summaryrefslogtreecommitdiffstats
path: root/fs/xfs/xfs_icache.c
diff options
context:
space:
mode:
authorBrian Foster <bfoster@redhat.com>2014-07-24 19:49:28 +1000
committerDave Chinner <david@fromorbit.com>2014-07-24 19:49:28 +1000
commitdc06f398f00059707236d456d954a3a9d2a829db (patch)
treeb7d0f9a2d9a109a32e6b72af3909b9465b406c23 /fs/xfs/xfs_icache.c
parentf4526397928fff052f795713748f376a2bba1b5e (diff)
downloadlinux-dc06f398f00059707236d456d954a3a9d2a829db.tar.gz
linux-dc06f398f00059707236d456d954a3a9d2a829db.tar.bz2
linux-dc06f398f00059707236d456d954a3a9d2a829db.zip
xfs: run an eofblocks scan on ENOSPC/EDQUOT
From: Brian Foster <bfoster@redhat.com> Speculative preallocation and and the associated throttling metrics assume we're working with large files on large filesystems. Users have reported inefficiencies in these mechanisms when we happen to be dealing with large files on smaller filesystems. This can occur because while prealloc throttling is aggressive under low free space conditions, it is not active until we reach 5% free space or less. For example, a 40GB filesystem has enough space for several files large enough to have multi-GB preallocations at any given time. If those files are slow growing, they might reserve preallocation for long periods of time as well as avoid the background scanner due to frequent modification. If a new file is written under these conditions, said file has no access to this already reserved space and premature ENOSPC is imminent. To handle this scenario, modify the buffered write ENOSPC handling and retry sequence to invoke an eofblocks scan. In the smaller filesystem scenario, the eofblocks scan resets the usage of preallocation such that when the 5% free space threshold is met, throttling effectively takes over to provide fair and efficient preallocation until legitimate ENOSPC. The eofblocks scan is selective based on the nature of the failure. For example, an EDQUOT failure in a particular quota will use a filtered scan for that quota. Because we don't know which quota might have caused an allocation failure at any given time, we include each applicable quota determined to be under low free space conditions in the scan. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
Diffstat (limited to 'fs/xfs/xfs_icache.c')
-rw-r--r--fs/xfs/xfs_icache.c52
1 files changed, 52 insertions, 0 deletions
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 43452081b705..981b2cf51985 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -33,6 +33,9 @@
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_bmap_util.h"
+#include "xfs_quota.h"
+#include "xfs_dquot_item.h"
+#include "xfs_dquot.h"
#include <linux/kthread.h>
#include <linux/freezer.h>
@@ -1300,6 +1303,55 @@ xfs_icache_free_eofblocks(
eofb, XFS_ICI_EOFBLOCKS_TAG);
}
+/*
+ * Run eofblocks scans on the quotas applicable to the inode. For inodes with
+ * multiple quotas, we don't know exactly which quota caused an allocation
+ * failure. We make a best effort by including each quota under low free space
+ * conditions (less than 1% free space) in the scan.
+ */
+int
+xfs_inode_free_quota_eofblocks(
+ struct xfs_inode *ip)
+{
+ int scan = 0;
+ struct xfs_eofblocks eofb = {0};
+ struct xfs_dquot *dq;
+
+ ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
+
+ /*
+ * Set the scan owner to avoid a potential livelock. Otherwise, the scan
+ * can repeatedly trylock on the inode we're currently processing. We
+ * run a sync scan to increase effectiveness and use the union filter to
+ * cover all applicable quotas in a single scan.
+ */
+ eofb.eof_scan_owner = ip->i_ino;
+ eofb.eof_flags = XFS_EOF_FLAGS_UNION|XFS_EOF_FLAGS_SYNC;
+
+ if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
+ dq = xfs_inode_dquot(ip, XFS_DQ_USER);
+ if (dq && xfs_dquot_lowsp(dq)) {
+ eofb.eof_uid = VFS_I(ip)->i_uid;
+ eofb.eof_flags |= XFS_EOF_FLAGS_UID;
+ scan = 1;
+ }
+ }
+
+ if (XFS_IS_GQUOTA_ENFORCED(ip->i_mount)) {
+ dq = xfs_inode_dquot(ip, XFS_DQ_GROUP);
+ if (dq && xfs_dquot_lowsp(dq)) {
+ eofb.eof_gid = VFS_I(ip)->i_gid;
+ eofb.eof_flags |= XFS_EOF_FLAGS_GID;
+ scan = 1;
+ }
+ }
+
+ if (scan)
+ xfs_icache_free_eofblocks(ip->i_mount, &eofb);
+
+ return scan;
+}
+
void
xfs_inode_set_eofblocks_tag(
xfs_inode_t *ip)