From 81a0298bdfab0203d360df7c9bf690d1d457f999 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Wed, 6 Sep 2017 16:24:43 -0700 Subject: [PATCH] mm, swap: don't use VMA based swap readahead if HDD is used as swap VMA based swap readahead will readahead the virtual pages that is continuous in the virtual address space. While the original swap readahead will readahead the swap slots that is continuous in the swap device. Although VMA based swap readahead is more correct for the swap slots to be readahead, it will trigger more small random readings, which may cause the performance of HDD (hard disk) to degrade heavily, and may finally exceed the benefit. To avoid the issue, in this patch, if the HDD is used as swap, the VMA based swap readahead will be disabled, and the original swap readahead will be used instead. Link: http://lkml.kernel.org/r/20170807054038.1843-6-ying.huang@intel.com Signed-off-by: "Huang, Ying" Cc: Johannes Weiner Cc: Minchan Kim Cc: Rik van Riel Cc: Shaohua Li Cc: Hugh Dickins Cc: Fengguang Wu Cc: Tim Chen Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 11 ++++++----- mm/swapfile.c | 8 +++++++- 2 files changed, 13 insertions(+), 6 deletions(-) diff --git a/include/linux/swap.h b/include/linux/swap.h index 61d63379e956..9c4ae6f14eea 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -400,16 +400,17 @@ extern struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask, struct vm_fault *vmf, struct vma_swap_readahead *swap_ra); -static inline bool swap_use_vma_readahead(void) -{ - return READ_ONCE(swap_vma_readahead); -} - /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; +extern atomic_t nr_rotate_swap; extern bool has_usable_swap(void); +static inline bool swap_use_vma_readahead(void) +{ + return READ_ONCE(swap_vma_readahead) && !atomic_read(&nr_rotate_swap); +} + /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { diff --git a/mm/swapfile.c b/mm/swapfile.c index 42eff9e4e972..4f8b3e08a547 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -96,6 +96,8 @@ static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); +atomic_t nr_rotate_swap = ATOMIC_INIT(0); + static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include SWAP_HAS_CONT flag */ @@ -2569,6 +2571,9 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); + if (!p->bdev || !blk_queue_nonrot(bdev_get_queue(p->bdev))) + atomic_dec(&nr_rotate_swap); + mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); @@ -3145,7 +3150,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) cluster = per_cpu_ptr(p->percpu_cluster, cpu); cluster_set_null(&cluster->index); } - } + } else + atomic_inc(&nr_rotate_swap); error = swap_cgroup_swapon(p->type, maxpages); if (error)