summaryrefslogtreecommitdiffstats
Commit message (Expand)AuthorAgeFilesLines
* sched/numa: Call task_numa_free() from do_execve()Rik van Riel2013-10-094-6/+13
* sched/numa: Use group fault statistics in numa placementMel Gorman2013-10-092-17/+108
* sched/numa: Stay on the same node if CLONE_VMRik van Riel2013-10-093-7/+11
* mm: numa: Do not batch handle PMD pagesMel Gorman2013-10-092-144/+4
* mm: numa: Do not group on RO pagesPeter Zijlstra2013-10-094-10/+47
* mm: numa: Copy cpupid on page migrationRik van Riel2013-10-091-0/+9
* sched/numa: Report a NUMA task group IDMel Gorman2013-10-093-0/+14
* sched/numa: Use {cpu, pid} to create task groups for shared faultsPeter Zijlstra2013-10-096-13/+182
* mm: numa: Change page last {nid,pid} into {cpu,pid}Peter Zijlstra2013-10-0913-109/+125
* sched/numa: Fix placement of workloads spread across multiple nodesRik van Riel2013-10-091-6/+5
* sched/numa: Favor placing a task on the preferred nodeMel Gorman2013-10-091-19/+35
* sched/numa: Use a system-wide search to find swap/migration candidatesMel Gorman2013-10-093-71/+199
* sched/numa: Introduce migrate_swap()Peter Zijlstra2013-10-097-14/+110
* stop_machine: Introduce stop_two_cpus()Peter Zijlstra2013-10-092-98/+175
* mm: numa: Trap pmd hinting faults only if we would otherwise trap PTE faultsMel Gorman2013-10-091-2/+5
* sched/numa: Do not trap hinting faults for shared librariesMel Gorman2013-10-091-0/+10
* sched/numa: Increment numa_migrate_seq when task runs in correct locationRik van Riel2013-10-091-1/+9
* sched/numa: Retry migration of tasks to CPU on a preferred nodeMel Gorman2013-10-092-7/+24
* sched/numa: Avoid overloading CPUs on a preferred NUMA nodeMel Gorman2013-10-091-29/+102
* mm: numa: Limit NUMA scanning to migrate-on-fault VMAsMel Gorman2013-10-093-1/+26
* sched/numa: Do not migrate memory immediately after switching nodeRik van Riel2013-10-093-3/+29
* sched/numa: Set preferred NUMA node based on number of private faultsMel Gorman2013-10-0912-82/+149
* sched/numa: Remove check that skips small VMAsMel Gorman2013-10-091-4/+0
* mm: numa: Scan pages with elevated page_mapcountMel Gorman2013-10-095-29/+18
* sched/numa: Check current->mm before allocating NUMA faultsMel Gorman2013-10-091-2/+4
* sched/numa: Add infrastructure for split shared/private accounting of NUMA hi...Mel Gorman2013-10-094-17/+47
* sched/numa: Reschedule task on preferred NUMA node once selectedMel Gorman2013-10-093-1/+65
* sched/numa: Resist moving tasks towards nodes with fewer hinting faultsMel Gorman2013-10-092-0/+41
* sched/numa: Favour moving tasks towards the preferred nodeMel Gorman2013-10-096-6/+83
* sched/numa: Update NUMA hinting faults once per scanMel Gorman2013-10-093-3/+27
* sched/numa: Select a preferred node with the most numa hinting faultsMel Gorman2013-10-093-2/+17
* sched/numa: Track NUMA hinting faults on per-node basisMel Gorman2013-10-094-1/+27
* sched/numa: Slow scan rate if no NUMA hinting faults are being recordedMel Gorman2013-10-091-0/+12
* sched/numa: Set the scan rate proportional to the memory usage of the task be...Mel Gorman2013-10-093-17/+83
* sched/numa: Initialise numa_next_scan properlyMel Gorman2013-10-092-2/+9
* Revert "mm: sched: numa: Delay PTE scanning until a task is scheduled on a ne...Mel Gorman2013-10-094-34/+1
* sched/numa: Continue PTE scanning even if migrate rate limitedPeter Zijlstra2013-10-091-8/+0
* sched/numa: Mitigate chance that same task always updates PTEsPeter Zijlstra2013-10-091-1/+7
* mm: numa: Do not migrate or account for hinting faults on the zero pageMel Gorman2013-10-092-1/+10
* mm: Only flush TLBs if a transhuge PMD is modified for NUMA pte scanningMel Gorman2013-10-092-7/+26
* mm: Do not flush TLB during protection change if !pte_present && !migration_e...Mel Gorman2013-10-091-1/+2
* mm: Account for a THP NUMA hinting update as one PTE updateMel Gorman2013-10-091-1/+1
* mm: Close races between THP migration and PMD numa clearingMel Gorman2013-10-092-26/+26
* mm: numa: Sanitize task_numa_fault() callsitesMel Gorman2013-10-092-44/+34
* mm: Prevent parallel splits during THP migrationMel Gorman2013-10-091-14/+30
* mm: Wait for THP migrations to complete during NUMA hinting faultsMel Gorman2013-10-091-7/+16
* mm: numa: Do not account for a hinting fault if we racedMel Gorman2013-10-091-1/+4
* sched/numa: Fix commentsPeter Zijlstra2013-10-092-5/+5
* mm: numa: Document automatic NUMA balancing sysctlsMel Gorman2013-10-091-0/+66
* Merge tag 'v3.12-rc4' into sched/coreIngo Molnar2013-10-09893-4829/+8754
|\
OpenPOWER on IntegriCloud