ceph: remove reliance on bdi congestion

The bdi congestion tracking in not widely used and will be removed.

CEPHfs is one of a small number of filesystems that uses it, setting just
the async (write) congestion flags at what it determines are appropriate
times.

The only remaining effect of the async flag is to cause (some)
WB_SYNC_NONE writes to be skipped.

So instead of setting the flag, set an internal flag and change:

 - .writepages to do nothing if WB_SYNC_NONE and the flag is set

 - .writepage to return AOP_WRITEPAGE_ACTIVATE if WB_SYNC_NONE and the
   flag is set.

The writepages change causes a behavioural change in that pageout() can
now return PAGE_ACTIVATE instead of PAGE_KEEP, so SetPageActive() will
be called on the page which (I think) wil further delay the next attempt
at writeout.  This might be a good thing.

Link: https://lkml.kernel.org/r/164549983739.9187.14895675781408171186.stgit@noble.brown
Signed-off-by: NeilBrown <neilb@suse.de>
Cc: Anna Schumaker <Anna.Schumaker@Netapp.com>
Cc: Chao Yu <chao@kernel.org>
Cc: Darrick J. Wong <djwong@kernel.org>
Cc: Ilya Dryomov <idryomov@gmail.com>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jeff Layton <jlayton@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Lars Ellenberg <lars.ellenberg@linbit.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Paolo Valente <paolo.valente@linaro.org>
Cc: Philipp Reisner <philipp.reisner@linbit.com>
Cc: Ryusuke Konishi <konishi.ryusuke@gmail.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index c98e5238a1b6ae16dccaed2c4a4e92589329ccfa..dc7af34640dd4a2f8c920815726867c1996e325d 100644 (file)
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -563,7 +563,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 
        if (atomic_long_inc_return(&fsc->writeback_count) >
            CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
-               set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
+               fsc->write_congested = true;
 
        req = ceph_osdc_new_request(osdc, &ci->i_layout, ceph_vino(inode), page_off, &len, 0, 1,
                                    CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE, snapc,
@@ -623,7 +623,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 
        if (atomic_long_dec_return(&fsc->writeback_count) <
            CONGESTION_OFF_THRESH(fsc->mount_options->congestion_kb))
-               clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
+               fsc->write_congested = false;
 
        return err;
 }
@@ -635,6 +635,10 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc)
        BUG_ON(!inode);
        ihold(inode);
 
+       if (wbc->sync_mode == WB_SYNC_NONE &&
+           ceph_inode_to_client(inode)->write_congested)
+               return AOP_WRITEPAGE_ACTIVATE;
+
        wait_on_page_fscache(page);
 
        err = writepage_nounlock(page, wbc);
@@ -707,8 +711,7 @@ static void writepages_finish(struct ceph_osd_request *req)
                        if (atomic_long_dec_return(&fsc->writeback_count) <
                             CONGESTION_OFF_THRESH(
                                        fsc->mount_options->congestion_kb))
-                               clear_bdi_congested(inode_to_bdi(inode),
-                                                   BLK_RW_ASYNC);
+                               fsc->write_congested = false;
 
                        ceph_put_snap_context(detach_page_private(page));
                        end_page_writeback(page);
@@ -760,6 +763,10 @@ static int ceph_writepages_start(struct address_space *mapping,
        bool done = false;
        bool caching = ceph_is_cache_enabled(inode);
 
+       if (wbc->sync_mode == WB_SYNC_NONE &&
+           fsc->write_congested)
+               return 0;
+
        dout("writepages_start %p (mode=%s)\n", inode,
             wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
             (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
@@ -954,11 +961,8 @@ get_more_pages:
 
                        if (atomic_long_inc_return(&fsc->writeback_count) >
                            CONGESTION_ON_THRESH(
-                                   fsc->mount_options->congestion_kb)) {
-                               set_bdi_congested(inode_to_bdi(inode),
-                                                 BLK_RW_ASYNC);
-                       }
-
+                                   fsc->mount_options->congestion_kb))
+                               fsc->write_congested = true;
 
                        pages[locked_pages++] = page;
                        pvec.pages[i] = NULL;

diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index bf79f369aec687f4058e3b8fbb78dd7a79e88866..4a3b77d049c76e588151a5fb5054272271aa711a 100644 (file)
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -802,6 +802,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
        fsc->have_copy_from2 = true;
 
        atomic_long_set(&fsc->writeback_count, 0);
+       fsc->write_congested = false;
 
        err = -ENOMEM;
        /*

diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 67f145e1ae7a34fce7e0b5d772d9143c25b837a9..0bd97aea231910a20c53bc1dfc9488b939ebcafa 100644 (file)
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -121,6 +121,7 @@ struct ceph_fs_client {
        struct ceph_mds_client *mdsc;
 
        atomic_long_t writeback_count;
+       bool write_congested;
 
        struct workqueue_struct *inode_wq;
        struct workqueue_struct *cap_wq;