Recent changes to numa balancing like adding group faults, merging numa_faults and numa_mem_faults have not been reflected in /proc.
Hence some of the numa_balancing information is not exposed or displays wrong info. This patchset tries to correct it. Before change: /proc/pid/sched clock-delta : 12 mm->numa_scan_seq : 34 numa_migrations, 1 numa_faults_memory, 0, 0, 1, 0, -1 numa_faults_memory, 1, 0, 0, 0, -1 numa_faults_memory, 0, 1, 0, 0, -1 numa_faults_memory, 1, 1, 0, 0, -1 numa_faults_memory, 0, 2, 0, 0, -1 numa_faults_memory, 1, 2, 0, 0, -1 numa_faults_memory, 0, 3, 0, 0, -1 numa_faults_memory, 1, 3, 0, 0, -1 After change: /proc/pid/sched clock-delta : 12 mm->numa_scan_seq : 34 numa_pages_migrated : 1 numa_preferred_nid : 0 total_numa_faults : 2627 current_node=0, numa_group_id=6958 numa_faults node=0 task_private=1344 task_shared=0 group_private=1344 group_shared=0 numa_faults node=1 task_private=641 task_shared=65 group_private=641 group_shared=65 numa_faults node=2 task_private=512 task_shared=0 group_private=512 group_shared=0 numa_faults node=3 task_private=64 task_shared=1 group_private=64 group_shared=1 Srikar Dronamraju (3): sched: Move print_cfs_rq declaration to kernel/sched/sched.h sched/numa: Show numa_group id in sched_debug task listings sched/numa: Fix numabalancing stats in /proc/pid/sched include/linux/sched.h | 2 -- kernel/sched/debug.c | 40 ++++++++++++++++++---------------------- kernel/sched/fair.c | 22 +++++++++++++++++++++- kernel/sched/sched.h | 13 +++++++++++++ 4 files changed, 52 insertions(+), 25 deletions(-) -- 1.8.3.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
