On 11/26/2012 01:11 PM, Bruno Wolff III wrote:
On Mon, Nov 26, 2012 at 12:19:11 -0700,
JD <jd1008(a)gmail.com> wrote:
>
> The Read/Write failures started in 3.6.X kernels, but do not appear
> in 3.7.
> 3.7 is doing the right thing by first issuing a hard reset to the
> sleeping
> drives before reading or committing the journals. 3.6.X was not
> sending any
> hard resets to the sleeping drives.
> I will be testing 3.6.7 to see if either of these issues is still
> present.
If it isn't, you can ask the Fedora kernel guys to batch port the fix.
If the fix is upstream, you can often get them to back port it.
FYI - for the fun of it.
Just rebooted back into 3.7.0
Tasks: 202 total, 2 running, 200 sleeping, 0 stopped, 0 zombie
Cpu(s): 5.9%us, 93.7%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.3%si,
0.0%st
Mem: 2065884k total, 1551872k used, 514012k free, 419776k buffers
Swap: 8385924k total, 0k used, 8385924k free, 470868k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
24 root 20 0 0 0 0 R 87.8 0.0 2:50.54 kswapd0
^
^
^
It just doesn't get any better than this :)