summaryrefslogtreecommitdiffstats
path: root/fs/nfs/write.c
diff options
context:
space:
mode:
authorTrond Myklebust <Trond.Myklebust@netapp.com>2009-03-11 19:10:30 +0100
committerTrond Myklebust <Trond.Myklebust@netapp.com>2009-03-11 19:10:30 +0100
commit72cb77f4a5ace37b12dcb47a0e8637a2c28ad881 (patch)
tree62fbdd7a34884f3ea9e1b0ba6bd5a4d78263f847 /fs/nfs/write.c
parentNFS: cleanup - remove struct nfs_inode->ncommit (diff)
downloadlinux-72cb77f4a5ace37b12dcb47a0e8637a2c28ad881.tar.xz
linux-72cb77f4a5ace37b12dcb47a0e8637a2c28ad881.zip
NFS: Throttle page dirtying while we're flushing to disk
The following patch is a combination of a patch by myself and Peter Staubach. Trond: If we allow other processes to dirty pages while a process is doing a consistency sync to disk, we can end up never making progress. Peter: Attached is a patch which addresses a continuing problem with the NFS client generating out of order WRITE requests. While this is compliant with all of the current protocol specifications, there are servers in the market which can not handle out of order WRITE requests very well. Also, this may lead to sub-optimal block allocations in the underlying file system on the server. This may cause the read throughputs to be reduced when reading the file from the server. Peter: There has been a lot of work recently done to address out of order issues on a systemic level. However, the NFS client is still susceptible to the problem. Out of order WRITE requests can occur when pdflush is in the middle of writing out pages while the process dirtying the pages calls generic_file_buffered_write which calls generic_perform_write which calls balance_dirty_pages_rate_limited which ends up calling writeback_inodes which ends up calling back into the NFS client to writes out dirty pages for the same file that pdflush happens to be working with. Signed-off-by: Peter Staubach <staubach@redhat.com> [modification by Trond to merge the two similar patches] Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Diffstat (limited to 'fs/nfs/write.c')
-rw-r--r--fs/nfs/write.c28
1 files changed, 19 insertions, 9 deletions
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 1a999939fedf..36fd35e0de83 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -313,19 +313,34 @@ static int nfs_writepages_callback(struct page *page, struct writeback_control *
int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
+ unsigned long *bitlock = &NFS_I(inode)->flags;
struct nfs_pageio_descriptor pgio;
int err;
+ /* Stop dirtying of new pages while we sync */
+ err = wait_on_bit_lock(bitlock, NFS_INO_FLUSHING,
+ nfs_wait_bit_killable, TASK_KILLABLE);
+ if (err)
+ goto out_err;
+
nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
nfs_pageio_init_write(&pgio, inode, wb_priority(wbc));
err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
nfs_pageio_complete(&pgio);
+
+ clear_bit_unlock(NFS_INO_FLUSHING, bitlock);
+ smp_mb__after_clear_bit();
+ wake_up_bit(bitlock, NFS_INO_FLUSHING);
+
if (err < 0)
- return err;
- if (pgio.pg_error < 0)
- return pgio.pg_error;
+ goto out_err;
+ err = pgio.pg_error;
+ if (err < 0)
+ goto out_err;
return 0;
+out_err:
+ return err;
}
/*
@@ -1432,18 +1447,13 @@ static int nfs_write_mapping(struct address_space *mapping, int how)
{
struct writeback_control wbc = {
.bdi = mapping->backing_dev_info,
- .sync_mode = WB_SYNC_NONE,
+ .sync_mode = WB_SYNC_ALL,
.nr_to_write = LONG_MAX,
.range_start = 0,
.range_end = LLONG_MAX,
.for_writepages = 1,
};
- int ret;
- ret = __nfs_write_mapping(mapping, &wbc, how);
- if (ret < 0)
- return ret;
- wbc.sync_mode = WB_SYNC_ALL;
return __nfs_write_mapping(mapping, &wbc, how);
}