Re: [MM] Make mm counters per cpu instead of atomic V2

[Andrew Morton]

On Fri, 6 Nov 2009 10:11:06 +0900
KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> wrote:

> On Thu, 5 Nov 2009 10:36:06 -0500 (EST)
> Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx> wrote:
> 
> > From: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
> > Subject: Make mm counters per cpu V2
> > 
> > Changing the mm counters to per cpu counters is possible after the introduction
> > of the generic per cpu operations (currently in percpu and -next).
> > 
> > With that the contention on the counters in mm_struct can be avoided. The
> > USE_SPLIT_PTLOCKS case distinction can go away. Larger SMP systems do not
> > need to perform atomic updates to mm counters anymore. Various code paths
> > can be simplified since per cpu counter updates are fast and batching
> > of counter updates is no longer needed.
> > 
> > One price to pay for these improvements is the need to scan over all percpu
> > counters when the actual count values are needed.
> > 
> > V1->V2
> > - Remove useless and buggy per cpu counter initialization.
> >   alloc_percpu already zeros the values.
> > 
> > Signed-off-by: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
> > 
> Thanks. My small concern is read-side.

Me too.

For example, with 1000 possible CPUs (possible, not present and not
online), and 1000 processes, ps(1) will have to wallow through a
million cachelines in task_statm().

And then we have get_mm_rs(), which now will hit 1000 cachelines.  And
get_mm_rs() is called (via
account_user_time()->acct_update_integrals()) from the clock tick.

Adding a thousand cache misses to the timer interrupt is the sort of
thing which makes people unhappy?

--
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/