This version of adaptive read-ahead patch features various clean ups.
Changes include:
- rewrote context based method to make it clean and robust
- improved accuracy of stateful thrashing threshold estimation
- nr_page_aging made right
- sorted out the thrashing protection logic
- enhanced debug/accounting facilities
Regards,
Wu Fengguang
Wu,
I will run some standard benchmarks and post the results soon.
The benchmarks I have are (1) DSS (TPCH) (2) iozone (3) sysbench (4)
tiobench
It will take atleast a week, since some disks on my machine have to be
replaced and the setup has to be remade.
RP
On Sat, Oct 29, 2005 at 02:02:16PM +0800, Wu Fengguang wrote:
> This version of adaptive read-ahead patch features various clean ups.
> Changes include:
> - rewrote context based method to make it clean and robust
> - improved accuracy of stateful thrashing threshold estimation
> - nr_page_aging made right
> - sorted out the thrashing protection logic
> - enhanced debug/accounting facilities
>
> Regards,
> Wu Fengguang
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
On Mon, Oct 31, 2005 at 01:45:14PM -0800, Ram Pai wrote:
> Wu,
>
> I will run some standard benchmarks and post the results soon.
> The benchmarks I have are (1) DSS (TPCH) (2) iozone (3) sysbench (4)
> tiobench
>
> It will take atleast a week, since some disks on my machine have to be
> replaced and the setup has to be remade.
Thank you for taking the trouble. In the meantime I will prepare a patch
against the stable 2.6.14, so that you can comfortably run vanilla 2.6.14
as the reference point.
Regards,
Wu Fengguang