Btrfs: add support for blkio controllers

This attaches accounting information to bios as we submit them so the
new blkio controllers can throttle on btrfs filesystems.

Not much is required, we're just associating bios with blkcgs during clone,
calling wbc_init_bio()/wbc_account_io() during writepages submission,
and attaching the bios to the current context during direct IO.

Finally if we are splitting bios during btrfs_map_bio, this attaches
accounting information to the split.

The end result is able to throttle nicely on single disk filesystems.  A
little more work is required for multi-device filesystems.

Signed-off-by: Chris Mason <clm@fb.com>

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f7536bc..230546b 100644 (file)
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1724,6 +1724,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
        bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
        bdi->congested_fn       = btrfs_congested_fn;
        bdi->congested_data     = info;
+       bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
        return 0;
 }
 

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 02d0581..b9755ce 100644 (file)
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2730,6 +2730,9 @@ struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask)
                btrfs_bio->csum = NULL;
                btrfs_bio->csum_allocated = NULL;
                btrfs_bio->end_io = NULL;
+               /* FIXME, put this into bio_clone_bioset */
+               if (bio->bi_css)
+                       bio_associate_blkcg(new, bio->bi_css);
        }
        return new;
 }
@@ -2790,6 +2793,7 @@ static int merge_bio(int rw, struct extent_io_tree *tree, struct page *page,
 }
 
 static int submit_extent_page(int rw, struct extent_io_tree *tree,
+                             struct writeback_control *wbc,
                              struct page *page, sector_t sector,
                              size_t size, unsigned long offset,
                              struct block_device *bdev,
@@ -2826,6 +2830,8 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
                        }
                        bio = NULL;
                } else {
+                       if (wbc)
+                               wbc_account_io(wbc, page, page_size);
                        return 0;
                }
        }
@@ -2841,6 +2847,10 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
        bio_add_page(bio, page, page_size, offset);
        bio->bi_end_io = end_io_func;
        bio->bi_private = tree;
+       if (wbc) {
+               wbc_init_bio(wbc, bio);
+               wbc_account_io(wbc, page, page_size);
+       }
 
        if (bio_ret)
                *bio_ret = bio;
@@ -3051,7 +3061,7 @@ static int __do_readpage(struct extent_io_tree *tree,
                }
 
                pnr -= page->index;
-               ret = submit_extent_page(rw, tree, page,
+               ret = submit_extent_page(rw, tree, NULL, page,
                                         sector, disk_io_size, pg_offset,
                                         bdev, bio, pnr,
                                         end_bio_extent_readpage, mirror_num,
@@ -3446,7 +3456,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
                                       page->index, cur, end);
                        }
 
-                       ret = submit_extent_page(write_flags, tree, page,
+                       ret = submit_extent_page(write_flags, tree, wbc, page,
                                                 sector, iosize, pg_offset,
                                                 bdev, &epd->bio, max_nr,
                                                 end_bio_extent_writepage,
@@ -3749,7 +3759,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 
                clear_page_dirty_for_io(p);
                set_page_writeback(p);
-               ret = submit_extent_page(rw, tree, p, offset >> 9,
+               ret = submit_extent_page(rw, tree, wbc, p, offset >> 9,
                                         PAGE_CACHE_SIZE, 0, bdev, &epd->bio,
                                         -1, end_bio_extent_buffer_writepage,
                                         0, epd->bio_flags, bio_flags);

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 79a7364..bda3c41 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7987,7 +7987,11 @@ static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev,
                                       u64 first_sector, gfp_t gfp_flags)
 {
        int nr_vecs = bio_get_nr_vecs(bdev);
-       return btrfs_bio_alloc(bdev, first_sector, nr_vecs, gfp_flags);
+       struct bio *bio;
+       bio = btrfs_bio_alloc(bdev, first_sector, nr_vecs, gfp_flags);
+       if (bio)
+               bio_associate_current(bio);
+       return bio;
 }
 
 static inline int btrfs_lookup_and_bind_dio_csum(struct btrfs_root *root,

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index cd7ef34..d366dd4 100644 (file)
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1033,6 +1033,7 @@ static int btrfs_fill_super(struct super_block *sb,
        sb->s_flags |= MS_POSIXACL;
 #endif
        sb->s_flags |= MS_I_VERSION;
+       sb->s_iflags |= SB_I_CGROUPWB;
        err = open_ctree(sb, fs_devices, (char *)data);
        if (err) {
                printk(KERN_ERR "BTRFS: open_ctree failed\n");

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index fb9abf1..88e2fe9 100644 (file)
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5942,6 +5942,14 @@ again:
        if (!bio)
                return -ENOMEM;
 
+       if (first_bio->bi_ioc) {
+               get_io_context_active(first_bio->bi_ioc);
+               bio->bi_ioc = first_bio->bi_ioc;
+       }
+       if (first_bio->bi_css) {
+               css_get(first_bio->bi_css);
+               bio->bi_css = first_bio->bi_css;
+       }
        while (bvec <= (first_bio->bi_io_vec + first_bio->bi_vcnt - 1)) {
                if (bio_add_page(bio, bvec->bv_page, bvec->bv_len,
                                 bvec->bv_offset) < bvec->bv_len) {