[continued from previous message]   
      
   Linux has write buffering. It's a FIFO of sorts.   
   But, it has a weird behavior.   
      
   If the source drive runs faster than the dest drive, we would   
   normally expect the FIFO queue to fill up as time passes.   
      
   The Linux one however, it does not write a damn thing until   
   it is half full. Imagine we are doing our 10GB of writes before   
   the wheels fall off. We could be thinking about our FIFO queue   
   right now.   
      
   The FIFO queue is likely at least, half full.   
      
   The write buffering, normally in the design of those, the   
   "size" of the queue is 1/8th to 1/10th of total system RAM.   
      
   You're at 16GB, we'll call it 2GB then. That does not give   
   an excuse for 10GB of writes to present a problem. Something   
   could happen around the 2GB mark, say, or the 1GB mark (the   
   half full point). But by the time we're copying 10GB, the   
   FIFO Queue is full, it provides back pressure, and the reader   
   process blocks until space is available in the FIFO Queue for   
   more writes. After the transfer is "finished", it takes   
   time for the queue to drain out to disk.   
      
       # [Manual option} Using a mount command for example   
      
       # When mounting your hard drives use -o sync which will   
       # turn off write buffering for the drive.   
      
       You can also set it up in your fstab:   
      
       /dev/sda1    /    ext4      sync    0   0   
      
   One detail is, the automounter will already have mounted the volume.   
      
   Maybe you could   "remount -o sync" to make it stop write buffering   
   the particular mount point.   
      
   Or, in this thread, you can stop an EXT4 from automounting,   
   then you could do your own mount of the USB thing. And then   
   one of the options would be the equal of   -o sync  kind of thing.   
      
      https://forums.linuxmint.com/viewtopic.php?t=456525   
      
   That's udev, and other distros may be using autofs.   
      
   By using   -o sync   for the USB device, that stops write buffering and   
   makes all writes go directly to disk.   
      
   *******   
      
   The other possibility, is there is a temperature issue, but the   
   drive heating up at the 10GB point, seems a bit too quick. It should   
   take longer than that to heat/overheat the thing. So this is not   
   likely to be the case.   
      
   In general, you don't want to use  -o sync  for all USB devices.   
   The USB flash sticks would work better without it, the HDD in enclosure,   
   don't mind either way (the hardware has options that allow smooth operation   
   with 512 byte writes (while the internal sectors are 4096 bytes on a 512e   
   drive).   
      
   I would be testing this with two different OSes here, to see if it is   
   ecosystem-specific.   
      
      Paul   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)