Re: [PATCH] sort: add --threads option to parallelize internal sort.

[Pádraig Brady]

On 08/03/10 09:11, Chen Guo wrote:
> The following runs are conducted on an idle Intel Xeon X5460, 2 dies of 4 cores 
> each. All values are averages of 20 runs.
>
> T=1: 5.10s
> T=2: 2.87s
> T=3: 2.71s
> T=4: 1.75s
> T=5: 1.66s
> T=6: 1.65s
> T=7: 1.67s
> T=8: 1.31s

Nice results!

A few quick questions:

Any thoughts on the interesting jump at T=8?
Have you tested in conjunction with the external || patch?
You previously mentioned a thread bug with memcoll. Is that worked around?

cheers,
Pádraig.