xfs: set up per-AG free space reservations
One unfortunate quirk of the reference count and reverse mapping
btrees -- they can expand in size when blocks are written to *other*
allocation groups if, say, one large extent becomes a lot of tiny
extents. Since we don't want to start throwing errors in the middle
of CoWing, we need to reserve some blocks to handle future expansion.
The transaction block reservation counters aren't sufficient here
because we have to have a reserve of blocks in every AG, not just
somewhere in the filesystem.
Therefore, create two per-AG block reservation pools. One feeds the
AGFL so that rmapbt expansion always succeeds, and the other feeds all
other metadata so that refcountbt expansion never fails.
Use the count of how many reserved blocks we need to have on hand to
create a virtual reservation in the AG. Through selective clamping of
the maximum length of allocation requests and of the length of the
longest free extent, we can make it look like there's less free space
in the AG unless the reservation owner is asking for blocks.
In other words, play some accounting tricks in-core to make sure that
we always have blocks available. On the plus side, there's nothing to
clean up if we crash, which is contrast to the strategy that the rough
draft used (actually removing extents from the freespace btrees).
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index b36676c..a3c2e2d 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -325,6 +325,22 @@
}
#endif
+/* per-AG block reservation data structures*/
+enum xfs_ag_resv_type {
+ XFS_AG_RESV_NONE = 0,
+ XFS_AG_RESV_METADATA,
+ XFS_AG_RESV_AGFL,
+};
+
+struct xfs_ag_resv {
+ /* number of blocks originally reserved here */
+ xfs_extlen_t ar_orig_reserved;
+ /* number of blocks reserved here */
+ xfs_extlen_t ar_reserved;
+ /* number of blocks originally asked for */
+ xfs_extlen_t ar_asked;
+};
+
/*
* Per-ag incore structure, copies of information in agf and agi, to improve the
* performance of allocation group selection.
@@ -372,8 +388,28 @@
/* for rcu-safe freeing */
struct rcu_head rcu_head;
int pagb_count; /* pagb slots in use */
+
+ /* Blocks reserved for all kinds of metadata. */
+ struct xfs_ag_resv pag_meta_resv;
+ /* Blocks reserved for just AGFL-based metadata. */
+ struct xfs_ag_resv pag_agfl_resv;
} xfs_perag_t;
+static inline struct xfs_ag_resv *
+xfs_perag_resv(
+ struct xfs_perag *pag,
+ enum xfs_ag_resv_type type)
+{
+ switch (type) {
+ case XFS_AG_RESV_METADATA:
+ return &pag->pag_meta_resv;
+ case XFS_AG_RESV_AGFL:
+ return &pag->pag_agfl_resv;
+ default:
+ return NULL;
+ }
+}
+
extern void xfs_uuid_table_free(void);
extern int xfs_log_sbcount(xfs_mount_t *);
extern __uint64_t xfs_default_resblks(xfs_mount_t *mp);