Subject: [merged] sched-add-tracepoints-related-to-numa-task-migration.patch removed from -mm tree To: mgorman@xxxxxxx,athorlton@xxxxxxx,riel@xxxxxxxxxx,mm-commits@xxxxxxxxxxxxxxx From: akpm@xxxxxxxxxxxxxxxxxxxx Date: Wed, 22 Jan 2014 12:14:46 -0800 The patch titled Subject: sched: add tracepoints related to NUMA task migration has been removed from the -mm tree. Its filename was sched-add-tracepoints-related-to-numa-task-migration.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Mel Gorman <mgorman@xxxxxxx> Subject: sched: add tracepoints related to NUMA task migration This patch adds three tracepoints o trace_sched_move_numa when a task is moved to a node o trace_sched_swap_numa when a task is swapped with another task o trace_sched_stick_numa when a numa-related migration fails The tracepoints allow the NUMA scheduler activity to be monitored and the following high-level metrics can be calculated o NUMA migrated stuck nr trace_sched_stick_numa o NUMA migrated idle nr trace_sched_move_numa o NUMA migrated swapped nr trace_sched_swap_numa o NUMA local swapped trace_sched_swap_numa src_nid == dst_nid (should never happen) o NUMA remote swapped trace_sched_swap_numa src_nid != dst_nid (should == NUMA migrated swapped) o NUMA group swapped trace_sched_swap_numa src_ngid == dst_ngid Maybe a small number of these are acceptable but a high number would be a major surprise. It would be even worse if bounces are frequent. o NUMA avg task migs. Average number of migrations for tasks o NUMA stddev task mig Self-explanatory o NUMA max task migs. Maximum number of migrations for a single task In general the intent of the tracepoints is to help diagnose problems where automatic NUMA balancing appears to be doing an excessive amount of useless work. [akpm@xxxxxxxxxxxxxxxxxxxx: remove semicolon-after-if, repair coding-style] Signed-off-by: Mel Gorman <mgorman@xxxxxxx> Reviewed-by: Rik van Riel <riel@xxxxxxxxxx> Cc: Alex Thorlton <athorlton@xxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/trace/events/sched.h | 87 +++++++++++++++++++++++++++++++++ kernel/sched/core.c | 2 kernel/sched/fair.c | 6 +- 3 files changed, 94 insertions(+), 1 deletion(-) diff -puN include/trace/events/sched.h~sched-add-tracepoints-related-to-numa-task-migration include/trace/events/sched.h --- a/include/trace/events/sched.h~sched-add-tracepoints-related-to-numa-task-migration +++ a/include/trace/events/sched.h @@ -443,6 +443,93 @@ TRACE_EVENT(sched_process_hang, ); #endif /* CONFIG_DETECT_HUNG_TASK */ +DECLARE_EVENT_CLASS(sched_move_task_template, + + TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu), + + TP_ARGS(tsk, src_cpu, dst_cpu), + + TP_STRUCT__entry( + __field( pid_t, pid ) + __field( pid_t, tgid ) + __field( pid_t, ngid ) + __field( int, src_cpu ) + __field( int, src_nid ) + __field( int, dst_cpu ) + __field( int, dst_nid ) + ), + + TP_fast_assign( + __entry->pid = task_pid_nr(tsk); + __entry->tgid = task_tgid_nr(tsk); + __entry->ngid = task_numa_group_id(tsk); + __entry->src_cpu = src_cpu; + __entry->src_nid = cpu_to_node(src_cpu); + __entry->dst_cpu = dst_cpu; + __entry->dst_nid = cpu_to_node(dst_cpu); + ), + + TP_printk("pid=%d tgid=%d ngid=%d src_cpu=%d src_nid=%d dst_cpu=%d dst_nid=%d", + __entry->pid, __entry->tgid, __entry->ngid, + __entry->src_cpu, __entry->src_nid, + __entry->dst_cpu, __entry->dst_nid) +); + +/* + * Tracks migration of tasks from one runqueue to another. Can be used to + * detect if automatic NUMA balancing is bouncing between nodes + */ +DEFINE_EVENT(sched_move_task_template, sched_move_numa, + TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu), + + TP_ARGS(tsk, src_cpu, dst_cpu) +); + +DEFINE_EVENT(sched_move_task_template, sched_stick_numa, + TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu), + + TP_ARGS(tsk, src_cpu, dst_cpu) +); + +TRACE_EVENT(sched_swap_numa, + + TP_PROTO(struct task_struct *src_tsk, int src_cpu, + struct task_struct *dst_tsk, int dst_cpu), + + TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu), + + TP_STRUCT__entry( + __field( pid_t, src_pid ) + __field( pid_t, src_tgid ) + __field( pid_t, src_ngid ) + __field( int, src_cpu ) + __field( int, src_nid ) + __field( pid_t, dst_pid ) + __field( pid_t, dst_tgid ) + __field( pid_t, dst_ngid ) + __field( int, dst_cpu ) + __field( int, dst_nid ) + ), + + TP_fast_assign( + __entry->src_pid = task_pid_nr(src_tsk); + __entry->src_tgid = task_tgid_nr(src_tsk); + __entry->src_ngid = task_numa_group_id(src_tsk); + __entry->src_cpu = src_cpu; + __entry->src_nid = cpu_to_node(src_cpu); + __entry->dst_pid = task_pid_nr(dst_tsk); + __entry->dst_tgid = task_tgid_nr(dst_tsk); + __entry->dst_ngid = task_numa_group_id(dst_tsk); + __entry->dst_cpu = dst_cpu; + __entry->dst_nid = cpu_to_node(dst_cpu); + ), + + TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d", + __entry->src_pid, __entry->src_tgid, __entry->src_ngid, + __entry->src_cpu, __entry->src_nid, + __entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid, + __entry->dst_cpu, __entry->dst_nid) +); #endif /* _TRACE_SCHED_H */ /* This part must be outside protection */ diff -puN kernel/sched/core.c~sched-add-tracepoints-related-to-numa-task-migration kernel/sched/core.c --- a/kernel/sched/core.c~sched-add-tracepoints-related-to-numa-task-migration +++ a/kernel/sched/core.c @@ -1108,6 +1108,7 @@ int migrate_swap(struct task_struct *cur if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task))) goto out; + trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu); ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg); out: @@ -4603,6 +4604,7 @@ int migrate_task_to(struct task_struct * /* TODO: This is not properly updating schedstats */ + trace_sched_move_numa(p, curr_cpu, target_cpu); return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg); } diff -puN kernel/sched/fair.c~sched-add-tracepoints-related-to-numa-task-migration kernel/sched/fair.c --- a/kernel/sched/fair.c~sched-add-tracepoints-related-to-numa-task-migration +++ a/kernel/sched/fair.c @@ -1250,11 +1250,15 @@ static int task_numa_migrate(struct task p->numa_scan_period = task_scan_min(p); if (env.best_task == NULL) { - int ret = migrate_task_to(p, env.best_cpu); + ret = migrate_task_to(p, env.best_cpu); + if (ret != 0) + trace_sched_stick_numa(p, env.src_cpu, env.best_cpu); return ret; } ret = migrate_swap(p, env.best_task); + if (ret != 0) + trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task)); put_task_struct(env.best_task); return ret; } _ Patches currently in -mm which might be from mgorman@xxxxxxx are origin.patch mm-remove-bug_on-from-mlock_vma_page.patch x86-mm-account-for-tlb-flushes-only-when-debugging.patch x86-mm-clean-up-inconsistencies-when-flushing-tlb-ranges.patch x86-mm-eliminate-redundant-page-table-walk-during-tlb-range-flushing.patch x86-mm-change-tlb_flushall_shift-for-ivybridge.patch mm-x86-revisit-tlb_flushall_shift-tuning-for-page-flushes-except-on-ivybridge.patch mm-page_alloc-allow-__gfp_nofail-to-allocate-below-watermarks-after-reclaim.patch mm-munlock-fix-potential-race-with-thp-page-split.patch numa-add-a-sysctl-for-numa_balancing.patch numa-add-a-sysctl-for-numa_balancing-fix.patch mm-vmscan-shrink-all-slab-objects-if-tight-on-memory.patch mm-vmscan-call-numa-unaware-shrinkers-irrespective-of-nodemask.patch mm-vmscan-respect-numa-policy-mask-when-shrinking-slab-on-direct-reclaim.patch mm-vmscan-move-call-to-shrink_slab-to-shrink_zones.patch mm-vmscan-remove-shrink_control-arg-from-do_try_to_free_pages.patch mm-show-message-when-updating-min_free_kbytes-in-thp.patch mm-improve-documentation-of-page_order-v2.patch mm-improve-documentation-of-page_order-v2-fix.patch linux-next.patch mm-migratec-fix-setting-of-cpupid-on-page-migration-twice-against-normal-page.patch zsmalloc-move-it-under-mm.patch zram-promote-zram-from-staging.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html