case XFS_AG_RESV_RMAPBT:
len -= xfs_perag_resv(pag, type)->ar_reserved;
break;
+ case XFS_AG_RESV_METAFILE:
case XFS_AG_RESV_NONE:
/* empty */
break;
switch (type) {
case XFS_AG_RESV_AGFL:
+ case XFS_AG_RESV_METAFILE:
return;
case XFS_AG_RESV_METADATA:
case XFS_AG_RESV_RMAPBT:
switch (type) {
case XFS_AG_RESV_AGFL:
+ case XFS_AG_RESV_METAFILE:
return;
case XFS_AG_RESV_METADATA:
case XFS_AG_RESV_RMAPBT:
#define XFS_ERRTAG_WB_DELAY_MS 42
#define XFS_ERRTAG_WRITE_DELAY_MS 43
#define XFS_ERRTAG_EXCHMAPS_FINISH_ONE 44
-#define XFS_ERRTAG_MAX 45
+#define XFS_ERRTAG_METAFILE_RESV_CRITICAL 45
+#define XFS_ERRTAG_MAX 46
/*
* Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
#define XFS_RANDOM_WB_DELAY_MS 3000
#define XFS_RANDOM_WRITE_DELAY_MS 3000
#define XFS_RANDOM_EXCHMAPS_FINISH_ONE 1
+#define XFS_RANDOM_METAFILE_RESV_CRITICAL 4
#endif /* __XFS_ERRORTAG_H_ */
#include "xfs_dir2_priv.h"
#include "xfs_parent.h"
#include "xfs_health.h"
+#include "xfs_errortag.h"
+#include "xfs_error.h"
+#include "xfs_btree.h"
+#include "xfs_alloc.h"
/*
* Metadata Directory Tree
#include "xfs_metafile.h"
#include "xfs_trace.h"
#include "xfs_inode.h"
+#include "xfs_quota.h"
+#include "xfs_errortag.h"
+#include "xfs_error.h"
+#include "xfs_alloc.h"
/* Set up an inode to be recognized as a metadata directory inode. */
void
ip->i_diflags2 &= ~XFS_DIFLAG2_METADATA;
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
}
+
+/*
+ * Is the amount of space that could be allocated towards a given metadata
+ * file at or beneath a certain threshold?
+ */
+static inline bool
+xfs_metafile_resv_can_cover(
+ struct xfs_inode *ip,
+ int64_t rhs)
+{
+ /*
+ * The amount of space that can be allocated to this metadata file is
+ * the remaining reservation for the particular metadata file + the
+ * global free block count. Take care of the first case to avoid
+ * touching the per-cpu counter.
+ */
+ if (ip->i_delayed_blks >= rhs)
+ return true;
+
+ /*
+ * There aren't enough blocks left in the inode's reservation, but it
+ * isn't critical unless there also isn't enough free space.
+ */
+ return __percpu_counter_compare(&ip->i_mount->m_fdblocks,
+ rhs - ip->i_delayed_blks, 2048) >= 0;
+}
+
+/*
+ * Is this metadata file critically low on blocks? For now we'll define that
+ * as the number of blocks we can get our hands on being less than 10% of what
+ * we reserved or less than some arbitrary number (maximum btree height).
+ */
+bool
+xfs_metafile_resv_critical(
+ struct xfs_inode *ip)
+{
+ uint64_t asked_low_water;
+
+ if (!ip)
+ return false;
+
+ ASSERT(xfs_is_metadir_inode(ip));
+ trace_xfs_metafile_resv_critical(ip, 0);
+
+ if (!xfs_metafile_resv_can_cover(ip, ip->i_mount->m_rtbtree_maxlevels))
+ return true;
+
+ asked_low_water = div_u64(ip->i_meta_resv_asked, 10);
+ if (!xfs_metafile_resv_can_cover(ip, asked_low_water))
+ return true;
+
+ return XFS_TEST_ERROR(false, ip->i_mount,
+ XFS_ERRTAG_METAFILE_RESV_CRITICAL);
+}
+
+/* Allocate a block from the metadata file's reservation. */
+void
+xfs_metafile_resv_alloc_space(
+ struct xfs_inode *ip,
+ struct xfs_alloc_arg *args)
+{
+ int64_t len = args->len;
+
+ ASSERT(xfs_is_metadir_inode(ip));
+ ASSERT(XFS_IS_DQDETACHED(ip));
+ ASSERT(args->resv == XFS_AG_RESV_METAFILE);
+
+ trace_xfs_metafile_resv_alloc_space(ip, args->len);
+
+ /*
+ * Allocate the blocks from the metadata inode's block reservation
+ * and update the ondisk sb counter.
+ */
+ if (ip->i_delayed_blks > 0) {
+ int64_t from_resv;
+
+ from_resv = min_t(int64_t, len, ip->i_delayed_blks);
+ ip->i_delayed_blks -= from_resv;
+ xfs_mod_delalloc(ip, 0, -from_resv);
+ xfs_trans_mod_sb(args->tp, XFS_TRANS_SB_RES_FDBLOCKS,
+ -from_resv);
+ len -= from_resv;
+ }
+
+ /*
+ * Any allocation in excess of the reservation requires in-core and
+ * on-disk fdblocks updates. If we can grab @len blocks from the
+ * in-core fdblocks then all we need to do is update the on-disk
+ * superblock; if not, then try to steal some from the transaction's
+ * block reservation. Overruns are only expected for rmap btrees.
+ */
+ if (len) {
+ unsigned int field;
+ int error;
+
+ error = xfs_dec_fdblocks(ip->i_mount, len, true);
+ if (error)
+ field = XFS_TRANS_SB_FDBLOCKS;
+ else
+ field = XFS_TRANS_SB_RES_FDBLOCKS;
+
+ xfs_trans_mod_sb(args->tp, field, -len);
+ }
+
+ ip->i_nblocks += args->len;
+ xfs_trans_log_inode(args->tp, ip, XFS_ILOG_CORE);
+}
+
+/* Free a block to the metadata file's reservation. */
+void
+xfs_metafile_resv_free_space(
+ struct xfs_inode *ip,
+ struct xfs_trans *tp,
+ xfs_filblks_t len)
+{
+ int64_t to_resv;
+
+ ASSERT(xfs_is_metadir_inode(ip));
+ ASSERT(XFS_IS_DQDETACHED(ip));
+ trace_xfs_metafile_resv_free_space(ip, len);
+
+ ip->i_nblocks -= len;
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+ /*
+ * Add the freed blocks back into the inode's delalloc reservation
+ * until it reaches the maximum size. Update the ondisk fdblocks only.
+ */
+ to_resv = ip->i_meta_resv_asked - (ip->i_nblocks + ip->i_delayed_blks);
+ if (to_resv > 0) {
+ to_resv = min_t(int64_t, to_resv, len);
+ ip->i_delayed_blks += to_resv;
+ xfs_mod_delalloc(ip, 0, to_resv);
+ xfs_trans_mod_sb(tp, XFS_TRANS_SB_RES_FDBLOCKS, to_resv);
+ len -= to_resv;
+ }
+
+ /*
+ * Everything else goes back to the filesystem, so update the in-core
+ * and on-disk counters.
+ */
+ if (len)
+ xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, len);
+}
+
+/* Release a metadata file's space reservation. */
+void
+xfs_metafile_resv_free(
+ struct xfs_inode *ip)
+{
+ if (!ip)
+ return;
+
+ ASSERT(xfs_is_metadir_inode(ip));
+ trace_xfs_metafile_resv_free(ip, 0);
+
+ xfs_mod_delalloc(ip, 0, -ip->i_delayed_blks);
+ xfs_add_fdblocks(ip->i_mount, ip->i_delayed_blks);
+ ip->i_delayed_blks = 0;
+ ip->i_meta_resv_asked = 0;
+}
+
+/* Set up a metadata file's space reservation. */
+int
+xfs_metafile_resv_init(
+ struct xfs_inode *ip,
+ xfs_filblks_t ask)
+{
+ xfs_filblks_t hidden_space;
+ xfs_filblks_t used;
+ int error;
+
+ if (!ip || ip->i_meta_resv_asked > 0)
+ return 0;
+
+ ASSERT(xfs_is_metadir_inode(ip));
+
+ /*
+ * Space taken by all other metadata btrees are accounted on-disk as
+ * used space. We therefore only hide the space that is reserved but
+ * not used by the trees.
+ */
+ used = ip->i_nblocks;
+ if (used > ask)
+ ask = used;
+ hidden_space = ask - used;
+
+ error = xfs_dec_fdblocks(ip->i_mount, hidden_space, true);
+ if (error) {
+ trace_xfs_metafile_resv_init_error(ip, error, _RET_IP_);
+ return error;
+ }
+
+ xfs_mod_delalloc(ip, 0, hidden_space);
+ ip->i_delayed_blks = hidden_space;
+ ip->i_meta_resv_asked = ask;
+
+ trace_xfs_metafile_resv_init(ip, ask);
+ return 0;
+}
enum xfs_metafile_type metafile_type);
void xfs_metafile_clear_iflag(struct xfs_trans *tp, struct xfs_inode *ip);
+/* Space reservations for metadata inodes. */
+struct xfs_alloc_arg;
+
+bool xfs_metafile_resv_critical(struct xfs_inode *ip);
+void xfs_metafile_resv_alloc_space(struct xfs_inode *ip,
+ struct xfs_alloc_arg *args);
+void xfs_metafile_resv_free_space(struct xfs_inode *ip, struct xfs_trans *tp,
+ xfs_filblks_t len);
+void xfs_metafile_resv_free(struct xfs_inode *ip);
+int xfs_metafile_resv_init(struct xfs_inode *ip, xfs_filblks_t ask);
+
/* Code specific to kernel/userspace; must be provided externally. */
int xfs_trans_metafile_iget(struct xfs_trans *tp, xfs_ino_t ino,
* altering fdblocks. If you think you need this you're wrong.
*/
XFS_AG_RESV_IGNORE,
+
+ /*
+ * This allocation activity is being done on behalf of a metadata file.
+ * These files maintain their own permanent space reservations and are
+ * required to adjust fdblocks using the xfs_metafile_resv_* helpers.
+ */
+ XFS_AG_RESV_METAFILE,
};
/* Results of scanning a btree keyspace to check occupancy. */
XFS_RANDOM_WB_DELAY_MS,
XFS_RANDOM_WRITE_DELAY_MS,
XFS_RANDOM_EXCHMAPS_FINISH_ONE,
+ XFS_RANDOM_METAFILE_RESV_CRITICAL,
};
struct xfs_errortag_attr {
XFS_ERRORTAG_ATTR_RW(wb_delay_ms, XFS_ERRTAG_WB_DELAY_MS);
XFS_ERRORTAG_ATTR_RW(write_delay_ms, XFS_ERRTAG_WRITE_DELAY_MS);
XFS_ERRORTAG_ATTR_RW(exchmaps_finish_one, XFS_ERRTAG_EXCHMAPS_FINISH_ONE);
+XFS_ERRORTAG_ATTR_RW(metafile_resv_crit, XFS_ERRTAG_METAFILE_RESV_CRITICAL);
static struct attribute *xfs_errortag_attrs[] = {
XFS_ERRORTAG_ATTR_LIST(noerror),
XFS_ERRORTAG_ATTR_LIST(wb_delay_ms),
XFS_ERRORTAG_ATTR_LIST(write_delay_ms),
XFS_ERRORTAG_ATTR_LIST(exchmaps_finish_one),
+ XFS_ERRORTAG_ATTR_LIST(metafile_resv_crit),
NULL,
};
ATTRIBUTE_GROUPS(xfs_errortag);
#include "xfs_ag.h"
#include "xfs_ag_resv.h"
#include "xfs_trace.h"
+#include "xfs_rtalloc.h"
/*
* Write new AG headers to disk. Non-transactional, but need to be
xfs_warn(mp,
"Error %d reserving per-AG metadata reserve pool.", error);
xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ return error;
+ }
+
+ if (xfs_has_realtime(mp)) {
+ err2 = xfs_rt_resv_init(mp);
+ if (err2 && err2 != -ENOSPC) {
+ xfs_warn(mp,
+ "Error %d reserving realtime metadata reserve pool.", err2);
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+ }
+
+ if (err2 && !error)
+ error = err2;
}
return error;
{
struct xfs_perag *pag = NULL;
+ if (xfs_has_realtime(mp))
+ xfs_rt_resv_free(mp);
+
while ((pag = xfs_perag_next(mp, pag)))
xfs_ag_resv_free(pag);
}
/* Miscellaneous state. */
unsigned long i_flags; /* see defined flags below */
uint64_t i_delayed_blks; /* count of delay alloc blks */
+ /* Space that has been set aside to root a btree in this file. */
+ uint64_t i_meta_resv_asked;
+
xfs_fsize_t i_disk_size; /* number of bytes in file */
xfs_rfsblock_t i_nblocks; /* # of direct & btree blocks */
prid_t i_projid; /* owner's project id */
mp->m_agbtree_maxlevels = max(levels, mp->m_refc_maxlevels);
}
+/* Compute maximum possible height for realtime btree types for this fs. */
+static inline void
+xfs_rtbtree_compute_maxlevels(
+ struct xfs_mount *mp)
+{
+ /* This will be filled in later. */
+ mp->m_rtbtree_maxlevels = 0;
+}
+
/*
* This function does the following on an initial mount of a file system:
* - reads the superblock from disk and init the mount struct
xfs_refcountbt_compute_maxlevels(mp);
xfs_agbtree_compute_maxlevels(mp);
+ xfs_rtbtree_compute_maxlevels(mp);
/*
* Check if sb_agblocks is aligned at stripe boundary. If sb_agblocks
uint m_rmap_maxlevels; /* max rmap btree levels */
uint m_refc_maxlevels; /* max refcount btree level */
unsigned int m_agbtree_maxlevels; /* max level of all AG btrees */
+ unsigned int m_rtbtree_maxlevels; /* max level of all rt btrees */
xfs_extlen_t m_ag_prealloc_blocks; /* reserved ag blocks */
uint m_alloc_set_aside; /* space we can't use */
uint m_ag_max_usable; /* max space per AG */
if (!error)
error = error2;
+
+ /* Reset the rt metadata btree space reservations. */
+ xfs_rt_resv_free(mp);
+ error2 = xfs_rt_resv_init(mp);
+ if (error2 && error2 != -ENOSPC)
+ error = error2;
}
out_unlock:
return 0;
}
+/* Free space reservations for rt metadata inodes. */
+void
+xfs_rt_resv_free(
+ struct xfs_mount *mp)
+{
+}
+
+/* Reserve space for rt metadata inodes' space expansion. */
+int
+xfs_rt_resv_init(
+ struct xfs_mount *mp)
+{
+ return 0;
+}
+
/*
* Read in the bmbt of an rt metadata inode so that we never have to load them
* at runtime. This enables the use of shared ILOCKs for rtbitmap scans. Use
xfs_rtmount_inodes(
struct xfs_mount *mp); /* file system mount structure */
+void xfs_rt_resv_free(struct xfs_mount *mp);
+int xfs_rt_resv_init(struct xfs_mount *mp);
+
/*
* Grow the realtime area of the filesystem.
*/
}
# define xfs_rtmount_inodes(m) (((mp)->m_sb.sb_rblocks == 0)? 0 : (-ENOSYS))
# define xfs_rtunmount_inodes(m)
+# define xfs_rt_resv_free(mp) ((void)0)
+# define xfs_rt_resv_init(mp) (0)
#endif /* CONFIG_XFS_RT */
#endif /* __XFS_RTALLOC_H__ */
TP_ARGS(dp, name, ino))
DEFINE_METADIR_EVENT(xfs_metadir_lookup);
+/* metadata inode space reservations */
+
+DECLARE_EVENT_CLASS(xfs_metafile_resv_class,
+ TP_PROTO(struct xfs_inode *ip, xfs_filblks_t len),
+ TP_ARGS(ip, len),
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+ __field(xfs_ino_t, ino)
+ __field(unsigned long long, freeblks)
+ __field(unsigned long long, reserved)
+ __field(unsigned long long, asked)
+ __field(unsigned long long, used)
+ __field(unsigned long long, len)
+ ),
+ TP_fast_assign(
+ struct xfs_mount *mp = ip->i_mount;
+
+ __entry->dev = mp->m_super->s_dev;
+ __entry->ino = ip->i_ino;
+ __entry->freeblks = percpu_counter_sum(&mp->m_fdblocks);
+ __entry->reserved = ip->i_delayed_blks;
+ __entry->asked = ip->i_meta_resv_asked;
+ __entry->used = ip->i_nblocks;
+ __entry->len = len;
+ ),
+ TP_printk("dev %d:%d ino 0x%llx freeblks %llu resv %llu ask %llu used %llu len %llu",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->ino,
+ __entry->freeblks,
+ __entry->reserved,
+ __entry->asked,
+ __entry->used,
+ __entry->len)
+)
+#define DEFINE_METAFILE_RESV_EVENT(name) \
+DEFINE_EVENT(xfs_metafile_resv_class, name, \
+ TP_PROTO(struct xfs_inode *ip, xfs_filblks_t len), \
+ TP_ARGS(ip, len))
+DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_init);
+DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free);
+DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_alloc_space);
+DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free_space);
+DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_critical);
+DEFINE_INODE_ERROR_EVENT(xfs_metafile_resv_init_error);
+
#endif /* _TRACE_XFS_H */
#undef TRACE_INCLUDE_PATH
projects / users / hch / xfs.git / commitdiff