Hi there,

Here are my results for the SanDisk Cruzer Blade 16GB tests. The unit seems to behave a bit better than the smaller ones already in the list. The USB ID is identical to those of the smaller ones, however.

At first, flashbench -a gave an uneven list of diff values. After reading that amount of writes can make a difference, I zeroed the (brand new) drive to all zeroes: dd if=/dev/zero of=/dev/sdx bs=4M. I then got the following:
sudo flashbench -a /dev/sdf --blocksize=1024

align 4294967296        pre 748µs       on 1.09ms       post 756µs      diff 335µs
align 2147483648        pre 749µs       on 1.16ms       post 751µs      diff 406µs
align 1073741824        pre 748µs       on 1.15ms       post 751µs      diff 402µs
align 536870912 pre 746µs       on 1.15ms       post 750µs      diff 401µs
align 268435456 pre 752µs       on 1.16ms       post 752µs      diff 408µs
align 134217728 pre 738µs       on 1.15ms       post 756µs      diff 406µs
align 67108864  pre 749µs       on 1.14ms       post 749µs      diff 395µs
align 33554432  pre 753µs       on 1.14ms       post 752µs      diff 392µs
align 16777216  pre 746µs       on 1.14ms       post 754µs      diff 394µs
align 8388608   pre 745µs       on 1.13ms       post 747µs      diff 388µs
align 4194304   pre 744µs       on 983µs        post 747µs      diff 237µs
align 2097152   pre 752µs       on 885µs        post 744µs      diff 137µs
align 1048576   pre 753µs       on 893µs        post 753µs      diff 140µs
align 524288    pre 752µs       on 880µs        post 739µs      diff 134µs
align 262144    pre 750µs       on 891µs        post 757µs      diff 137µs
align 65536     pre 748µs       on 888µs        post 750µs      diff 139µs
align 32768     pre 749µs       on 883µs        post 745µs      diff 137µs
align 16384     pre 750µs       on 890µs        post 751µs      diff 139µs
align 8192      pre 745µs       on 803µs        post 748µs      diff 56.8µs
align 4096      pre 747µs       on 804µs        post 753µs      diff 53.5µs
align 2048      pre 746µs       on 803µs        post 745µs      diff 57.3µs

Leading to an assumption of erase size of 4M and page size of 8K.

With a sequence of

sudo flashbench -O --erasesize=$[4*1024*1024] --blocksize=$[8*1024] /dev/sdf --open-au-nr=X

Where X increased linearly from 2 to 10 I determined the cutoff at AU=8

Because of:
AU=2
4MiB    22M/s  
2MiB    21.9M/s
1MiB    21.9M/s
512KiB  21.6M/s
256KiB  20.9M/s
128KiB  19.3M/s
64KiB   18.7M/s
32KiB   16.2M/s
16KiB   11.4M/s
8KiB    6.99M/s

AU=7
4MiB    22M/s  
2MiB    21.9M/s
1MiB    21.8M/s
512KiB  21.6M/s
256KiB  20.6M/s
128KiB  19.1M/s
64KiB   18.3M/s
32KiB   15.7M/s
16KiB   10.8M/s
8KiB    6.58M/s

AU=8
4MiB    14.4M/s
2MiB    21.4M/s
1MiB    21.8M/s
512KiB  21.6M/s
256KiB  20.6M/s
128KiB  19.1M/s
64KiB   18.2M/s
32KiB   15.6M/s
16KiB   10.7M/s
8KiB    6.47M/s

AU=9
4MiB    11.3M/s
2MiB    7M/s   
1MiB    4.58M/s
512KiB  5.15M/s
256KiB  5.4M/s 
128KiB  4.96M/s
64KiB   5.84M/s
32KiB   5.17M/s
16KiB   4.91M/s
8KiB    3.7M/s

Random performance sucks at smaller sizes. Results nearly the same for AU=1 through 6

sudo flashbench -O --erasesize=$[4*1024*1024] --blocksize=$[8*1024] /dev/sdf --random --open-au-nr=6
[sudo] password for gaby:
4MiB    22.2M/s
2MiB    22M/s  
1MiB    22M/s  
512KiB  20M/s  
256KiB  9.8M/s 
128KiB  2.69M/s
64KiB   1.12M/s
32KiB   563K/s 
16KiB   285K/s 
8KiB    132K/s

If there's anything else I can test/check, let me know?

Regards,
Gaby Schilders