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

Re: What on Earth is JFFS2 GC doing?



David Woodhouse wrote:

> What if you just delete all the files and start again?

Ok, after a rm -rf *

"df" says:

/dev/mtdblock1            8192      1876      6316  23% /mnt/jffs1
(why did it not go back to the 16% used?)

The console said:

CHIP_ERASE:Erasing_at_address: 0x4c0000
CHIP_ERASE:Erasing_at_address: 0x480000

<now starting my jitter test program)

JitterTest (my program) says:

<SNIP>
 100.015000 ms   0.015000 ms
 109.992000 ms   9.992000 ms
 100.006000 ms   0.006000 ms

<SNIP>

 100.001000 ms   0.001000 ms
 100.011000 ms   0.011000 ms
CHIP_ERASE:Erasing_at_address: 0x440000
 2793.380000 ms   2693.380000 ms!
 626.668000 ms   526.668000 ms
 100.011000 ms   0.011000 ms
 100.217000 ms   0.217000 ms
 99.764000 ms   -0.236000 ms
/dev/mtdblock1            8192      1888      6304  23% /mnt/jffs1
 101.405000 ms   1.405000 ms
 98.541000 ms   -1.459000 ms

<SNIP>

 99.999000 ms   -0.001000 ms
 100.004000 ms   0.004000 ms
CHIP_ERASE:Erasing_at_address: 0x400000
 2622.155000 ms   2522.155000 ms
 617.953000 ms   517.953000 ms
 99.972000 ms   -0.028000 ms
 116.615000 ms   16.615000 ms
 113.379000 ms   13.379000 ms
/dev/mtdblock1            8192      1896      6296  23% /mnt/jffs1
 99.921000 ms   -0.079000 ms
 99.999000 ms   -0.001000 ms

<SNIP>

Ctrl+C detected. Worst Jitter time was:2693.380000ms
JitterTest exiting.
/dev/mtdblock1            8192      1896      6296  23% /mnt/jffs1


So I guess that jitter times went back down.


>
> What if you delete all the files, reboot and start again?

I didn't do this test, as jitter times had gone back down without even a
reboot (but I can if you want me to).

Vipin



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