Re: [patch 01/13] io-accounting: core statistics

[Andrew Morton]

On Fri, 08 Dec 2006 13:04:15 +0100
Eric Dumazet <dada1@xxxxxxxxxxxxx> wrote:

> akpm@xxxxxxxx a écrit :
> > From: Andrew Morton <akpm@xxxxxxxx>
> > 
> > The present per-task IO accounting isn't very useful.  It simply counts the
> > number of bytes passed into read() and write().  So if a process reads 1MB
> > from an already-cached file, it is accused of having performed 1MB of I/O,
> > which is wrong.
> 
> Any chance we can report some io accounting values in getresource()/wait4()... 
> too ?

That sounds logical.

> # /usr/bin/time find /usr -name 'foo'
> 0.24user 0.22system 0:00.70elapsed 66%CPU (0avgtext+0avgdata 0maxresident)k
> 0inputs+0outputs (0major+222minor)pagefaults 0swaps

But where?  ri_inblock and ru_outblock seem to be count-of-operations, not
number-of-bytes.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/