| To: | Dave Chinner <david@xxxxxxxxxxxxx> |
|---|---|
| Subject: | [RFC PATCH 0/4] Automatic NUMA balancing and PROT_NONE handling followup v2r8 |
| From: | Mel Gorman <mgorman@xxxxxxx> |
| Date: | Sat, 7 Mar 2015 15:20:47 +0000 |
| Cc: | Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>, Ingo Molnar <mingo@xxxxxxxxxx>, Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>, Aneesh Kumar <aneesh.kumar@xxxxxxxxxxxxxxxxxx>, Linux Kernel Mailing List <linux-kernel@xxxxxxxxxxxxxxx>, Linux-MM <linux-mm@xxxxxxxxx>, xfs@xxxxxxxxxxx, linuxppc-dev@xxxxxxxxxxxxxxxx, Mel Gorman <mgorman@xxxxxxx> |
| Delivered-to: | xfs@xxxxxxxxxxx |
Dave Chinner reported a problem due to excessive NUMA balancing activity and bisected it. The first patch in this series corrects a major problem that is unlikely to affect Dave but is still serious. Patch 2 is a minor cleanup that was spotted while looking at scan rate control. Patch 3 is minor and unlikely to make a difference but is still an inconsistentcy between base and THP handling. Patch 4 is the important one, it slows PTE scan updates if migrations are failing or throttled. Details of the performance impact on local tests is included in the patch. include/linux/migrate.h | 5 ----- include/linux/sched.h | 9 +++++---- kernel/sched/fair.c | 8 ++++++-- mm/huge_memory.c | 8 +++++--- mm/memory.c | 3 ++- mm/migrate.c | 20 -------------------- 6 files changed, 18 insertions(+), 35 deletions(-) -- 2.1.2 |
| <Prev in Thread] | Current Thread | [Next in Thread> |
|---|---|---|
| ||
| Previous by Date: | [PATCH 3/4] mm: numa: Mark huge PTEs young when clearing NUMA hinting faults, Mel Gorman |
|---|---|
| Next by Date: | [PATCH 4/4] mm: numa: Slow PTE scan rate if migration failures occur, Mel Gorman |
| Previous by Thread: | XFS hangs with XFS: possible memory allocation deadlock in kmem_alloc, Michael Meier |
| Next by Thread: | [PATCH 2/4] mm: numa: Remove migrate_ratelimited, Mel Gorman |
| Indexes: | [Date] [Thread] [Top] [All Lists] |