Skip to contentSkip to conversation

latest patches degrade reiser4 performance substantially

DISCUSSION Hans Reiser 2 participants 3 messages Sep 21, 2005

lore
Share & tools
lore
#0 lore raw

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.

Hans

#1 lore raw
Quoted 4 lines · Hans Reiser

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

#2 lore raw
Quoted 13 lines · Andrew Morton
Quoted 5 lines · Hans Reiser

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

Quoted 11 lines

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

I'll have vs check to make sure it is reiser4 changes causing the
drop. Thanks much for the suggestion we check that.