Emmc issue?

[stuartiannaylor]

Is there a problem with the emmc chips mine on image writes dips and crests but is extremely slow.
Its sometime dips to 3MB/s averages about 7.5MB/s sometimes manages 12MB/s.

Even cheap SD cards manage a faster write than this thing?!
I notice this especially when writing the image and it gets quite warm as it is when removed.

[stuartiannaylor]

Is there a problem with the emmc chips mine on image writes dips and crests but is extremely slow.
Its sometime dips to 3MB/s averages about 7.5MB/s sometimes manages 12MB/s.

Even cheap SD cards manage a faster write than this thing?!
I notice this especially when writing the image and it gets quite warm as it is when removed.

Sorry to bump but buying back a RockPro64 has me like a noob again after a long gap.
I know the Forsee emmc isn't the fastest but thinking the above in serial writes is surely a sign that maybe I have a dud?

Is this true or is this approx normal for the emmc modules?
Anyone?

[z4v4l]

if you have that usb-emmc adapter, try it on a PC. If the speed is still low as there, then the module is not fully well doing. I saw here tests of eMMCs sold by Pine and they showed ~50 MB/s.

[stuartiannaylor]

if you have that usb-emmc adapter, try it on a PC. If the speed is still low as there, then the module is not fully well doing. I saw here tests of eMMCs sold by Pine and they showed ~50 MB/s.

That is in the PC via usb-emmc yeah something aint right its 5MB/s

Nope something with the usb-emmc as when writing images I have been thinking that is so slow.
It gets quite warm as well

1073741824 bytes (1.1 GB, 1.0 GiB) copied, 21.2077 s, 50.6 MB/s if mounted on the RockPro64

Think its just the adapter as tried in various ports usb 3/2 and always the same

[z4v4l]

aha, it's good then, the module is OK. I think the adapter as well, it just probably is not meant to squeeze all the speed out of the module, it's for flashing only. finally, - writes are way slower than reads, plus going through additional translation (USB <-> eMMC) adds to overhead. also, maybe it runs in 1 bit (or 4 bits) bus width (as opposed to normal 8 bits), who knows.

[neilman]

Following this discussion I thought I would try to check the speed of my original 16GB eMMC as supplied with my PineBook (1080) which I replaced early on with a 64GB eMMC. I have the official USB adapter and used it to program my new 64GB eMMC module successfully last year.

I was hoping to provide a read/write figure for my surplus eMMC module but...

I formatted the drive with (Windows) SDFormatter successfully then followed that using the H2TestW media test program when I was plugged into a UBS 3 port.

It managed to write to the whole drive at a constant speed of 15.9MBps but on switching to verify the drive disappeared and the LED on the USB programmer went steady. The drive no longer existed to Windows.

Unplugged it and re-seated it, the drive appeared again and the USB LED flashed, Windows explorer confirmed the drive was full of 1GB test files  but selecting verify only, the eMMC immediately disappeared again.

Repeated the whole process using a USB 2 port and, apart from write speed now at 15.3MBps it disappeared again on verify.

Tried Etcher with a Q4OS Pinebook image and writing was ok but verification failed again.

Don't know whether the eMMC is now faulty (it was stored in an antistatic bag whilst plugged in the programmer) or the programmer

[stuartiannaylor]

Following this discussion I thought I would try to check the speed of my original 16GB eMMC as supplied with my PineBook (1080) which I replaced early on with a 64GB eMMC. I have the official USB adapter and used it to program my new 64GB eMMC module successfully last year.

I was hoping to provide a read/write figure for my surplus eMMC module but...

I formatted the drive with (Windows) SDFormatter successfully then followed that using the H2TestW media test program when I was plugged into a UBS 3 port.

It managed to write to the whole drive at a constant speed of 15.9MBps but on switching to verify the drive disappeared and the LED on the USB programmer went steady. The drive no longer existed to Windows.

Unplugged it and re-seated it, the drive appeared again and the USB LED flashed, Windows explorer confirmed the drive was full of 1GB test files  but selecting verify only, the eMMC immediately disappeared again.

Repeated the whole process using a USB 2 port and, apart from write speed now at 15.3MBps it disappeared again on verify.

Tried Etcher with a Q4OS Pinebook image and writing was ok but verification failed again.

Don't know whether the eMMC is now faulty (it was stored in an antistatic bag whilst plugged in the programmer) or the programmer

DD is not a really good test so used iozone as almost 90-95% of normal activity is going to be small 4k files.

Code:

       Command line used: iozone -e -I -a -s 250M -r 4k -r 16k -r 512k -r 1024k -r 16384k -i 0 -i 1 -i 2
       Output is in kBytes/sec
       Time Resolution = 0.000001 seconds.
       Processor cache size set to 1024 kBytes.
       Processor cache line size set to 32 bytes.
       File stride size set to 17 * record size.
                                                             random    random     bkwd    record    stride
             kB  reclen    write  rewrite    read    reread    read     write     read   rewrite      read   fwrite frewrite    fread  freread
         256000       4     2065     2088     7301     7303     5593     1425
         256000      16     6486     7265    28303    29047    29014     6356
         256000     512    15325    14409   107559   110071   108360    13137
         256000    1024    13470    13567   112071   112890   114135    12399
         256000   16384    13026    13714   117179   120009   120015    12817

No wonder I have been sat confused thinking this emmc seems slower than SD, those figures really suck.
I am going to burn the image again so its fresh with and Ayufan but boy!!!
Its not just usb adaptor dunno where hdparm gets its figures but do iozone to real world timings the results are extremely poor.

Think there is a couple of probs writing on windows seems to quickly drop because the emmc / adaptor gets quite warm.
If you run iozone on windows then wow but what the F is happening with the rk3399? But sustained writes drops from those wonderful figures to suck city pretty quick.

Code:

       Command line used: iozone -e -I -a -s 250M -r 4k -r 16k -r 512k -r 1024k -r 16384k -i 0 -i 1 -i 2
       Output is in Kbytes/sec
       Time Resolution = -0.000000 seconds.
       Processor cache size set to 1024 Kbytes.
       Processor cache line size set to 32 bytes.
       File stride size set to 17 * record size.
                                                           random  random    bkwd   record   stride                    
             KB  reclen   write rewrite    read    reread    read   write    read  rewrite     read   fwrite frewrite   fread  freread
         256000       4  245281  288604  1141253  1169749  591445  193319                                              
         256000      16  295191  301778  2414916  3037014 1760110  276703                                              
         256000     512  319541  319514  4077387  5308383 4831446  324607                                              
         256000    1024  326327  324847  5414311  5556725 4987608  326130                                              
         256000   16384  315242  317253  4127388  4202814 4044966  320733                                              

https://github.com/ayufan-rock64/linux-b...mhf.img.xz

Code:

       Command line used: iozone -e -I -a -s 250M -r 4k -r 16k -r 512k -r 1024k -r 16384k -i 0 -i 1 -i 2
       Output is in kBytes/sec
       Time Resolution = 0.000001 seconds.
       Processor cache size set to 1024 kBytes.
       Processor cache line size set to 32 bytes.
       File stride size set to 17 * record size.
                                                             random    random     bkwd    record    stride
             kB  reclen    write  rewrite    read    reread    read     write     read   rewrite      read   fwrite frewrite    fread  freread
         256000       4     2083     2199     6908     6891     5155     1431
         256000      16     6340     7387    30967    30377    30230     6443
         256000     512    15679    14352   102581   103662   104033    12753
         256000    1024    13169    13524   104729   107799   108613    12195
         256000   16384    12851    13681   114358   118152   118905    12850

SD Card with same https://github.com/ayufan-rock64/linux-b...mhf.img.xz

Code:

       Command line used: iozone -e -I -a -s 250M -r 4k -r 16k -r 512k -r 1024k -r 16384k -i 0 -i 1 -i 2
       Output is in kBytes/sec
       Time Resolution = 0.000001 seconds.
       Processor cache size set to 1024 kBytes.
       Processor cache line size set to 32 bytes.
       File stride size set to 17 * record size.
                                                             random    random     bkwd    record    stride
             kB  reclen    write  rewrite    read    reread    read     write     read   rewrite      read   fwrite frewrite    fread  freread
         256000       4     5517     6097     9271     9262     7268     5342
         256000      16    10904    11170    22138    22246    19064    10875
         256000     512    25052    28489    57366    57453    56779    27967
         256000    1024    30793    31098    59722    59973    59748    26963
         256000   16384    33204    33066    64785    64381    64118    32491

You might get higher big rec length reads on the emmc but in use you notice even sd feels faster in boot and use.