nfs: remove reliance on bdi congestion

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

NFS is one of a small number of filesystems that uses it, setting just
the async (write) congestion flag 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/164549983738.9187.3972219847989393182.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/nfs/write.c b/fs/nfs/write.c
index 987a187bd39aa8ef6d7d8836b5a40634fbfa7815..7c986164018ec133fe6dd61b9e7079a0c3300973 100644 (file)
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -417,7 +417,7 @@ static void nfs_set_page_writeback(struct page *page)
 
        if (atomic_long_inc_return(&nfss->writeback) >
                        NFS_CONGESTION_ON_THRESH)
-               set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
+               nfss->write_congested = 1;
 }
 
 static void nfs_end_page_writeback(struct nfs_page *req)
@@ -433,7 +433,7 @@ static void nfs_end_page_writeback(struct nfs_page *req)
 
        end_page_writeback(req->wb_page);
        if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
-               clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
+               nfss->write_congested = 0;
 }
 
 /*
@@ -672,6 +672,10 @@ static int nfs_writepage_locked(struct page *page,
        struct inode *inode = page_file_mapping(page)->host;
        int err;
 
+       if (wbc->sync_mode == WB_SYNC_NONE &&
+           NFS_SERVER(inode)->write_congested)
+               return AOP_WRITEPAGE_ACTIVATE;
+
        nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
        nfs_pageio_init_write(&pgio, inode, 0,
                                false, &nfs_async_write_completion_ops);
@@ -719,6 +723,10 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
        int priority = 0;
        int err;
 
+       if (wbc->sync_mode == WB_SYNC_NONE &&
+           NFS_SERVER(inode)->write_congested)
+               return 0;
+
        nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
 
        if (!(mntflags & NFS_MOUNT_WRITE_EAGER) || wbc->for_kupdate ||
@@ -1893,7 +1901,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
        }
        nfss = NFS_SERVER(data->inode);
        if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
-               clear_bdi_congested(inode_to_bdi(data->inode), BLK_RW_ASYNC);
+               nfss->write_congested = 0;
 
        nfs_init_cinfo(&cinfo, data->inode, data->dreq);
        nfs_commit_end(cinfo.mds);

diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index ca0959e51e817cfd5002d79200da255077f85811..6aa2a200676aba0502898d50423f77614c366661 100644 (file)
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -138,6 +138,7 @@ struct nfs_server {
        struct nlm_host         *nlm_host;      /* NLM client handle */
        struct nfs_iostats __percpu *io_stats;  /* I/O statistics */
        atomic_long_t           writeback;      /* number of writeback pages */
+       unsigned int            write_congested;/* flag set when writeback gets too high */
        unsigned int            flags;          /* various flags */
 
 /* The following are for internal use only. Also see uapi/linux/nfs_mount.h */