I've already submitted a pair of patches for option 1. I don't think
option 2 gains us anything. I think it's more likely we should worry
about all_unreclaimable being set when shrink_slab is returning 0 and we
are encountering so many dirty pages that pages_scanned is high enough.
Okay.
Colin reported he had no problem with patch 1 in this series and
mine(ie, just cond_resched right after balance_pgdat call without no
patch of shrink_slab).
If Colin's test is successful, I don't insist on mine.
(I don't want to drag on for days :( )
If KOSAKI agree, let's ask the test to Colin and confirm our last test.
KOSAKI. Could you post a your opinion?
Yeah.
I also don't have any motivation to ignore Colin's test result.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>