summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_rmap_item.c
diff options
context:
space:
mode:
authorDarrick J. Wong <darrick.wong@oracle.com>2020-09-27 16:18:13 -0700
committerDarrick J. Wong <darrick.wong@oracle.com>2020-10-07 08:40:28 -0700
commit4e919af7827a6adfc28e82cd6c4ffcfcc3dd6118 (patch)
tree289d32e2f0a16fdf8838bf33557ec91650b5359c /fs/xfs/xfs_rmap_item.c
parent27dada070d59c28a441f1907d2cec891b17dcb26 (diff)
xfs: periodically relog deferred intent items
There's a subtle design flaw in the deferred log item code that can lead to pinning the log tail. Taking up the defer ops chain examples from the previous commit, we can get trapped in sequences like this: Caller hands us a transaction t0 with D0-D3 attached. The defer ops chain will look like the following if the transaction rolls succeed: t1: D0(t0), D1(t0), D2(t0), D3(t0) t2: d4(t1), d5(t1), D1(t0), D2(t0), D3(t0) t3: d5(t1), D1(t0), D2(t0), D3(t0) ... t9: d9(t7), D3(t0) t10: D3(t0) t11: d10(t10), d11(t10) t12: d11(t10) In transaction 9, we finish d9 and try to roll to t10 while holding onto an intent item for D3 that we logged in t0. The previous commit changed the order in which we place new defer ops in the defer ops processing chain to reduce the maximum chain length. Now make xfs_defer_finish_noroll capable of relogging the entire chain periodically so that we can always move the log tail forward. Most chains will never get relogged, except for operations that generate very long chains (large extents containing many blocks with different sharing levels) or are on filesystems with small logs and a lot of ongoing metadata updates. Callers are now required to ensure that the transaction reservation is large enough to handle logging done items and new intent items for the maximum possible chain length. Most callers are careful to keep the chain lengths low, so the overhead should be minimal. The decision to relog an intent item is made based on whether the intent was logged in a previous checkpoint, since there's no point in relogging an intent into the same checkpoint. Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Brian Foster <bfoster@redhat.com>
Diffstat (limited to 'fs/xfs/xfs_rmap_item.c')
-rw-r--r--fs/xfs/xfs_rmap_item.c27
1 files changed, 27 insertions, 0 deletions
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index 1163f32c3e62..7adc996ca6e3 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -583,6 +583,32 @@ xfs_rui_item_match(
return RUI_ITEM(lip)->rui_format.rui_id == intent_id;
}
+/* Relog an intent item to push the log tail forward. */
+static struct xfs_log_item *
+xfs_rui_item_relog(
+ struct xfs_log_item *intent,
+ struct xfs_trans *tp)
+{
+ struct xfs_rud_log_item *rudp;
+ struct xfs_rui_log_item *ruip;
+ struct xfs_map_extent *extp;
+ unsigned int count;
+
+ count = RUI_ITEM(intent)->rui_format.rui_nextents;
+ extp = RUI_ITEM(intent)->rui_format.rui_extents;
+
+ tp->t_flags |= XFS_TRANS_DIRTY;
+ rudp = xfs_trans_get_rud(tp, RUI_ITEM(intent));
+ set_bit(XFS_LI_DIRTY, &rudp->rud_item.li_flags);
+
+ ruip = xfs_rui_init(tp->t_mountp, count);
+ memcpy(ruip->rui_format.rui_extents, extp, count * sizeof(*extp));
+ atomic_set(&ruip->rui_next_extent, count);
+ xfs_trans_add_item(tp, &ruip->rui_item);
+ set_bit(XFS_LI_DIRTY, &ruip->rui_item.li_flags);
+ return &ruip->rui_item;
+}
+
static const struct xfs_item_ops xfs_rui_item_ops = {
.iop_size = xfs_rui_item_size,
.iop_format = xfs_rui_item_format,
@@ -590,6 +616,7 @@ static const struct xfs_item_ops xfs_rui_item_ops = {
.iop_release = xfs_rui_item_release,
.iop_recover = xfs_rui_item_recover,
.iop_match = xfs_rui_item_match,
+ .iop_relog = xfs_rui_item_relog,
};
/*