From: NeilBrown <neilb@xxxxxxx>
Subject: 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@xxxxxxx>
Cc: Anna Schumaker <Anna.Schumaker@xxxxxxxxxx>
Cc: Chao Yu <chao@xxxxxxxxxx>
Cc: Darrick J. Wong <djwong@xxxxxxxxxx>
Cc: Ilya Dryomov <idryomov@xxxxxxxxx>
Cc: Jaegeuk Kim <jaegeuk@xxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Jeff Layton <jlayton@xxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Lars Ellenberg <lars.ellenberg@xxxxxxxxxx>
Cc: Miklos Szeredi <miklos@xxxxxxxxxx>
Cc: Paolo Valente <paolo.valente@xxxxxxxxxx>
Cc: Philipp Reisner <philipp.reisner@xxxxxxxxxx>
Cc: Ryusuke Konishi <konishi.ryusuke@xxxxxxxxx>
Cc: Trond Myklebust <trond.myklebust@xxxxxxxxxxxxxxx>
Cc: Wu Fengguang <fengguang.wu@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/nfs/write.c | 14 +++++++++++---
include/linux/nfs_fs_sb.h | 1 +
2 files changed, 12 insertions(+), 3 deletions(-)
--- a/fs/nfs/write.c~nfs-remove-reliance-on-bdi-congestion
+++ a/fs/nfs/write.c
@@ -417,7 +417,7 @@ static void nfs_set_page_writeback(struc
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(struc
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 p
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
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(str
}
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);
--- a/include/linux/nfs_fs_sb.h~nfs-remove-reliance-on-bdi-congestion
+++ a/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 */
_
