Hans Reiser <[EMAIL PROTECTED]> wrote: > > At the this time we have no idea which patch is responsible, probably in > a day or two we'll have a patch to fix it. >
OK. I assume this performance change is demonstrable in just
2.6.14-rc2+reiser4? Beware that there are other changes in the -mm lineup
which might cause regressions. Notably
mm-try-to-allocate-higher-order-pages-in-rmqueue_bulk.patch
and
per-task-predictive-write-throttling-1.patch
per-task-predictive-write-throttling-1-tweaks.patch
