reduce overhead for tg->shares distribution
Status from this message: Thanks, applied!
Get series with b4
b4 am [email protected]Versions newest first · linked by author and title
- v4 Latest11 patches 12 repliesApplied
- v311 patches 6 repliesSuperseded
- v211 patches 4 repliesSuperseded
Earlier versions · 1
| Version | Posted | Patches | Replies | Status |
|---|---|---|---|---|
| v1 RFC | 12 patches | 15 replies | Superseded |
Changes from the cover letter
v4
all patches
- fix "-p0" stripping
Patches in v4 Applied
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/11 | sched: rewrite tg_shares_upinclude/ kernel/ kernel/ +3 more | +162 | 1 reply | |
| 2/11 | sched: on-demand (active) cfs_rq listkernel/ kernel/ kernel/ | +92 | 1 reply | |
| 3/11 | sched: make tg_shares_up() walk on-demandkernel/ kernel/ | +58 | 1 reply | |
| 4/11 | sched: fix load corruption from update_cfs_shareskernel/ | +8 | 1 reply | |
| 5/11 | sched: fix update_cfs_load synchronizationkernel/ kernel/ | +22 | 1 reply | |
| 6/11 | sched: hierarchal order on shares update listkernel/ | +16 | 1 reply | |
| 7/11 | sched: add sysctl_sched_shares_windowinclude/ kernel/ kernel/ | +16 | 1 reply | |
| 8/11 | sched: update shares on idle_balancekernel/ | +1 | 1 reply | |
| 9/11 | sched: demand based update_cfs_load()kernel/ kernel/ | +20 | 1 reply | |
| 10/11 | sched: allow update_cfs_load to update global loadkernel/ | +29 | 1 reply | |
| 11/11 | sched: update tg->shares after cpu.shares writekernel/ | +11 | 1 reply |
Reviews trailers per patch
No Reviewed-by, Acked-by or Tested-by trailers for v4 yet.
Cover letter [tg_shares_up rewrite v4 00/11] reduce overhead for tg->shares distribution
This is v4 of the tg_shares_up re-write previously posted at:
http://lkml.org/lkml/2010/10/16/17
Corrected versus the previous version is the quilt patch-strip level.
The key idea behind this patchset is an idea of Peter Zijlstra'a to compute global loads as a function of local averages, avoiding the cpu-cpu interactions which previously plagued tg_shares_up.
Beyond bug fixes not much material has changed since v1 as results seem favourable/stable.
Changes:
v4
all patches
- fix "-p0" stripping
v3 (http://lkml.org/lkml/2010/11/11/526)
sched-rework-tg_shares_up.patch
- remove lint: {max,min}_sched_shares_ratelimit from sysctl.c
sched-tg-ondemand.patch
- (bug fix) fix synchronization on leaf_cfs_rq_list removal during task_group reclaim.
- fix !CONFIG_FAIR_GROUP_SCHED build
- fix comment on what task_group_lock protects
sched-tg-global_update_load.patch
- add missing arguments to update_cfs_load() in !CONFIG_FAIR_GROUP_SCHED case
v2 (http://lkml.org/lkml/2010/11/10/618)
sched-rework-tg_shares_up.patch
- (bug fix) use owning tg->shares value in effective_load
- remove redundant cfs_rq_of() in {enqueue,dequeue}_entity
sched-tg-add-shares_window_sysctl.patch
- update comment on sysctl interpretation
sched-tg-fix-update_cfs_load.patch
- update comment to reflect periods instead of foldings (more intuitive)
Some motivation again:
24 thread Intel box, 150 active cgroups, multiple threads/group, system load at ~90% (sample size=10s):
tip:
2.64% [k] tg_shares_up <!>
0.15% [k] __set_se_sharespatched:
0.02% [k] update_cfs_load
0.01% [k] update_cpu_load
0.00% [k] update_cfs_sharesFairness coverage for the above at: http://rs5.risingnet.net/~pjt/patches/shares_data_v1.txt
Thanks,
- Paul