* Use is subject to license terms.
*/
+/*
+ * Copyright (c) 2013, 2015 by Delphix. All rights reserved.
+ */
+
#include <sys/zfs_context.h>
#include <sys/dnode.h>
#include <sys/dmu_objset.h>
#include <sys/kstat.h>
/*
- * I'm against tune-ables, but these should probably exist as tweakable globals
- * until we can get this working the way we want it to.
+ * This tunable disables predictive prefetch. Note that it leaves "prescient"
+ * prefetch (e.g. prefetch for zfs send) intact. Unlike predictive prefetch,
+ * prescient prefetch never issues i/os that end up not being needed,
+ * so it can't hurt performance.
*/
-int zfs_prefetch_disable = 0;
+int zfs_prefetch_disable = B_FALSE;
/* max # of streams per zfetch */
unsigned int zfetch_max_streams = 8;
/* min time before stream reclaim */
unsigned int zfetch_min_sec_reap = 2;
-/* max number of blocks to fetch at a time */
-unsigned int zfetch_block_cap = 256;
-/* number of bytes in a array_read at which we stop prefetching (1Mb) */
+/* max bytes to prefetch per stream (default 8MB) */
+unsigned int zfetch_max_distance = 8 * 1024 * 1024;
+/* max bytes to prefetch indirects for per stream (default 64MB) */
+unsigned int zfetch_max_idistance = 64 * 1024 * 1024;
+/* max number of bytes in an array_read in which we allow prefetching (1MB) */
unsigned long zfetch_array_rd_sz = 1024 * 1024;
-/* forward decls for static routines */
-static int dmu_zfetch_colinear(zfetch_t *, zstream_t *);
-static void dmu_zfetch_dofetch(zfetch_t *, zstream_t *);
-static uint64_t dmu_zfetch_fetch(dnode_t *, uint64_t, uint64_t);
-static uint64_t dmu_zfetch_fetchsz(dnode_t *, uint64_t, uint64_t);
-static int dmu_zfetch_find(zfetch_t *, zstream_t *, int);
-static int dmu_zfetch_stream_insert(zfetch_t *, zstream_t *);
-static zstream_t *dmu_zfetch_stream_reclaim(zfetch_t *);
-static void dmu_zfetch_stream_remove(zfetch_t *, zstream_t *);
-static int dmu_zfetch_streams_equal(zstream_t *, zstream_t *);
-
typedef struct zfetch_stats {
kstat_named_t zfetchstat_hits;
kstat_named_t zfetchstat_misses;
- kstat_named_t zfetchstat_colinear_hits;
- kstat_named_t zfetchstat_colinear_misses;
- kstat_named_t zfetchstat_stride_hits;
- kstat_named_t zfetchstat_stride_misses;
- kstat_named_t zfetchstat_reclaim_successes;
- kstat_named_t zfetchstat_reclaim_failures;
- kstat_named_t zfetchstat_stream_resets;
- kstat_named_t zfetchstat_stream_noresets;
- kstat_named_t zfetchstat_bogus_streams;
+ kstat_named_t zfetchstat_max_streams;
} zfetch_stats_t;
static zfetch_stats_t zfetch_stats = {
{ "hits", KSTAT_DATA_UINT64 },
{ "misses", KSTAT_DATA_UINT64 },
- { "colinear_hits", KSTAT_DATA_UINT64 },
- { "colinear_misses", KSTAT_DATA_UINT64 },
- { "stride_hits", KSTAT_DATA_UINT64 },
- { "stride_misses", KSTAT_DATA_UINT64 },
- { "reclaim_successes", KSTAT_DATA_UINT64 },
- { "reclaim_failures", KSTAT_DATA_UINT64 },
- { "streams_resets", KSTAT_DATA_UINT64 },
- { "streams_noresets", KSTAT_DATA_UINT64 },
- { "bogus_streams", KSTAT_DATA_UINT64 },
+ { "max_streams", KSTAT_DATA_UINT64 },
};
-#define ZFETCHSTAT_INCR(stat, val) \
- atomic_add_64(&zfetch_stats.stat.value.ui64, (val));
-
-#define ZFETCHSTAT_BUMP(stat) ZFETCHSTAT_INCR(stat, 1);
+#define ZFETCHSTAT_BUMP(stat) \
+ atomic_inc_64(&zfetch_stats.stat.value.ui64);
kstat_t *zfetch_ksp;
-/*
- * Given a zfetch structure and a zstream structure, determine whether the
- * blocks to be read are part of a co-linear pair of existing prefetch
- * streams. If a set is found, coalesce the streams, removing one, and
- * configure the prefetch so it looks for a strided access pattern.
- *
- * In other words: if we find two sequential access streams that are
- * the same length and distance N appart, and this read is N from the
- * last stream, then we are probably in a strided access pattern. So
- * combine the two sequential streams into a single strided stream.
- *
- * If no co-linear streams are found, return NULL.
- */
-static int
-dmu_zfetch_colinear(zfetch_t *zf, zstream_t *zh)
-{
- zstream_t *z_walk;
- zstream_t *z_comp;
-
- if (! rw_tryenter(&zf->zf_rwlock, RW_WRITER))
- return (0);
-
- if (zh == NULL) {
- rw_exit(&zf->zf_rwlock);
- return (0);
- }
-
- for (z_walk = list_head(&zf->zf_stream); z_walk;
- z_walk = list_next(&zf->zf_stream, z_walk)) {
- for (z_comp = list_next(&zf->zf_stream, z_walk); z_comp;
- z_comp = list_next(&zf->zf_stream, z_comp)) {
- int64_t diff;
-
- if (z_walk->zst_len != z_walk->zst_stride ||
- z_comp->zst_len != z_comp->zst_stride) {
- continue;
- }
-
- diff = z_comp->zst_offset - z_walk->zst_offset;
- if (z_comp->zst_offset + diff == zh->zst_offset) {
- z_walk->zst_offset = zh->zst_offset;
- z_walk->zst_direction = diff < 0 ? -1 : 1;
- z_walk->zst_stride =
- diff * z_walk->zst_direction;
- z_walk->zst_ph_offset =
- zh->zst_offset + z_walk->zst_stride;
- dmu_zfetch_stream_remove(zf, z_comp);
- mutex_destroy(&z_comp->zst_lock);
- kmem_free(z_comp, sizeof (zstream_t));
-
- dmu_zfetch_dofetch(zf, z_walk);
-
- rw_exit(&zf->zf_rwlock);
- return (1);
- }
-
- diff = z_walk->zst_offset - z_comp->zst_offset;
- if (z_walk->zst_offset + diff == zh->zst_offset) {
- z_walk->zst_offset = zh->zst_offset;
- z_walk->zst_direction = diff < 0 ? -1 : 1;
- z_walk->zst_stride =
- diff * z_walk->zst_direction;
- z_walk->zst_ph_offset =
- zh->zst_offset + z_walk->zst_stride;
- dmu_zfetch_stream_remove(zf, z_comp);
- mutex_destroy(&z_comp->zst_lock);
- kmem_free(z_comp, sizeof (zstream_t));
-
- dmu_zfetch_dofetch(zf, z_walk);
-
- rw_exit(&zf->zf_rwlock);
- return (1);
- }
- }
- }
-
- rw_exit(&zf->zf_rwlock);
- return (0);
-}
-
-/*
- * Given a zstream_t, determine the bounds of the prefetch. Then call the
- * routine that actually prefetches the individual blocks.
- */
-static void
-dmu_zfetch_dofetch(zfetch_t *zf, zstream_t *zs)
-{
- uint64_t prefetch_tail;
- uint64_t prefetch_limit;
- uint64_t prefetch_ofst;
- uint64_t prefetch_len;
- uint64_t blocks_fetched;
-
- zs->zst_stride = MAX((int64_t)zs->zst_stride, zs->zst_len);
- zs->zst_cap = MIN(zfetch_block_cap, 2 * zs->zst_cap);
-
- prefetch_tail = MAX((int64_t)zs->zst_ph_offset,
- (int64_t)(zs->zst_offset + zs->zst_stride));
- /*
- * XXX: use a faster division method?
- */
- prefetch_limit = zs->zst_offset + zs->zst_len +
- (zs->zst_cap * zs->zst_stride) / zs->zst_len;
-
- while (prefetch_tail < prefetch_limit) {
- prefetch_ofst = zs->zst_offset + zs->zst_direction *
- (prefetch_tail - zs->zst_offset);
-
- prefetch_len = zs->zst_len;
-
- /*
- * Don't prefetch beyond the end of the file, if working
- * backwards.
- */
- if ((zs->zst_direction == ZFETCH_BACKWARD) &&
- (prefetch_ofst > prefetch_tail)) {
- prefetch_len += prefetch_ofst;
- prefetch_ofst = 0;
- }
-
- /* don't prefetch more than we're supposed to */
- if (prefetch_len > zs->zst_len)
- break;
-
- blocks_fetched = dmu_zfetch_fetch(zf->zf_dnode,
- prefetch_ofst, zs->zst_len);
-
- prefetch_tail += zs->zst_stride;
- /* stop if we've run out of stuff to prefetch */
- if (blocks_fetched < zs->zst_len)
- break;
- }
- zs->zst_ph_offset = prefetch_tail;
- zs->zst_last = ddi_get_lbolt();
-}
-
void
zfetch_init(void)
{
-
zfetch_ksp = kstat_create("zfs", 0, "zfetchstats", "misc",
KSTAT_TYPE_NAMED, sizeof (zfetch_stats) / sizeof (kstat_named_t),
KSTAT_FLAG_VIRTUAL);
void
dmu_zfetch_init(zfetch_t *zf, dnode_t *dno)
{
- if (zf == NULL) {
+ if (zf == NULL)
return;
- }
zf->zf_dnode = dno;
- zf->zf_stream_cnt = 0;
- zf->zf_alloc_fail = 0;
list_create(&zf->zf_stream, sizeof (zstream_t),
- offsetof(zstream_t, zst_node));
+ offsetof(zstream_t, zs_node));
rw_init(&zf->zf_rwlock, NULL, RW_DEFAULT, NULL);
}
-/*
- * This function computes the actual size, in blocks, that can be prefetched,
- * and fetches it.
- */
-static uint64_t
-dmu_zfetch_fetch(dnode_t *dn, uint64_t blkid, uint64_t nblks)
-{
- uint64_t fetchsz;
- uint64_t i;
-
- fetchsz = dmu_zfetch_fetchsz(dn, blkid, nblks);
-
- for (i = 0; i < fetchsz; i++) {
- dbuf_prefetch(dn, blkid + i);
- }
-
- return (fetchsz);
-}
-
-/*
- * this function returns the number of blocks that would be prefetched, based
- * upon the supplied dnode, blockid, and nblks. This is used so that we can
- * update streams in place, and then prefetch with their old value after the
- * fact. This way, we can delay the prefetch, but subsequent accesses to the
- * stream won't result in the same data being prefetched multiple times.
- */
-static uint64_t
-dmu_zfetch_fetchsz(dnode_t *dn, uint64_t blkid, uint64_t nblks)
-{
- uint64_t fetchsz;
-
- if (blkid > dn->dn_maxblkid) {
- return (0);
- }
-
- /* compute fetch size */
- if (blkid + nblks + 1 > dn->dn_maxblkid) {
- fetchsz = (dn->dn_maxblkid - blkid) + 1;
- ASSERT(blkid + fetchsz - 1 <= dn->dn_maxblkid);
- } else {
- fetchsz = nblks;
- }
-
-
- return (fetchsz);
-}
-
-/*
- * given a zfetch and a zstream structure, see if there is an associated zstream
- * for this block read. If so, it starts a prefetch for the stream it
- * located and returns true, otherwise it returns false
- */
-static int
-dmu_zfetch_find(zfetch_t *zf, zstream_t *zh, int prefetched)
+static void
+dmu_zfetch_stream_remove(zfetch_t *zf, zstream_t *zs)
{
- zstream_t *zs;
- int64_t diff;
- int reset = !prefetched;
- int rc = 0;
-
- if (zh == NULL)
- return (0);
-
- /*
- * XXX: This locking strategy is a bit coarse; however, it's impact has
- * yet to be tested. If this turns out to be an issue, it can be
- * modified in a number of different ways.
- */
-
- rw_enter(&zf->zf_rwlock, RW_READER);
-top:
-
- for (zs = list_head(&zf->zf_stream); zs;
- zs = list_next(&zf->zf_stream, zs)) {
-
- /*
- * XXX - should this be an assert?
- */
- if (zs->zst_len == 0) {
- /* bogus stream */
- ZFETCHSTAT_BUMP(zfetchstat_bogus_streams);
- continue;
- }
-
- /*
- * We hit this case when we are in a strided prefetch stream:
- * we will read "len" blocks before "striding".
- */
- if (zh->zst_offset >= zs->zst_offset &&
- zh->zst_offset < zs->zst_offset + zs->zst_len) {
- if (prefetched) {
- /* already fetched */
- ZFETCHSTAT_BUMP(zfetchstat_stride_hits);
- rc = 1;
- goto out;
- } else {
- ZFETCHSTAT_BUMP(zfetchstat_stride_misses);
- }
- }
-
- /*
- * This is the forward sequential read case: we increment
- * len by one each time we hit here, so we will enter this
- * case on every read.
- */
- if (zh->zst_offset == zs->zst_offset + zs->zst_len) {
-
- reset = !prefetched && zs->zst_len > 1;
-
- mutex_enter(&zs->zst_lock);
-
- if (zh->zst_offset != zs->zst_offset + zs->zst_len) {
- mutex_exit(&zs->zst_lock);
- goto top;
- }
- zs->zst_len += zh->zst_len;
- diff = zs->zst_len - zfetch_block_cap;
- if (diff > 0) {
- zs->zst_offset += diff;
- zs->zst_len = zs->zst_len > diff ?
- zs->zst_len - diff : 0;
- }
- zs->zst_direction = ZFETCH_FORWARD;
-
- break;
-
- /*
- * Same as above, but reading backwards through the file.
- */
- } else if (zh->zst_offset == zs->zst_offset - zh->zst_len) {
- /* backwards sequential access */
-
- reset = !prefetched && zs->zst_len > 1;
-
- mutex_enter(&zs->zst_lock);
-
- if (zh->zst_offset != zs->zst_offset - zh->zst_len) {
- mutex_exit(&zs->zst_lock);
- goto top;
- }
-
- zs->zst_offset = zs->zst_offset > zh->zst_len ?
- zs->zst_offset - zh->zst_len : 0;
- zs->zst_ph_offset = zs->zst_ph_offset > zh->zst_len ?
- zs->zst_ph_offset - zh->zst_len : 0;
- zs->zst_len += zh->zst_len;
-
- diff = zs->zst_len - zfetch_block_cap;
- if (diff > 0) {
- zs->zst_ph_offset = zs->zst_ph_offset > diff ?
- zs->zst_ph_offset - diff : 0;
- zs->zst_len = zs->zst_len > diff ?
- zs->zst_len - diff : zs->zst_len;
- }
- zs->zst_direction = ZFETCH_BACKWARD;
-
- break;
-
- } else if ((zh->zst_offset - zs->zst_offset - zs->zst_stride <
- zs->zst_len) && (zs->zst_len != zs->zst_stride)) {
- /* strided forward access */
-
- mutex_enter(&zs->zst_lock);
-
- if ((zh->zst_offset - zs->zst_offset - zs->zst_stride >=
- zs->zst_len) || (zs->zst_len == zs->zst_stride)) {
- mutex_exit(&zs->zst_lock);
- goto top;
- }
-
- zs->zst_offset += zs->zst_stride;
- zs->zst_direction = ZFETCH_FORWARD;
-
- break;
-
- } else if ((zh->zst_offset - zs->zst_offset + zs->zst_stride <
- zs->zst_len) && (zs->zst_len != zs->zst_stride)) {
- /* strided reverse access */
-
- mutex_enter(&zs->zst_lock);
-
- if ((zh->zst_offset - zs->zst_offset + zs->zst_stride >=
- zs->zst_len) || (zs->zst_len == zs->zst_stride)) {
- mutex_exit(&zs->zst_lock);
- goto top;
- }
-
- zs->zst_offset = zs->zst_offset > zs->zst_stride ?
- zs->zst_offset - zs->zst_stride : 0;
- zs->zst_ph_offset = (zs->zst_ph_offset >
- (2 * zs->zst_stride)) ?
- (zs->zst_ph_offset - (2 * zs->zst_stride)) : 0;
- zs->zst_direction = ZFETCH_BACKWARD;
-
- break;
- }
- }
-
- if (zs) {
- if (reset) {
- zstream_t *remove = zs;
-
- ZFETCHSTAT_BUMP(zfetchstat_stream_resets);
- rc = 0;
- mutex_exit(&zs->zst_lock);
- rw_exit(&zf->zf_rwlock);
- rw_enter(&zf->zf_rwlock, RW_WRITER);
- /*
- * Relocate the stream, in case someone removes
- * it while we were acquiring the WRITER lock.
- */
- for (zs = list_head(&zf->zf_stream); zs;
- zs = list_next(&zf->zf_stream, zs)) {
- if (zs == remove) {
- dmu_zfetch_stream_remove(zf, zs);
- mutex_destroy(&zs->zst_lock);
- kmem_free(zs, sizeof (zstream_t));
- break;
- }
- }
- } else {
- ZFETCHSTAT_BUMP(zfetchstat_stream_noresets);
- rc = 1;
- dmu_zfetch_dofetch(zf, zs);
- mutex_exit(&zs->zst_lock);
- }
- }
-out:
- rw_exit(&zf->zf_rwlock);
- return (rc);
+ ASSERT(RW_WRITE_HELD(&zf->zf_rwlock));
+ list_remove(&zf->zf_stream, zs);
+ mutex_destroy(&zs->zs_lock);
+ kmem_free(zs, sizeof (*zs));
}
/*
- * Clean-up state associated with a zfetch structure. This frees allocated
- * structure members, empties the zf_stream tree, and generally makes things
- * nice. This doesn't free the zfetch_t itself, that's left to the caller.
+ * Clean-up state associated with a zfetch structure (e.g. destroy the
+ * streams). This doesn't free the zfetch_t itself, that's left to the caller.
*/
void
-dmu_zfetch_rele(zfetch_t *zf)
+dmu_zfetch_fini(zfetch_t *zf)
{
- zstream_t *zs;
- zstream_t *zs_next;
+ zstream_t *zs;
ASSERT(!RW_LOCK_HELD(&zf->zf_rwlock));
- for (zs = list_head(&zf->zf_stream); zs; zs = zs_next) {
- zs_next = list_next(&zf->zf_stream, zs);
-
- list_remove(&zf->zf_stream, zs);
- mutex_destroy(&zs->zst_lock);
- kmem_free(zs, sizeof (zstream_t));
- }
+ rw_enter(&zf->zf_rwlock, RW_WRITER);
+ while ((zs = list_head(&zf->zf_stream)) != NULL)
+ dmu_zfetch_stream_remove(zf, zs);
+ rw_exit(&zf->zf_rwlock);
list_destroy(&zf->zf_stream);
rw_destroy(&zf->zf_rwlock);
}
/*
- * Given a zfetch and zstream structure, insert the zstream structure into the
- * AVL tree contained within the zfetch structure. Peform the appropriate
- * book-keeping. It is possible that another thread has inserted a stream which
- * matches one that we are about to insert, so we must be sure to check for this
- * case. If one is found, return failure, and let the caller cleanup the
- * duplicates.
+ * If there aren't too many streams already, create a new stream.
+ * The "blkid" argument is the next block that we expect this stream to access.
+ * While we're here, clean up old streams (which haven't been
+ * accessed for at least zfetch_min_sec_reap seconds).
*/
-static int
-dmu_zfetch_stream_insert(zfetch_t *zf, zstream_t *zs)
+static void
+dmu_zfetch_stream_create(zfetch_t *zf, uint64_t blkid)
{
- zstream_t *zs_walk;
- zstream_t *zs_next;
+ zstream_t *zs_next;
+ int numstreams = 0;
ASSERT(RW_WRITE_HELD(&zf->zf_rwlock));
- for (zs_walk = list_head(&zf->zf_stream); zs_walk; zs_walk = zs_next) {
- zs_next = list_next(&zf->zf_stream, zs_walk);
-
- if (dmu_zfetch_streams_equal(zs_walk, zs)) {
- return (0);
- }
- }
-
- list_insert_head(&zf->zf_stream, zs);
- zf->zf_stream_cnt++;
- return (1);
-}
-
-
-/*
- * Walk the list of zstreams in the given zfetch, find an old one (by time), and
- * reclaim it for use by the caller.
- */
-static zstream_t *
-dmu_zfetch_stream_reclaim(zfetch_t *zf)
-{
- zstream_t *zs;
-
- if (! rw_tryenter(&zf->zf_rwlock, RW_WRITER))
- return (0);
-
- for (zs = list_head(&zf->zf_stream); zs;
- zs = list_next(&zf->zf_stream, zs)) {
-
- if (((ddi_get_lbolt() - zs->zst_last)/hz) > zfetch_min_sec_reap)
- break;
+ /*
+ * Clean up old streams.
+ */
+ for (zstream_t *zs = list_head(&zf->zf_stream);
+ zs != NULL; zs = zs_next) {
+ zs_next = list_next(&zf->zf_stream, zs);
+ if (((gethrtime() - zs->zs_atime) / NANOSEC) >
+ zfetch_min_sec_reap)
+ dmu_zfetch_stream_remove(zf, zs);
+ else
+ numstreams++;
}
- if (zs) {
- dmu_zfetch_stream_remove(zf, zs);
- mutex_destroy(&zs->zst_lock);
- bzero(zs, sizeof (zstream_t));
- } else {
- zf->zf_alloc_fail++;
+ /*
+ * The maximum number of streams is normally zfetch_max_streams,
+ * but for small files we lower it such that it's at least possible
+ * for all the streams to be non-overlapping.
+ *
+ * If we are already at the maximum number of streams for this file,
+ * even after removing old streams, then don't create this stream.
+ */
+ uint32_t max_streams = MAX(1, MIN(zfetch_max_streams,
+ zf->zf_dnode->dn_maxblkid * zf->zf_dnode->dn_datablksz /
+ zfetch_max_distance));
+ if (numstreams >= max_streams) {
+ ZFETCHSTAT_BUMP(zfetchstat_max_streams);
+ return;
}
- rw_exit(&zf->zf_rwlock);
- return (zs);
-}
+ zstream_t *zs = kmem_zalloc(sizeof (*zs), KM_SLEEP);
+ zs->zs_blkid = blkid;
+ zs->zs_pf_blkid = blkid;
+ zs->zs_ipf_blkid = blkid;
+ zs->zs_atime = gethrtime();
+ mutex_init(&zs->zs_lock, NULL, MUTEX_DEFAULT, NULL);
-/*
- * Given a zfetch and zstream structure, remove the zstream structure from its
- * container in the zfetch structure. Perform the appropriate book-keeping.
- */
-static void
-dmu_zfetch_stream_remove(zfetch_t *zf, zstream_t *zs)
-{
- ASSERT(RW_WRITE_HELD(&zf->zf_rwlock));
-
- list_remove(&zf->zf_stream, zs);
- zf->zf_stream_cnt--;
-}
-
-static int
-dmu_zfetch_streams_equal(zstream_t *zs1, zstream_t *zs2)
-{
- if (zs1->zst_offset != zs2->zst_offset)
- return (0);
-
- if (zs1->zst_len != zs2->zst_len)
- return (0);
-
- if (zs1->zst_stride != zs2->zst_stride)
- return (0);
-
- if (zs1->zst_ph_offset != zs2->zst_ph_offset)
- return (0);
-
- if (zs1->zst_cap != zs2->zst_cap)
- return (0);
-
- if (zs1->zst_direction != zs2->zst_direction)
- return (0);
-
- return (1);
+ list_insert_head(&zf->zf_stream, zs);
}
/*
- * This is the prefetch entry point. It calls all of the other dmu_zfetch
- * routines to create, delete, find, or operate upon prefetch streams.
+ * This is the predictive prefetch entry point. It associates dnode access
+ * specified with blkid and nblks arguments with prefetch stream, predicts
+ * further accesses based on that stats and initiates speculative prefetch.
+ * fetch_data argument specifies whether actual data blocks should be fetched:
+ * FALSE -- prefetch only indirect blocks for predicted data blocks;
+ * TRUE -- prefetch predicted data blocks plus following indirect blocks.
*/
void
-dmu_zfetch(zfetch_t *zf, uint64_t offset, uint64_t size, int prefetched)
+dmu_zfetch(zfetch_t *zf, uint64_t blkid, uint64_t nblks, boolean_t fetch_data)
{
- zstream_t zst;
- zstream_t *newstream;
- int fetched;
- int inserted;
- unsigned int blkshft;
- uint64_t blksz;
+ zstream_t *zs;
+ int64_t pf_start, ipf_start, ipf_istart, ipf_iend;
+ int64_t pf_ahead_blks, max_blks;
+ int epbs, max_dist_blks, pf_nblks, ipf_nblks;
+ uint64_t end_of_access_blkid;
+ end_of_access_blkid = blkid + nblks;
+ spa_t *spa = zf->zf_dnode->dn_objset->os_spa;
if (zfs_prefetch_disable)
return;
+ /*
+ * If we haven't yet loaded the indirect vdevs' mappings, we
+ * can only read from blocks that we carefully ensure are on
+ * concrete vdevs (or previously-loaded indirect vdevs). So we
+ * can't allow the predictive prefetcher to attempt reads of other
+ * blocks (e.g. of the MOS's dnode obejct).
+ */
+ if (!spa_indirect_vdevs_loaded(spa))
+ return;
- /* files that aren't ln2 blocksz are only one block -- nothing to do */
- if (!zf->zf_dnode->dn_datablkshift)
+ /*
+ * As a fast path for small (single-block) files, ignore access
+ * to the first block.
+ */
+ if (blkid == 0)
return;
- /* convert offset and size, into blockid and nblocks */
- blkshft = zf->zf_dnode->dn_datablkshift;
- blksz = (1 << blkshft);
+ rw_enter(&zf->zf_rwlock, RW_READER);
- bzero(&zst, sizeof (zstream_t));
- zst.zst_offset = offset >> blkshft;
- zst.zst_len = (P2ROUNDUP(offset + size, blksz) -
- P2ALIGN(offset, blksz)) >> blkshft;
+ /*
+ * Find matching prefetch stream. Depending on whether the accesses
+ * are block-aligned, first block of the new access may either follow
+ * the last block of the previous access, or be equal to it.
+ */
+ for (zs = list_head(&zf->zf_stream); zs != NULL;
+ zs = list_next(&zf->zf_stream, zs)) {
+ if (blkid == zs->zs_blkid || blkid + 1 == zs->zs_blkid) {
+ mutex_enter(&zs->zs_lock);
+ /*
+ * zs_blkid could have changed before we
+ * acquired zs_lock; re-check them here.
+ */
+ if (blkid == zs->zs_blkid) {
+ break;
+ } else if (blkid + 1 == zs->zs_blkid) {
+ blkid++;
+ nblks--;
+ if (nblks == 0) {
+ /* Already prefetched this before. */
+ mutex_exit(&zs->zs_lock);
+ rw_exit(&zf->zf_rwlock);
+ return;
+ }
+ break;
+ }
+ mutex_exit(&zs->zs_lock);
+ }
+ }
- fetched = dmu_zfetch_find(zf, &zst, prefetched);
- if (fetched) {
- ZFETCHSTAT_BUMP(zfetchstat_hits);
- } else {
+ if (zs == NULL) {
+ /*
+ * This access is not part of any existing stream. Create
+ * a new stream for it.
+ */
ZFETCHSTAT_BUMP(zfetchstat_misses);
- if ((fetched = dmu_zfetch_colinear(zf, &zst))) {
- ZFETCHSTAT_BUMP(zfetchstat_colinear_hits);
- } else {
- ZFETCHSTAT_BUMP(zfetchstat_colinear_misses);
- }
+ if (rw_tryupgrade(&zf->zf_rwlock))
+ dmu_zfetch_stream_create(zf, end_of_access_blkid);
+ rw_exit(&zf->zf_rwlock);
+ return;
}
- if (!fetched) {
- newstream = dmu_zfetch_stream_reclaim(zf);
+ /*
+ * This access was to a block that we issued a prefetch for on
+ * behalf of this stream. Issue further prefetches for this stream.
+ *
+ * Normally, we start prefetching where we stopped
+ * prefetching last (zs_pf_blkid). But when we get our first
+ * hit on this stream, zs_pf_blkid == zs_blkid, we don't
+ * want to prefetch the block we just accessed. In this case,
+ * start just after the block we just accessed.
+ */
+ pf_start = MAX(zs->zs_pf_blkid, end_of_access_blkid);
+ /*
+ * Double our amount of prefetched data, but don't let the
+ * prefetch get further ahead than zfetch_max_distance.
+ */
+ if (fetch_data) {
+ max_dist_blks =
+ zfetch_max_distance >> zf->zf_dnode->dn_datablkshift;
/*
- * we still couldn't find a stream, drop the lock, and allocate
- * one if possible. Otherwise, give up and go home.
+ * Previously, we were (zs_pf_blkid - blkid) ahead. We
+ * want to now be double that, so read that amount again,
+ * plus the amount we are catching up by (i.e. the amount
+ * read just now).
*/
- if (newstream) {
- ZFETCHSTAT_BUMP(zfetchstat_reclaim_successes);
- } else {
- uint64_t maxblocks;
- uint32_t max_streams;
- uint32_t cur_streams;
-
- ZFETCHSTAT_BUMP(zfetchstat_reclaim_failures);
- cur_streams = zf->zf_stream_cnt;
- maxblocks = zf->zf_dnode->dn_maxblkid;
-
- max_streams = MIN(zfetch_max_streams,
- (maxblocks / zfetch_block_cap));
- if (max_streams == 0) {
- max_streams++;
- }
-
- if (cur_streams >= max_streams) {
- return;
- }
- newstream = kmem_zalloc(sizeof (zstream_t), KM_PUSHPAGE);
- }
+ pf_ahead_blks = zs->zs_pf_blkid - blkid + nblks;
+ max_blks = max_dist_blks - (pf_start - end_of_access_blkid);
+ pf_nblks = MIN(pf_ahead_blks, max_blks);
+ } else {
+ pf_nblks = 0;
+ }
- newstream->zst_offset = zst.zst_offset;
- newstream->zst_len = zst.zst_len;
- newstream->zst_stride = zst.zst_len;
- newstream->zst_ph_offset = zst.zst_len + zst.zst_offset;
- newstream->zst_cap = zst.zst_len;
- newstream->zst_direction = ZFETCH_FORWARD;
- newstream->zst_last = ddi_get_lbolt();
+ zs->zs_pf_blkid = pf_start + pf_nblks;
- mutex_init(&newstream->zst_lock, NULL, MUTEX_DEFAULT, NULL);
+ /*
+ * Do the same for indirects, starting from where we stopped last,
+ * or where we will stop reading data blocks (and the indirects
+ * that point to them).
+ */
+ ipf_start = MAX(zs->zs_ipf_blkid, zs->zs_pf_blkid);
+ max_dist_blks = zfetch_max_idistance >> zf->zf_dnode->dn_datablkshift;
+ /*
+ * We want to double our distance ahead of the data prefetch
+ * (or reader, if we are not prefetching data). Previously, we
+ * were (zs_ipf_blkid - blkid) ahead. To double that, we read
+ * that amount again, plus the amount we are catching up by
+ * (i.e. the amount read now + the amount of data prefetched now).
+ */
+ pf_ahead_blks = zs->zs_ipf_blkid - blkid + nblks + pf_nblks;
+ max_blks = max_dist_blks - (ipf_start - end_of_access_blkid);
+ ipf_nblks = MIN(pf_ahead_blks, max_blks);
+ zs->zs_ipf_blkid = ipf_start + ipf_nblks;
+
+ epbs = zf->zf_dnode->dn_indblkshift - SPA_BLKPTRSHIFT;
+ ipf_istart = P2ROUNDUP(ipf_start, 1 << epbs) >> epbs;
+ ipf_iend = P2ROUNDUP(zs->zs_ipf_blkid, 1 << epbs) >> epbs;
+
+ zs->zs_atime = gethrtime();
+ zs->zs_blkid = end_of_access_blkid;
+ mutex_exit(&zs->zs_lock);
+ rw_exit(&zf->zf_rwlock);
- rw_enter(&zf->zf_rwlock, RW_WRITER);
- inserted = dmu_zfetch_stream_insert(zf, newstream);
- rw_exit(&zf->zf_rwlock);
+ /*
+ * dbuf_prefetch() is asynchronous (even when it needs to read
+ * indirect blocks), but we still prefer to drop our locks before
+ * calling it to reduce the time we hold them.
+ */
- if (!inserted) {
- mutex_destroy(&newstream->zst_lock);
- kmem_free(newstream, sizeof (zstream_t));
- }
+ for (int i = 0; i < pf_nblks; i++) {
+ dbuf_prefetch(zf->zf_dnode, 0, pf_start + i,
+ ZIO_PRIORITY_ASYNC_READ, ARC_FLAG_PREDICTIVE_PREFETCH);
+ }
+ for (int64_t iblk = ipf_istart; iblk < ipf_iend; iblk++) {
+ dbuf_prefetch(zf->zf_dnode, 1, iblk,
+ ZIO_PRIORITY_ASYNC_READ, ARC_FLAG_PREDICTIVE_PREFETCH);
}
+ ZFETCHSTAT_BUMP(zfetchstat_hits);
}
-#if defined(_KERNEL) && defined(HAVE_SPL)
+#if defined(_KERNEL)
+/* BEGIN CSTYLED */
module_param(zfs_prefetch_disable, int, 0644);
MODULE_PARM_DESC(zfs_prefetch_disable, "Disable all ZFS prefetching");
module_param(zfetch_min_sec_reap, uint, 0644);
MODULE_PARM_DESC(zfetch_min_sec_reap, "Min time before stream reclaim");
-module_param(zfetch_block_cap, uint, 0644);
-MODULE_PARM_DESC(zfetch_block_cap, "Max number of blocks to fetch at a time");
+module_param(zfetch_max_distance, uint, 0644);
+MODULE_PARM_DESC(zfetch_max_distance,
+ "Max bytes to prefetch per stream (default 8MB)");
module_param(zfetch_array_rd_sz, ulong, 0644);
MODULE_PARM_DESC(zfetch_array_rd_sz, "Number of bytes in a array_read");
+/* END CSTYLED */
#endif
-
projects / mirror_zfs.git / blobdiff