[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: JFFS2: powerfailtesting again



We are using AMD flash - the family which includes 29LV160D (2MB, 16 bit).
Interesting factoid:  if you look at the specs for write times and erase times,
the
range is amazingly wide - from pretty reasonable to uncomfortably long.  I was 
hoping it was largely temperature dependent, meaning long times were associated
with high temperatures.  Not so, we are told. At least for the AMD devices,
sector erase times tend to start out on the high side - a sector erase could
take as long 
as 4 seconds and be in spec when new!.  As they "break in", they move down in
the range
of the low end of the spec (0.7 -1.0 sec, after what may be 10s of thousands of
cycles).
They stay there during most of their life, then start rising towards the end of
their life
(after say 5-600K cycles) and can reach the max and still be in spec (15
seconds!).
I don't have good info what the variation over a large lot of parts is, but we
will be
finding out!  I also have not looked at a broad range of flash parts, but the
technology
is fairly similar when you are talking similar parts, and this appears to be a
characteristic
of the flash storage mechanism itself, so i think it's safe to assume all these
types
of parts will exhibit this kind of behaviour to some degree.

clearly, if the above variation is critical to your product given the way it
will be used,
this must be characterized and considered carefully - as a hardware issue!




-----Original Message-----
From: Vladimir Serov [mailto:vserov@xxxxxxx.com]
Sent: Thursday, June 07, 2001 12:37 AM
To: Vipin Malik
Cc: David Woodhouse; jffs-dev@xxxxxxx.com
Subject: Re: JFFS2: powerfailtesting again


Vipin Malik wrote:

>
> Did you really mean 3 *minutes*, NOT seconds?

Yes I do. Take a look into attached PS file in my previous message.

> What processor are you using?

StrongARM 1100 @133MHz ~ 124 Bogomips, 32Mb SDRAM , 4Mb16bit wide Intel boot
block flash - 28F320C3 , see
http://developer.intel.com/design/flcomp/datashts/29064510.pdf

>
>
> There is something wrong for sure. On my 100MHz 486 with a 8MB flash
> partition
> with about 5MB of data on it (JFFS2), I don't have any blocks more than a few
> seconds
> at a time.

I have big incompressible file on fs , could this be a problem ?
I'm using Intel boot flash and it takes (currently) less than 0.5 sec to erase
sector on it, but it could be longer according to specification.

>
> I have a small program that runs as a real time POSIX task (in the kernel).
> In writing out a few 10's of bytes
> every 100ms, the worst case block I got on the wakeup time for the task was
> ~600ms. This was writing
> to the fs that was ~60% full.
>
> >From what I remember I had let the task run for hours. Maybe I need to let it
> run for days and see what the
> worst case time would be. :)
>

try to fill fs 100% and restart immediately.

My FS is almost unchangeable except for rapid updates of single file up to 100%
of free space and fast reboot after this - try to do this several times . If
this
triggers the problem ?

Vladimir.
PS. BTW thank you for your information and discussion.


To unsubscribe from this list: send the line "unsubscribe jffs-dev" in
the body of a message to majordomo@xxxxxxx.com

To unsubscribe from this list: send the line "unsubscribe jffs-dev" in
the body of a message to majordomo@xxxxxxx.com