Re: Long Format VHPT patches

From: Peter Chubb <peterc_at_gelato.unsw.edu.au>
Date: 2004-08-26 08:46:44
>>>>> "Arun" == Arun Sharma <arun.sharma@intel.com> writes:

Arun> On 8/25/2004 10:01 AM, Jesse Barnes wrote:
>> On Tuesday, August 24, 2004 7:34 pm, Ian Wienand wrote:
>>> 11-lf-VHPT-kconfig.patch
>>  Given your conclusions in the paper, would it make sense to
>> unconditionally switch to long format VHPT?  It would simplify
>> things a little and maybe avoid some trouble in the future.
>> 

Arun> When the super page optimizations are implemented, long format
Arun> might be a more attractive option. Without it, the increased
Arun> cache footprint of the long format pte is not compensated by the
Arun> benefits on the workloads we tried.


I suggest that we do like we did for the large block device patch ---
enable it unconditionally in the -mm and other test series, then flip
back to a config option in mainline.  That way, anyone using 2.6 for a
production kernel gets a choice, and while we're in test phase, the
patch gets a good workout.

-- 
Dr Peter Chubb  http://www.gelato.unsw.edu.au  peterc AT gelato.unsw.edu.au
The technical we do immediately,  the political takes *forever*
-
To unsubscribe from this list: send the line "unsubscribe linux-ia64" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Received on Wed Aug 25 19:25:54 2004

This archive was generated by hypermail 2.1.8 : 2005-08-02 09:20:30 EST