diff for duplicates of <20170324123710.GA10672@aaronlu.sh.intel.com> diff --git a/a/1.txt b/N1/1.txt index 587479c..1383c1f 100644 --- a/a/1.txt +++ b/N1/1.txt @@ -23,12 +23,12 @@ Still on EX, I restricted the allocation to be only on node 1, with 120G memory allocated there: max_active time compared to base lock from perf -base(no parallel) 3.81s A+-3.3% N/A <1% -1 3.10s A+-7.7% a??18.6% 14.76% -2 2.44s A+-13.6% a??35.9% 36.95% -4 2.07s A+-13.6% a??45.6% 59.67% -8 1.98s A+-0.4% a??48.0% 62.59% -16 2.01s A+-2.4% a??47.2% 79.62% +base(no parallel) 3.81s ±3.3% N/A <1% +1 3.10s ±7.7% ↓18.6% 14.76% +2 2.44s ±13.6% ↓35.9% 36.95% +4 2.07s ±13.6% ↓45.6% 59.67% +8 1.98s ±0.4% ↓48.0% 62.59% +16 2.01s ±2.4% ↓47.2% 79.62% If we can improve the scalibility of freeing a given zone, then parallel free will be able to achieve more. @@ -38,9 +38,3 @@ zone->lock in free_pcppages_bulk: 62.59% 62.59% [kernel.kallsyms] [k] native_queued_spin_lock_slowpath 37.17% native_queued_spin_lock_slowpath;_raw_spin_lock_irqsave;free_pcppages_bulk;free_hot_cold_page;free_hot_cold_page_list;release_pages;free_pages_and_swap_cache;tlb_flush_mmu_free_batches;batch_free_work;process_one_work;worker_thread;kthread;ret_from_fork 25.27% native_queued_spin_lock_slowpath;_raw_spin_lock_irqsave;release_pages;free_pages_and_swap_cache;tlb_flush_mmu_free_batches;batch_free_work;process_one_work;worker_thread;kthread;ret_from_fork - --- -To unsubscribe, send a message with 'unsubscribe linux-mm' in -the body to majordomo@kvack.org. For more info on Linux MM, -see: http://www.linux-mm.org/ . -Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a> diff --git a/a/content_digest b/N1/content_digest index 1daa505..abd9ac6 100644 --- a/a/content_digest +++ b/N1/content_digest @@ -40,12 +40,12 @@ "120G memory allocated there:\n" "\n" "max_active time compared to base lock from perf\n" - "base(no parallel) 3.81s A+-3.3% N/A <1%\n" - "1 3.10s A+-7.7% a??18.6% 14.76%\n" - "2 2.44s A+-13.6% a??35.9% 36.95%\n" - "4 2.07s A+-13.6% a??45.6% 59.67%\n" - "8 1.98s A+-0.4% a??48.0% 62.59%\n" - "16 2.01s A+-2.4% a??47.2% 79.62%\n" + "base(no parallel) 3.81s \302\2613.3% N/A <1%\n" + "1 3.10s \302\2617.7% \342\206\22318.6% 14.76%\n" + "2 2.44s \302\26113.6% \342\206\22335.9% 36.95%\n" + "4 2.07s \302\26113.6% \342\206\22345.6% 59.67%\n" + "8 1.98s \302\2610.4% \342\206\22348.0% 62.59%\n" + "16 2.01s \302\2612.4% \342\206\22347.2% 79.62%\n" "\n" "If we can improve the scalibility of freeing a given zone, then parallel\n" "free will be able to achieve more.\n" @@ -54,12 +54,6 @@ "zone->lock in free_pcppages_bulk:\n" " 62.59% 62.59% [kernel.kallsyms] [k] native_queued_spin_lock_slowpath\n" "37.17% native_queued_spin_lock_slowpath;_raw_spin_lock_irqsave;free_pcppages_bulk;free_hot_cold_page;free_hot_cold_page_list;release_pages;free_pages_and_swap_cache;tlb_flush_mmu_free_batches;batch_free_work;process_one_work;worker_thread;kthread;ret_from_fork\n" - "25.27% native_queued_spin_lock_slowpath;_raw_spin_lock_irqsave;release_pages;free_pages_and_swap_cache;tlb_flush_mmu_free_batches;batch_free_work;process_one_work;worker_thread;kthread;ret_from_fork\n" - "\n" - "--\n" - "To unsubscribe, send a message with 'unsubscribe linux-mm' in\n" - "the body to majordomo@kvack.org. For more info on Linux MM,\n" - "see: http://www.linux-mm.org/ .\n" - "Don't email: <a href=mailto:\"dont@kvack.org\"> email@kvack.org </a>" + 25.27% native_queued_spin_lock_slowpath;_raw_spin_lock_irqsave;release_pages;free_pages_and_swap_cache;tlb_flush_mmu_free_batches;batch_free_work;process_one_work;worker_thread;kthread;ret_from_fork -7fb31f74106204c804910ea52df6d95ae3eb813aec0fe8d11d27f7bb4371c17f +82c36a96c9d3f697dc7c8a81d2211fbd4916d59771cd5b02e3a526db06124e4f
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.