| commit | 4161f66d193c22aaa9e8714572d118897ec4062c | |
| author | Matthew Dillon <dillon@apollo.backplane.com> | |
| Sun, 31 Jul 2016 03:40:06 +0000 (30 20:40 -0700) | ||
| committer | Matthew Dillon <dillon@apollo.backplane.com> | |
| Sun, 31 Jul 2016 07:02:50 +0000 (31 00:02 -0700) | ||
| tree | 8c5e15d5bebcbf165feccfa472e2548d7b4ba30f | treesnapshot (tar.gz zip) |
| parent | cede4056848b741110ec3f00a73c7b194e7869e0 | commitdiff |
kernel - Refactor cpu localization for VM page allocations (3)
* Instead of iterating the cpus in the mask starting at cpu #0, iterate
starting at mycpu to the end, then from 0 to mycpu - 1.
This fixes random masked wakeups from favoring lower-numbered cpus.
* The user process scheduler (usched_dfly) was favoring lower-numbered
cpus due to a bug in the simple selection algorithm, causing forked
processes to initially weight improperly. A high fork or fork/exec
rate skewed the way the cpus were loaded.
Fix this by correctly scanning cpus from the (scancpu) rover.
* For now, use a random 'previous' affinity for initially scheduling a
fork.
* Instead of iterating the cpus in the mask starting at cpu #0, iterate
starting at mycpu to the end, then from 0 to mycpu - 1.
This fixes random masked wakeups from favoring lower-numbered cpus.
* The user process scheduler (usched_dfly) was favoring lower-numbered
cpus due to a bug in the simple selection algorithm, causing forked
processes to initially weight improperly. A high fork or fork/exec
rate skewed the way the cpus were loaded.
Fix this by correctly scanning cpus from the (scancpu) rover.
* For now, use a random 'previous' affinity for initially scheduling a
fork.
| sys/cpu/x86_64/include/cpumask.h | diffblobblamehistory | |
| sys/kern/lwkt_ipiq.c | diffblobblamehistory | |
| sys/kern/usched_dfly.c | diffblobblamehistory | |
| sys/vm/vm_zeroidle.c | diffblobblamehistory |