From af1839d722c986ffeaae1e70a6ef1c75ff38dcd5 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 15:51:01 -0800 Subject: mm: numa: trace tasks that fail migration due to rate limiting A low local/remote numa hinting fault ratio is potentially explained by failed migrations. This patch adds a tracepoint that fires when migration fails due to migration rate limitation. Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Cc: Alex Thorlton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/migrate.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index ec2a6cc..3075ffb 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -45,6 +45,32 @@ TRACE_EVENT(mm_migrate_pages, __print_symbolic(__entry->reason, MIGRATE_REASON)) ); +TRACE_EVENT(mm_numa_migrate_ratelimit, + + TP_PROTO(struct task_struct *p, int dst_nid, unsigned long nr_pages), + + TP_ARGS(p, dst_nid, nr_pages), + + TP_STRUCT__entry( + __array( char, comm, TASK_COMM_LEN) + __field( pid_t, pid) + __field( int, dst_nid) + __field( unsigned long, nr_pages) + ), + + TP_fast_assign( + memcpy(__entry->comm, p->comm, TASK_COMM_LEN); + __entry->pid = p->pid; + __entry->dst_nid = dst_nid; + __entry->nr_pages = nr_pages; + ), + + TP_printk("comm=%s pid=%d dst_nid=%d nr_pages=%lu", + __entry->comm, + __entry->pid, + __entry->dst_nid, + __entry->nr_pages) +); #endif /* _TRACE_MIGRATE_H */ /* This part must be outside protection */ -- cgit v1.1 From 286549dcaf4f128cb04f0ad56dfb677d7d19b500 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 15:51:03 -0800 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@linux-foundation.org: remove semicolon-after-if, repair coding-style] Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Cc: Alex Thorlton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/sched.h | 87 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 87 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index 04c3084..67e1bbf 100644 --- a/include/trace/events/sched.h +++ b/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 */ -- cgit v1.1 From 0eb927c0ab789d3d7d69f68acb850f69d4e7c36f Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 21 Jan 2014 15:51:05 -0800 Subject: mm: compaction: trace compaction begin and end The broad goal of the series is to improve allocation success rates for huge pages through memory compaction, while trying not to increase the compaction overhead. The original objective was to reintroduce capturing of high-order pages freed by the compaction, before they are split by concurrent activity. However, several bugs and opportunities for simple improvements were found in the current implementation, mostly through extra tracepoints (which are however too ugly for now to be considered for sending). The patches mostly deal with two mechanisms that reduce compaction overhead, which is caching the progress of migrate and free scanners, and marking pageblocks where isolation failed to be skipped during further scans. Patch 1 (from mgorman) adds tracepoints that allow calculate time spent in compaction and potentially debug scanner pfn values. Patch 2 encapsulates the some functionality for handling deferred compactions for better maintainability, without a functional change type is not determined without being actually needed. Patch 3 fixes a bug where cached scanner pfn's are sometimes reset only after they have been read to initialize a compaction run. Patch 4 fixes a bug where scanners meeting is sometimes not properly detected and can lead to multiple compaction attempts quitting early without doing any work. Patch 5 improves the chances of sync compaction to process pageblocks that async compaction has skipped due to being !MIGRATE_MOVABLE. Patch 6 improves the chances of sync direct compaction to actually do anything when called after async compaction fails during allocation slowpath. The impact of patches were validated using mmtests's stress-highalloc benchmark with mmtests's stress-highalloc benchmark on a x86_64 machine with 4GB memory. Due to instability of the results (mostly related to the bugs fixed by patches 2 and 3), 10 iterations were performed, taking min,mean,max values for success rates and mean values for time and vmstat-based metrics. First, the default GFP_HIGHUSER_MOVABLE allocations were tested with the patches stacked on top of v3.13-rc2. Patch 2 is OK to serve as baseline due to no functional changes in 1 and 2. Comments below. stress-highalloc 3.13-rc2 3.13-rc2 3.13-rc2 3.13-rc2 3.13-rc2 2-nothp 3-nothp 4-nothp 5-nothp 6-nothp Success 1 Min 9.00 ( 0.00%) 10.00 (-11.11%) 43.00 (-377.78%) 43.00 (-377.78%) 33.00 (-266.67%) Success 1 Mean 27.50 ( 0.00%) 25.30 ( 8.00%) 45.50 (-65.45%) 45.90 (-66.91%) 46.30 (-68.36%) Success 1 Max 36.00 ( 0.00%) 36.00 ( 0.00%) 47.00 (-30.56%) 48.00 (-33.33%) 52.00 (-44.44%) Success 2 Min 10.00 ( 0.00%) 8.00 ( 20.00%) 46.00 (-360.00%) 45.00 (-350.00%) 35.00 (-250.00%) Success 2 Mean 26.40 ( 0.00%) 23.50 ( 10.98%) 47.30 (-79.17%) 47.60 (-80.30%) 48.10 (-82.20%) Success 2 Max 34.00 ( 0.00%) 33.00 ( 2.94%) 48.00 (-41.18%) 50.00 (-47.06%) 54.00 (-58.82%) Success 3 Min 65.00 ( 0.00%) 63.00 ( 3.08%) 85.00 (-30.77%) 84.00 (-29.23%) 85.00 (-30.77%) Success 3 Mean 76.70 ( 0.00%) 70.50 ( 8.08%) 86.20 (-12.39%) 85.50 (-11.47%) 86.00 (-12.13%) Success 3 Max 87.00 ( 0.00%) 86.00 ( 1.15%) 88.00 ( -1.15%) 87.00 ( 0.00%) 87.00 ( 0.00%) 3.13-rc2 3.13-rc2 3.13-rc2 3.13-rc2 3.13-rc2 2-nothp 3-nothp 4-nothp 5-nothp 6-nothp User 6437.72 6459.76 5960.32 5974.55 6019.67 System 1049.65 1049.09 1029.32 1031.47 1032.31 Elapsed 1856.77 1874.48 1949.97 1994.22 1983.15 3.13-rc2 3.13-rc2 3.13-rc2 3.13-rc2 3.13-rc2 2-nothp 3-nothp 4-nothp 5-nothp 6-nothp Minor Faults 253952267 254581900 250030122 250507333 250157829 Major Faults 420 407 506 530 530 Swap Ins 4 9 9 6 6 Swap Outs 398 375 345 346 333 Direct pages scanned 197538 189017 298574 287019 299063 Kswapd pages scanned 1809843 1801308 1846674 1873184 1861089 Kswapd pages reclaimed 1806972 1798684 1844219 1870509 1858622 Direct pages reclaimed 197227 188829 298380 286822 298835 Kswapd efficiency 99% 99% 99% 99% 99% Kswapd velocity 953.382 970.449 952.243 934.569 922.286 Direct efficiency 99% 99% 99% 99% 99% Direct velocity 104.058 101.832 153.961 143.200 148.205 Percentage direct scans 9% 9% 13% 13% 13% Zone normal velocity 347.289 359.676 348.063 339.933 332.983 Zone dma32 velocity 710.151 712.605 758.140 737.835 737.507 Zone dma velocity 0.000 0.000 0.000 0.000 0.000 Page writes by reclaim 557.600 429.000 353.600 426.400 381.800 Page writes file 159 53 7 79 48 Page writes anon 398 375 345 346 333 Page reclaim immediate 825 644 411 575 420 Sector Reads 2781750 2769780 2878547 2939128 2910483 Sector Writes 12080843 12083351 12012892 12002132 12010745 Page rescued immediate 0 0 0 0 0 Slabs scanned 1575654 1545344 1778406 1786700 1794073 Direct inode steals 9657 10037 15795 14104 14645 Kswapd inode steals 46857 46335 50543 50716 51796 Kswapd skipped wait 0 0 0 0 0 THP fault alloc 97 91 81 71 77 THP collapse alloc 456 506 546 544 565 THP splits 6 5 5 4 4 THP fault fallback 0 1 0 0 0 THP collapse fail 14 14 12 13 12 Compaction stalls 1006 980 1537 1536 1548 Compaction success 303 284 562 559 578 Compaction failures 702 696 974 976 969 Page migrate success 1177325 1070077 3927538 3781870 3877057 Page migrate failure 0 0 0 0 0 Compaction pages isolated 2547248 2306457 8301218 8008500 8200674 Compaction migrate scanned 42290478 38832618 153961130 154143900 159141197 Compaction free scanned 89199429 79189151 356529027 351943166 356326727 Compaction cost 1566 1426 5312 5156 5294 NUMA PTE updates 0 0 0 0 0 NUMA hint faults 0 0 0 0 0 NUMA hint local faults 0 0 0 0 0 NUMA hint local percent 100 100 100 100 100 NUMA pages migrated 0 0 0 0 0 AutoNUMA cost 0 0 0 0 0 Observations: - The "Success 3" line is allocation success rate with system idle (phases 1 and 2 are with background interference). I used to get stable values around 85% with vanilla 3.11. The lower min and mean values came with 3.12. This was bisected to commit 81c0a2bb ("mm: page_alloc: fair zone allocator policy") As explained in comment for patch 3, I don't think the commit is wrong, but that it makes the effect of compaction bugs worse. From patch 3 onwards, the results are OK and match the 3.11 results. - Patch 4 also clearly helps phases 1 and 2, and exceeds any results I've seen with 3.11 (I didn't measure it that thoroughly then, but it was never above 40%). - Compaction cost and number of scanned pages is higher, especially due to patch 4. However, keep in mind that patches 3 and 4 fix existing bugs in the current design of compaction overhead mitigation, they do not change it. If overhead is found unacceptable, then it should be decreased differently (and consistently, not due to random conditions) than the current implementation does. In contrast, patches 5 and 6 (which are not strictly bug fixes) do not increase the overhead (but also not success rates). This might be a limitation of the stress-highalloc benchmark as it's quite uniform. Another set of results is when configuring stress-highalloc t allocate with similar flags as THP uses: (GFP_HIGHUSER_MOVABLE|__GFP_NOMEMALLOC|__GFP_NORETRY|__GFP_NO_KSWAPD) stress-highalloc 3.13-rc2 3.13-rc2 3.13-rc2 3.13-rc2 3.13-rc2 2-thp 3-thp 4-thp 5-thp 6-thp Success 1 Min 2.00 ( 0.00%) 7.00 (-250.00%) 18.00 (-800.00%) 19.00 (-850.00%) 26.00 (-1200.00%) Success 1 Mean 19.20 ( 0.00%) 17.80 ( 7.29%) 29.20 (-52.08%) 29.90 (-55.73%) 32.80 (-70.83%) Success 1 Max 27.00 ( 0.00%) 29.00 ( -7.41%) 35.00 (-29.63%) 36.00 (-33.33%) 37.00 (-37.04%) Success 2 Min 3.00 ( 0.00%) 8.00 (-166.67%) 21.00 (-600.00%) 21.00 (-600.00%) 32.00 (-966.67%) Success 2 Mean 19.30 ( 0.00%) 17.90 ( 7.25%) 32.20 (-66.84%) 32.60 (-68.91%) 35.70 (-84.97%) Success 2 Max 27.00 ( 0.00%) 30.00 (-11.11%) 36.00 (-33.33%) 37.00 (-37.04%) 39.00 (-44.44%) Success 3 Min 62.00 ( 0.00%) 62.00 ( 0.00%) 85.00 (-37.10%) 75.00 (-20.97%) 64.00 ( -3.23%) Success 3 Mean 66.30 ( 0.00%) 65.50 ( 1.21%) 85.60 (-29.11%) 83.40 (-25.79%) 83.50 (-25.94%) Success 3 Max 70.00 ( 0.00%) 69.00 ( 1.43%) 87.00 (-24.29%) 86.00 (-22.86%) 87.00 (-24.29%) 3.13-rc2 3.13-rc2 3.13-rc2 3.13-rc2 3.13-rc2 2-thp 3-thp 4-thp 5-thp 6-thp User 6547.93 6475.85 6265.54 6289.46 6189.96 System 1053.42 1047.28 1043.23 1042.73 1038.73 Elapsed 1835.43 1821.96 1908.67 1912.74 1956.38 3.13-rc2 3.13-rc2 3.13-rc2 3.13-rc2 3.13-rc2 2-thp 3-thp 4-thp 5-thp 6-thp Minor Faults 256805673 253106328 253222299 249830289 251184418 Major Faults 395 375 423 434 448 Swap Ins 12 10 10 12 9 Swap Outs 530 537 487 455 415 Direct pages scanned 71859 86046 153244 152764 190713 Kswapd pages scanned 1900994 1870240 1898012 1892864 1880520 Kswapd pages reclaimed 1897814 1867428 1894939 1890125 1877924 Direct pages reclaimed 71766 85908 153167 152643 190600 Kswapd efficiency 99% 99% 99% 99% 99% Kswapd velocity 1029.000 1067.782 1000.091 991.049 951.218 Direct efficiency 99% 99% 99% 99% 99% Direct velocity 38.897 49.127 80.747 79.983 96.468 Percentage direct scans 3% 4% 7% 7% 9% Zone normal velocity 351.377 372.494 348.910 341.689 335.310 Zone dma32 velocity 716.520 744.414 731.928 729.343 712.377 Zone dma velocity 0.000 0.000 0.000 0.000 0.000 Page writes by reclaim 669.300 604.000 545.700 538.900 429.900 Page writes file 138 66 58 83 14 Page writes anon 530 537 487 455 415 Page reclaim immediate 806 655 772 548 517 Sector Reads 2711956 2703239 2811602 2818248 2839459 Sector Writes 12163238 12018662 12038248 11954736 11994892 Page rescued immediate 0 0 0 0 0 Slabs scanned 1385088 1388364 1507968 1513292 1558656 Direct inode steals 1739 2564 4622 5496 6007 Kswapd inode steals 47461 46406 47804 48013 48466 Kswapd skipped wait 0 0 0 0 0 THP fault alloc 110 82 84 69 70 THP collapse alloc 445 482 467 462 539 THP splits 6 5 4 5 3 THP fault fallback 3 0 0 0 0 THP collapse fail 15 14 14 14 13 Compaction stalls 659 685 1033 1073 1111 Compaction success 222 225 410 427 456 Compaction failures 436 460 622 646 655 Page migrate success 446594 439978 1085640 1095062 1131716 Page migrate failure 0 0 0 0 0 Compaction pages isolated 1029475 1013490 2453074 2482698 2565400 Compaction migrate scanned 9955461 11344259 24375202 27978356 30494204 Compaction free scanned 27715272 28544654 80150615 82898631 85756132 Compaction cost 552 555 1344 1379 1436 NUMA PTE updates 0 0 0 0 0 NUMA hint faults 0 0 0 0 0 NUMA hint local faults 0 0 0 0 0 NUMA hint local percent 100 100 100 100 100 NUMA pages migrated 0 0 0 0 0 AutoNUMA cost 0 0 0 0 0 There are some differences from the previous results for THP-like allocations: - Here, the bad result for unpatched kernel in phase 3 is much more consistent to be between 65-70% and not related to the "regression" in 3.12. Still there is the improvement from patch 4 onwards, which brings it on par with simple GFP_HIGHUSER_MOVABLE allocations. - Compaction costs have increased, but nowhere near as much as the non-THP case. Again, the patches should be worth the gained determininsm. - Patches 5 and 6 somewhat increase the number of migrate-scanned pages. This is most likely due to __GFP_NO_KSWAPD flag, which means the cached pfn's and pageblock skip bits are not reset by kswapd that often (at least in phase 3 where no concurrent activity would wake up kswapd) and the patches thus help the sync-after-async compaction. It doesn't however show that the sync compaction would help so much with success rates, which can be again seen as a limitation of the benchmark scenario. This patch (of 6): Add two tracepoints for compaction begin and end of a zone. Using this it is possible to calculate how much time a workload is spending within compaction and potentially debug problems related to cached pfns for scanning. In combination with the direct reclaim and slab trace points it should be possible to estimate most allocation-related overhead for a workload. Signed-off-by: Mel Gorman Signed-off-by: Vlastimil Babka Cc: Rik van Riel Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/trace/events/compaction.h | 42 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 42 insertions(+) (limited to 'include/trace') diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h index fde1b3e..06f544e 100644 --- a/include/trace/events/compaction.h +++ b/include/trace/events/compaction.h @@ -67,6 +67,48 @@ TRACE_EVENT(mm_compaction_migratepages, __entry->nr_failed) ); +TRACE_EVENT(mm_compaction_begin, + TP_PROTO(unsigned long zone_start, unsigned long migrate_start, + unsigned long free_start, unsigned long zone_end), + + TP_ARGS(zone_start, migrate_start, free_start, zone_end), + + TP_STRUCT__entry( + __field(unsigned long, zone_start) + __field(unsigned long, migrate_start) + __field(unsigned long, free_start) + __field(unsigned long, zone_end) + ), + + TP_fast_assign( + __entry->zone_start = zone_start; + __entry->migrate_start = migrate_start; + __entry->free_start = free_start; + __entry->zone_end = zone_end; + ), + + TP_printk("zone_start=%lu migrate_start=%lu free_start=%lu zone_end=%lu", + __entry->zone_start, + __entry->migrate_start, + __entry->free_start, + __entry->zone_end) +); + +TRACE_EVENT(mm_compaction_end, + TP_PROTO(int status), + + TP_ARGS(status), + + TP_STRUCT__entry( + __field(int, status) + ), + + TP_fast_assign( + __entry->status = status; + ), + + TP_printk("status=%d", __entry->status) +); #endif /* _TRACE_COMPACTION_H */ -- cgit v1.1