NFS: avoid waiting at all in nfs_release_page when congested.

If nfs_release_page() is called on a sequence of pages which are all
in the same file which is blocked on COMMIT, each page could
contribute a 1 second delay which could be come excessive.  I have
seen delays of as much as 208 seconds.

To keep the delay to one second, mark the bdi as write-congested
if the commit didn't finished.  Once it does finish, the
write-congested flag will be cleared by nfs_commit_release_pages().

With this, the longest total delay in try_to_free_pages that I have
seen is under 3 seconds.  With no waiting in nfs_release_page at all
I have seen delays of nearly 1.5 seconds.

Signed-off-by: NeilBrown <neilb@suse.de>
Acked-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 325df0a..24832d0 100644 (file)
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -477,7 +477,8 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
 
        /* Always try to initiate a 'commit' if relevant, but only
         * wait for it if __GFP_WAIT is set and the calling process is
-        * allowed to block.  Even then, only wait 1 second.
+        * allowed to block.  Even then, only wait 1 second and only
+        * if the 'bdi' is not congested.
         * Waiting indefinitely can cause deadlocks when the NFS
         * server is on this machine, and there is no particular need
         * to wait extensively here.  A short wait has the benefit
@@ -488,9 +489,13 @@ static int nfs_release_page(struct page *page, gfp_t gfp)
                nfs_commit_inode(mapping->host, 0);
                if ((gfp & __GFP_WAIT) &&
                    !current_is_kswapd() &&
-                   !(current->flags & PF_FSTRANS)) {
+                   !(current->flags & PF_FSTRANS) &&
+                   !bdi_write_congested(&nfss->backing_dev_info)) {
                        wait_on_page_bit_killable_timeout(page, PG_private,
                                                          HZ);
+                       if (PagePrivate(page))
+                               set_bdi_congested(&nfss->backing_dev_info,
+                                                 BLK_RW_ASYNC);
                }
        }
        /* If PagePrivate() is set, then the page is not freeable */

diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index c063a4e..1249384 100644 (file)
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1611,6 +1611,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
        struct nfs_page *req;
        int status = data->task.tk_status;
        struct nfs_commit_info cinfo;
+       struct nfs_server *nfss;
 
        while (!list_empty(&data->pages)) {
                req = nfs_list_entry(data->pages.next);
@@ -1644,6 +1645,10 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
        next:
                nfs_unlock_and_release_request(req);
        }
+       nfss = NFS_SERVER(data->inode);
+       if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
+               clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+
        nfs_init_cinfo(&cinfo, data->inode, data->dreq);
        if (atomic_dec_and_test(&cinfo.mds->rpcs_out))
                nfs_commit_clear_lock(NFS_I(data->inode));