Re: 2.5.70-mm1

[Martin J. Bligh]

>> Well, that just seems to make the box hang in SDET (actually, moving it
>>  outside lock_kernel makes it hang in a similar way). Not sure it's 
>>  *caused* by this ... it might just change timing enough to trigger it.
> 
> Yes, sorry.  Looks like you hit the filemap.c screwup.  The below should
> fix it.

OK, seems to work now, but it's still no faster:

SDET 128  (see disclaimer)
                           Throughput    Std. Dev
          2.5.70-mm1-ext2       100.0%         0.1%
          2.5.70-mm1-ext3        22.7%         2.0%
          2.5.70-mm1-noxa        21.4%         4.6%
          2.5.70-mm2-ext3        20.5%         2.4%

(last one has both your patches in).

I had the sem tracing one in there too, but got no output. I might have
another look at that later on ...

M.