187K/s 192K/s 192K/s

15 years

Results for danelec 16G class 4 micro SD card manfid 0x000002 oemid 0x544d

by Tim Small

root@netboot:~# (cd /sys/block/mmcblk0/device/ ; for i in * ; do if [ -f $i ] ; then echo -n "$i: " ; cat $i ; fi ; done) cid: 02544d534431364760dcbf359a00a800 csd: 400e00325b590000777f7f800a400000 date: 08/2010 fwrev: 0x0 hwrev: 0x6 manfid: 0x000002 name: SD16G oemid: 0x544d scr: 02b5800026027102 serial: 0xdcbf359a type: SD uevent: DRIVER=mmcblk MMC_TYPE=SD MMC_NAME=SD16G MODALIAS=mmc:block root@netboot:~# ~/flashbench/flashbench -a /dev/mmcblk0 --blocksize=1024 align 536870912 pre 838µs on 1.12ms post 960µs diff 222µs align 268435456 pre 859µs on 1.09ms post 955µs diff 186µs align 134217728 pre 860µs on 1.1ms post 957µs diff 196µs align 67108864 pre 861µs on 1.11ms post 957µs diff 203µs align 33554432 pre 860µs on 1.11ms post 960µs diff 197µs align 16777216 pre 861µs on 1.11ms post 953µs diff 203µs align 8388608 pre 859µs on 1.11ms post 961µs diff 198µs align 4194304 pre 863µs on 1.1ms post 925µs diff 211µs align 2097152 pre 862µs on 1.11ms post 965µs diff 199µs align 1048576 pre 954µs on 978µs post 970µs diff 15.8µs align 524288 pre 951µs on 977µs post 973µs diff 14.8µs align 262144 pre 947µs on 977µs post 967µs diff 19.8µs align 131072 pre 947µs on 983µs post 969µs diff 25.5µs align 65536 pre 951µs on 981µs post 956µs diff 26.9µs align 32768 pre 948µs on 977µs post 963µs diff 21.6µs align 16384 pre 950µs on 978µs post 950µs diff 27.7µs align 8192 pre 963µs on 960µs post 963µs diff -3106ns align 4096 pre 962µs on 969µs post 956µs diff 10.1µs align 2048 pre 963µs on 953µs post 951µs diff -3893ns >From which I guess 2M erase block size. Not sure how to interpret the last 4 rows. Only 1 open allocation unit by the look of the following :-( root@netboot:~# ~/flashbench/flashbench --open-au --open-au-nr=1 --erasesize=$[2 * 1024 * 1024] --blocksize=$[256 * 1024] /dev/mmcblk0 2MiB 3.68M/s 1MiB 3.16M/s 512KiB 3.06M/s 256KiB 3.33M/s root@netboot:~# ~/flashbench/flashbench --open-au --open-au-nr=2 --erasesize=$[2 * 1024 * 1024] --blocksize=$[256 * 1024] /dev/mmcblk0 2MiB 3.09M/s 1MiB 2.01M/s 512KiB 1.43M/s 256KiB 618K/s root@netboot:~# ~/flashbench/flashbench -f /dev/mmcblk04MiB 2.51M/s 2.46M/s 3.73M/s 3.72M/s 3.72M/s 3.72M/s 2MiB 3.7M/s 2.46M/s 3.73M/s 3.73M/s 3.72M/s 3.72M/s 1MiB 3.7M/s 2.46M/s 3.73M/s 3.74M/s 3.72M/s 3.72M/s 512KiB 3.7M/s 2.45M/s 3.72M/s 3.7M/s 3.73M/s 3.73M/s 256KiB 3.71M/s 2.63M/s 3.72M/s 3.73M/s 3.72M/s 3.72M/s 128KiB 3.71M/s 2.82M/s 3.73M/s 3.72M/s 3.72M/s 3.72M/s 64KiB 3.71M/s 3.01M/s 3.72M/s 3.72M/s 3.72M/s 3.72M/s 32KiB 3.58M/s 2.73M/s 3.57M/s 3.57M/s 3.58M/s 3.57M/s 16KiB 2.95M/s 2.25M/s 2.94M/s 2.95M/s 2.94M/s 2.95M/s The --scatter-order=<n> --scatter-span=<m> arguments are not really documented, so I didn't know how I should be using them, so I didn't. There are some strange outliers on the plot, most of which seem to end up consistently in the same place. This card has had an HD image file copied over it (with dd) prior to any of these results being generated.

15 years

Re: [Flashbench] 2.6.38: XFS/USB/HW issue, or failing USB stick?

by Arnd Bergmann

On Friday 18 March 2011 18:45:34 Justin Piszcz wrote: > On Fri, 18 Mar 2011, Arnd Bergmann wrote: > > Getting back to the rogiinal question, I'd recommend testing the > > stick by doing raw accesses instead of a file system. A simple > > Ok, here are the results: > > root@sysresccd /root % time dd if=/dev/zero of=/dev/sda oflag=direct bs=4M > dd: writing `/dev/sda': No space left on device > 1961+0 records in > 1960+0 records out > 8220835840 bytes (8.2 GB) copied, 283.744 s, 29.0 MB/s Ok, so no immediate problem there. > > I'm also interested in results from flashbench > > (git://git.linaro.org/people/arnd/flashbench.git, e.g. like > > http://lists.linaro.org/pipermail/flashbench-results/2011-March/000039.html) > > That might help explain how the stick failed. > > Certainly, testing below, following this: > http://lists.linaro.org/pipermail/flashbench-results/2011-March/000039.html I'm sorry, I should have been more specific. Unfortunately, running flashbench is not very user friendly yet. The results indicate that the device does not have a 2 MB erase block size but rather 4 or 8, which is more common on 8 GB media. > # ./flashbench --open-au --open-au-nr=1 /dev/sda --blocksize=8192 --erasesize=$[2* 1024 * 1024] --random > 2MiB 29.5M/s > 1MiB 29.1M/s > 512KiB 28.5M/s > 256KiB 22.8M/s > 128KiB 23.8M/s > 64KiB 24.4M/s > 32KiB 18.9M/s > 16KiB 13.1M/s > 8KiB 8.22M/s > > # ./flashbench --open-au --open-au-nr=4 /dev/sda --blocksize=8192 --erasesize=$[2* 1024 * 1024] --random > 2MiB 25.9M/s > 1MiB 21.8M/s > 512KiB 15M/s > 256KiB 11.9M/s > 128KiB 12.1M/s > 64KiB 13.6M/s > 32KiB 9.81M/s > 16KiB 6.41M/s > 8KiB 3.88M/s The numbers are jumping around a bit with the incorrectly guessed erasesize. These values should be more like the ones in the first test. Can you rerun with --erasesize=$[4 * 1024 * 1024]? Also, what is the output of 'lsusb' for this stick? I'd like to add the data to https://wiki.linaro.org/WorkingGroups/KernelConsolidation/Projects/FlashCar… > # ./flashbench --open-au --open-au-nr=5 /dev/sda --blocksize=8192 --erasesize=$[2* 1024 * 1024] --random > 2MiB 29.2M/s > 1MiB 27.8M/s > 512KiB 18.4M/s > 256KiB 7.82M/s > 128KiB 4.62M/s > 64KiB 2.47M/s > 32KiB 1.26M/s > 16KiB 642K/s > 8KiB 327K/s This is where your drive stops coping with the accesses: Writing small blocks to four different erase blocks (2MB for the test, probably larger) works fine, but writing to five of them is devestating for performance, going from 30 MB/s to 300 KB/s, or lower if you were to write smaller than 8 KB blocks. The cutoff at --open-au-nr=4 is coincidentally the same as for the SD card I was testing. This is what happens in the animation in http://lwn.net/Articles/428799/. The example given there is for a drive that can only have two open AUs (allocation units aka erase blocks), while yours does 4. > (did not run one with 7) Note that the test results I had with 6 and 7 are without --random, so the cut-off there was higher for that card when writing an multiple erase blocks from start to finish instead of writing random sectors inside of them. > # ./flashbench --findfat --fat-nr=10 /dev/sda --blocksize=1024 --erasesize=$[2* 1024 * 1024] --random > 2MiB 22.7M/s 19.1M/s 15.5M/s 13.1M/s 29.5M/s 29.5M/s 29.6M/s 29.6M/s 29.5M/s 29.5M/s > 1MiB 20.6M/s 13.3M/s 13.3M/s 20.8M/s 18.1M/s 17.8M/s 18M/s 18.3M/s 18.8M/s 18.6M/s > 512KiB 18.4M/s 18.6M/s 18.3M/s 18.1M/s 23.5M/s 23.2M/s 23.5M/s 23.5M/s 23.4M/s 23.4M/s > 256KiB 26.9M/s 21.3M/s 21.2M/s 21M/s 21.1M/s 21.2M/s 21.1M/s 21.1M/s 20.6M/s 21M/s > 128KiB 22.2M/s 22.3M/s 22.6M/s 21.4M/s 21.5M/s 21.3M/s 21.6M/s 21.3M/s 21.4M/s 21.4M/s > 64KiB 23.9M/s 22.6M/s 22.9M/s 23M/s 22.5M/s 22.4M/s 22.4M/s 22.4M/s 22.5M/s 22.4M/s > 32KiB 18.2M/s 18.3M/s 18.3M/s 18.3M/s 18.3M/s 18.4M/s 18.3M/s 18.2M/s 18.3M/s 18.3M/s > 16KiB 12.9M/s 12.9M/s 13M/s 13M/s 12.9M/s 13M/s 12.9M/s 12.9M/s 12.9M/s 12.9M/s > 8KiB 8.14M/s 8.15M/s 8.15M/s 8.15M/s 8.15M/s 8.14M/s 8.14M/s 8.15M/s 8.15M/s 8.06M/s > 4KiB 4.07M/s 4.08M/s 4.07M/s 4.06M/s 4.04M/s 4.04M/s 4.04M/s 4.04M/s 4.04M/s 4.04M/s > 2KiB 2.02M/s 2.02M/s 2.02M/s 2.02M/s 2.02M/s 2.01M/s 2.01M/s 2.01M/s 2.01M/s 2.02M/s > 1KiB 956K/s 954K/s 956K/s 953K/s 947K/s 947K/s 947K/s 950K/s 947K/s 948K/s > One thing that is very clear from this is that this stick has a page size of 8KB, and that it requires at least 64 KB transfers for the maximum speed. If your partition is not aligned to 8 KB or more (better: to the erase block size, e.g. 4 MB) or if the file system writes smaller than 8 KB naturally aligned blocks at once, the drive has to do read-modify-write cycles that severely impact performance and the expected life-time. I cannot see any block that is optimzied for storing the FAT, which is good, as this means that the manufacturer did not exclusively design the stick for FAT32, as is normally the case with flash memory cards. For this stick, I would strongly recommend creating the file system in a way that writes at least 16 KB naturally aligned blocks at all times, but I don't know if that's supported by XFS. Also, the limitation of forcing a garbage collection when writing to more than four 4 MB (or so) segments may be a problem, depending on how XFS stores its metadata. The good news is that it can do random write access inside of the erase blocks. Arnd

15 years

Sandisk Netbook Edition 8 GB SDHC Class 2

by Arnd Bergmann

I wanted to find out if the Sandisk Netbook Edition does anything particularly well for Netbooks. Apparently this is not the case, it's a standard Sandisk Algorithm for older cards. Well, 20€ wasted ;-) This card can write random access to 6 2MB allocation units, but does not store a lookup table, so it always needs to garbage-collect the allocation unit when it does this, making random access relatively slow. Minimum size for random-access writes is 64 KB, anything smaller seems to do 64 KB copy-on-write. As a twist, it can do random access to 4 segments, but linear access to 6 segments. $ head /sys/block/mmcblk0/device/{cid,csd,scr,*rev,*id,name,serial} ==> /sys/block/mmcblk0/device/cid <== 035344534430384780708b1879009500 ==> /sys/block/mmcblk0/device/csd <== 400e00325b5900003b377f800a404000 ==> /sys/block/mmcblk0/device/scr <== 0235000000000000 ==> /sys/block/mmcblk0/device/fwrev <== 0x0 ==> /sys/block/mmcblk0/device/hwrev <== 0x8 ==> /sys/block/mmcblk0/device/cid <== 035344534430384780708b1879009500 ==> /sys/block/mmcblk0/device/manfid <== 0x000003 ==> /sys/block/mmcblk0/device/oemid <== 0x5344 ==> /sys/block/mmcblk0/device/name <== SD08G ==> /sys/block/mmcblk0/device/serial <== 0x708b1879 $ sudo ./flashbench --open-au --open-au-nr=1 /dev/mmcblk0 --blocksize=8192 \ --erasesize=$[2* 1024 * 1024] --random 2MiB 5.34M/s 1MiB 3.01M/s 512KiB 2.39M/s 256KiB 2.34M/s 128KiB 2.37M/s 64KiB 2.31M/s 32KiB 1.69M/s 16KiB 1.69M/s 8KiB 861K/s $ sudo ./flashbench --open-au --open-au-nr=4 /dev/mmcblk0 --blocksize=8192 \--erasesize=$[2* 1024 * 1024] --random 2MiB 4.08M/s 1MiB 4.96M/s 512KiB 3.05M/s 256KiB 2.36M/s 128KiB 2.33M/s 64KiB 2.3M/s 32KiB 1.91M/s 16KiB 1.61M/s 8KiB 835K/s $ sudo ./flashbench --open-au --open-au-nr=5 /dev/mmcblk0 --blocksize=8192 \ --erasesize=$[2* 1024 * 1024] --random 2MiB 3.32M/s 1MiB 4.5M/s 512KiB 3.11M/s 256KiB 2.27M/s 128KiB 2.14M/s 64KiB 1.38M/s 32KiB 715K/s 16KiB 395K/s 8KiB 193K/s $ sudo ./flashbench --open-au --open-au-nr=6 /dev/mmcblk0 --blocksize=1024 \ --erasesize=$[2* 1024 * 1024] 2MiB 5.36M/s 1MiB 5.38M/s 512KiB 5.38M/s 256KiB 5.38M/s 128KiB 5.38M/s 64KiB 5.38M/s 32KiB 4.54M/s 16KiB 3.46M/s 8KiB 2.59M/s 4KiB 1.35M/s 2KiB 631K/s 1KiB 308K/s $ sudo ./flashbench --open-au --open-au-nr=7 /dev/mmcblk0 --blocksize=1024 --erasesize=$[2* 1024 * 1024] 2MiB 5.42M/s 1MiB 4.19M/s 512KiB 2.15M/s 256KiB 1.12M/s 128KiB 583K/s 64KiB 299K/s 32KiB 152K/s ^C $ sudo ./flashbench --findfat --fat-nr=10 /dev/mmcblk0 --blocksize=1024 --erasesize=$[2* 1024 * 1024] --random 2MiB 5.29M/s 5.37M/s 5.38M/s 3.34M/s 3.33M/s 3.35M/s 3.35M/s 3.37M/s 5.33M/s 5.37M/s 1MiB 4.3M/s 4.36M/s 4.37M/s 3.26M/s 4.36M/s 2.24M/s 3.65M/s 3.49M/s 3.67M/s 3.69M/s 512KiB 3.32M/s 3.36M/s 3.36M/s 3.19M/s 3.34M/s 3.36M/s 3.35M/s 3.35M/s 3.36M/s 3.34M/s 256KiB 3.94M/s 3.95M/s 3.91M/s 3.86M/s 3.93M/s 3.94M/s 3.8M/s 3.93M/s 3.94M/s 3.92M/s 128KiB 4.35M/s 4.35M/s 4.34M/s 4.19M/s 4.34M/s 4.35M/s 4.35M/s 4.23M/s 4.35M/s 4.35M/s 64KiB 4.47M/s 4.58M/s 4.58M/s 4.46M/s 4.56M/s 4.57M/s 4.57M/s 4.48M/s 4.56M/s 4.55M/s 32KiB 3.67M/s 3.77M/s 3.73M/s 3.7M/s 3.76M/s 3.72M/s 3.76M/s 3.72M/s 3.74M/s 3.72M/s 16KiB 2.63M/s 2.64M/s 2.65M/s 2.62M/s 2.56M/s 2.61M/s 2.62M/s 2.62M/s 2.6M/s 2.61M/s 8KiB 1.45M/s 1.47M/s 1.48M/s 1.46M/s 1.45M/s 1.46M/s 1.46M/s 1.44M/s 1.47M/s 1.47M/s 4KiB 647K/s 645K/s 643K/s 644K/s 642K/s 642K/s 638K/s 637K/s 638K/s 637K/s

15 years

Transcend ultra 2GB Industrial 'CF100BA8' hdparm

by Philippe De Muyter

Hello Arnd, Here are the hdparm and smartctl outputs for the first card I tested (Transcend ultra 2GB Industrial 'CF100BA8'). There seems to be no dma mode there, only PIO. Philippe tmp179:~ # cat /proc/partitions major minor #blocks name 8 0 244198584 sda 8 1 2103296 sda1 8 2 20972544 sda2 8 16 1990296 sdb tmp179:~ # hdparm -i /dev/sdb /dev/sdb: Model=PIO, FwRev=20100202, SerialNo=20100716 CF100BA8 Config={ HardSect NotMFM Fixed DTR>10Mbs } RawCHS=3949/16/63, TrkSize=0, SectSize=576, ECCbytes=4 BuffType=DualPort, BuffSize=1kB, MaxMultSect=1, MultSect=off CurCHS=3949/16/63, CurSects=3980592, LBA=yes, LBAsects=3980592 IORDY=no, tPIO={min:120,w/IORDY:120} PIO modes: pio0 pio1 pio2 pio3 pio4 AdvancedPM=yes: disabled (255) Drive conforms to: Unspecified: ATA/ATAPI-4 * signifies the current active mode tmp179:~ # hdparm -I /dev/sdb /dev/sdb: CompactFlash ATA device Model Number: PIO Serial Number: 20100716 CF100BA8 Firmware Revision: 20100202 Standards: Supported: 4 Likely used: 6 Configuration: Logical max current cylinders 3949 3949 heads 16 16 sectors/track 63 63 -- CHS current addressable sectors: 3980592 LBA user addressable sectors: 3980592 Logical/Physical Sector size: 512 bytes device size with M = 1024*1024: 1943 MBytes device size with M = 1000*1000: 2038 MBytes (2 GB) cache/buffer size = 1 KBytes (type=DualPort) Capabilities: LBA, IORDY(may be)(cannot be disabled) Standby timer values: spec'd by Vendor R/W multiple sector transfer: Max = 1 Current = 0 Advanced power management level: disabled DMA: not supported PIO: pio0 pio1 pio2 pio3 pio4 Cycle time: no flow control=120ns IORDY flow control=120ns Commands/features: Enabled Supported: * SMART feature set Security Mode feature set Power Management feature set WRITE_BUFFER command READ_BUFFER command NOP cmd CFA feature set Advanced Power Management feature set * Gen1 signaling speed (1.5Gb/s) * CFA Power Level 1 (max 500mA) Security: Master password revision code = 65534 supported not enabled not locked not frozen not expired: security count not supported: enhanced erase 2min for SECURITY ERASE UNIT. Integrity word not set (found 0x0000, expected 0x52a5) tmp179:~ # smartctl --all -T permissive /dev/sdb smartctl 5.40 2010-10-16 r3189 [i686-pc-linux-gnu] (SUSE RPM) Copyright (C) 2002-10 by Bruce Allen, http://smartmontools.sourceforge.net === START OF INFORMATION SECTION === Device Model: PIO Serial Number: 20100716 CF100BA8 Firmware Version: 20100202 User Capacity: 2,038,063,104 bytes Device is: Not in smartctl database [for details use: -P showall] ATA Version is: 4 ATA Standard is: Exact ATA specification draft version not indicated Local Time is: Fri Mar 18 11:35:28 2011 CET SMART support is: Ambiguous - ATA IDENTIFY DEVICE words 85-87 don't show if SMART is enabled. Checking to be sure by trying SMART RETURN STATUS command. SMART support is: Available - device has SMART capability. SMART support is: Enabled === START OF READ SMART DATA SECTION === SMART overall-health self-assessment test result: PASSED General SMART Values: Offline data collection status: (0x26) Offline data collection activity is in a Reserved state. Auto Offline Data Collection: Disabled. Total time to complete Offline data collection: ( 3) seconds. Offline data collection capabilities: (0x00) Offline data collection not supported. SMART capabilities: (0x0002) Does not save SMART data before entering power-saving mode. Supports SMART auto save timer. Error logging capability: (0x00) Error logging NOT supported. No General Purpose Logging support. SMART Attributes Data Structure revision number: 1 Vendor Specific SMART Attributes with Thresholds: ID# ATTRIBUTE_NAME FLAG VALUE WORST THRESH TYPE UPDATED WHEN_FAILED RAW_VALUE 1 Raw_Read_Error_Rate 0x0000 100 100 000 Old_age Offline - 0 2 Throughput_Performance 0x0000 100 100 000 Old_age Offline - 0 5 Reallocated_Sector_Ct 0x0000 100 100 000 Old_age Offline - 0 7 Seek_Error_Rate 0x0000 100 100 000 Old_age Offline - 0 8 Seek_Time_Performance 0x0000 100 100 000 Old_age Offline - 0 12 Power_Cycle_Count 0x0000 100 100 000 Old_age Offline - 43 195 Hardware_ECC_Recovered 0x0000 100 100 000 Old_age Offline - 0 196 Reallocated_Event_Count 0x0000 100 100 000 Old_age Offline - 0 197 Current_Pending_Sector 0x0000 100 100 000 Old_age Offline - 0 198 Offline_Uncorrectable 0x0000 100 100 000 Old_age Offline - 0 199 UDMA_CRC_Error_Count 0x0000 100 100 000 Old_age Offline - 0 200 Multi_Zone_Error_Rate 0x0000 100 100 000 Old_age Offline - 0 Warning: device does not support Error Logging Error SMART Error Log Read failed: Input/output error Smartctl: SMART Error Log Read Failed Warning: device does not support Self Test Logging Error SMART Error Self-Test Log Read failed: Input/output error Smartctl: SMART Self Test Log Read Failed Device does not support Selective Self Tests/Logging tmp179:~ # -- Philippe De Muyter +32 2 6101532 Macq SA rue de l'Aeronef 2 B-1140 Bruxelles

15 years

Re: [Flashbench] flashbench : time_read: Invalid argument

by arnd.bergmann＠linaro.org

On Saturday 05 March 2011 00:55:29 Philippe De Muyter wrote: > I have read with interest your article in lwn, and decided to try your flashbench > program to discover the characteristics of the CF card we use. > > Unfortunately, > > ./flashbench -a -b 1K /dev/sdb > > fails with endless : > > time_read: Invalid argument > > Looking with strace, I get e.g.: > > pread64(3, 0xb3728000, 1, 1023410175) = -1 EINVAL (Invalid argument) > > Is that a behavior you can explain (and fix) ? Yes, there are two known problems that I need to fix: 1. flashbench uses O_DIRECT for talking to the device, which means that all accesses must be on multiples of full sectors based on the underlying device sector size. It should detect this 2. command line arguments currently need to be natural numbers. There is no parser for interpreting arguments like 1K or 4M as kilobytes and megabytes. It should work when you do ./flashbench -a -b 1024 /dev/sdb Arnd

15 years

Re: [Flashbench] flashbench: Usage and understanding -s and -f ?

by Arnd Bergmann

On Sunday 13 March 2011, Dirk Behme wrote: > Hi Arnd, > > reading the flashbench README [1] what I really like is the > explanation of the -a and the -O option. Explaining the options in > this README, giving the examples and how to interpret the resulting > figures really does help. > > Somehow I miss something similar for the -s and -f options. I.e. how > to select the proper values for --scatter-order and --scatter-span and > how to interpret the output of -s and -f. > > Once I understood it, I would be able to send a patch for the README ;) > > Additionally, it would be nice to give the flashbench options used for > the graphs [2] [3] in the LWN article. The LWN article explains quite > nicely how to interpret the given graphs, but it's not mentioned which > flashbench options were used to get these graphs. > > Many thanks for your help and best regards > > Dirk > > [1] > http://git.linaro.org/gitweb?p=people/arnd/flashbench.git;a=blob;f=README;h… > Sorry for the late reply. I promise I'll get to it and update the README. I should actually remove --scatter-order, it's too difficult to understand this. It specifies the log2 of the number of blocks in terms of --blocksize to be tested at the start of the medium. The output file can be interpreted by gnuplot -p -e 'plot "output.file"' or by importing it into a spreadsheet program like oocalc and using the XY chart function on two columns. For --findfat, the output shows how each of the first N erase blocks on the drive reacts to certain access patterns within the erase block. Most drives do something different for a few blocks in the beginning to optimize storing the FAT on them. Each column is one erase block here. If they are all the same, the card does not have an optimzied FAT area. Arnd

15 years, 1 month

Re: [Flashbench] Fwd: flashbench results APACER SD Embedded(SLC) 4GB:

by Arnd Bergmann

On Friday 04 March 2011 20:16:05 Xianghua Xiao wrote: > From the data below it appears APACER has a 1MB erasing block instead > of the typical 4MB? Yes, and this is not surprising for an SLC card, although it is the first one I have seen. > Also from the following email(waiting for approval on the list, will > forward to you soon), that looks like a 4MB erasing block but is > slower than APACER. Sorry, I need to find the place on the mailing list settings to allow non-members to post, and approve the mails you already sent. > Does open-au-nr with higher number mean the underlying filesystem esp > ext4 will do better, Yes > does that imply multithread parallel writing to some extent? No, it's not about threads, but about how the data is laid out. ext4 will have to write data, metadata and journal data for many accesses, but these three are normally in different locations on the driver, so you need at least three open segments for the first process that is writing data. If you have other processes that also write to the drive, or one process writing to multiple files, you will need more. > open-au-nr means how many different segments you can use > to write to in the same time(so you don't need wait for one segment)? Yes. The apacer card evidently can write to three segments, but not to six. Can you also try 4 and 5 segments? The interesting number is the maximum. For the unigen card, it looks like it does not handle random access well, independent of the number of AUs. Best try again without --random. > I probably will recommend APACER over UNIGEN, does that make sense? Depends on the other measurements. Arnd

15 years, 1 month

flashbench result: Unigen SDHC 4GB

by Xianghua Xiao

./flashbench -a /dev/sdd2 align 67108864 pre 1.6ms on 1.6ms post 1.52ms diff 34.9µs align 33554432 pre 1.59ms on 1.59ms post 1.53ms diff 31.6µs align 16777216 pre 1.58ms on 1.59ms post 1.52ms diff 36.8µs align 8388608 pre 1.71ms on 1.72ms post 1.6ms diff 70.6µs align 4194304 pre 1.72ms on 1.72ms post 1.58ms diff 71.5µs align 2097152 pre 1.54ms on 1.55ms post 1.51ms diff 21.1µs align 1048576 pre 1.55ms on 1.57ms post 1.52ms diff 30.6µs align 524288 pre 1.55ms on 1.56ms post 1.52ms diff 25µs align 262144 pre 1.52ms on 1.52ms post 1.51ms diff 2.85µs align 131072 pre 1.51ms on 1.52ms post 1.52ms diff 3.14µs align 65536 pre 1.52ms on 1.52ms post 1.52ms diff 244ns align 32768 pre 1.52ms on 1.52ms post 1.52ms diff 4.51µs ./flashbench --open-au --open-au-nr=1 /dev/sdd2 4MiB 8.34M/s 2MiB 8.57M/s 1MiB 8.71M/s 512KiB 8.74M/s 256KiB 8.57M/s 128KiB 7.96M/s 64KiB 16.9M/s 32KiB 5.89M/s 16KiB 3.56M/s ./flashbench --open-au --open-au-nr=2 /dev/sdd2 4MiB 8.69M/s 2MiB 7.47M/s 1MiB 6.12M/s 512KiB 8.79M/s 256KiB 8.52M/s 128KiB 8.22M/s 64KiB 8.57M/s 32KiB 5.99M/s 16KiB 3.66M/s ./flashbench --open-au --open-au-nr=3 /dev/sdd2 4MiB 8.51M/s 2MiB 7.48M/s 1MiB 6.04M/s 512KiB 4.37M/s 256KiB 2.43M/s 128KiB 1.42M/s 64KiB 808K/s 32KiB 425K/s 16KiB 216K/s head /sys/block/sdd/device/* ==> /sys/block/sdd/device/block <== head: error reading `/sys/block/sdd/device/block': Is a directory ==> /sys/block/sdd/device/bsg <== head: error reading `/sys/block/sdd/device/bsg': Is a directory head: cannot open `/sys/block/sdd/device/delete' for reading: Permission denied ==> /sys/block/sdd/device/device_blocked <== 0 ==> /sys/block/sdd/device/dh_state <== detached ==> /sys/block/sdd/device/driver <== head: error reading `/sys/block/sdd/device/driver': Is a directory ==> /sys/block/sdd/device/evt_media_change <== 0 ==> /sys/block/sdd/device/generic <== head: error reading `/sys/block/sdd/device/generic': Is a directory ==> /sys/block/sdd/device/iocounterbits <== 32 ==> /sys/block/sdd/device/iodone_cnt <== 0x249d5d ==> /sys/block/sdd/device/ioerr_cnt <== 0x218be3 ==> /sys/block/sdd/device/iorequest_cnt <== 0x249d5d ==> /sys/block/sdd/device/max_sectors <== 240 ==> /sys/block/sdd/device/modalias <== scsi:t-0x00 ==> /sys/block/sdd/device/model <== STORAGE DEVICE ==> /sys/block/sdd/device/power <== head: error reading `/sys/block/sdd/device/power': Is a directory ==> /sys/block/sdd/device/queue_depth <== 1 ==> /sys/block/sdd/device/queue_type <== none head: cannot open `/sys/block/sdd/device/rescan' for reading: Permission denied ==> /sys/block/sdd/device/rev <== 9744 ==> /sys/block/sdd/device/scsi_device <== head: error reading `/sys/block/sdd/device/scsi_device': Is a directory ==> /sys/block/sdd/device/scsi_disk <== head: error reading `/sys/block/sdd/device/scsi_disk': Is a directory ==> /sys/block/sdd/device/scsi_generic <== head: error reading `/sys/block/sdd/device/scsi_generic': Is a directory ==> /sys/block/sdd/device/scsi_level <== 0 ==> /sys/block/sdd/device/state <== running ==> /sys/block/sdd/device/subsystem <== head: error reading `/sys/block/sdd/device/subsystem': Is a directory ==> /sys/block/sdd/device/timeout <== 30 ==> /sys/block/sdd/device/type <== 0 ==> /sys/block/sdd/device/uevent <== DEVTYPE=scsi_device DRIVER=sd MODALIAS=scsi:t-0x00 ==> /sys/block/sdd/device/vendor <== Generic

15 years, 1 month

Jump to page:

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

Flashbench-results