Re: New FAT32 performance

[A complimentary Cc of this posting was sent to
KO Myung-Hun
<komh@xxxxxxxxxxxx>], who wrote in article <gi5lg8$2tm$1@xxxxxxxxxxxxxxxxx>:
Copy from USB hard disk to local hard disk (via File Commander): 4.7MB/sec
Copy from local hard disk to USB hard disk (via File Commander): 3.2MB/sec
Copy from local hard disk to USB hard disk (via File Commander): 1.1MB/sec

(last number is with lazy write enabled). Still orders of magnitude
slower than on Win*...

[Actually, I want to take the last statement back. I never checked
how *this particular* USB enclosure interacts with Win*; so the slow
read speed may be related to a cheap chipset (no pun intended).]

So strange. I want to know your cache settings of File Commander.

I do not know which setting you mean here. There is no such thing
mentioned in .INF file, and in f9 c a.

And I suggest to test your scenario using 'xcopy' as well.

I may have a GB or so free on the drive yet, so may experiment now...
OK, I copy 300MiB (from a drive which does 20MB/sec when copying to
`nul') to USB. It takes

0:02:33.95 with /L:off

(it is very close to the end of free space - but I expect it to be
continuous, since all I did after formatting was to write a handful of
very large files - without any significant deletion; FC gives a
similar speed now).

With /L:on, CPU jumps to about 35% (of 850MHz); it takes

0:07:37.32 with /L:on.

[Interestingly enough, it is a lot of sound from drive with /L:off;
when cache is enabled, writing is almost silent.]

Hope this helps,
Ilya

P.S. Before xcopy:

DISKIDLE : 1000 milliseconds.
BUFFERIDLE: 500 milliseconds.
MAXAGE : 5000 milliseconds.

Read-Ahead sector count for drive N: is 128.

CACHE has space for 4096 sectors
CACHE contains 4096 sectors
There are 0 dirty sectors in cache.
The cache hits ratio is 6%.
FAT32.IFS has currently 6 GDT segments allocated.

======================================================= After:
Current priority is Idle time.

DISKIDLE : 1000 milliseconds.
BUFFERIDLE: 500 milliseconds.
MAXAGE : 5000 milliseconds.

Read-Ahead sector count for drive N: is 128.

CACHE has space for 4096 sectors
CACHE contains 4096 sectors
There are 0 dirty sectors in cache.
The cache hits ratio is 6%.
FAT32.IFS has currently 6 GDT segments allocated.
.

Relevant Pages

  • Re: New FAT32 performance
    ... Copy from local hard disk to USB hard disk (via File Commander): ... CACHE has space for 4096 sectors ...
    (comp.os.os2.setup.storage)
  • Re: Linux kernel - Libata bad block error handling to user mode program
    ... If O_DIRECT and no write cache, ... corruption, either in the kernel or in the drive. ... successfully written to all the sectors of the drive and it had taken ...
    (Linux-Kernel)
  • wishful thinking about atomic, multi-sector or full MD stripe width, writes in storage
    ... SAS) without battery backed write cache. ... You simply cannot do that with any storage device! ... Note that even without MD raid, the file system issues IO's in file system block size and most commodity storage devices use a 512 byte sector size which means that we have to update 8 512b sectors. ... These are all examples that can after a power loss, even a local device, do a partial update of that 4KB write range of sectors. ...
    (Linux-Kernel)
  • Re: Need new computer
    ... Good processor, you'll be able to use 3GB of the 4GB of RAM, giving ... Good sized primary hard disk drive. ... I recommend one with at least a 4MB cache. ... there are advantages to a quad I'd go strongly in that direction. ...
    (alt.sys.pc-clone.dell)
  • Re: Event ID 32 - write cache enabled
    ... The local domain controller could not disable the software-based disk write ... cache on the following hard disk. ... So, it does appear the Windows is attemtping the disable the write cache, ...
    (microsoft.public.windows.server.general)