Index of /pub/linux/kernel.org/kernel/people/rml/vm/low-latency-zap_page_range
Name Last modified Size Description
Parent Directory -
README 2002-07-24 06:11 498
v2.4/ 2013-01-26 00:42 -
v2.5/ 2013-01-26 00:42 -
sha256sums.asc 2023-04-26 06:12 958
The lock hold time in zap_page_range is horrid. This patch breaks the
work up into chunks and relinquishes the lock after each iteration.
This drastically lowers latency by creating a preemption point, as well
as lowering lock contention.
The chunk size is ZAP_BLOCK_SIZE and currently 256*PAGE_SIZE.
This lowers the maximum latency in zap_page_range from 10~20ms (on a
dual Athlon - one of the worst latencies recorded) to unmeasurable.
The patch contains some other cleanups too.
-- rml