nfsd: Reduce contention for the nfsd_file nf_rwsem

When flushing out the unstable file writes as part of a COMMIT call, try
to perform most of of the data writes and waits outside the semaphore.

This means that if the client is sending the COMMIT as part of a memory
reclaim operation, then it can continue performing I/O, with contention
for the lock occurring only once the data sync is finished.

Fixes: 5011af4c698a ("nfsd: Fix stable writes")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
 Tested-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>

diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index d73d3c9..a224a5e 100644 (file)
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1123,6 +1123,19 @@ out:
 }
 
 #ifdef CONFIG_NFSD_V3
+static int
+nfsd_filemap_write_and_wait_range(struct nfsd_file *nf, loff_t offset,
+                                 loff_t end)
+{
+       struct address_space *mapping = nf->nf_file->f_mapping;
+       int ret = filemap_fdatawrite_range(mapping, offset, end);
+
+       if (ret)
+               return ret;
+       filemap_fdatawait_range_keep_errors(mapping, offset, end);
+       return 0;
+}
+
 /*
  * Commit all pending writes to stable storage.
  *
@@ -1153,10 +1166,11 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
        if (err)
                goto out;
        if (EX_ISSYNC(fhp->fh_export)) {
-               int err2;
+               int err2 = nfsd_filemap_write_and_wait_range(nf, offset, end);
 
                down_write(&nf->nf_rwsem);
-               err2 = vfs_fsync_range(nf->nf_file, offset, end, 0);
+               if (!err2)
+                       err2 = vfs_fsync_range(nf->nf_file, offset, end, 0);
                switch (err2) {
                case 0:
                        nfsd_copy_boot_verifier(verf, net_generic(nf->nf_net,