From b430e9d1c6d416306d44dbf3aa3148be7af78abc Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Wed, 3 Jul 2013 15:01:24 -0700 Subject: [PATCH] mm: remove compressed copy from zram in-memory Swap subsystem does lazy swap slot free with expecting the page would be swapped out again so we can avoid unnecessary write. But the problem in in-memory swap(ex, zram) is that it consumes memory space until vm_swap_full(ie, used half of all of swap device) condition meet. It could be bad if we use multiple swap device, small in-memory swap and big storage swap or in-memory swap alone. This patch makes swap subsystem free swap slot as soon as swap-read is completed and make the swapcache page dirty so the page should be written out the swap device to reclaim it. It means we never lose it. I tested this patch with kernel compile workload. 1. before compile time : 9882.42 zram max wasted space by fragmentation: 13471881 byte memory space consumed by zram: 174227456 byte the number of slot free notify: 206684 2. after compile time : 9653.90 zram max wasted space by fragmentation: 11805932 byte memory space consumed by zram: 154001408 byte the number of slot free notify: 426972 [akpm@linux-foundation.org: tweak comment text] [artem.savkov@gmail.com: fix BUG due to non-swapcache pages in end_swap_bio_read()] [akpm@linux-foundation.org: invert unlikely() test, augment comment, 80-col cleanup] Signed-off-by: Dan Magenheimer Signed-off-by: Minchan Kim Signed-off-by: Artem Savkov Cc: Hugh Dickins Cc: Seth Jennings Cc: Nitin Gupta Cc: Konrad Rzeszutek Wilk Cc: Shaohua Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_io.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 48 insertions(+), 2 deletions(-) diff --git a/mm/page_io.c b/mm/page_io.c index a8a3ef45fed7..ba05b64e5d8d 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -21,6 +21,7 @@ #include #include #include +#include #include static struct bio *get_swap_bio(gfp_t gfp_flags, @@ -80,9 +81,54 @@ void end_swap_bio_read(struct bio *bio, int err) imajor(bio->bi_bdev->bd_inode), iminor(bio->bi_bdev->bd_inode), (unsigned long long)bio->bi_sector); - } else { - SetPageUptodate(page); + goto out; } + + SetPageUptodate(page); + + /* + * There is no guarantee that the page is in swap cache - the software + * suspend code (at least) uses end_swap_bio_read() against a non- + * swapcache page. So we must check PG_swapcache before proceeding with + * this optimization. + */ + if (likely(PageSwapCache(page))) { + struct swap_info_struct *sis; + + sis = page_swap_info(page); + if (sis->flags & SWP_BLKDEV) { + /* + * The swap subsystem performs lazy swap slot freeing, + * expecting that the page will be swapped out again. + * So we can avoid an unnecessary write if the page + * isn't redirtied. + * This is good for real swap storage because we can + * reduce unnecessary I/O and enhance wear-leveling + * if an SSD is used as the as swap device. + * But if in-memory swap device (eg zram) is used, + * this causes a duplicated copy between uncompressed + * data in VM-owned memory and compressed data in + * zram-owned memory. So let's free zram-owned memory + * and make the VM-owned decompressed page *dirty*, + * so the page should be swapped out somewhere again if + * we again wish to reclaim it. + */ + struct gendisk *disk = sis->bdev->bd_disk; + if (disk->fops->swap_slot_free_notify) { + swp_entry_t entry; + unsigned long offset; + + entry.val = page_private(page); + offset = swp_offset(entry); + + SetPageDirty(page); + disk->fops->swap_slot_free_notify(sis->bdev, + offset); + } + } + } + +out: unlock_page(page); bio_put(bio); }