summaryrefslogtreecommitdiff
path: root/mm/swapfile.c
diff options
context:
space:
mode:
authorHuang Ying <ying.huang@intel.com>2020-06-02 07:49:22 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2020-06-02 20:59:09 +0300
commit490705888107c3edf8c264ec930909107f76a984 (patch)
tree834c78c44b43de71a528ad4c6374bbfbec8c0fe7 /mm/swapfile.c
parent09fe06ce0bf5abe53b77a9515d7fb7579edec9c0 (diff)
downloadlinux-490705888107c3edf8c264ec930909107f76a984.tar.xz
swap: reduce lock contention on swap cache from swap slots allocation
In some swap scalability test, it is found that there are heavy lock contention on swap cache even if we have split one swap cache radix tree per swap device to one swap cache radix tree every 64 MB trunk in commit 4b3ef9daa4fc ("mm/swap: split swap cache into 64MB trunks"). The reason is as follow. After the swap device becomes fragmented so that there's no free swap cluster, the swap device will be scanned linearly to find the free swap slots. swap_info_struct->cluster_next is the next scanning base that is shared by all CPUs. So nearby free swap slots will be allocated for different CPUs. The probability for multiple CPUs to operate on the same 64 MB trunk is high. This causes the lock contention on the swap cache. To solve the issue, in this patch, for SSD swap device, a percpu version next scanning base (cluster_next_cpu) is added. Every CPU will use its own per-cpu next scanning base. And after finishing scanning a 64MB trunk, the per-cpu scanning base will be changed to the beginning of another randomly selected 64MB trunk. In this way, the probability for multiple CPUs to operate on the same 64 MB trunk is reduced greatly. Thus the lock contention is reduced too. For HDD, because sequential access is more important for IO performance, the original shared next scanning base is used. To test the patch, we have run 16-process pmbench memory benchmark on a 2-socket server machine with 48 cores. One ram disk is configured as the swap device per socket. The pmbench working-set size is much larger than the available memory so that swapping is triggered. The memory read/write ratio is 80/20 and the accessing pattern is random. In the original implementation, the lock contention on the swap cache is heavy. The perf profiling data of the lock contention code path is as following, _raw_spin_lock_irq.add_to_swap_cache.add_to_swap.shrink_page_list: 7.91 _raw_spin_lock_irqsave.__remove_mapping.shrink_page_list: 7.11 _raw_spin_lock.swapcache_free_entries.free_swap_slot.__swap_entry_free: 2.51 _raw_spin_lock_irqsave.swap_cgroup_record.mem_cgroup_uncharge_swap: 1.66 _raw_spin_lock_irq.shrink_inactive_list.shrink_lruvec.shrink_node: 1.29 _raw_spin_lock.free_pcppages_bulk.drain_pages_zone.drain_pages: 1.03 _raw_spin_lock_irq.shrink_active_list.shrink_lruvec.shrink_node: 0.93 After applying this patch, it becomes, _raw_spin_lock.swapcache_free_entries.free_swap_slot.__swap_entry_free: 3.58 _raw_spin_lock_irq.shrink_inactive_list.shrink_lruvec.shrink_node: 2.3 _raw_spin_lock_irqsave.swap_cgroup_record.mem_cgroup_uncharge_swap: 2.26 _raw_spin_lock_irq.shrink_active_list.shrink_lruvec.shrink_node: 1.8 _raw_spin_lock.free_pcppages_bulk.drain_pages_zone.drain_pages: 1.19 The lock contention on the swap cache is almost eliminated. And the pmbench score increases 18.5%. The swapin throughput increases 18.7% from 2.96 GB/s to 3.51 GB/s. While the swapout throughput increases 18.5% from 2.99 GB/s to 3.54 GB/s. We need really fast disk to show the benefit. I have tried this on 2 Intel P3600 NVMe disks. The performance improvement is only about 1%. The improvement should be better on the faster disks, such as Intel Optane disk. [ying.huang@intel.com: fix cluster_next_cpu allocation and freeing, per Daniel] Link: http://lkml.kernel.org/r/20200525002648.336325-1-ying.huang@intel.com [ying.huang@intel.com: v4] Link: http://lkml.kernel.org/r/20200529010840.928819-1-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Tim Chen <tim.c.chen@linux.intel.com> Cc: Hugh Dickins <hughd@google.com> Link: http://lkml.kernel.org/r/20200520031502.175659-1-ying.huang@intel.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/swapfile.c')
-rw-r--r--mm/swapfile.c61
1 files changed, 56 insertions, 5 deletions
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 18dfccb91123..c531d2687dd0 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -613,10 +613,12 @@ new_cluster:
} else if (!cluster_list_empty(&si->discard_clusters)) {
/*
* we don't have free cluster but have some clusters in
- * discarding, do discard now and reclaim them
+ * discarding, do discard now and reclaim them, then
+ * reread cluster_next_cpu since we dropped si->lock
*/
swap_do_scheduled_discard(si);
- *scan_base = *offset = si->cluster_next;
+ *scan_base = this_cpu_read(*si->cluster_next_cpu);
+ *offset = *scan_base;
goto new_cluster;
} else
return false;
@@ -722,6 +724,34 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
}
}
+static void set_cluster_next(struct swap_info_struct *si, unsigned long next)
+{
+ unsigned long prev;
+
+ if (!(si->flags & SWP_SOLIDSTATE)) {
+ si->cluster_next = next;
+ return;
+ }
+
+ prev = this_cpu_read(*si->cluster_next_cpu);
+ /*
+ * Cross the swap address space size aligned trunk, choose
+ * another trunk randomly to avoid lock contention on swap
+ * address space if possible.
+ */
+ if ((prev >> SWAP_ADDRESS_SPACE_SHIFT) !=
+ (next >> SWAP_ADDRESS_SPACE_SHIFT)) {
+ /* No free swap slots available */
+ if (si->highest_bit <= si->lowest_bit)
+ return;
+ next = si->lowest_bit +
+ prandom_u32_max(si->highest_bit - si->lowest_bit + 1);
+ next = ALIGN_DOWN(next, SWAP_ADDRESS_SPACE_PAGES);
+ next = max_t(unsigned int, next, si->lowest_bit);
+ }
+ this_cpu_write(*si->cluster_next_cpu, next);
+}
+
static int scan_swap_map_slots(struct swap_info_struct *si,
unsigned char usage, int nr,
swp_entry_t slots[])
@@ -746,7 +776,16 @@ static int scan_swap_map_slots(struct swap_info_struct *si,
*/
si->flags += SWP_SCANNING;
- scan_base = offset = si->cluster_next;
+ /*
+ * Use percpu scan base for SSD to reduce lock contention on
+ * cluster and swap cache. For HDD, sequential access is more
+ * important.
+ */
+ if (si->flags & SWP_SOLIDSTATE)
+ scan_base = this_cpu_read(*si->cluster_next_cpu);
+ else
+ scan_base = si->cluster_next;
+ offset = scan_base;
/* SSD algorithm */
if (si->cluster_info) {
@@ -835,7 +874,6 @@ checks:
unlock_cluster(ci);
swap_range_alloc(si, offset, 1);
- si->cluster_next = offset + 1;
slots[n_ret++] = swp_entry(si->type, offset);
/* got enough slots or reach max slots? */
@@ -884,6 +922,7 @@ checks:
}
done:
+ set_cluster_next(si, offset + 1);
si->flags -= SWP_SCANNING;
return n_ret;
@@ -2653,6 +2692,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
mutex_unlock(&swapon_mutex);
free_percpu(p->percpu_cluster);
p->percpu_cluster = NULL;
+ free_percpu(p->cluster_next_cpu);
+ p->cluster_next_cpu = NULL;
vfree(swap_map);
kvfree(cluster_info);
kvfree(frontswap_map);
@@ -3205,11 +3246,19 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
unsigned long ci, nr_cluster;
p->flags |= SWP_SOLIDSTATE;
+ p->cluster_next_cpu = alloc_percpu(unsigned int);
+ if (!p->cluster_next_cpu) {
+ error = -ENOMEM;
+ goto bad_swap_unlock_inode;
+ }
/*
* select a random position to start with to help wear leveling
* SSD
*/
- p->cluster_next = 1 + prandom_u32_max(p->highest_bit);
+ for_each_possible_cpu(cpu) {
+ per_cpu(*p->cluster_next_cpu, cpu) =
+ 1 + prandom_u32_max(p->highest_bit);
+ }
nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER);
cluster_info = kvcalloc(nr_cluster, sizeof(*cluster_info),
@@ -3325,6 +3374,8 @@ bad_swap_unlock_inode:
bad_swap:
free_percpu(p->percpu_cluster);
p->percpu_cluster = NULL;
+ free_percpu(p->cluster_next_cpu);
+ p->cluster_next_cpu = NULL;
if (inode && S_ISBLK(inode->i_mode) && p->bdev) {
set_blocksize(p->bdev, p->old_block_size);
blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);