7:37 a.m.
On 18-11-12 11:10:35, Alexander Duyck wrote:
The point I was trying to make is that it doesn't. You say it is an
order of magnitude better but it is essentially 3.5x vs 3.8x and to
achieve the 3.8x you are using a ton of system resources. My approach
is meant to do more with less, while this approach will throw a
quarter of the system at page initialization.
3.8x is a bug, that is going to be fixed before ktasks are accepted. The
final results will be close to time/nthreads.
Using more resources to initialize pages is fine, because other CPUs are
idling during this time in boot.
Lets wait for what Daniel finds out after Linux Plumber. And we can
continue this discussion in ktask thread.
An added advantage to my approach is that it speeds up things
regardless of the number of cores used, whereas the scaling approach
Yes, I agree, I like your approach. It is clean, simplifies, and
improves the performance. I have tested it on both ARM and x86, and
verified the performance improvements. So:
Tested-by: Pavel Tatashin <pasha.tatashin(a)soleen.com>
requires that there be more cores available to use. So for example
on
some of the new AMD Zen stuff I am not sure the benefit would be all
that great since if I am not mistaken each tile is only 8 processors
so at most you are only doubling the processing power applied to the
initialization. In such a case it is likely that my approach would
fare much better then this approach since I don't require additional
cores to achieve the same results.
Anyway there are tradeoffs we have to take into account.
I will go over the changes you suggested after Plumbers. I just need
to figure out if I am doing incremental changes, or if Andrew wants me
to just resubmit the whole set. I can probably deal with these changes
either way since most of them are pretty small.
Send the full series again, Andrew is very good at taking only
incremental changes once a new version is posted of something
that is already in mm-tree.
Thank you,
Pasha