Messages in this thread | | | Date | Mon, 1 Feb 1999 15:09:26 +0100 (CET) | From | Andrea Arcangeli <> | Subject | Re: 2.2.1 seems to be stable under high load |
| |
On Mon, 1 Feb 1999, Dr. Werner Fink wrote:
> > > > To fix the problem I pointed out above, probably we only need to replace: > > > > > + if (kswapd && p == current->next_run && rss < limit) > > > + continue; > > > + if (p == current && rss < limit) > > > continue; > > > > with: > > > > if (!kswapd && p == current && rss < limit) > > continue; > > > > This heuristic make sense to me... but there's to say that we just have > > the swap cache that should just cope fine with these issues. > > kswapd isn't swappable therefore `p == current && rss < limit' would work.
Yes of course ;)
> My small patch points out that avoiding the page request calling swap_in() > will increase performance even if swap cache avoids I/O from disk.
Ah, it's not only the swap cache, also the check for pte_young() in try_to_swap_out() act as a first barrier to avoid swapping out our working set.
Andrea Arcangeli
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |