numa/core patches
Status from this message: NACK, as already posted several times.
Get series with b4
b4 am [email protected]Versions newest first
Patches in v1
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/31 | sched, numa, mm: Make find_busiest_queue() a methodkernel/ | +12 | 0 replies | |
| 2/31 | sched, numa, mm: Describe the NUMA scheduling problem formallyDocumentation/ | +230 | 2 replies | |
| 3/31 | mm/thp: Preserve pgprot across huge page splitarch/ mm/ | +51 | 1 reply | |
| 4/31 | x86/mm: Introduce pte_accessible()arch/ include/ | +10 | 3 replies | |
| 5/31 | x86/mm: Reduce tlb flushes from ptep_set_access_flags()arch/ | +16 | 43 replies | |
| 6/31 | mm: Only flush the TLB when clearing an accessible ptemm/ | +2 | 0 replies | |
| 7/31 | sched, numa, mm, s390/thp: Implement pmd_pgprot() for s390arch/ | +13 | 1 reply | |
| 8/31 | sched, numa, mm, MIPS/thp: Add pmd_pgprot() implementationarch/ | +2 | 0 replies | |
| 9/31 | mm/pgprot: Move the pgprot_modify() fallback definition to mm.hinclude/ mm/ | +13 | 0 replies | |
| 10/31 | mm/mpol: Remove NUMA_INTERLEAVE_HITdrivers/ include/ mm/ +1 more | +22 | 2 replies | |
| 11/31 | mm/mpol: Make MPOL_LOCAL a real policyinclude/ mm/ | +7 | 1 reply | |
| 12/31 | mm/mpol: Add MPOL_MF_NOOPinclude/ mm/ | +7 | 1 reply | |
| 13/31 | mm/mpol: Check for misplaced pageinclude/ include/ mm/ | +85 | 0 replies | |
| 14/31 | mm/mpol: Create special PROT_NONE infrastructureinclude/ include/ mm/ +2 more | +154 | 1 reply | |
| 15/31 | mm/mpol: Add MPOL_MF_LAZYinclude/ mm/ | +42 | 1 reply | |
| 16/31 | numa, mm: Support NUMA hinting page faults from gup/gup_fastinclude/ mm/ | +18 | 0 replies | |
| 17/31 | mm/migrate: Introduce migrate_misplaced_page()include/ include/ mm/ | +87 | 1 reply | |
| 18/31 | mm/mpol: Use special PROT_NONE to migrate pagesmm/ mm/ | +85 | 0 replies | |
| 19/31 | sched, numa, mm: Introduce tsk_home_node()arch/ include/ include/ +2 more | +71 | 1 reply | |
| 20/31 | sched, numa, mm/mpol: Make mempolicy home-node awaremm/ | +27 | 2 replies | |
| 21/31 | sched, numa, mm: Introduce sched_feat_numa()kernel/ | +6 | 1 reply | |
| 22/31 | sched, numa, mm: Implement THP migrationmm/ mm/ | +104 | 1 reply | |
| 23/31 | sched, numa, mm: Implement home-node awarenessinclude/ kernel/ kernel/ +3 more | +384 | 1 reply | |
| 24/31 | sched, numa, mm: Introduce last_nid in the pageframeinclude/ include/ include/ +3 more | +143 | 1 reply | |
| 25/31 | sched, numa, mm/mpol: Add_MPOL_F_HOMEinclude/ mm/ | +34 | 0 replies | |
| 26/31 | sched, numa, mm: Add fault driven placement and migration policyinclude/ include/ kernel/ +6 more | +282 | 8 replies | |
| 27/31 | sched, numa, mm: Add credits for NUMA placementCREDITS kernel/ mm/ | +6 | 0 replies | |
| 28/31 | sched, numa, mm: Implement constant, per task Working Set Sampling (WSS) rateinclude/ include/ kernel/ +1 more | +39 | 1 reply | |
| 29/31 | sched, numa, mm: Add NUMA_MIGRATION feature flagkernel/ kernel/ | +6 | 0 replies | |
| 30/31 | sched, numa, mm: Implement slow start for working set samplinginclude/ kernel/ kernel/ +1 more | +16 | 1 reply | |
| 31/31 | sched, numa, mm: Add memcg support to do_huge_pmd_numa_page()mm/ | +9 | 0 replies |
Reviews trailers per patch
11 of 31 patches have a Reviewed-by or Acked-by.
| Patch | Rik van Riel | Peter Zijlstra | Lee Schermerhorn | Andrea Arcangeli | Reported-by: Fengguang Wu | Christoph Lameter | Dan Carpenter | David Rientjes | Linus Torvalds | Zhouping Liu | Mel Gorman | Hugh Dickins |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Series | T-b | Not-Yet-Signed-off-by | ||||||||||
| 1/31 | ||||||||||||
| 2/31 | ||||||||||||
| 3/31 | R-b | |||||||||||
| 4/31 | Fixed-by | |||||||||||
| 5/31 | ||||||||||||
| 6/31 | ||||||||||||
| 7/31 | ||||||||||||
| 8/31 | ||||||||||||
| 9/31 | A-b | |||||||||||
| 10/31 | R-b | |||||||||||
| 11/31 | R-b | Requested-by | A-b | |||||||||
| 12/31 | R-b | Bug-Reported-by | ||||||||||
| 13/31 | R-b | |||||||||||
| 14/31 | R-b | |||||||||||
| 15/31 | R-b | |||||||||||
| 16/31 | Originally-by | |||||||||||
| 17/31 | R-b | Based-on-work-by | ||||||||||
| 18/31 | R-b | |||||||||||
| 19/31 | ||||||||||||
| 20/31 | ||||||||||||
| 21/31 | ||||||||||||
| 22/31 | ||||||||||||
| 23/31 | ||||||||||||
| 24/31 | ||||||||||||
| 25/31 | ||||||||||||
| 26/31 | Fixes-by | |||||||||||
| 27/31 | A-b | |||||||||||
| 28/31 | Based-on-idea-by | Bug-Found-By | ||||||||||
| 29/31 | ||||||||||||
| 30/31 | ||||||||||||
| 31/31 |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes. Scroll the table sideways for all 12 reviewers.
Cover letter [PATCH 00/31] numa/core patches
Hi all,
Here's a re-post of the NUMA scheduling and migration improvement patches that we are working on. These include techniques from AutoNUMA and the sched/numa tree and form a unified basis - it has got all the bits that look good and mergeable.
With these patches applied, the mbind system calls expand to new modes of lazy-migration binding, and if the CONFIG_SCHED_NUMA=y .config option is enabled the scheduler will automatically sample the working set of tasks via page faults. Based on that information the scheduler then tries to balance smartly, put tasks on a home node and migrate CPU work and memory on the same node.
They are functional in their current state and have had testing on a variety of x86 NUMA hardware.
These patches will continue their life in tip:numa/core and unless there are major showstoppers they are intended for the v3.8 merge window.
We believe that they provide a solid basis for future work.
Please review .. once again and holler if you see anything funny! :-)
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>