4 * The contents of this file are subject to the terms of the
5 * Common Development and Distribution License (the "License").
6 * You may not use this file except in compliance with the License.
8 * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
9 * or http://www.opensolaris.org/os/licensing.
10 * See the License for the specific language governing permissions
11 * and limitations under the License.
13 * When distributing Covered Code, include this CDDL HEADER in each
14 * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
15 * If applicable, add the following below this CDDL HEADER, with the
16 * fields enclosed by brackets "[]" replaced with your own identifying
17 * information: Portions Copyright [yyyy] [name of copyright owner]
22 * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
23 * Copyright 2011 Nexenta Systems, Inc. All rights reserved.
24 * Copyright (c) 2011 by Delphix. All rights reserved.
28 * DVA-based Adjustable Replacement Cache
30 * While much of the theory of operation used here is
31 * based on the self-tuning, low overhead replacement cache
32 * presented by Megiddo and Modha at FAST 2003, there are some
33 * significant differences:
35 * 1. The Megiddo and Modha model assumes any page is evictable.
36 * Pages in its cache cannot be "locked" into memory. This makes
37 * the eviction algorithm simple: evict the last page in the list.
38 * This also make the performance characteristics easy to reason
39 * about. Our cache is not so simple. At any given moment, some
40 * subset of the blocks in the cache are un-evictable because we
41 * have handed out a reference to them. Blocks are only evictable
42 * when there are no external references active. This makes
43 * eviction far more problematic: we choose to evict the evictable
44 * blocks that are the "lowest" in the list.
46 * There are times when it is not possible to evict the requested
47 * space. In these circumstances we are unable to adjust the cache
48 * size. To prevent the cache growing unbounded at these times we
49 * implement a "cache throttle" that slows the flow of new data
50 * into the cache until we can make space available.
52 * 2. The Megiddo and Modha model assumes a fixed cache size.
53 * Pages are evicted when the cache is full and there is a cache
54 * miss. Our model has a variable sized cache. It grows with
55 * high use, but also tries to react to memory pressure from the
56 * operating system: decreasing its size when system memory is
59 * 3. The Megiddo and Modha model assumes a fixed page size. All
60 * elements of the cache are therefor exactly the same size. So
61 * when adjusting the cache size following a cache miss, its simply
62 * a matter of choosing a single page to evict. In our model, we
63 * have variable sized cache blocks (rangeing from 512 bytes to
64 * 128K bytes). We therefor choose a set of blocks to evict to make
65 * space for a cache miss that approximates as closely as possible
66 * the space used by the new block.
68 * See also: "ARC: A Self-Tuning, Low Overhead Replacement Cache"
69 * by N. Megiddo & D. Modha, FAST 2003
75 * A new reference to a cache buffer can be obtained in two
76 * ways: 1) via a hash table lookup using the DVA as a key,
77 * or 2) via one of the ARC lists. The arc_read() interface
78 * uses method 1, while the internal arc algorithms for
79 * adjusting the cache use method 2. We therefor provide two
80 * types of locks: 1) the hash table lock array, and 2) the
83 * Buffers do not have their own mutexes, rather they rely on the
84 * hash table mutexes for the bulk of their protection (i.e. most
85 * fields in the arc_buf_hdr_t are protected by these mutexes).
87 * buf_hash_find() returns the appropriate mutex (held) when it
88 * locates the requested buffer in the hash table. It returns
89 * NULL for the mutex if the buffer was not in the table.
91 * buf_hash_remove() expects the appropriate hash mutex to be
92 * already held before it is invoked.
94 * Each arc state also has a mutex which is used to protect the
95 * buffer list associated with the state. When attempting to
96 * obtain a hash table lock while holding an arc list lock you
97 * must use: mutex_tryenter() to avoid deadlock. Also note that
98 * the active state mutex must be held before the ghost state mutex.
100 * Arc buffers may have an associated eviction callback function.
101 * This function will be invoked prior to removing the buffer (e.g.
102 * in arc_do_user_evicts()). Note however that the data associated
103 * with the buffer may be evicted prior to the callback. The callback
104 * must be made with *no locks held* (to prevent deadlock). Additionally,
105 * the users of callbacks must ensure that their private data is
106 * protected from simultaneous callbacks from arc_buf_evict()
107 * and arc_do_user_evicts().
109 * It as also possible to register a callback which is run when the
110 * arc_meta_limit is reached and no buffers can be safely evicted. In
111 * this case the arc user should drop a reference on some arc buffers so
112 * they can be reclaimed and the arc_meta_limit honored. For example,
113 * when using the ZPL each dentry holds a references on a znode. These
114 * dentries must be pruned before the arc buffer holding the znode can
117 * Note that the majority of the performance stats are manipulated
118 * with atomic operations.
120 * The L2ARC uses the l2arc_buflist_mtx global mutex for the following:
122 * - L2ARC buflist creation
123 * - L2ARC buflist eviction
124 * - L2ARC write completion, which walks L2ARC buflists
125 * - ARC header destruction, as it removes from L2ARC buflists
126 * - ARC header release, as it removes from L2ARC buflists
131 #include <sys/zfs_context.h>
133 #include <sys/vdev.h>
134 #include <sys/vdev_impl.h>
136 #include <sys/vmsystm.h>
138 #include <sys/fs/swapnode.h>
141 #include <sys/callb.h>
142 #include <sys/kstat.h>
143 #include <sys/dmu_tx.h>
144 #include <zfs_fletcher.h>
146 static kmutex_t arc_reclaim_thr_lock
;
147 static kcondvar_t arc_reclaim_thr_cv
; /* used to signal reclaim thr */
148 static uint8_t arc_thread_exit
;
150 /* number of bytes to prune from caches when at arc_meta_limit is reached */
151 uint_t arc_meta_prune
= 1048576;
153 typedef enum arc_reclaim_strategy
{
154 ARC_RECLAIM_AGGR
, /* Aggressive reclaim strategy */
155 ARC_RECLAIM_CONS
/* Conservative reclaim strategy */
156 } arc_reclaim_strategy_t
;
158 /* number of seconds before growing cache again */
159 static int arc_grow_retry
= 5;
161 /* expiration time for arc_no_grow */
162 static clock_t arc_grow_time
= 0;
164 /* shift of arc_c for calculating both min and max arc_p */
165 static int arc_p_min_shift
= 4;
167 /* log2(fraction of arc to reclaim) */
168 static int arc_shrink_shift
= 5;
171 * minimum lifespan of a prefetch block in clock ticks
172 * (initialized in arc_init())
174 static int arc_min_prefetch_lifespan
;
179 * The arc has filled available memory and has now warmed up.
181 static boolean_t arc_warm
;
184 * These tunables are for performance analysis.
186 unsigned long zfs_arc_max
= 0;
187 unsigned long zfs_arc_min
= 0;
188 unsigned long zfs_arc_meta_limit
= 0;
189 int zfs_arc_grow_retry
= 0;
190 int zfs_arc_shrink_shift
= 0;
191 int zfs_arc_p_min_shift
= 0;
192 int zfs_disable_dup_eviction
= 0;
193 int zfs_arc_meta_prune
= 0;
196 * Note that buffers can be in one of 6 states:
197 * ARC_anon - anonymous (discussed below)
198 * ARC_mru - recently used, currently cached
199 * ARC_mru_ghost - recentely used, no longer in cache
200 * ARC_mfu - frequently used, currently cached
201 * ARC_mfu_ghost - frequently used, no longer in cache
202 * ARC_l2c_only - exists in L2ARC but not other states
203 * When there are no active references to the buffer, they are
204 * are linked onto a list in one of these arc states. These are
205 * the only buffers that can be evicted or deleted. Within each
206 * state there are multiple lists, one for meta-data and one for
207 * non-meta-data. Meta-data (indirect blocks, blocks of dnodes,
208 * etc.) is tracked separately so that it can be managed more
209 * explicitly: favored over data, limited explicitly.
211 * Anonymous buffers are buffers that are not associated with
212 * a DVA. These are buffers that hold dirty block copies
213 * before they are written to stable storage. By definition,
214 * they are "ref'd" and are considered part of arc_mru
215 * that cannot be freed. Generally, they will aquire a DVA
216 * as they are written and migrate onto the arc_mru list.
218 * The ARC_l2c_only state is for buffers that are in the second
219 * level ARC but no longer in any of the ARC_m* lists. The second
220 * level ARC itself may also contain buffers that are in any of
221 * the ARC_m* states - meaning that a buffer can exist in two
222 * places. The reason for the ARC_l2c_only state is to keep the
223 * buffer header in the hash table, so that reads that hit the
224 * second level ARC benefit from these fast lookups.
227 typedef struct arc_state
{
228 list_t arcs_list
[ARC_BUFC_NUMTYPES
]; /* list of evictable buffers */
229 uint64_t arcs_lsize
[ARC_BUFC_NUMTYPES
]; /* amount of evictable data */
230 uint64_t arcs_size
; /* total amount of data in this state */
235 static arc_state_t ARC_anon
;
236 static arc_state_t ARC_mru
;
237 static arc_state_t ARC_mru_ghost
;
238 static arc_state_t ARC_mfu
;
239 static arc_state_t ARC_mfu_ghost
;
240 static arc_state_t ARC_l2c_only
;
242 typedef struct arc_stats
{
243 kstat_named_t arcstat_hits
;
244 kstat_named_t arcstat_misses
;
245 kstat_named_t arcstat_demand_data_hits
;
246 kstat_named_t arcstat_demand_data_misses
;
247 kstat_named_t arcstat_demand_metadata_hits
;
248 kstat_named_t arcstat_demand_metadata_misses
;
249 kstat_named_t arcstat_prefetch_data_hits
;
250 kstat_named_t arcstat_prefetch_data_misses
;
251 kstat_named_t arcstat_prefetch_metadata_hits
;
252 kstat_named_t arcstat_prefetch_metadata_misses
;
253 kstat_named_t arcstat_mru_hits
;
254 kstat_named_t arcstat_mru_ghost_hits
;
255 kstat_named_t arcstat_mfu_hits
;
256 kstat_named_t arcstat_mfu_ghost_hits
;
257 kstat_named_t arcstat_deleted
;
258 kstat_named_t arcstat_recycle_miss
;
259 kstat_named_t arcstat_mutex_miss
;
260 kstat_named_t arcstat_evict_skip
;
261 kstat_named_t arcstat_evict_l2_cached
;
262 kstat_named_t arcstat_evict_l2_eligible
;
263 kstat_named_t arcstat_evict_l2_ineligible
;
264 kstat_named_t arcstat_hash_elements
;
265 kstat_named_t arcstat_hash_elements_max
;
266 kstat_named_t arcstat_hash_collisions
;
267 kstat_named_t arcstat_hash_chains
;
268 kstat_named_t arcstat_hash_chain_max
;
269 kstat_named_t arcstat_p
;
270 kstat_named_t arcstat_c
;
271 kstat_named_t arcstat_c_min
;
272 kstat_named_t arcstat_c_max
;
273 kstat_named_t arcstat_size
;
274 kstat_named_t arcstat_hdr_size
;
275 kstat_named_t arcstat_data_size
;
276 kstat_named_t arcstat_other_size
;
277 kstat_named_t arcstat_anon_size
;
278 kstat_named_t arcstat_anon_evict_data
;
279 kstat_named_t arcstat_anon_evict_metadata
;
280 kstat_named_t arcstat_mru_size
;
281 kstat_named_t arcstat_mru_evict_data
;
282 kstat_named_t arcstat_mru_evict_metadata
;
283 kstat_named_t arcstat_mru_ghost_size
;
284 kstat_named_t arcstat_mru_ghost_evict_data
;
285 kstat_named_t arcstat_mru_ghost_evict_metadata
;
286 kstat_named_t arcstat_mfu_size
;
287 kstat_named_t arcstat_mfu_evict_data
;
288 kstat_named_t arcstat_mfu_evict_metadata
;
289 kstat_named_t arcstat_mfu_ghost_size
;
290 kstat_named_t arcstat_mfu_ghost_evict_data
;
291 kstat_named_t arcstat_mfu_ghost_evict_metadata
;
292 kstat_named_t arcstat_l2_hits
;
293 kstat_named_t arcstat_l2_misses
;
294 kstat_named_t arcstat_l2_feeds
;
295 kstat_named_t arcstat_l2_rw_clash
;
296 kstat_named_t arcstat_l2_read_bytes
;
297 kstat_named_t arcstat_l2_write_bytes
;
298 kstat_named_t arcstat_l2_writes_sent
;
299 kstat_named_t arcstat_l2_writes_done
;
300 kstat_named_t arcstat_l2_writes_error
;
301 kstat_named_t arcstat_l2_writes_hdr_miss
;
302 kstat_named_t arcstat_l2_evict_lock_retry
;
303 kstat_named_t arcstat_l2_evict_reading
;
304 kstat_named_t arcstat_l2_free_on_write
;
305 kstat_named_t arcstat_l2_abort_lowmem
;
306 kstat_named_t arcstat_l2_cksum_bad
;
307 kstat_named_t arcstat_l2_io_error
;
308 kstat_named_t arcstat_l2_size
;
309 kstat_named_t arcstat_l2_hdr_size
;
310 kstat_named_t arcstat_memory_throttle_count
;
311 kstat_named_t arcstat_duplicate_buffers
;
312 kstat_named_t arcstat_duplicate_buffers_size
;
313 kstat_named_t arcstat_duplicate_reads
;
314 kstat_named_t arcstat_memory_direct_count
;
315 kstat_named_t arcstat_memory_indirect_count
;
316 kstat_named_t arcstat_no_grow
;
317 kstat_named_t arcstat_tempreserve
;
318 kstat_named_t arcstat_loaned_bytes
;
319 kstat_named_t arcstat_prune
;
320 kstat_named_t arcstat_meta_used
;
321 kstat_named_t arcstat_meta_limit
;
322 kstat_named_t arcstat_meta_max
;
325 static arc_stats_t arc_stats
= {
326 { "hits", KSTAT_DATA_UINT64
},
327 { "misses", KSTAT_DATA_UINT64
},
328 { "demand_data_hits", KSTAT_DATA_UINT64
},
329 { "demand_data_misses", KSTAT_DATA_UINT64
},
330 { "demand_metadata_hits", KSTAT_DATA_UINT64
},
331 { "demand_metadata_misses", KSTAT_DATA_UINT64
},
332 { "prefetch_data_hits", KSTAT_DATA_UINT64
},
333 { "prefetch_data_misses", KSTAT_DATA_UINT64
},
334 { "prefetch_metadata_hits", KSTAT_DATA_UINT64
},
335 { "prefetch_metadata_misses", KSTAT_DATA_UINT64
},
336 { "mru_hits", KSTAT_DATA_UINT64
},
337 { "mru_ghost_hits", KSTAT_DATA_UINT64
},
338 { "mfu_hits", KSTAT_DATA_UINT64
},
339 { "mfu_ghost_hits", KSTAT_DATA_UINT64
},
340 { "deleted", KSTAT_DATA_UINT64
},
341 { "recycle_miss", KSTAT_DATA_UINT64
},
342 { "mutex_miss", KSTAT_DATA_UINT64
},
343 { "evict_skip", KSTAT_DATA_UINT64
},
344 { "evict_l2_cached", KSTAT_DATA_UINT64
},
345 { "evict_l2_eligible", KSTAT_DATA_UINT64
},
346 { "evict_l2_ineligible", KSTAT_DATA_UINT64
},
347 { "hash_elements", KSTAT_DATA_UINT64
},
348 { "hash_elements_max", KSTAT_DATA_UINT64
},
349 { "hash_collisions", KSTAT_DATA_UINT64
},
350 { "hash_chains", KSTAT_DATA_UINT64
},
351 { "hash_chain_max", KSTAT_DATA_UINT64
},
352 { "p", KSTAT_DATA_UINT64
},
353 { "c", KSTAT_DATA_UINT64
},
354 { "c_min", KSTAT_DATA_UINT64
},
355 { "c_max", KSTAT_DATA_UINT64
},
356 { "size", KSTAT_DATA_UINT64
},
357 { "hdr_size", KSTAT_DATA_UINT64
},
358 { "data_size", KSTAT_DATA_UINT64
},
359 { "other_size", KSTAT_DATA_UINT64
},
360 { "anon_size", KSTAT_DATA_UINT64
},
361 { "anon_evict_data", KSTAT_DATA_UINT64
},
362 { "anon_evict_metadata", KSTAT_DATA_UINT64
},
363 { "mru_size", KSTAT_DATA_UINT64
},
364 { "mru_evict_data", KSTAT_DATA_UINT64
},
365 { "mru_evict_metadata", KSTAT_DATA_UINT64
},
366 { "mru_ghost_size", KSTAT_DATA_UINT64
},
367 { "mru_ghost_evict_data", KSTAT_DATA_UINT64
},
368 { "mru_ghost_evict_metadata", KSTAT_DATA_UINT64
},
369 { "mfu_size", KSTAT_DATA_UINT64
},
370 { "mfu_evict_data", KSTAT_DATA_UINT64
},
371 { "mfu_evict_metadata", KSTAT_DATA_UINT64
},
372 { "mfu_ghost_size", KSTAT_DATA_UINT64
},
373 { "mfu_ghost_evict_data", KSTAT_DATA_UINT64
},
374 { "mfu_ghost_evict_metadata", KSTAT_DATA_UINT64
},
375 { "l2_hits", KSTAT_DATA_UINT64
},
376 { "l2_misses", KSTAT_DATA_UINT64
},
377 { "l2_feeds", KSTAT_DATA_UINT64
},
378 { "l2_rw_clash", KSTAT_DATA_UINT64
},
379 { "l2_read_bytes", KSTAT_DATA_UINT64
},
380 { "l2_write_bytes", KSTAT_DATA_UINT64
},
381 { "l2_writes_sent", KSTAT_DATA_UINT64
},
382 { "l2_writes_done", KSTAT_DATA_UINT64
},
383 { "l2_writes_error", KSTAT_DATA_UINT64
},
384 { "l2_writes_hdr_miss", KSTAT_DATA_UINT64
},
385 { "l2_evict_lock_retry", KSTAT_DATA_UINT64
},
386 { "l2_evict_reading", KSTAT_DATA_UINT64
},
387 { "l2_free_on_write", KSTAT_DATA_UINT64
},
388 { "l2_abort_lowmem", KSTAT_DATA_UINT64
},
389 { "l2_cksum_bad", KSTAT_DATA_UINT64
},
390 { "l2_io_error", KSTAT_DATA_UINT64
},
391 { "l2_size", KSTAT_DATA_UINT64
},
392 { "l2_hdr_size", KSTAT_DATA_UINT64
},
393 { "memory_throttle_count", KSTAT_DATA_UINT64
},
394 { "duplicate_buffers", KSTAT_DATA_UINT64
},
395 { "duplicate_buffers_size", KSTAT_DATA_UINT64
},
396 { "duplicate_reads", KSTAT_DATA_UINT64
},
397 { "memory_direct_count", KSTAT_DATA_UINT64
},
398 { "memory_indirect_count", KSTAT_DATA_UINT64
},
399 { "arc_no_grow", KSTAT_DATA_UINT64
},
400 { "arc_tempreserve", KSTAT_DATA_UINT64
},
401 { "arc_loaned_bytes", KSTAT_DATA_UINT64
},
402 { "arc_prune", KSTAT_DATA_UINT64
},
403 { "arc_meta_used", KSTAT_DATA_UINT64
},
404 { "arc_meta_limit", KSTAT_DATA_UINT64
},
405 { "arc_meta_max", KSTAT_DATA_UINT64
},
408 #define ARCSTAT(stat) (arc_stats.stat.value.ui64)
410 #define ARCSTAT_INCR(stat, val) \
411 atomic_add_64(&arc_stats.stat.value.ui64, (val));
413 #define ARCSTAT_BUMP(stat) ARCSTAT_INCR(stat, 1)
414 #define ARCSTAT_BUMPDOWN(stat) ARCSTAT_INCR(stat, -1)
416 #define ARCSTAT_MAX(stat, val) { \
418 while ((val) > (m = arc_stats.stat.value.ui64) && \
419 (m != atomic_cas_64(&arc_stats.stat.value.ui64, m, (val)))) \
423 #define ARCSTAT_MAXSTAT(stat) \
424 ARCSTAT_MAX(stat##_max, arc_stats.stat.value.ui64)
427 * We define a macro to allow ARC hits/misses to be easily broken down by
428 * two separate conditions, giving a total of four different subtypes for
429 * each of hits and misses (so eight statistics total).
431 #define ARCSTAT_CONDSTAT(cond1, stat1, notstat1, cond2, stat2, notstat2, stat) \
434 ARCSTAT_BUMP(arcstat_##stat1##_##stat2##_##stat); \
436 ARCSTAT_BUMP(arcstat_##stat1##_##notstat2##_##stat); \
440 ARCSTAT_BUMP(arcstat_##notstat1##_##stat2##_##stat); \
442 ARCSTAT_BUMP(arcstat_##notstat1##_##notstat2##_##stat);\
447 static arc_state_t
*arc_anon
;
448 static arc_state_t
*arc_mru
;
449 static arc_state_t
*arc_mru_ghost
;
450 static arc_state_t
*arc_mfu
;
451 static arc_state_t
*arc_mfu_ghost
;
452 static arc_state_t
*arc_l2c_only
;
455 * There are several ARC variables that are critical to export as kstats --
456 * but we don't want to have to grovel around in the kstat whenever we wish to
457 * manipulate them. For these variables, we therefore define them to be in
458 * terms of the statistic variable. This assures that we are not introducing
459 * the possibility of inconsistency by having shadow copies of the variables,
460 * while still allowing the code to be readable.
462 #define arc_size ARCSTAT(arcstat_size) /* actual total arc size */
463 #define arc_p ARCSTAT(arcstat_p) /* target size of MRU */
464 #define arc_c ARCSTAT(arcstat_c) /* target size of cache */
465 #define arc_c_min ARCSTAT(arcstat_c_min) /* min target cache size */
466 #define arc_c_max ARCSTAT(arcstat_c_max) /* max target cache size */
467 #define arc_no_grow ARCSTAT(arcstat_no_grow)
468 #define arc_tempreserve ARCSTAT(arcstat_tempreserve)
469 #define arc_loaned_bytes ARCSTAT(arcstat_loaned_bytes)
470 #define arc_meta_used ARCSTAT(arcstat_meta_used)
471 #define arc_meta_limit ARCSTAT(arcstat_meta_limit)
472 #define arc_meta_max ARCSTAT(arcstat_meta_max)
474 typedef struct l2arc_buf_hdr l2arc_buf_hdr_t
;
476 typedef struct arc_callback arc_callback_t
;
478 struct arc_callback
{
480 arc_done_func_t
*acb_done
;
482 zio_t
*acb_zio_dummy
;
483 arc_callback_t
*acb_next
;
486 typedef struct arc_write_callback arc_write_callback_t
;
488 struct arc_write_callback
{
490 arc_done_func_t
*awcb_ready
;
491 arc_done_func_t
*awcb_done
;
496 /* protected by hash lock */
501 kmutex_t b_freeze_lock
;
502 zio_cksum_t
*b_freeze_cksum
;
505 arc_buf_hdr_t
*b_hash_next
;
510 arc_callback_t
*b_acb
;
514 arc_buf_contents_t b_type
;
518 /* protected by arc state mutex */
519 arc_state_t
*b_state
;
520 list_node_t b_arc_node
;
522 /* updated atomically */
523 clock_t b_arc_access
;
525 /* self protecting */
528 l2arc_buf_hdr_t
*b_l2hdr
;
529 list_node_t b_l2node
;
532 static list_t arc_prune_list
;
533 static kmutex_t arc_prune_mtx
;
534 static arc_buf_t
*arc_eviction_list
;
535 static kmutex_t arc_eviction_mtx
;
536 static arc_buf_hdr_t arc_eviction_hdr
;
537 static void arc_get_data_buf(arc_buf_t
*buf
);
538 static void arc_access(arc_buf_hdr_t
*buf
, kmutex_t
*hash_lock
);
539 static int arc_evict_needed(arc_buf_contents_t type
);
540 static void arc_evict_ghost(arc_state_t
*state
, uint64_t spa
, int64_t bytes
);
542 static boolean_t
l2arc_write_eligible(uint64_t spa_guid
, arc_buf_hdr_t
*ab
);
544 #define GHOST_STATE(state) \
545 ((state) == arc_mru_ghost || (state) == arc_mfu_ghost || \
546 (state) == arc_l2c_only)
549 * Private ARC flags. These flags are private ARC only flags that will show up
550 * in b_flags in the arc_hdr_buf_t. Some flags are publicly declared, and can
551 * be passed in as arc_flags in things like arc_read. However, these flags
552 * should never be passed and should only be set by ARC code. When adding new
553 * public flags, make sure not to smash the private ones.
556 #define ARC_IN_HASH_TABLE (1 << 9) /* this buffer is hashed */
557 #define ARC_IO_IN_PROGRESS (1 << 10) /* I/O in progress for buf */
558 #define ARC_IO_ERROR (1 << 11) /* I/O failed for buf */
559 #define ARC_FREED_IN_READ (1 << 12) /* buf freed while in read */
560 #define ARC_BUF_AVAILABLE (1 << 13) /* block not in active use */
561 #define ARC_INDIRECT (1 << 14) /* this is an indirect block */
562 #define ARC_FREE_IN_PROGRESS (1 << 15) /* hdr about to be freed */
563 #define ARC_L2_WRITING (1 << 16) /* L2ARC write in progress */
564 #define ARC_L2_EVICTED (1 << 17) /* evicted during I/O */
565 #define ARC_L2_WRITE_HEAD (1 << 18) /* head of write list */
567 #define HDR_IN_HASH_TABLE(hdr) ((hdr)->b_flags & ARC_IN_HASH_TABLE)
568 #define HDR_IO_IN_PROGRESS(hdr) ((hdr)->b_flags & ARC_IO_IN_PROGRESS)
569 #define HDR_IO_ERROR(hdr) ((hdr)->b_flags & ARC_IO_ERROR)
570 #define HDR_PREFETCH(hdr) ((hdr)->b_flags & ARC_PREFETCH)
571 #define HDR_FREED_IN_READ(hdr) ((hdr)->b_flags & ARC_FREED_IN_READ)
572 #define HDR_BUF_AVAILABLE(hdr) ((hdr)->b_flags & ARC_BUF_AVAILABLE)
573 #define HDR_FREE_IN_PROGRESS(hdr) ((hdr)->b_flags & ARC_FREE_IN_PROGRESS)
574 #define HDR_L2CACHE(hdr) ((hdr)->b_flags & ARC_L2CACHE)
575 #define HDR_L2_READING(hdr) ((hdr)->b_flags & ARC_IO_IN_PROGRESS && \
576 (hdr)->b_l2hdr != NULL)
577 #define HDR_L2_WRITING(hdr) ((hdr)->b_flags & ARC_L2_WRITING)
578 #define HDR_L2_EVICTED(hdr) ((hdr)->b_flags & ARC_L2_EVICTED)
579 #define HDR_L2_WRITE_HEAD(hdr) ((hdr)->b_flags & ARC_L2_WRITE_HEAD)
585 #define HDR_SIZE ((int64_t)sizeof (arc_buf_hdr_t))
586 #define L2HDR_SIZE ((int64_t)sizeof (l2arc_buf_hdr_t))
589 * Hash table routines
592 #define HT_LOCK_ALIGN 64
593 #define HT_LOCK_PAD (P2NPHASE(sizeof (kmutex_t), (HT_LOCK_ALIGN)))
598 unsigned char pad
[HT_LOCK_PAD
];
602 #define BUF_LOCKS 256
603 typedef struct buf_hash_table
{
605 arc_buf_hdr_t
**ht_table
;
606 struct ht_lock ht_locks
[BUF_LOCKS
];
609 static buf_hash_table_t buf_hash_table
;
611 #define BUF_HASH_INDEX(spa, dva, birth) \
612 (buf_hash(spa, dva, birth) & buf_hash_table.ht_mask)
613 #define BUF_HASH_LOCK_NTRY(idx) (buf_hash_table.ht_locks[idx & (BUF_LOCKS-1)])
614 #define BUF_HASH_LOCK(idx) (&(BUF_HASH_LOCK_NTRY(idx).ht_lock))
615 #define HDR_LOCK(hdr) \
616 (BUF_HASH_LOCK(BUF_HASH_INDEX(hdr->b_spa, &hdr->b_dva, hdr->b_birth)))
618 uint64_t zfs_crc64_table
[256];
624 #define L2ARC_WRITE_SIZE (8 * 1024 * 1024) /* initial write max */
625 #define L2ARC_HEADROOM 2 /* num of writes */
626 #define L2ARC_FEED_SECS 1 /* caching interval secs */
627 #define L2ARC_FEED_MIN_MS 200 /* min caching interval ms */
629 #define l2arc_writes_sent ARCSTAT(arcstat_l2_writes_sent)
630 #define l2arc_writes_done ARCSTAT(arcstat_l2_writes_done)
633 * L2ARC Performance Tunables
635 unsigned long l2arc_write_max
= L2ARC_WRITE_SIZE
; /* def max write size */
636 unsigned long l2arc_write_boost
= L2ARC_WRITE_SIZE
; /* extra warmup write */
637 unsigned long l2arc_headroom
= L2ARC_HEADROOM
; /* # of dev writes */
638 unsigned long l2arc_feed_secs
= L2ARC_FEED_SECS
; /* interval seconds */
639 unsigned long l2arc_feed_min_ms
= L2ARC_FEED_MIN_MS
; /* min interval msecs */
640 int l2arc_noprefetch
= B_TRUE
; /* don't cache prefetch bufs */
641 int l2arc_feed_again
= B_TRUE
; /* turbo warmup */
642 int l2arc_norw
= B_TRUE
; /* no reads during writes */
647 typedef struct l2arc_dev
{
648 vdev_t
*l2ad_vdev
; /* vdev */
649 spa_t
*l2ad_spa
; /* spa */
650 uint64_t l2ad_hand
; /* next write location */
651 uint64_t l2ad_write
; /* desired write size, bytes */
652 uint64_t l2ad_boost
; /* warmup write boost, bytes */
653 uint64_t l2ad_start
; /* first addr on device */
654 uint64_t l2ad_end
; /* last addr on device */
655 uint64_t l2ad_evict
; /* last addr eviction reached */
656 boolean_t l2ad_first
; /* first sweep through */
657 boolean_t l2ad_writing
; /* currently writing */
658 list_t
*l2ad_buflist
; /* buffer list */
659 list_node_t l2ad_node
; /* device list node */
662 static list_t L2ARC_dev_list
; /* device list */
663 static list_t
*l2arc_dev_list
; /* device list pointer */
664 static kmutex_t l2arc_dev_mtx
; /* device list mutex */
665 static l2arc_dev_t
*l2arc_dev_last
; /* last device used */
666 static kmutex_t l2arc_buflist_mtx
; /* mutex for all buflists */
667 static list_t L2ARC_free_on_write
; /* free after write buf list */
668 static list_t
*l2arc_free_on_write
; /* free after write list ptr */
669 static kmutex_t l2arc_free_on_write_mtx
; /* mutex for list */
670 static uint64_t l2arc_ndev
; /* number of devices */
672 typedef struct l2arc_read_callback
{
673 arc_buf_t
*l2rcb_buf
; /* read buffer */
674 spa_t
*l2rcb_spa
; /* spa */
675 blkptr_t l2rcb_bp
; /* original blkptr */
676 zbookmark_t l2rcb_zb
; /* original bookmark */
677 int l2rcb_flags
; /* original flags */
678 } l2arc_read_callback_t
;
680 typedef struct l2arc_write_callback
{
681 l2arc_dev_t
*l2wcb_dev
; /* device info */
682 arc_buf_hdr_t
*l2wcb_head
; /* head of write buflist */
683 } l2arc_write_callback_t
;
685 struct l2arc_buf_hdr
{
686 /* protected by arc_buf_hdr mutex */
687 l2arc_dev_t
*b_dev
; /* L2ARC device */
688 uint64_t b_daddr
; /* disk address, offset byte */
691 typedef struct l2arc_data_free
{
692 /* protected by l2arc_free_on_write_mtx */
695 void (*l2df_func
)(void *, size_t);
696 list_node_t l2df_list_node
;
699 static kmutex_t l2arc_feed_thr_lock
;
700 static kcondvar_t l2arc_feed_thr_cv
;
701 static uint8_t l2arc_thread_exit
;
703 static void l2arc_read_done(zio_t
*zio
);
704 static void l2arc_hdr_stat_add(void);
705 static void l2arc_hdr_stat_remove(void);
708 buf_hash(uint64_t spa
, const dva_t
*dva
, uint64_t birth
)
710 uint8_t *vdva
= (uint8_t *)dva
;
711 uint64_t crc
= -1ULL;
714 ASSERT(zfs_crc64_table
[128] == ZFS_CRC64_POLY
);
716 for (i
= 0; i
< sizeof (dva_t
); i
++)
717 crc
= (crc
>> 8) ^ zfs_crc64_table
[(crc
^ vdva
[i
]) & 0xFF];
719 crc
^= (spa
>>8) ^ birth
;
724 #define BUF_EMPTY(buf) \
725 ((buf)->b_dva.dva_word[0] == 0 && \
726 (buf)->b_dva.dva_word[1] == 0 && \
729 #define BUF_EQUAL(spa, dva, birth, buf) \
730 ((buf)->b_dva.dva_word[0] == (dva)->dva_word[0]) && \
731 ((buf)->b_dva.dva_word[1] == (dva)->dva_word[1]) && \
732 ((buf)->b_birth == birth) && ((buf)->b_spa == spa)
735 buf_discard_identity(arc_buf_hdr_t
*hdr
)
737 hdr
->b_dva
.dva_word
[0] = 0;
738 hdr
->b_dva
.dva_word
[1] = 0;
743 static arc_buf_hdr_t
*
744 buf_hash_find(uint64_t spa
, const dva_t
*dva
, uint64_t birth
, kmutex_t
**lockp
)
746 uint64_t idx
= BUF_HASH_INDEX(spa
, dva
, birth
);
747 kmutex_t
*hash_lock
= BUF_HASH_LOCK(idx
);
750 mutex_enter(hash_lock
);
751 for (buf
= buf_hash_table
.ht_table
[idx
]; buf
!= NULL
;
752 buf
= buf
->b_hash_next
) {
753 if (BUF_EQUAL(spa
, dva
, birth
, buf
)) {
758 mutex_exit(hash_lock
);
764 * Insert an entry into the hash table. If there is already an element
765 * equal to elem in the hash table, then the already existing element
766 * will be returned and the new element will not be inserted.
767 * Otherwise returns NULL.
769 static arc_buf_hdr_t
*
770 buf_hash_insert(arc_buf_hdr_t
*buf
, kmutex_t
**lockp
)
772 uint64_t idx
= BUF_HASH_INDEX(buf
->b_spa
, &buf
->b_dva
, buf
->b_birth
);
773 kmutex_t
*hash_lock
= BUF_HASH_LOCK(idx
);
777 ASSERT(!HDR_IN_HASH_TABLE(buf
));
779 mutex_enter(hash_lock
);
780 for (fbuf
= buf_hash_table
.ht_table
[idx
], i
= 0; fbuf
!= NULL
;
781 fbuf
= fbuf
->b_hash_next
, i
++) {
782 if (BUF_EQUAL(buf
->b_spa
, &buf
->b_dva
, buf
->b_birth
, fbuf
))
786 buf
->b_hash_next
= buf_hash_table
.ht_table
[idx
];
787 buf_hash_table
.ht_table
[idx
] = buf
;
788 buf
->b_flags
|= ARC_IN_HASH_TABLE
;
790 /* collect some hash table performance data */
792 ARCSTAT_BUMP(arcstat_hash_collisions
);
794 ARCSTAT_BUMP(arcstat_hash_chains
);
796 ARCSTAT_MAX(arcstat_hash_chain_max
, i
);
799 ARCSTAT_BUMP(arcstat_hash_elements
);
800 ARCSTAT_MAXSTAT(arcstat_hash_elements
);
806 buf_hash_remove(arc_buf_hdr_t
*buf
)
808 arc_buf_hdr_t
*fbuf
, **bufp
;
809 uint64_t idx
= BUF_HASH_INDEX(buf
->b_spa
, &buf
->b_dva
, buf
->b_birth
);
811 ASSERT(MUTEX_HELD(BUF_HASH_LOCK(idx
)));
812 ASSERT(HDR_IN_HASH_TABLE(buf
));
814 bufp
= &buf_hash_table
.ht_table
[idx
];
815 while ((fbuf
= *bufp
) != buf
) {
816 ASSERT(fbuf
!= NULL
);
817 bufp
= &fbuf
->b_hash_next
;
819 *bufp
= buf
->b_hash_next
;
820 buf
->b_hash_next
= NULL
;
821 buf
->b_flags
&= ~ARC_IN_HASH_TABLE
;
823 /* collect some hash table performance data */
824 ARCSTAT_BUMPDOWN(arcstat_hash_elements
);
826 if (buf_hash_table
.ht_table
[idx
] &&
827 buf_hash_table
.ht_table
[idx
]->b_hash_next
== NULL
)
828 ARCSTAT_BUMPDOWN(arcstat_hash_chains
);
832 * Global data structures and functions for the buf kmem cache.
834 static kmem_cache_t
*hdr_cache
;
835 static kmem_cache_t
*buf_cache
;
842 #if defined(_KERNEL) && defined(HAVE_SPL)
843 /* Large allocations which do not require contiguous pages
844 * should be using vmem_free() in the linux kernel */
845 vmem_free(buf_hash_table
.ht_table
,
846 (buf_hash_table
.ht_mask
+ 1) * sizeof (void *));
848 kmem_free(buf_hash_table
.ht_table
,
849 (buf_hash_table
.ht_mask
+ 1) * sizeof (void *));
851 for (i
= 0; i
< BUF_LOCKS
; i
++)
852 mutex_destroy(&buf_hash_table
.ht_locks
[i
].ht_lock
);
853 kmem_cache_destroy(hdr_cache
);
854 kmem_cache_destroy(buf_cache
);
858 * Constructor callback - called when the cache is empty
859 * and a new buf is requested.
863 hdr_cons(void *vbuf
, void *unused
, int kmflag
)
865 arc_buf_hdr_t
*buf
= vbuf
;
867 bzero(buf
, sizeof (arc_buf_hdr_t
));
868 refcount_create(&buf
->b_refcnt
);
869 cv_init(&buf
->b_cv
, NULL
, CV_DEFAULT
, NULL
);
870 mutex_init(&buf
->b_freeze_lock
, NULL
, MUTEX_DEFAULT
, NULL
);
871 list_link_init(&buf
->b_arc_node
);
872 list_link_init(&buf
->b_l2node
);
873 arc_space_consume(sizeof (arc_buf_hdr_t
), ARC_SPACE_HDRS
);
880 buf_cons(void *vbuf
, void *unused
, int kmflag
)
882 arc_buf_t
*buf
= vbuf
;
884 bzero(buf
, sizeof (arc_buf_t
));
885 mutex_init(&buf
->b_evict_lock
, NULL
, MUTEX_DEFAULT
, NULL
);
886 rw_init(&buf
->b_data_lock
, NULL
, RW_DEFAULT
, NULL
);
887 arc_space_consume(sizeof (arc_buf_t
), ARC_SPACE_HDRS
);
893 * Destructor callback - called when a cached buf is
894 * no longer required.
898 hdr_dest(void *vbuf
, void *unused
)
900 arc_buf_hdr_t
*buf
= vbuf
;
902 ASSERT(BUF_EMPTY(buf
));
903 refcount_destroy(&buf
->b_refcnt
);
904 cv_destroy(&buf
->b_cv
);
905 mutex_destroy(&buf
->b_freeze_lock
);
906 arc_space_return(sizeof (arc_buf_hdr_t
), ARC_SPACE_HDRS
);
911 buf_dest(void *vbuf
, void *unused
)
913 arc_buf_t
*buf
= vbuf
;
915 mutex_destroy(&buf
->b_evict_lock
);
916 rw_destroy(&buf
->b_data_lock
);
917 arc_space_return(sizeof (arc_buf_t
), ARC_SPACE_HDRS
);
924 uint64_t hsize
= 1ULL << 12;
928 * The hash table is big enough to fill all of physical memory
929 * with an average 64K block size. The table will take up
930 * totalmem*sizeof(void*)/64K (eg. 128KB/GB with 8-byte pointers).
932 while (hsize
* 65536 < physmem
* PAGESIZE
)
935 buf_hash_table
.ht_mask
= hsize
- 1;
936 #if defined(_KERNEL) && defined(HAVE_SPL)
937 /* Large allocations which do not require contiguous pages
938 * should be using vmem_alloc() in the linux kernel */
939 buf_hash_table
.ht_table
=
940 vmem_zalloc(hsize
* sizeof (void*), KM_SLEEP
);
942 buf_hash_table
.ht_table
=
943 kmem_zalloc(hsize
* sizeof (void*), KM_NOSLEEP
);
945 if (buf_hash_table
.ht_table
== NULL
) {
946 ASSERT(hsize
> (1ULL << 8));
951 hdr_cache
= kmem_cache_create("arc_buf_hdr_t", sizeof (arc_buf_hdr_t
),
952 0, hdr_cons
, hdr_dest
, NULL
, NULL
, NULL
, 0);
953 buf_cache
= kmem_cache_create("arc_buf_t", sizeof (arc_buf_t
),
954 0, buf_cons
, buf_dest
, NULL
, NULL
, NULL
, 0);
956 for (i
= 0; i
< 256; i
++)
957 for (ct
= zfs_crc64_table
+ i
, *ct
= i
, j
= 8; j
> 0; j
--)
958 *ct
= (*ct
>> 1) ^ (-(*ct
& 1) & ZFS_CRC64_POLY
);
960 for (i
= 0; i
< BUF_LOCKS
; i
++) {
961 mutex_init(&buf_hash_table
.ht_locks
[i
].ht_lock
,
962 NULL
, MUTEX_DEFAULT
, NULL
);
966 #define ARC_MINTIME (hz>>4) /* 62 ms */
969 arc_cksum_verify(arc_buf_t
*buf
)
973 if (!(zfs_flags
& ZFS_DEBUG_MODIFY
))
976 mutex_enter(&buf
->b_hdr
->b_freeze_lock
);
977 if (buf
->b_hdr
->b_freeze_cksum
== NULL
||
978 (buf
->b_hdr
->b_flags
& ARC_IO_ERROR
)) {
979 mutex_exit(&buf
->b_hdr
->b_freeze_lock
);
982 fletcher_2_native(buf
->b_data
, buf
->b_hdr
->b_size
, &zc
);
983 if (!ZIO_CHECKSUM_EQUAL(*buf
->b_hdr
->b_freeze_cksum
, zc
))
984 panic("buffer modified while frozen!");
985 mutex_exit(&buf
->b_hdr
->b_freeze_lock
);
989 arc_cksum_equal(arc_buf_t
*buf
)
994 mutex_enter(&buf
->b_hdr
->b_freeze_lock
);
995 fletcher_2_native(buf
->b_data
, buf
->b_hdr
->b_size
, &zc
);
996 equal
= ZIO_CHECKSUM_EQUAL(*buf
->b_hdr
->b_freeze_cksum
, zc
);
997 mutex_exit(&buf
->b_hdr
->b_freeze_lock
);
1003 arc_cksum_compute(arc_buf_t
*buf
, boolean_t force
)
1005 if (!force
&& !(zfs_flags
& ZFS_DEBUG_MODIFY
))
1008 mutex_enter(&buf
->b_hdr
->b_freeze_lock
);
1009 if (buf
->b_hdr
->b_freeze_cksum
!= NULL
) {
1010 mutex_exit(&buf
->b_hdr
->b_freeze_lock
);
1013 buf
->b_hdr
->b_freeze_cksum
= kmem_alloc(sizeof (zio_cksum_t
),
1015 fletcher_2_native(buf
->b_data
, buf
->b_hdr
->b_size
,
1016 buf
->b_hdr
->b_freeze_cksum
);
1017 mutex_exit(&buf
->b_hdr
->b_freeze_lock
);
1021 arc_buf_thaw(arc_buf_t
*buf
)
1023 if (zfs_flags
& ZFS_DEBUG_MODIFY
) {
1024 if (buf
->b_hdr
->b_state
!= arc_anon
)
1025 panic("modifying non-anon buffer!");
1026 if (buf
->b_hdr
->b_flags
& ARC_IO_IN_PROGRESS
)
1027 panic("modifying buffer while i/o in progress!");
1028 arc_cksum_verify(buf
);
1031 mutex_enter(&buf
->b_hdr
->b_freeze_lock
);
1032 if (buf
->b_hdr
->b_freeze_cksum
!= NULL
) {
1033 kmem_free(buf
->b_hdr
->b_freeze_cksum
, sizeof (zio_cksum_t
));
1034 buf
->b_hdr
->b_freeze_cksum
= NULL
;
1037 if (zfs_flags
& ZFS_DEBUG_MODIFY
) {
1038 if (buf
->b_hdr
->b_thawed
)
1039 kmem_free(buf
->b_hdr
->b_thawed
, 1);
1040 buf
->b_hdr
->b_thawed
= kmem_alloc(1, KM_SLEEP
);
1043 mutex_exit(&buf
->b_hdr
->b_freeze_lock
);
1047 arc_buf_freeze(arc_buf_t
*buf
)
1049 kmutex_t
*hash_lock
;
1051 if (!(zfs_flags
& ZFS_DEBUG_MODIFY
))
1054 hash_lock
= HDR_LOCK(buf
->b_hdr
);
1055 mutex_enter(hash_lock
);
1057 ASSERT(buf
->b_hdr
->b_freeze_cksum
!= NULL
||
1058 buf
->b_hdr
->b_state
== arc_anon
);
1059 arc_cksum_compute(buf
, B_FALSE
);
1060 mutex_exit(hash_lock
);
1064 add_reference(arc_buf_hdr_t
*ab
, kmutex_t
*hash_lock
, void *tag
)
1066 ASSERT(MUTEX_HELD(hash_lock
));
1068 if ((refcount_add(&ab
->b_refcnt
, tag
) == 1) &&
1069 (ab
->b_state
!= arc_anon
)) {
1070 uint64_t delta
= ab
->b_size
* ab
->b_datacnt
;
1071 list_t
*list
= &ab
->b_state
->arcs_list
[ab
->b_type
];
1072 uint64_t *size
= &ab
->b_state
->arcs_lsize
[ab
->b_type
];
1074 ASSERT(!MUTEX_HELD(&ab
->b_state
->arcs_mtx
));
1075 mutex_enter(&ab
->b_state
->arcs_mtx
);
1076 ASSERT(list_link_active(&ab
->b_arc_node
));
1077 list_remove(list
, ab
);
1078 if (GHOST_STATE(ab
->b_state
)) {
1079 ASSERT3U(ab
->b_datacnt
, ==, 0);
1080 ASSERT3P(ab
->b_buf
, ==, NULL
);
1084 ASSERT3U(*size
, >=, delta
);
1085 atomic_add_64(size
, -delta
);
1086 mutex_exit(&ab
->b_state
->arcs_mtx
);
1087 /* remove the prefetch flag if we get a reference */
1088 if (ab
->b_flags
& ARC_PREFETCH
)
1089 ab
->b_flags
&= ~ARC_PREFETCH
;
1094 remove_reference(arc_buf_hdr_t
*ab
, kmutex_t
*hash_lock
, void *tag
)
1097 arc_state_t
*state
= ab
->b_state
;
1099 ASSERT(state
== arc_anon
|| MUTEX_HELD(hash_lock
));
1100 ASSERT(!GHOST_STATE(state
));
1102 if (((cnt
= refcount_remove(&ab
->b_refcnt
, tag
)) == 0) &&
1103 (state
!= arc_anon
)) {
1104 uint64_t *size
= &state
->arcs_lsize
[ab
->b_type
];
1106 ASSERT(!MUTEX_HELD(&state
->arcs_mtx
));
1107 mutex_enter(&state
->arcs_mtx
);
1108 ASSERT(!list_link_active(&ab
->b_arc_node
));
1109 list_insert_head(&state
->arcs_list
[ab
->b_type
], ab
);
1110 ASSERT(ab
->b_datacnt
> 0);
1111 atomic_add_64(size
, ab
->b_size
* ab
->b_datacnt
);
1112 mutex_exit(&state
->arcs_mtx
);
1118 * Move the supplied buffer to the indicated state. The mutex
1119 * for the buffer must be held by the caller.
1122 arc_change_state(arc_state_t
*new_state
, arc_buf_hdr_t
*ab
, kmutex_t
*hash_lock
)
1124 arc_state_t
*old_state
= ab
->b_state
;
1125 int64_t refcnt
= refcount_count(&ab
->b_refcnt
);
1126 uint64_t from_delta
, to_delta
;
1128 ASSERT(MUTEX_HELD(hash_lock
));
1129 ASSERT(new_state
!= old_state
);
1130 ASSERT(refcnt
== 0 || ab
->b_datacnt
> 0);
1131 ASSERT(ab
->b_datacnt
== 0 || !GHOST_STATE(new_state
));
1132 ASSERT(ab
->b_datacnt
<= 1 || old_state
!= arc_anon
);
1134 from_delta
= to_delta
= ab
->b_datacnt
* ab
->b_size
;
1137 * If this buffer is evictable, transfer it from the
1138 * old state list to the new state list.
1141 if (old_state
!= arc_anon
) {
1142 int use_mutex
= !MUTEX_HELD(&old_state
->arcs_mtx
);
1143 uint64_t *size
= &old_state
->arcs_lsize
[ab
->b_type
];
1146 mutex_enter(&old_state
->arcs_mtx
);
1148 ASSERT(list_link_active(&ab
->b_arc_node
));
1149 list_remove(&old_state
->arcs_list
[ab
->b_type
], ab
);
1152 * If prefetching out of the ghost cache,
1153 * we will have a non-zero datacnt.
1155 if (GHOST_STATE(old_state
) && ab
->b_datacnt
== 0) {
1156 /* ghost elements have a ghost size */
1157 ASSERT(ab
->b_buf
== NULL
);
1158 from_delta
= ab
->b_size
;
1160 ASSERT3U(*size
, >=, from_delta
);
1161 atomic_add_64(size
, -from_delta
);
1164 mutex_exit(&old_state
->arcs_mtx
);
1166 if (new_state
!= arc_anon
) {
1167 int use_mutex
= !MUTEX_HELD(&new_state
->arcs_mtx
);
1168 uint64_t *size
= &new_state
->arcs_lsize
[ab
->b_type
];
1171 mutex_enter(&new_state
->arcs_mtx
);
1173 list_insert_head(&new_state
->arcs_list
[ab
->b_type
], ab
);
1175 /* ghost elements have a ghost size */
1176 if (GHOST_STATE(new_state
)) {
1177 ASSERT(ab
->b_datacnt
== 0);
1178 ASSERT(ab
->b_buf
== NULL
);
1179 to_delta
= ab
->b_size
;
1181 atomic_add_64(size
, to_delta
);
1184 mutex_exit(&new_state
->arcs_mtx
);
1188 ASSERT(!BUF_EMPTY(ab
));
1189 if (new_state
== arc_anon
&& HDR_IN_HASH_TABLE(ab
))
1190 buf_hash_remove(ab
);
1192 /* adjust state sizes */
1194 atomic_add_64(&new_state
->arcs_size
, to_delta
);
1196 ASSERT3U(old_state
->arcs_size
, >=, from_delta
);
1197 atomic_add_64(&old_state
->arcs_size
, -from_delta
);
1199 ab
->b_state
= new_state
;
1201 /* adjust l2arc hdr stats */
1202 if (new_state
== arc_l2c_only
)
1203 l2arc_hdr_stat_add();
1204 else if (old_state
== arc_l2c_only
)
1205 l2arc_hdr_stat_remove();
1209 arc_space_consume(uint64_t space
, arc_space_type_t type
)
1211 ASSERT(type
>= 0 && type
< ARC_SPACE_NUMTYPES
);
1216 case ARC_SPACE_DATA
:
1217 ARCSTAT_INCR(arcstat_data_size
, space
);
1219 case ARC_SPACE_OTHER
:
1220 ARCSTAT_INCR(arcstat_other_size
, space
);
1222 case ARC_SPACE_HDRS
:
1223 ARCSTAT_INCR(arcstat_hdr_size
, space
);
1225 case ARC_SPACE_L2HDRS
:
1226 ARCSTAT_INCR(arcstat_l2_hdr_size
, space
);
1230 atomic_add_64(&arc_meta_used
, space
);
1231 atomic_add_64(&arc_size
, space
);
1235 arc_space_return(uint64_t space
, arc_space_type_t type
)
1237 ASSERT(type
>= 0 && type
< ARC_SPACE_NUMTYPES
);
1242 case ARC_SPACE_DATA
:
1243 ARCSTAT_INCR(arcstat_data_size
, -space
);
1245 case ARC_SPACE_OTHER
:
1246 ARCSTAT_INCR(arcstat_other_size
, -space
);
1248 case ARC_SPACE_HDRS
:
1249 ARCSTAT_INCR(arcstat_hdr_size
, -space
);
1251 case ARC_SPACE_L2HDRS
:
1252 ARCSTAT_INCR(arcstat_l2_hdr_size
, -space
);
1256 ASSERT(arc_meta_used
>= space
);
1257 if (arc_meta_max
< arc_meta_used
)
1258 arc_meta_max
= arc_meta_used
;
1259 atomic_add_64(&arc_meta_used
, -space
);
1260 ASSERT(arc_size
>= space
);
1261 atomic_add_64(&arc_size
, -space
);
1265 arc_data_buf_alloc(uint64_t size
)
1267 if (arc_evict_needed(ARC_BUFC_DATA
))
1268 cv_signal(&arc_reclaim_thr_cv
);
1269 atomic_add_64(&arc_size
, size
);
1270 return (zio_data_buf_alloc(size
));
1274 arc_data_buf_free(void *buf
, uint64_t size
)
1276 zio_data_buf_free(buf
, size
);
1277 ASSERT(arc_size
>= size
);
1278 atomic_add_64(&arc_size
, -size
);
1282 arc_buf_alloc(spa_t
*spa
, int size
, void *tag
, arc_buf_contents_t type
)
1287 ASSERT3U(size
, >, 0);
1288 hdr
= kmem_cache_alloc(hdr_cache
, KM_PUSHPAGE
);
1289 ASSERT(BUF_EMPTY(hdr
));
1292 hdr
->b_spa
= spa_load_guid(spa
);
1293 hdr
->b_state
= arc_anon
;
1294 hdr
->b_arc_access
= 0;
1295 buf
= kmem_cache_alloc(buf_cache
, KM_PUSHPAGE
);
1298 buf
->b_efunc
= NULL
;
1299 buf
->b_private
= NULL
;
1302 arc_get_data_buf(buf
);
1305 ASSERT(refcount_is_zero(&hdr
->b_refcnt
));
1306 (void) refcount_add(&hdr
->b_refcnt
, tag
);
1311 static char *arc_onloan_tag
= "onloan";
1314 * Loan out an anonymous arc buffer. Loaned buffers are not counted as in
1315 * flight data by arc_tempreserve_space() until they are "returned". Loaned
1316 * buffers must be returned to the arc before they can be used by the DMU or
1320 arc_loan_buf(spa_t
*spa
, int size
)
1324 buf
= arc_buf_alloc(spa
, size
, arc_onloan_tag
, ARC_BUFC_DATA
);
1326 atomic_add_64(&arc_loaned_bytes
, size
);
1331 * Return a loaned arc buffer to the arc.
1334 arc_return_buf(arc_buf_t
*buf
, void *tag
)
1336 arc_buf_hdr_t
*hdr
= buf
->b_hdr
;
1338 ASSERT(buf
->b_data
!= NULL
);
1339 (void) refcount_add(&hdr
->b_refcnt
, tag
);
1340 (void) refcount_remove(&hdr
->b_refcnt
, arc_onloan_tag
);
1342 atomic_add_64(&arc_loaned_bytes
, -hdr
->b_size
);
1345 /* Detach an arc_buf from a dbuf (tag) */
1347 arc_loan_inuse_buf(arc_buf_t
*buf
, void *tag
)
1351 ASSERT(buf
->b_data
!= NULL
);
1353 (void) refcount_add(&hdr
->b_refcnt
, arc_onloan_tag
);
1354 (void) refcount_remove(&hdr
->b_refcnt
, tag
);
1355 buf
->b_efunc
= NULL
;
1356 buf
->b_private
= NULL
;
1358 atomic_add_64(&arc_loaned_bytes
, hdr
->b_size
);
1362 arc_buf_clone(arc_buf_t
*from
)
1365 arc_buf_hdr_t
*hdr
= from
->b_hdr
;
1366 uint64_t size
= hdr
->b_size
;
1368 ASSERT(hdr
->b_state
!= arc_anon
);
1370 buf
= kmem_cache_alloc(buf_cache
, KM_PUSHPAGE
);
1373 buf
->b_efunc
= NULL
;
1374 buf
->b_private
= NULL
;
1375 buf
->b_next
= hdr
->b_buf
;
1377 arc_get_data_buf(buf
);
1378 bcopy(from
->b_data
, buf
->b_data
, size
);
1381 * This buffer already exists in the arc so create a duplicate
1382 * copy for the caller. If the buffer is associated with user data
1383 * then track the size and number of duplicates. These stats will be
1384 * updated as duplicate buffers are created and destroyed.
1386 if (hdr
->b_type
== ARC_BUFC_DATA
) {
1387 ARCSTAT_BUMP(arcstat_duplicate_buffers
);
1388 ARCSTAT_INCR(arcstat_duplicate_buffers_size
, size
);
1390 hdr
->b_datacnt
+= 1;
1395 arc_buf_add_ref(arc_buf_t
*buf
, void* tag
)
1398 kmutex_t
*hash_lock
;
1401 * Check to see if this buffer is evicted. Callers
1402 * must verify b_data != NULL to know if the add_ref
1405 mutex_enter(&buf
->b_evict_lock
);
1406 if (buf
->b_data
== NULL
) {
1407 mutex_exit(&buf
->b_evict_lock
);
1410 hash_lock
= HDR_LOCK(buf
->b_hdr
);
1411 mutex_enter(hash_lock
);
1413 ASSERT3P(hash_lock
, ==, HDR_LOCK(hdr
));
1414 mutex_exit(&buf
->b_evict_lock
);
1416 ASSERT(hdr
->b_state
== arc_mru
|| hdr
->b_state
== arc_mfu
);
1417 add_reference(hdr
, hash_lock
, tag
);
1418 DTRACE_PROBE1(arc__hit
, arc_buf_hdr_t
*, hdr
);
1419 arc_access(hdr
, hash_lock
);
1420 mutex_exit(hash_lock
);
1421 ARCSTAT_BUMP(arcstat_hits
);
1422 ARCSTAT_CONDSTAT(!(hdr
->b_flags
& ARC_PREFETCH
),
1423 demand
, prefetch
, hdr
->b_type
!= ARC_BUFC_METADATA
,
1424 data
, metadata
, hits
);
1428 * Free the arc data buffer. If it is an l2arc write in progress,
1429 * the buffer is placed on l2arc_free_on_write to be freed later.
1432 arc_buf_data_free(arc_buf_hdr_t
*hdr
, void (*free_func
)(void *, size_t),
1433 void *data
, size_t size
)
1435 if (HDR_L2_WRITING(hdr
)) {
1436 l2arc_data_free_t
*df
;
1437 df
= kmem_alloc(sizeof (l2arc_data_free_t
), KM_PUSHPAGE
);
1438 df
->l2df_data
= data
;
1439 df
->l2df_size
= size
;
1440 df
->l2df_func
= free_func
;
1441 mutex_enter(&l2arc_free_on_write_mtx
);
1442 list_insert_head(l2arc_free_on_write
, df
);
1443 mutex_exit(&l2arc_free_on_write_mtx
);
1444 ARCSTAT_BUMP(arcstat_l2_free_on_write
);
1446 free_func(data
, size
);
1451 arc_buf_destroy(arc_buf_t
*buf
, boolean_t recycle
, boolean_t all
)
1455 /* free up data associated with the buf */
1457 arc_state_t
*state
= buf
->b_hdr
->b_state
;
1458 uint64_t size
= buf
->b_hdr
->b_size
;
1459 arc_buf_contents_t type
= buf
->b_hdr
->b_type
;
1461 arc_cksum_verify(buf
);
1464 if (type
== ARC_BUFC_METADATA
) {
1465 arc_buf_data_free(buf
->b_hdr
, zio_buf_free
,
1467 arc_space_return(size
, ARC_SPACE_DATA
);
1469 ASSERT(type
== ARC_BUFC_DATA
);
1470 arc_buf_data_free(buf
->b_hdr
,
1471 zio_data_buf_free
, buf
->b_data
, size
);
1472 ARCSTAT_INCR(arcstat_data_size
, -size
);
1473 atomic_add_64(&arc_size
, -size
);
1476 if (list_link_active(&buf
->b_hdr
->b_arc_node
)) {
1477 uint64_t *cnt
= &state
->arcs_lsize
[type
];
1479 ASSERT(refcount_is_zero(&buf
->b_hdr
->b_refcnt
));
1480 ASSERT(state
!= arc_anon
);
1482 ASSERT3U(*cnt
, >=, size
);
1483 atomic_add_64(cnt
, -size
);
1485 ASSERT3U(state
->arcs_size
, >=, size
);
1486 atomic_add_64(&state
->arcs_size
, -size
);
1490 * If we're destroying a duplicate buffer make sure
1491 * that the appropriate statistics are updated.
1493 if (buf
->b_hdr
->b_datacnt
> 1 &&
1494 buf
->b_hdr
->b_type
== ARC_BUFC_DATA
) {
1495 ARCSTAT_BUMPDOWN(arcstat_duplicate_buffers
);
1496 ARCSTAT_INCR(arcstat_duplicate_buffers_size
, -size
);
1498 ASSERT(buf
->b_hdr
->b_datacnt
> 0);
1499 buf
->b_hdr
->b_datacnt
-= 1;
1502 /* only remove the buf if requested */
1506 /* remove the buf from the hdr list */
1507 for (bufp
= &buf
->b_hdr
->b_buf
; *bufp
!= buf
; bufp
= &(*bufp
)->b_next
)
1509 *bufp
= buf
->b_next
;
1512 ASSERT(buf
->b_efunc
== NULL
);
1514 /* clean up the buf */
1516 kmem_cache_free(buf_cache
, buf
);
1520 arc_hdr_destroy(arc_buf_hdr_t
*hdr
)
1522 l2arc_buf_hdr_t
*l2hdr
= hdr
->b_l2hdr
;
1524 ASSERT(refcount_is_zero(&hdr
->b_refcnt
));
1525 ASSERT3P(hdr
->b_state
, ==, arc_anon
);
1526 ASSERT(!HDR_IO_IN_PROGRESS(hdr
));
1528 if (l2hdr
!= NULL
) {
1529 boolean_t buflist_held
= MUTEX_HELD(&l2arc_buflist_mtx
);
1531 * To prevent arc_free() and l2arc_evict() from
1532 * attempting to free the same buffer at the same time,
1533 * a FREE_IN_PROGRESS flag is given to arc_free() to
1534 * give it priority. l2arc_evict() can't destroy this
1535 * header while we are waiting on l2arc_buflist_mtx.
1537 * The hdr may be removed from l2ad_buflist before we
1538 * grab l2arc_buflist_mtx, so b_l2hdr is rechecked.
1540 if (!buflist_held
) {
1541 mutex_enter(&l2arc_buflist_mtx
);
1542 l2hdr
= hdr
->b_l2hdr
;
1545 if (l2hdr
!= NULL
) {
1546 list_remove(l2hdr
->b_dev
->l2ad_buflist
, hdr
);
1547 ARCSTAT_INCR(arcstat_l2_size
, -hdr
->b_size
);
1548 kmem_free(l2hdr
, sizeof (l2arc_buf_hdr_t
));
1549 if (hdr
->b_state
== arc_l2c_only
)
1550 l2arc_hdr_stat_remove();
1551 hdr
->b_l2hdr
= NULL
;
1555 mutex_exit(&l2arc_buflist_mtx
);
1558 if (!BUF_EMPTY(hdr
)) {
1559 ASSERT(!HDR_IN_HASH_TABLE(hdr
));
1560 buf_discard_identity(hdr
);
1562 while (hdr
->b_buf
) {
1563 arc_buf_t
*buf
= hdr
->b_buf
;
1566 mutex_enter(&arc_eviction_mtx
);
1567 mutex_enter(&buf
->b_evict_lock
);
1568 ASSERT(buf
->b_hdr
!= NULL
);
1569 arc_buf_destroy(hdr
->b_buf
, FALSE
, FALSE
);
1570 hdr
->b_buf
= buf
->b_next
;
1571 buf
->b_hdr
= &arc_eviction_hdr
;
1572 buf
->b_next
= arc_eviction_list
;
1573 arc_eviction_list
= buf
;
1574 mutex_exit(&buf
->b_evict_lock
);
1575 mutex_exit(&arc_eviction_mtx
);
1577 arc_buf_destroy(hdr
->b_buf
, FALSE
, TRUE
);
1580 if (hdr
->b_freeze_cksum
!= NULL
) {
1581 kmem_free(hdr
->b_freeze_cksum
, sizeof (zio_cksum_t
));
1582 hdr
->b_freeze_cksum
= NULL
;
1584 if (hdr
->b_thawed
) {
1585 kmem_free(hdr
->b_thawed
, 1);
1586 hdr
->b_thawed
= NULL
;
1589 ASSERT(!list_link_active(&hdr
->b_arc_node
));
1590 ASSERT3P(hdr
->b_hash_next
, ==, NULL
);
1591 ASSERT3P(hdr
->b_acb
, ==, NULL
);
1592 kmem_cache_free(hdr_cache
, hdr
);
1596 arc_buf_free(arc_buf_t
*buf
, void *tag
)
1598 arc_buf_hdr_t
*hdr
= buf
->b_hdr
;
1599 int hashed
= hdr
->b_state
!= arc_anon
;
1601 ASSERT(buf
->b_efunc
== NULL
);
1602 ASSERT(buf
->b_data
!= NULL
);
1605 kmutex_t
*hash_lock
= HDR_LOCK(hdr
);
1607 mutex_enter(hash_lock
);
1609 ASSERT3P(hash_lock
, ==, HDR_LOCK(hdr
));
1611 (void) remove_reference(hdr
, hash_lock
, tag
);
1612 if (hdr
->b_datacnt
> 1) {
1613 arc_buf_destroy(buf
, FALSE
, TRUE
);
1615 ASSERT(buf
== hdr
->b_buf
);
1616 ASSERT(buf
->b_efunc
== NULL
);
1617 hdr
->b_flags
|= ARC_BUF_AVAILABLE
;
1619 mutex_exit(hash_lock
);
1620 } else if (HDR_IO_IN_PROGRESS(hdr
)) {
1623 * We are in the middle of an async write. Don't destroy
1624 * this buffer unless the write completes before we finish
1625 * decrementing the reference count.
1627 mutex_enter(&arc_eviction_mtx
);
1628 (void) remove_reference(hdr
, NULL
, tag
);
1629 ASSERT(refcount_is_zero(&hdr
->b_refcnt
));
1630 destroy_hdr
= !HDR_IO_IN_PROGRESS(hdr
);
1631 mutex_exit(&arc_eviction_mtx
);
1633 arc_hdr_destroy(hdr
);
1635 if (remove_reference(hdr
, NULL
, tag
) > 0)
1636 arc_buf_destroy(buf
, FALSE
, TRUE
);
1638 arc_hdr_destroy(hdr
);
1643 arc_buf_remove_ref(arc_buf_t
*buf
, void* tag
)
1645 arc_buf_hdr_t
*hdr
= buf
->b_hdr
;
1646 kmutex_t
*hash_lock
= HDR_LOCK(hdr
);
1647 int no_callback
= (buf
->b_efunc
== NULL
);
1649 if (hdr
->b_state
== arc_anon
) {
1650 ASSERT(hdr
->b_datacnt
== 1);
1651 arc_buf_free(buf
, tag
);
1652 return (no_callback
);
1655 mutex_enter(hash_lock
);
1657 ASSERT3P(hash_lock
, ==, HDR_LOCK(hdr
));
1658 ASSERT(hdr
->b_state
!= arc_anon
);
1659 ASSERT(buf
->b_data
!= NULL
);
1661 (void) remove_reference(hdr
, hash_lock
, tag
);
1662 if (hdr
->b_datacnt
> 1) {
1664 arc_buf_destroy(buf
, FALSE
, TRUE
);
1665 } else if (no_callback
) {
1666 ASSERT(hdr
->b_buf
== buf
&& buf
->b_next
== NULL
);
1667 ASSERT(buf
->b_efunc
== NULL
);
1668 hdr
->b_flags
|= ARC_BUF_AVAILABLE
;
1670 ASSERT(no_callback
|| hdr
->b_datacnt
> 1 ||
1671 refcount_is_zero(&hdr
->b_refcnt
));
1672 mutex_exit(hash_lock
);
1673 return (no_callback
);
1677 arc_buf_size(arc_buf_t
*buf
)
1679 return (buf
->b_hdr
->b_size
);
1683 * Called from the DMU to determine if the current buffer should be
1684 * evicted. In order to ensure proper locking, the eviction must be initiated
1685 * from the DMU. Return true if the buffer is associated with user data and
1686 * duplicate buffers still exist.
1689 arc_buf_eviction_needed(arc_buf_t
*buf
)
1692 boolean_t evict_needed
= B_FALSE
;
1694 if (zfs_disable_dup_eviction
)
1697 mutex_enter(&buf
->b_evict_lock
);
1701 * We are in arc_do_user_evicts(); let that function
1702 * perform the eviction.
1704 ASSERT(buf
->b_data
== NULL
);
1705 mutex_exit(&buf
->b_evict_lock
);
1707 } else if (buf
->b_data
== NULL
) {
1709 * We have already been added to the arc eviction list;
1710 * recommend eviction.
1712 ASSERT3P(hdr
, ==, &arc_eviction_hdr
);
1713 mutex_exit(&buf
->b_evict_lock
);
1717 if (hdr
->b_datacnt
> 1 && hdr
->b_type
== ARC_BUFC_DATA
)
1718 evict_needed
= B_TRUE
;
1720 mutex_exit(&buf
->b_evict_lock
);
1721 return (evict_needed
);
1725 * Evict buffers from list until we've removed the specified number of
1726 * bytes. Move the removed buffers to the appropriate evict state.
1727 * If the recycle flag is set, then attempt to "recycle" a buffer:
1728 * - look for a buffer to evict that is `bytes' long.
1729 * - return the data block from this buffer rather than freeing it.
1730 * This flag is used by callers that are trying to make space for a
1731 * new buffer in a full arc cache.
1733 * This function makes a "best effort". It skips over any buffers
1734 * it can't get a hash_lock on, and so may not catch all candidates.
1735 * It may also return without evicting as much space as requested.
1738 arc_evict(arc_state_t
*state
, uint64_t spa
, int64_t bytes
, boolean_t recycle
,
1739 arc_buf_contents_t type
)
1741 arc_state_t
*evicted_state
;
1742 uint64_t bytes_evicted
= 0, skipped
= 0, missed
= 0;
1743 arc_buf_hdr_t
*ab
, *ab_prev
= NULL
;
1744 list_t
*list
= &state
->arcs_list
[type
];
1745 kmutex_t
*hash_lock
;
1746 boolean_t have_lock
;
1747 void *stolen
= NULL
;
1749 ASSERT(state
== arc_mru
|| state
== arc_mfu
);
1751 evicted_state
= (state
== arc_mru
) ? arc_mru_ghost
: arc_mfu_ghost
;
1753 mutex_enter(&state
->arcs_mtx
);
1754 mutex_enter(&evicted_state
->arcs_mtx
);
1756 for (ab
= list_tail(list
); ab
; ab
= ab_prev
) {
1757 ab_prev
= list_prev(list
, ab
);
1758 /* prefetch buffers have a minimum lifespan */
1759 if (HDR_IO_IN_PROGRESS(ab
) ||
1760 (spa
&& ab
->b_spa
!= spa
) ||
1761 (ab
->b_flags
& (ARC_PREFETCH
|ARC_INDIRECT
) &&
1762 ddi_get_lbolt() - ab
->b_arc_access
<
1763 arc_min_prefetch_lifespan
)) {
1767 /* "lookahead" for better eviction candidate */
1768 if (recycle
&& ab
->b_size
!= bytes
&&
1769 ab_prev
&& ab_prev
->b_size
== bytes
)
1771 hash_lock
= HDR_LOCK(ab
);
1772 have_lock
= MUTEX_HELD(hash_lock
);
1773 if (have_lock
|| mutex_tryenter(hash_lock
)) {
1774 ASSERT3U(refcount_count(&ab
->b_refcnt
), ==, 0);
1775 ASSERT(ab
->b_datacnt
> 0);
1777 arc_buf_t
*buf
= ab
->b_buf
;
1778 if (!mutex_tryenter(&buf
->b_evict_lock
)) {
1783 bytes_evicted
+= ab
->b_size
;
1784 if (recycle
&& ab
->b_type
== type
&&
1785 ab
->b_size
== bytes
&&
1786 !HDR_L2_WRITING(ab
)) {
1787 stolen
= buf
->b_data
;
1792 mutex_enter(&arc_eviction_mtx
);
1793 arc_buf_destroy(buf
,
1794 buf
->b_data
== stolen
, FALSE
);
1795 ab
->b_buf
= buf
->b_next
;
1796 buf
->b_hdr
= &arc_eviction_hdr
;
1797 buf
->b_next
= arc_eviction_list
;
1798 arc_eviction_list
= buf
;
1799 mutex_exit(&arc_eviction_mtx
);
1800 mutex_exit(&buf
->b_evict_lock
);
1802 mutex_exit(&buf
->b_evict_lock
);
1803 arc_buf_destroy(buf
,
1804 buf
->b_data
== stolen
, TRUE
);
1809 ARCSTAT_INCR(arcstat_evict_l2_cached
,
1812 if (l2arc_write_eligible(ab
->b_spa
, ab
)) {
1813 ARCSTAT_INCR(arcstat_evict_l2_eligible
,
1817 arcstat_evict_l2_ineligible
,
1822 if (ab
->b_datacnt
== 0) {
1823 arc_change_state(evicted_state
, ab
, hash_lock
);
1824 ASSERT(HDR_IN_HASH_TABLE(ab
));
1825 ab
->b_flags
|= ARC_IN_HASH_TABLE
;
1826 ab
->b_flags
&= ~ARC_BUF_AVAILABLE
;
1827 DTRACE_PROBE1(arc__evict
, arc_buf_hdr_t
*, ab
);
1830 mutex_exit(hash_lock
);
1831 if (bytes
>= 0 && bytes_evicted
>= bytes
)
1838 mutex_exit(&evicted_state
->arcs_mtx
);
1839 mutex_exit(&state
->arcs_mtx
);
1841 if (bytes_evicted
< bytes
)
1842 dprintf("only evicted %lld bytes from %x\n",
1843 (longlong_t
)bytes_evicted
, state
);
1846 ARCSTAT_INCR(arcstat_evict_skip
, skipped
);
1849 ARCSTAT_INCR(arcstat_mutex_miss
, missed
);
1852 * We have just evicted some date into the ghost state, make
1853 * sure we also adjust the ghost state size if necessary.
1856 arc_mru_ghost
->arcs_size
+ arc_mfu_ghost
->arcs_size
> arc_c
) {
1857 int64_t mru_over
= arc_anon
->arcs_size
+ arc_mru
->arcs_size
+
1858 arc_mru_ghost
->arcs_size
- arc_c
;
1860 if (mru_over
> 0 && arc_mru_ghost
->arcs_lsize
[type
] > 0) {
1862 MIN(arc_mru_ghost
->arcs_lsize
[type
], mru_over
);
1863 arc_evict_ghost(arc_mru_ghost
, 0, todelete
);
1864 } else if (arc_mfu_ghost
->arcs_lsize
[type
] > 0) {
1865 int64_t todelete
= MIN(arc_mfu_ghost
->arcs_lsize
[type
],
1866 arc_mru_ghost
->arcs_size
+
1867 arc_mfu_ghost
->arcs_size
- arc_c
);
1868 arc_evict_ghost(arc_mfu_ghost
, 0, todelete
);
1876 * Remove buffers from list until we've removed the specified number of
1877 * bytes. Destroy the buffers that are removed.
1880 arc_evict_ghost(arc_state_t
*state
, uint64_t spa
, int64_t bytes
)
1882 arc_buf_hdr_t
*ab
, *ab_prev
;
1883 arc_buf_hdr_t marker
;
1884 list_t
*list
= &state
->arcs_list
[ARC_BUFC_DATA
];
1885 kmutex_t
*hash_lock
;
1886 uint64_t bytes_deleted
= 0;
1887 uint64_t bufs_skipped
= 0;
1889 ASSERT(GHOST_STATE(state
));
1890 bzero(&marker
, sizeof(marker
));
1892 mutex_enter(&state
->arcs_mtx
);
1893 for (ab
= list_tail(list
); ab
; ab
= ab_prev
) {
1894 ab_prev
= list_prev(list
, ab
);
1895 if (spa
&& ab
->b_spa
!= spa
)
1898 /* ignore markers */
1902 hash_lock
= HDR_LOCK(ab
);
1903 /* caller may be trying to modify this buffer, skip it */
1904 if (MUTEX_HELD(hash_lock
))
1906 if (mutex_tryenter(hash_lock
)) {
1907 ASSERT(!HDR_IO_IN_PROGRESS(ab
));
1908 ASSERT(ab
->b_buf
== NULL
);
1909 ARCSTAT_BUMP(arcstat_deleted
);
1910 bytes_deleted
+= ab
->b_size
;
1912 if (ab
->b_l2hdr
!= NULL
) {
1914 * This buffer is cached on the 2nd Level ARC;
1915 * don't destroy the header.
1917 arc_change_state(arc_l2c_only
, ab
, hash_lock
);
1918 mutex_exit(hash_lock
);
1920 arc_change_state(arc_anon
, ab
, hash_lock
);
1921 mutex_exit(hash_lock
);
1922 arc_hdr_destroy(ab
);
1925 DTRACE_PROBE1(arc__delete
, arc_buf_hdr_t
*, ab
);
1926 if (bytes
>= 0 && bytes_deleted
>= bytes
)
1928 } else if (bytes
< 0) {
1930 * Insert a list marker and then wait for the
1931 * hash lock to become available. Once its
1932 * available, restart from where we left off.
1934 list_insert_after(list
, ab
, &marker
);
1935 mutex_exit(&state
->arcs_mtx
);
1936 mutex_enter(hash_lock
);
1937 mutex_exit(hash_lock
);
1938 mutex_enter(&state
->arcs_mtx
);
1939 ab_prev
= list_prev(list
, &marker
);
1940 list_remove(list
, &marker
);
1944 mutex_exit(&state
->arcs_mtx
);
1946 if (list
== &state
->arcs_list
[ARC_BUFC_DATA
] &&
1947 (bytes
< 0 || bytes_deleted
< bytes
)) {
1948 list
= &state
->arcs_list
[ARC_BUFC_METADATA
];
1953 ARCSTAT_INCR(arcstat_mutex_miss
, bufs_skipped
);
1957 if (bytes_deleted
< bytes
)
1958 dprintf("only deleted %lld bytes from %p\n",
1959 (longlong_t
)bytes_deleted
, state
);
1965 int64_t adjustment
, delta
;
1971 adjustment
= MIN((int64_t)(arc_size
- arc_c
),
1972 (int64_t)(arc_anon
->arcs_size
+ arc_mru
->arcs_size
+ arc_meta_used
-
1975 if (adjustment
> 0 && arc_mru
->arcs_lsize
[ARC_BUFC_DATA
] > 0) {
1976 delta
= MIN(arc_mru
->arcs_lsize
[ARC_BUFC_DATA
], adjustment
);
1977 (void) arc_evict(arc_mru
, 0, delta
, FALSE
, ARC_BUFC_DATA
);
1978 adjustment
-= delta
;
1981 if (adjustment
> 0 && arc_mru
->arcs_lsize
[ARC_BUFC_METADATA
] > 0) {
1982 delta
= MIN(arc_mru
->arcs_lsize
[ARC_BUFC_METADATA
], adjustment
);
1983 (void) arc_evict(arc_mru
, 0, delta
, FALSE
,
1991 adjustment
= arc_size
- arc_c
;
1993 if (adjustment
> 0 && arc_mfu
->arcs_lsize
[ARC_BUFC_DATA
] > 0) {
1994 delta
= MIN(adjustment
, arc_mfu
->arcs_lsize
[ARC_BUFC_DATA
]);
1995 (void) arc_evict(arc_mfu
, 0, delta
, FALSE
, ARC_BUFC_DATA
);
1996 adjustment
-= delta
;
1999 if (adjustment
> 0 && arc_mfu
->arcs_lsize
[ARC_BUFC_METADATA
] > 0) {
2000 int64_t delta
= MIN(adjustment
,
2001 arc_mfu
->arcs_lsize
[ARC_BUFC_METADATA
]);
2002 (void) arc_evict(arc_mfu
, 0, delta
, FALSE
,
2007 * Adjust ghost lists
2010 adjustment
= arc_mru
->arcs_size
+ arc_mru_ghost
->arcs_size
- arc_c
;
2012 if (adjustment
> 0 && arc_mru_ghost
->arcs_size
> 0) {
2013 delta
= MIN(arc_mru_ghost
->arcs_size
, adjustment
);
2014 arc_evict_ghost(arc_mru_ghost
, 0, delta
);
2018 arc_mru_ghost
->arcs_size
+ arc_mfu_ghost
->arcs_size
- arc_c
;
2020 if (adjustment
> 0 && arc_mfu_ghost
->arcs_size
> 0) {
2021 delta
= MIN(arc_mfu_ghost
->arcs_size
, adjustment
);
2022 arc_evict_ghost(arc_mfu_ghost
, 0, delta
);
2027 * Request that arc user drop references so that N bytes can be released
2028 * from the cache. This provides a mechanism to ensure the arc can honor
2029 * the arc_meta_limit and reclaim buffers which are pinned in the cache
2030 * by higher layers. (i.e. the zpl)
2033 arc_do_user_prune(int64_t adjustment
)
2035 arc_prune_func_t
*func
;
2037 arc_prune_t
*cp
, *np
;
2039 mutex_enter(&arc_prune_mtx
);
2041 cp
= list_head(&arc_prune_list
);
2042 while (cp
!= NULL
) {
2044 private = cp
->p_private
;
2045 np
= list_next(&arc_prune_list
, cp
);
2046 refcount_add(&cp
->p_refcnt
, func
);
2047 mutex_exit(&arc_prune_mtx
);
2050 func(adjustment
, private);
2052 mutex_enter(&arc_prune_mtx
);
2054 /* User removed prune callback concurrently with execution */
2055 if (refcount_remove(&cp
->p_refcnt
, func
) == 0) {
2056 ASSERT(!list_link_active(&cp
->p_node
));
2057 refcount_destroy(&cp
->p_refcnt
);
2058 kmem_free(cp
, sizeof (*cp
));
2064 ARCSTAT_BUMP(arcstat_prune
);
2065 mutex_exit(&arc_prune_mtx
);
2069 arc_do_user_evicts(void)
2071 mutex_enter(&arc_eviction_mtx
);
2072 while (arc_eviction_list
!= NULL
) {
2073 arc_buf_t
*buf
= arc_eviction_list
;
2074 arc_eviction_list
= buf
->b_next
;
2075 mutex_enter(&buf
->b_evict_lock
);
2077 mutex_exit(&buf
->b_evict_lock
);
2078 mutex_exit(&arc_eviction_mtx
);
2080 if (buf
->b_efunc
!= NULL
)
2081 VERIFY(buf
->b_efunc(buf
) == 0);
2083 buf
->b_efunc
= NULL
;
2084 buf
->b_private
= NULL
;
2085 kmem_cache_free(buf_cache
, buf
);
2086 mutex_enter(&arc_eviction_mtx
);
2088 mutex_exit(&arc_eviction_mtx
);
2092 * Evict only meta data objects from the cache leaving the data objects.
2093 * This is only used to enforce the tunable arc_meta_limit, if we are
2094 * unable to evict enough buffers notify the user via the prune callback.
2097 arc_adjust_meta(int64_t adjustment
, boolean_t may_prune
)
2101 if (adjustment
> 0 && arc_mru
->arcs_lsize
[ARC_BUFC_METADATA
] > 0) {
2102 delta
= MIN(arc_mru
->arcs_lsize
[ARC_BUFC_METADATA
], adjustment
);
2103 arc_evict(arc_mru
, 0, delta
, FALSE
, ARC_BUFC_METADATA
);
2104 adjustment
-= delta
;
2107 if (adjustment
> 0 && arc_mfu
->arcs_lsize
[ARC_BUFC_METADATA
] > 0) {
2108 delta
= MIN(arc_mfu
->arcs_lsize
[ARC_BUFC_METADATA
], adjustment
);
2109 arc_evict(arc_mfu
, 0, delta
, FALSE
, ARC_BUFC_METADATA
);
2110 adjustment
-= delta
;
2113 if (may_prune
&& (adjustment
> 0) && (arc_meta_used
> arc_meta_limit
))
2114 arc_do_user_prune(arc_meta_prune
);
2118 * Flush all *evictable* data from the cache for the given spa.
2119 * NOTE: this will not touch "active" (i.e. referenced) data.
2122 arc_flush(spa_t
*spa
)
2127 guid
= spa_load_guid(spa
);
2129 while (list_head(&arc_mru
->arcs_list
[ARC_BUFC_DATA
])) {
2130 (void) arc_evict(arc_mru
, guid
, -1, FALSE
, ARC_BUFC_DATA
);
2134 while (list_head(&arc_mru
->arcs_list
[ARC_BUFC_METADATA
])) {
2135 (void) arc_evict(arc_mru
, guid
, -1, FALSE
, ARC_BUFC_METADATA
);
2139 while (list_head(&arc_mfu
->arcs_list
[ARC_BUFC_DATA
])) {
2140 (void) arc_evict(arc_mfu
, guid
, -1, FALSE
, ARC_BUFC_DATA
);
2144 while (list_head(&arc_mfu
->arcs_list
[ARC_BUFC_METADATA
])) {
2145 (void) arc_evict(arc_mfu
, guid
, -1, FALSE
, ARC_BUFC_METADATA
);
2150 arc_evict_ghost(arc_mru_ghost
, guid
, -1);
2151 arc_evict_ghost(arc_mfu_ghost
, guid
, -1);
2153 mutex_enter(&arc_reclaim_thr_lock
);
2154 arc_do_user_evicts();
2155 mutex_exit(&arc_reclaim_thr_lock
);
2156 ASSERT(spa
|| arc_eviction_list
== NULL
);
2160 arc_shrink(uint64_t bytes
)
2162 if (arc_c
> arc_c_min
) {
2165 to_free
= bytes
? bytes
: arc_c
>> arc_shrink_shift
;
2167 if (arc_c
> arc_c_min
+ to_free
)
2168 atomic_add_64(&arc_c
, -to_free
);
2172 atomic_add_64(&arc_p
, -(arc_p
>> arc_shrink_shift
));
2173 if (arc_c
> arc_size
)
2174 arc_c
= MAX(arc_size
, arc_c_min
);
2176 arc_p
= (arc_c
>> 1);
2177 ASSERT(arc_c
>= arc_c_min
);
2178 ASSERT((int64_t)arc_p
>= 0);
2181 if (arc_size
> arc_c
)
2186 arc_kmem_reap_now(arc_reclaim_strategy_t strat
, uint64_t bytes
)
2189 kmem_cache_t
*prev_cache
= NULL
;
2190 kmem_cache_t
*prev_data_cache
= NULL
;
2191 extern kmem_cache_t
*zio_buf_cache
[];
2192 extern kmem_cache_t
*zio_data_buf_cache
[];
2195 * An aggressive reclamation will shrink the cache size as well as
2196 * reap free buffers from the arc kmem caches.
2198 if (strat
== ARC_RECLAIM_AGGR
)
2201 for (i
= 0; i
< SPA_MAXBLOCKSIZE
>> SPA_MINBLOCKSHIFT
; i
++) {
2202 if (zio_buf_cache
[i
] != prev_cache
) {
2203 prev_cache
= zio_buf_cache
[i
];
2204 kmem_cache_reap_now(zio_buf_cache
[i
]);
2206 if (zio_data_buf_cache
[i
] != prev_data_cache
) {
2207 prev_data_cache
= zio_data_buf_cache
[i
];
2208 kmem_cache_reap_now(zio_data_buf_cache
[i
]);
2212 kmem_cache_reap_now(buf_cache
);
2213 kmem_cache_reap_now(hdr_cache
);
2217 * Unlike other ZFS implementations this thread is only responsible for
2218 * adapting the target ARC size on Linux. The responsibility for memory
2219 * reclamation has been entirely delegated to the arc_shrinker_func()
2220 * which is registered with the VM. To reflect this change in behavior
2221 * the arc_reclaim thread has been renamed to arc_adapt.
2224 arc_adapt_thread(void)
2229 CALLB_CPR_INIT(&cpr
, &arc_reclaim_thr_lock
, callb_generic_cpr
, FTAG
);
2231 mutex_enter(&arc_reclaim_thr_lock
);
2232 while (arc_thread_exit
== 0) {
2234 arc_reclaim_strategy_t last_reclaim
= ARC_RECLAIM_CONS
;
2236 if (spa_get_random(100) == 0) {
2239 if (last_reclaim
== ARC_RECLAIM_CONS
) {
2240 last_reclaim
= ARC_RECLAIM_AGGR
;
2242 last_reclaim
= ARC_RECLAIM_CONS
;
2246 last_reclaim
= ARC_RECLAIM_AGGR
;
2250 /* reset the growth delay for every reclaim */
2251 arc_grow_time
= ddi_get_lbolt()+(arc_grow_retry
* hz
);
2253 arc_kmem_reap_now(last_reclaim
, 0);
2256 #endif /* !_KERNEL */
2258 /* No recent memory pressure allow the ARC to grow. */
2259 if (arc_no_grow
&& ddi_get_lbolt() >= arc_grow_time
)
2260 arc_no_grow
= FALSE
;
2263 * Keep meta data usage within limits, arc_shrink() is not
2264 * used to avoid collapsing the arc_c value when only the
2265 * arc_meta_limit is being exceeded.
2267 prune
= (int64_t)arc_meta_used
- (int64_t)arc_meta_limit
;
2269 arc_adjust_meta(prune
, B_TRUE
);
2273 if (arc_eviction_list
!= NULL
)
2274 arc_do_user_evicts();
2276 /* block until needed, or one second, whichever is shorter */
2277 CALLB_CPR_SAFE_BEGIN(&cpr
);
2278 (void) cv_timedwait_interruptible(&arc_reclaim_thr_cv
,
2279 &arc_reclaim_thr_lock
, (ddi_get_lbolt() + hz
));
2280 CALLB_CPR_SAFE_END(&cpr
, &arc_reclaim_thr_lock
);
2283 arc_thread_exit
= 0;
2284 cv_broadcast(&arc_reclaim_thr_cv
);
2285 CALLB_CPR_EXIT(&cpr
); /* drops arc_reclaim_thr_lock */
2291 * Determine the amount of memory eligible for eviction contained in the
2292 * ARC. All clean data reported by the ghost lists can always be safely
2293 * evicted. Due to arc_c_min, the same does not hold for all clean data
2294 * contained by the regular mru and mfu lists.
2296 * In the case of the regular mru and mfu lists, we need to report as
2297 * much clean data as possible, such that evicting that same reported
2298 * data will not bring arc_size below arc_c_min. Thus, in certain
2299 * circumstances, the total amount of clean data in the mru and mfu
2300 * lists might not actually be evictable.
2302 * The following two distinct cases are accounted for:
2304 * 1. The sum of the amount of dirty data contained by both the mru and
2305 * mfu lists, plus the ARC's other accounting (e.g. the anon list),
2306 * is greater than or equal to arc_c_min.
2307 * (i.e. amount of dirty data >= arc_c_min)
2309 * This is the easy case; all clean data contained by the mru and mfu
2310 * lists is evictable. Evicting all clean data can only drop arc_size
2311 * to the amount of dirty data, which is greater than arc_c_min.
2313 * 2. The sum of the amount of dirty data contained by both the mru and
2314 * mfu lists, plus the ARC's other accounting (e.g. the anon list),
2315 * is less than arc_c_min.
2316 * (i.e. arc_c_min > amount of dirty data)
2318 * 2.1. arc_size is greater than or equal arc_c_min.
2319 * (i.e. arc_size >= arc_c_min > amount of dirty data)
2321 * In this case, not all clean data from the regular mru and mfu
2322 * lists is actually evictable; we must leave enough clean data
2323 * to keep arc_size above arc_c_min. Thus, the maximum amount of
2324 * evictable data from the two lists combined, is exactly the
2325 * difference between arc_size and arc_c_min.
2327 * 2.2. arc_size is less than arc_c_min
2328 * (i.e. arc_c_min > arc_size > amount of dirty data)
2330 * In this case, none of the data contained in the mru and mfu
2331 * lists is evictable, even if it's clean. Since arc_size is
2332 * already below arc_c_min, evicting any more would only
2333 * increase this negative difference.
2336 arc_evictable_memory(void) {
2337 uint64_t arc_clean
=
2338 arc_mru
->arcs_lsize
[ARC_BUFC_DATA
] +
2339 arc_mru
->arcs_lsize
[ARC_BUFC_METADATA
] +
2340 arc_mfu
->arcs_lsize
[ARC_BUFC_DATA
] +
2341 arc_mfu
->arcs_lsize
[ARC_BUFC_METADATA
];
2342 uint64_t ghost_clean
=
2343 arc_mru_ghost
->arcs_lsize
[ARC_BUFC_DATA
] +
2344 arc_mru_ghost
->arcs_lsize
[ARC_BUFC_METADATA
] +
2345 arc_mfu_ghost
->arcs_lsize
[ARC_BUFC_DATA
] +
2346 arc_mfu_ghost
->arcs_lsize
[ARC_BUFC_METADATA
];
2347 uint64_t arc_dirty
= MAX((int64_t)arc_size
- (int64_t)arc_clean
, 0);
2349 if (arc_dirty
>= arc_c_min
)
2350 return (ghost_clean
+ arc_clean
);
2352 return (ghost_clean
+ MAX((int64_t)arc_size
- (int64_t)arc_c_min
, 0));
2356 __arc_shrinker_func(struct shrinker
*shrink
, struct shrink_control
*sc
)
2360 /* The arc is considered warm once reclaim has occurred */
2361 if (unlikely(arc_warm
== B_FALSE
))
2364 /* Return the potential number of reclaimable pages */
2365 pages
= btop(arc_evictable_memory());
2366 if (sc
->nr_to_scan
== 0)
2369 /* Not allowed to perform filesystem reclaim */
2370 if (!(sc
->gfp_mask
& __GFP_FS
))
2373 /* Reclaim in progress */
2374 if (mutex_tryenter(&arc_reclaim_thr_lock
) == 0)
2378 * Evict the requested number of pages by shrinking arc_c the
2379 * requested amount. If there is nothing left to evict just
2380 * reap whatever we can from the various arc slabs.
2383 arc_kmem_reap_now(ARC_RECLAIM_AGGR
, ptob(sc
->nr_to_scan
));
2384 pages
= btop(arc_evictable_memory());
2386 arc_kmem_reap_now(ARC_RECLAIM_CONS
, ptob(sc
->nr_to_scan
));
2391 * When direct reclaim is observed it usually indicates a rapid
2392 * increase in memory pressure. This occurs because the kswapd
2393 * threads were unable to asynchronously keep enough free memory
2394 * available. In this case set arc_no_grow to briefly pause arc
2395 * growth to avoid compounding the memory pressure.
2397 if (current_is_kswapd()) {
2398 ARCSTAT_BUMP(arcstat_memory_indirect_count
);
2400 arc_no_grow
= B_TRUE
;
2401 arc_grow_time
= ddi_get_lbolt() + (arc_grow_retry
* hz
);
2402 ARCSTAT_BUMP(arcstat_memory_direct_count
);
2405 mutex_exit(&arc_reclaim_thr_lock
);
2409 SPL_SHRINKER_CALLBACK_WRAPPER(arc_shrinker_func
);
2411 SPL_SHRINKER_DECLARE(arc_shrinker
, arc_shrinker_func
, DEFAULT_SEEKS
);
2412 #endif /* _KERNEL */
2415 * Adapt arc info given the number of bytes we are trying to add and
2416 * the state that we are comming from. This function is only called
2417 * when we are adding new content to the cache.
2420 arc_adapt(int bytes
, arc_state_t
*state
)
2423 uint64_t arc_p_min
= (arc_c
>> arc_p_min_shift
);
2425 if (state
== arc_l2c_only
)
2430 * Adapt the target size of the MRU list:
2431 * - if we just hit in the MRU ghost list, then increase
2432 * the target size of the MRU list.
2433 * - if we just hit in the MFU ghost list, then increase
2434 * the target size of the MFU list by decreasing the
2435 * target size of the MRU list.
2437 if (state
== arc_mru_ghost
) {
2438 mult
= ((arc_mru_ghost
->arcs_size
>= arc_mfu_ghost
->arcs_size
) ?
2439 1 : (arc_mfu_ghost
->arcs_size
/arc_mru_ghost
->arcs_size
));
2440 mult
= MIN(mult
, 10); /* avoid wild arc_p adjustment */
2442 arc_p
= MIN(arc_c
- arc_p_min
, arc_p
+ bytes
* mult
);
2443 } else if (state
== arc_mfu_ghost
) {
2446 mult
= ((arc_mfu_ghost
->arcs_size
>= arc_mru_ghost
->arcs_size
) ?
2447 1 : (arc_mru_ghost
->arcs_size
/arc_mfu_ghost
->arcs_size
));
2448 mult
= MIN(mult
, 10);
2450 delta
= MIN(bytes
* mult
, arc_p
);
2451 arc_p
= MAX(arc_p_min
, arc_p
- delta
);
2453 ASSERT((int64_t)arc_p
>= 0);
2458 if (arc_c
>= arc_c_max
)
2462 * If we're within (2 * maxblocksize) bytes of the target
2463 * cache size, increment the target cache size
2465 if (arc_size
> arc_c
- (2ULL << SPA_MAXBLOCKSHIFT
)) {
2466 atomic_add_64(&arc_c
, (int64_t)bytes
);
2467 if (arc_c
> arc_c_max
)
2469 else if (state
== arc_anon
)
2470 atomic_add_64(&arc_p
, (int64_t)bytes
);
2474 ASSERT((int64_t)arc_p
>= 0);
2478 * Check if the cache has reached its limits and eviction is required
2482 arc_evict_needed(arc_buf_contents_t type
)
2484 if (type
== ARC_BUFC_METADATA
&& arc_meta_used
>= arc_meta_limit
)
2490 return (arc_size
> arc_c
);
2494 * The buffer, supplied as the first argument, needs a data block.
2495 * So, if we are at cache max, determine which cache should be victimized.
2496 * We have the following cases:
2498 * 1. Insert for MRU, p > sizeof(arc_anon + arc_mru) ->
2499 * In this situation if we're out of space, but the resident size of the MFU is
2500 * under the limit, victimize the MFU cache to satisfy this insertion request.
2502 * 2. Insert for MRU, p <= sizeof(arc_anon + arc_mru) ->
2503 * Here, we've used up all of the available space for the MRU, so we need to
2504 * evict from our own cache instead. Evict from the set of resident MRU
2507 * 3. Insert for MFU (c - p) > sizeof(arc_mfu) ->
2508 * c minus p represents the MFU space in the cache, since p is the size of the
2509 * cache that is dedicated to the MRU. In this situation there's still space on
2510 * the MFU side, so the MRU side needs to be victimized.
2512 * 4. Insert for MFU (c - p) < sizeof(arc_mfu) ->
2513 * MFU's resident set is consuming more space than it has been allotted. In
2514 * this situation, we must victimize our own cache, the MFU, for this insertion.
2517 arc_get_data_buf(arc_buf_t
*buf
)
2519 arc_state_t
*state
= buf
->b_hdr
->b_state
;
2520 uint64_t size
= buf
->b_hdr
->b_size
;
2521 arc_buf_contents_t type
= buf
->b_hdr
->b_type
;
2523 arc_adapt(size
, state
);
2526 * We have not yet reached cache maximum size,
2527 * just allocate a new buffer.
2529 if (!arc_evict_needed(type
)) {
2530 if (type
== ARC_BUFC_METADATA
) {
2531 buf
->b_data
= zio_buf_alloc(size
);
2532 arc_space_consume(size
, ARC_SPACE_DATA
);
2534 ASSERT(type
== ARC_BUFC_DATA
);
2535 buf
->b_data
= zio_data_buf_alloc(size
);
2536 ARCSTAT_INCR(arcstat_data_size
, size
);
2537 atomic_add_64(&arc_size
, size
);
2543 * If we are prefetching from the mfu ghost list, this buffer
2544 * will end up on the mru list; so steal space from there.
2546 if (state
== arc_mfu_ghost
)
2547 state
= buf
->b_hdr
->b_flags
& ARC_PREFETCH
? arc_mru
: arc_mfu
;
2548 else if (state
== arc_mru_ghost
)
2551 if (state
== arc_mru
|| state
== arc_anon
) {
2552 uint64_t mru_used
= arc_anon
->arcs_size
+ arc_mru
->arcs_size
;
2553 state
= (arc_mfu
->arcs_lsize
[type
] >= size
&&
2554 arc_p
> mru_used
) ? arc_mfu
: arc_mru
;
2557 uint64_t mfu_space
= arc_c
- arc_p
;
2558 state
= (arc_mru
->arcs_lsize
[type
] >= size
&&
2559 mfu_space
> arc_mfu
->arcs_size
) ? arc_mru
: arc_mfu
;
2562 if ((buf
->b_data
= arc_evict(state
, 0, size
, TRUE
, type
)) == NULL
) {
2563 if (type
== ARC_BUFC_METADATA
) {
2564 buf
->b_data
= zio_buf_alloc(size
);
2565 arc_space_consume(size
, ARC_SPACE_DATA
);
2568 * If we are unable to recycle an existing meta buffer
2569 * signal the reclaim thread. It will notify users
2570 * via the prune callback to drop references. The
2571 * prune callback in run in the context of the reclaim
2572 * thread to avoid deadlocking on the hash_lock.
2574 cv_signal(&arc_reclaim_thr_cv
);
2576 ASSERT(type
== ARC_BUFC_DATA
);
2577 buf
->b_data
= zio_data_buf_alloc(size
);
2578 ARCSTAT_INCR(arcstat_data_size
, size
);
2579 atomic_add_64(&arc_size
, size
);
2582 ARCSTAT_BUMP(arcstat_recycle_miss
);
2584 ASSERT(buf
->b_data
!= NULL
);
2587 * Update the state size. Note that ghost states have a
2588 * "ghost size" and so don't need to be updated.
2590 if (!GHOST_STATE(buf
->b_hdr
->b_state
)) {
2591 arc_buf_hdr_t
*hdr
= buf
->b_hdr
;
2593 atomic_add_64(&hdr
->b_state
->arcs_size
, size
);
2594 if (list_link_active(&hdr
->b_arc_node
)) {
2595 ASSERT(refcount_is_zero(&hdr
->b_refcnt
));
2596 atomic_add_64(&hdr
->b_state
->arcs_lsize
[type
], size
);
2599 * If we are growing the cache, and we are adding anonymous
2600 * data, and we have outgrown arc_p, update arc_p
2602 if (arc_size
< arc_c
&& hdr
->b_state
== arc_anon
&&
2603 arc_anon
->arcs_size
+ arc_mru
->arcs_size
> arc_p
)
2604 arc_p
= MIN(arc_c
, arc_p
+ size
);
2609 * This routine is called whenever a buffer is accessed.
2610 * NOTE: the hash lock is dropped in this function.
2613 arc_access(arc_buf_hdr_t
*buf
, kmutex_t
*hash_lock
)
2617 ASSERT(MUTEX_HELD(hash_lock
));
2619 if (buf
->b_state
== arc_anon
) {
2621 * This buffer is not in the cache, and does not
2622 * appear in our "ghost" list. Add the new buffer
2626 ASSERT(buf
->b_arc_access
== 0);
2627 buf
->b_arc_access
= ddi_get_lbolt();
2628 DTRACE_PROBE1(new_state__mru
, arc_buf_hdr_t
*, buf
);
2629 arc_change_state(arc_mru
, buf
, hash_lock
);
2631 } else if (buf
->b_state
== arc_mru
) {
2632 now
= ddi_get_lbolt();
2635 * If this buffer is here because of a prefetch, then either:
2636 * - clear the flag if this is a "referencing" read
2637 * (any subsequent access will bump this into the MFU state).
2639 * - move the buffer to the head of the list if this is
2640 * another prefetch (to make it less likely to be evicted).
2642 if ((buf
->b_flags
& ARC_PREFETCH
) != 0) {
2643 if (refcount_count(&buf
->b_refcnt
) == 0) {
2644 ASSERT(list_link_active(&buf
->b_arc_node
));
2646 buf
->b_flags
&= ~ARC_PREFETCH
;
2647 ARCSTAT_BUMP(arcstat_mru_hits
);
2649 buf
->b_arc_access
= now
;
2654 * This buffer has been "accessed" only once so far,
2655 * but it is still in the cache. Move it to the MFU
2658 if (now
> buf
->b_arc_access
+ ARC_MINTIME
) {
2660 * More than 125ms have passed since we
2661 * instantiated this buffer. Move it to the
2662 * most frequently used state.
2664 buf
->b_arc_access
= now
;
2665 DTRACE_PROBE1(new_state__mfu
, arc_buf_hdr_t
*, buf
);
2666 arc_change_state(arc_mfu
, buf
, hash_lock
);
2668 ARCSTAT_BUMP(arcstat_mru_hits
);
2669 } else if (buf
->b_state
== arc_mru_ghost
) {
2670 arc_state_t
*new_state
;
2672 * This buffer has been "accessed" recently, but
2673 * was evicted from the cache. Move it to the
2677 if (buf
->b_flags
& ARC_PREFETCH
) {
2678 new_state
= arc_mru
;
2679 if (refcount_count(&buf
->b_refcnt
) > 0)
2680 buf
->b_flags
&= ~ARC_PREFETCH
;
2681 DTRACE_PROBE1(new_state__mru
, arc_buf_hdr_t
*, buf
);
2683 new_state
= arc_mfu
;
2684 DTRACE_PROBE1(new_state__mfu
, arc_buf_hdr_t
*, buf
);
2687 buf
->b_arc_access
= ddi_get_lbolt();
2688 arc_change_state(new_state
, buf
, hash_lock
);
2690 ARCSTAT_BUMP(arcstat_mru_ghost_hits
);
2691 } else if (buf
->b_state
== arc_mfu
) {
2693 * This buffer has been accessed more than once and is
2694 * still in the cache. Keep it in the MFU state.
2696 * NOTE: an add_reference() that occurred when we did
2697 * the arc_read() will have kicked this off the list.
2698 * If it was a prefetch, we will explicitly move it to
2699 * the head of the list now.
2701 if ((buf
->b_flags
& ARC_PREFETCH
) != 0) {
2702 ASSERT(refcount_count(&buf
->b_refcnt
) == 0);
2703 ASSERT(list_link_active(&buf
->b_arc_node
));
2705 ARCSTAT_BUMP(arcstat_mfu_hits
);
2706 buf
->b_arc_access
= ddi_get_lbolt();
2707 } else if (buf
->b_state
== arc_mfu_ghost
) {
2708 arc_state_t
*new_state
= arc_mfu
;
2710 * This buffer has been accessed more than once but has
2711 * been evicted from the cache. Move it back to the
2715 if (buf
->b_flags
& ARC_PREFETCH
) {
2717 * This is a prefetch access...
2718 * move this block back to the MRU state.
2720 ASSERT3U(refcount_count(&buf
->b_refcnt
), ==, 0);
2721 new_state
= arc_mru
;
2724 buf
->b_arc_access
= ddi_get_lbolt();
2725 DTRACE_PROBE1(new_state__mfu
, arc_buf_hdr_t
*, buf
);
2726 arc_change_state(new_state
, buf
, hash_lock
);
2728 ARCSTAT_BUMP(arcstat_mfu_ghost_hits
);
2729 } else if (buf
->b_state
== arc_l2c_only
) {
2731 * This buffer is on the 2nd Level ARC.
2734 buf
->b_arc_access
= ddi_get_lbolt();
2735 DTRACE_PROBE1(new_state__mfu
, arc_buf_hdr_t
*, buf
);
2736 arc_change_state(arc_mfu
, buf
, hash_lock
);
2738 ASSERT(!"invalid arc state");
2742 /* a generic arc_done_func_t which you can use */
2745 arc_bcopy_func(zio_t
*zio
, arc_buf_t
*buf
, void *arg
)
2747 if (zio
== NULL
|| zio
->io_error
== 0)
2748 bcopy(buf
->b_data
, arg
, buf
->b_hdr
->b_size
);
2749 VERIFY(arc_buf_remove_ref(buf
, arg
) == 1);
2752 /* a generic arc_done_func_t */
2754 arc_getbuf_func(zio_t
*zio
, arc_buf_t
*buf
, void *arg
)
2756 arc_buf_t
**bufp
= arg
;
2757 if (zio
&& zio
->io_error
) {
2758 VERIFY(arc_buf_remove_ref(buf
, arg
) == 1);
2762 ASSERT(buf
->b_data
);
2767 arc_read_done(zio_t
*zio
)
2769 arc_buf_hdr_t
*hdr
, *found
;
2771 arc_buf_t
*abuf
; /* buffer we're assigning to callback */
2772 kmutex_t
*hash_lock
;
2773 arc_callback_t
*callback_list
, *acb
;
2774 int freeable
= FALSE
;
2776 buf
= zio
->io_private
;
2780 * The hdr was inserted into hash-table and removed from lists
2781 * prior to starting I/O. We should find this header, since
2782 * it's in the hash table, and it should be legit since it's
2783 * not possible to evict it during the I/O. The only possible
2784 * reason for it not to be found is if we were freed during the
2787 found
= buf_hash_find(hdr
->b_spa
, &hdr
->b_dva
, hdr
->b_birth
,
2790 ASSERT((found
== NULL
&& HDR_FREED_IN_READ(hdr
) && hash_lock
== NULL
) ||
2791 (found
== hdr
&& DVA_EQUAL(&hdr
->b_dva
, BP_IDENTITY(zio
->io_bp
))) ||
2792 (found
== hdr
&& HDR_L2_READING(hdr
)));
2794 hdr
->b_flags
&= ~ARC_L2_EVICTED
;
2795 if (l2arc_noprefetch
&& (hdr
->b_flags
& ARC_PREFETCH
))
2796 hdr
->b_flags
&= ~ARC_L2CACHE
;
2798 /* byteswap if necessary */
2799 callback_list
= hdr
->b_acb
;
2800 ASSERT(callback_list
!= NULL
);
2801 if (BP_SHOULD_BYTESWAP(zio
->io_bp
) && zio
->io_error
== 0) {
2802 dmu_object_byteswap_t bswap
=
2803 DMU_OT_BYTESWAP(BP_GET_TYPE(zio
->io_bp
));
2804 arc_byteswap_func_t
*func
= BP_GET_LEVEL(zio
->io_bp
) > 0 ?
2805 byteswap_uint64_array
:
2806 dmu_ot_byteswap
[bswap
].ob_func
;
2807 func(buf
->b_data
, hdr
->b_size
);
2810 arc_cksum_compute(buf
, B_FALSE
);
2812 if (hash_lock
&& zio
->io_error
== 0 && hdr
->b_state
== arc_anon
) {
2814 * Only call arc_access on anonymous buffers. This is because
2815 * if we've issued an I/O for an evicted buffer, we've already
2816 * called arc_access (to prevent any simultaneous readers from
2817 * getting confused).
2819 arc_access(hdr
, hash_lock
);
2822 /* create copies of the data buffer for the callers */
2824 for (acb
= callback_list
; acb
; acb
= acb
->acb_next
) {
2825 if (acb
->acb_done
) {
2827 ARCSTAT_BUMP(arcstat_duplicate_reads
);
2828 abuf
= arc_buf_clone(buf
);
2830 acb
->acb_buf
= abuf
;
2835 hdr
->b_flags
&= ~ARC_IO_IN_PROGRESS
;
2836 ASSERT(!HDR_BUF_AVAILABLE(hdr
));
2838 ASSERT(buf
->b_efunc
== NULL
);
2839 ASSERT(hdr
->b_datacnt
== 1);
2840 hdr
->b_flags
|= ARC_BUF_AVAILABLE
;
2843 ASSERT(refcount_is_zero(&hdr
->b_refcnt
) || callback_list
!= NULL
);
2845 if (zio
->io_error
!= 0) {
2846 hdr
->b_flags
|= ARC_IO_ERROR
;
2847 if (hdr
->b_state
!= arc_anon
)
2848 arc_change_state(arc_anon
, hdr
, hash_lock
);
2849 if (HDR_IN_HASH_TABLE(hdr
))
2850 buf_hash_remove(hdr
);
2851 freeable
= refcount_is_zero(&hdr
->b_refcnt
);
2855 * Broadcast before we drop the hash_lock to avoid the possibility
2856 * that the hdr (and hence the cv) might be freed before we get to
2857 * the cv_broadcast().
2859 cv_broadcast(&hdr
->b_cv
);
2862 mutex_exit(hash_lock
);
2865 * This block was freed while we waited for the read to
2866 * complete. It has been removed from the hash table and
2867 * moved to the anonymous state (so that it won't show up
2870 ASSERT3P(hdr
->b_state
, ==, arc_anon
);
2871 freeable
= refcount_is_zero(&hdr
->b_refcnt
);
2874 /* execute each callback and free its structure */
2875 while ((acb
= callback_list
) != NULL
) {
2877 acb
->acb_done(zio
, acb
->acb_buf
, acb
->acb_private
);
2879 if (acb
->acb_zio_dummy
!= NULL
) {
2880 acb
->acb_zio_dummy
->io_error
= zio
->io_error
;
2881 zio_nowait(acb
->acb_zio_dummy
);
2884 callback_list
= acb
->acb_next
;
2885 kmem_free(acb
, sizeof (arc_callback_t
));
2889 arc_hdr_destroy(hdr
);
2893 * "Read" the block at the specified DVA (in bp) via the
2894 * cache. If the block is found in the cache, invoke the provided
2895 * callback immediately and return. Note that the `zio' parameter
2896 * in the callback will be NULL in this case, since no IO was
2897 * required. If the block is not in the cache pass the read request
2898 * on to the spa with a substitute callback function, so that the
2899 * requested block will be added to the cache.
2901 * If a read request arrives for a block that has a read in-progress,
2902 * either wait for the in-progress read to complete (and return the
2903 * results); or, if this is a read with a "done" func, add a record
2904 * to the read to invoke the "done" func when the read completes,
2905 * and return; or just return.
2907 * arc_read_done() will invoke all the requested "done" functions
2908 * for readers of this block.
2910 * Normal callers should use arc_read and pass the arc buffer and offset
2911 * for the bp. But if you know you don't need locking, you can use
2915 arc_read(zio_t
*pio
, spa_t
*spa
, const blkptr_t
*bp
, arc_buf_t
*pbuf
,
2916 arc_done_func_t
*done
, void *private, int priority
, int zio_flags
,
2917 uint32_t *arc_flags
, const zbookmark_t
*zb
)
2923 * XXX This happens from traverse callback funcs, for
2924 * the objset_phys_t block.
2926 return (arc_read_nolock(pio
, spa
, bp
, done
, private, priority
,
2927 zio_flags
, arc_flags
, zb
));
2930 ASSERT(!refcount_is_zero(&pbuf
->b_hdr
->b_refcnt
));
2931 ASSERT3U((char *)bp
- (char *)pbuf
->b_data
, <, pbuf
->b_hdr
->b_size
);
2932 rw_enter(&pbuf
->b_data_lock
, RW_READER
);
2934 err
= arc_read_nolock(pio
, spa
, bp
, done
, private, priority
,
2935 zio_flags
, arc_flags
, zb
);
2936 rw_exit(&pbuf
->b_data_lock
);
2942 arc_read_nolock(zio_t
*pio
, spa_t
*spa
, const blkptr_t
*bp
,
2943 arc_done_func_t
*done
, void *private, int priority
, int zio_flags
,
2944 uint32_t *arc_flags
, const zbookmark_t
*zb
)
2947 arc_buf_t
*buf
= NULL
;
2948 kmutex_t
*hash_lock
;
2950 uint64_t guid
= spa_load_guid(spa
);
2953 hdr
= buf_hash_find(guid
, BP_IDENTITY(bp
), BP_PHYSICAL_BIRTH(bp
),
2955 if (hdr
&& hdr
->b_datacnt
> 0) {
2957 *arc_flags
|= ARC_CACHED
;
2959 if (HDR_IO_IN_PROGRESS(hdr
)) {
2961 if (*arc_flags
& ARC_WAIT
) {
2962 cv_wait(&hdr
->b_cv
, hash_lock
);
2963 mutex_exit(hash_lock
);
2966 ASSERT(*arc_flags
& ARC_NOWAIT
);
2969 arc_callback_t
*acb
= NULL
;
2971 acb
= kmem_zalloc(sizeof (arc_callback_t
),
2973 acb
->acb_done
= done
;
2974 acb
->acb_private
= private;
2976 acb
->acb_zio_dummy
= zio_null(pio
,
2977 spa
, NULL
, NULL
, NULL
, zio_flags
);
2979 ASSERT(acb
->acb_done
!= NULL
);
2980 acb
->acb_next
= hdr
->b_acb
;
2982 add_reference(hdr
, hash_lock
, private);
2983 mutex_exit(hash_lock
);
2986 mutex_exit(hash_lock
);
2990 ASSERT(hdr
->b_state
== arc_mru
|| hdr
->b_state
== arc_mfu
);
2993 add_reference(hdr
, hash_lock
, private);
2995 * If this block is already in use, create a new
2996 * copy of the data so that we will be guaranteed
2997 * that arc_release() will always succeed.
3001 ASSERT(buf
->b_data
);
3002 if (HDR_BUF_AVAILABLE(hdr
)) {
3003 ASSERT(buf
->b_efunc
== NULL
);
3004 hdr
->b_flags
&= ~ARC_BUF_AVAILABLE
;
3006 buf
= arc_buf_clone(buf
);
3009 } else if (*arc_flags
& ARC_PREFETCH
&&
3010 refcount_count(&hdr
->b_refcnt
) == 0) {
3011 hdr
->b_flags
|= ARC_PREFETCH
;
3013 DTRACE_PROBE1(arc__hit
, arc_buf_hdr_t
*, hdr
);
3014 arc_access(hdr
, hash_lock
);
3015 if (*arc_flags
& ARC_L2CACHE
)
3016 hdr
->b_flags
|= ARC_L2CACHE
;
3017 mutex_exit(hash_lock
);
3018 ARCSTAT_BUMP(arcstat_hits
);
3019 ARCSTAT_CONDSTAT(!(hdr
->b_flags
& ARC_PREFETCH
),
3020 demand
, prefetch
, hdr
->b_type
!= ARC_BUFC_METADATA
,
3021 data
, metadata
, hits
);
3024 done(NULL
, buf
, private);
3026 uint64_t size
= BP_GET_LSIZE(bp
);
3027 arc_callback_t
*acb
;
3030 boolean_t devw
= B_FALSE
;
3033 /* this block is not in the cache */
3034 arc_buf_hdr_t
*exists
;
3035 arc_buf_contents_t type
= BP_GET_BUFC_TYPE(bp
);
3036 buf
= arc_buf_alloc(spa
, size
, private, type
);
3038 hdr
->b_dva
= *BP_IDENTITY(bp
);
3039 hdr
->b_birth
= BP_PHYSICAL_BIRTH(bp
);
3040 hdr
->b_cksum0
= bp
->blk_cksum
.zc_word
[0];
3041 exists
= buf_hash_insert(hdr
, &hash_lock
);
3043 /* somebody beat us to the hash insert */
3044 mutex_exit(hash_lock
);
3045 buf_discard_identity(hdr
);
3046 (void) arc_buf_remove_ref(buf
, private);
3047 goto top
; /* restart the IO request */
3049 /* if this is a prefetch, we don't have a reference */
3050 if (*arc_flags
& ARC_PREFETCH
) {
3051 (void) remove_reference(hdr
, hash_lock
,
3053 hdr
->b_flags
|= ARC_PREFETCH
;
3055 if (*arc_flags
& ARC_L2CACHE
)
3056 hdr
->b_flags
|= ARC_L2CACHE
;
3057 if (BP_GET_LEVEL(bp
) > 0)
3058 hdr
->b_flags
|= ARC_INDIRECT
;
3060 /* this block is in the ghost cache */
3061 ASSERT(GHOST_STATE(hdr
->b_state
));
3062 ASSERT(!HDR_IO_IN_PROGRESS(hdr
));
3063 ASSERT3U(refcount_count(&hdr
->b_refcnt
), ==, 0);
3064 ASSERT(hdr
->b_buf
== NULL
);
3066 /* if this is a prefetch, we don't have a reference */
3067 if (*arc_flags
& ARC_PREFETCH
)
3068 hdr
->b_flags
|= ARC_PREFETCH
;
3070 add_reference(hdr
, hash_lock
, private);
3071 if (*arc_flags
& ARC_L2CACHE
)
3072 hdr
->b_flags
|= ARC_L2CACHE
;
3073 buf
= kmem_cache_alloc(buf_cache
, KM_PUSHPAGE
);
3076 buf
->b_efunc
= NULL
;
3077 buf
->b_private
= NULL
;
3080 ASSERT(hdr
->b_datacnt
== 0);
3082 arc_get_data_buf(buf
);
3083 arc_access(hdr
, hash_lock
);
3086 ASSERT(!GHOST_STATE(hdr
->b_state
));
3088 acb
= kmem_zalloc(sizeof (arc_callback_t
), KM_PUSHPAGE
);
3089 acb
->acb_done
= done
;
3090 acb
->acb_private
= private;
3092 ASSERT(hdr
->b_acb
== NULL
);
3094 hdr
->b_flags
|= ARC_IO_IN_PROGRESS
;
3096 if (HDR_L2CACHE(hdr
) && hdr
->b_l2hdr
!= NULL
&&
3097 (vd
= hdr
->b_l2hdr
->b_dev
->l2ad_vdev
) != NULL
) {
3098 devw
= hdr
->b_l2hdr
->b_dev
->l2ad_writing
;
3099 addr
= hdr
->b_l2hdr
->b_daddr
;
3101 * Lock out device removal.
3103 if (vdev_is_dead(vd
) ||
3104 !spa_config_tryenter(spa
, SCL_L2ARC
, vd
, RW_READER
))
3108 mutex_exit(hash_lock
);
3110 ASSERT3U(hdr
->b_size
, ==, size
);
3111 DTRACE_PROBE4(arc__miss
, arc_buf_hdr_t
*, hdr
, blkptr_t
*, bp
,
3112 uint64_t, size
, zbookmark_t
*, zb
);
3113 ARCSTAT_BUMP(arcstat_misses
);
3114 ARCSTAT_CONDSTAT(!(hdr
->b_flags
& ARC_PREFETCH
),
3115 demand
, prefetch
, hdr
->b_type
!= ARC_BUFC_METADATA
,
3116 data
, metadata
, misses
);
3118 if (vd
!= NULL
&& l2arc_ndev
!= 0 && !(l2arc_norw
&& devw
)) {
3120 * Read from the L2ARC if the following are true:
3121 * 1. The L2ARC vdev was previously cached.
3122 * 2. This buffer still has L2ARC metadata.
3123 * 3. This buffer isn't currently writing to the L2ARC.
3124 * 4. The L2ARC entry wasn't evicted, which may
3125 * also have invalidated the vdev.
3126 * 5. This isn't prefetch and l2arc_noprefetch is set.
3128 if (hdr
->b_l2hdr
!= NULL
&&
3129 !HDR_L2_WRITING(hdr
) && !HDR_L2_EVICTED(hdr
) &&
3130 !(l2arc_noprefetch
&& HDR_PREFETCH(hdr
))) {
3131 l2arc_read_callback_t
*cb
;
3133 DTRACE_PROBE1(l2arc__hit
, arc_buf_hdr_t
*, hdr
);
3134 ARCSTAT_BUMP(arcstat_l2_hits
);
3136 cb
= kmem_zalloc(sizeof (l2arc_read_callback_t
),
3138 cb
->l2rcb_buf
= buf
;
3139 cb
->l2rcb_spa
= spa
;
3142 cb
->l2rcb_flags
= zio_flags
;
3145 * l2arc read. The SCL_L2ARC lock will be
3146 * released by l2arc_read_done().
3148 rzio
= zio_read_phys(pio
, vd
, addr
, size
,
3149 buf
->b_data
, ZIO_CHECKSUM_OFF
,
3150 l2arc_read_done
, cb
, priority
, zio_flags
|
3151 ZIO_FLAG_DONT_CACHE
| ZIO_FLAG_CANFAIL
|
3152 ZIO_FLAG_DONT_PROPAGATE
|
3153 ZIO_FLAG_DONT_RETRY
, B_FALSE
);
3154 DTRACE_PROBE2(l2arc__read
, vdev_t
*, vd
,
3156 ARCSTAT_INCR(arcstat_l2_read_bytes
, size
);
3158 if (*arc_flags
& ARC_NOWAIT
) {
3163 ASSERT(*arc_flags
& ARC_WAIT
);
3164 if (zio_wait(rzio
) == 0)
3167 /* l2arc read error; goto zio_read() */
3169 DTRACE_PROBE1(l2arc__miss
,
3170 arc_buf_hdr_t
*, hdr
);
3171 ARCSTAT_BUMP(arcstat_l2_misses
);
3172 if (HDR_L2_WRITING(hdr
))
3173 ARCSTAT_BUMP(arcstat_l2_rw_clash
);
3174 spa_config_exit(spa
, SCL_L2ARC
, vd
);
3178 spa_config_exit(spa
, SCL_L2ARC
, vd
);
3179 if (l2arc_ndev
!= 0) {
3180 DTRACE_PROBE1(l2arc__miss
,
3181 arc_buf_hdr_t
*, hdr
);
3182 ARCSTAT_BUMP(arcstat_l2_misses
);
3186 rzio
= zio_read(pio
, spa
, bp
, buf
->b_data
, size
,
3187 arc_read_done
, buf
, priority
, zio_flags
, zb
);
3189 if (*arc_flags
& ARC_WAIT
)
3190 return (zio_wait(rzio
));
3192 ASSERT(*arc_flags
& ARC_NOWAIT
);
3199 arc_add_prune_callback(arc_prune_func_t
*func
, void *private)
3203 p
= kmem_alloc(sizeof(*p
), KM_SLEEP
);
3205 p
->p_private
= private;
3206 list_link_init(&p
->p_node
);
3207 refcount_create(&p
->p_refcnt
);
3209 mutex_enter(&arc_prune_mtx
);
3210 refcount_add(&p
->p_refcnt
, &arc_prune_list
);
3211 list_insert_head(&arc_prune_list
, p
);
3212 mutex_exit(&arc_prune_mtx
);
3218 arc_remove_prune_callback(arc_prune_t
*p
)
3220 mutex_enter(&arc_prune_mtx
);
3221 list_remove(&arc_prune_list
, p
);
3222 if (refcount_remove(&p
->p_refcnt
, &arc_prune_list
) == 0) {
3223 refcount_destroy(&p
->p_refcnt
);
3224 kmem_free(p
, sizeof (*p
));
3226 mutex_exit(&arc_prune_mtx
);
3230 arc_set_callback(arc_buf_t
*buf
, arc_evict_func_t
*func
, void *private)
3232 ASSERT(buf
->b_hdr
!= NULL
);
3233 ASSERT(buf
->b_hdr
->b_state
!= arc_anon
);
3234 ASSERT(!refcount_is_zero(&buf
->b_hdr
->b_refcnt
) || func
== NULL
);
3235 ASSERT(buf
->b_efunc
== NULL
);
3236 ASSERT(!HDR_BUF_AVAILABLE(buf
->b_hdr
));
3238 buf
->b_efunc
= func
;
3239 buf
->b_private
= private;
3243 * This is used by the DMU to let the ARC know that a buffer is
3244 * being evicted, so the ARC should clean up. If this arc buf
3245 * is not yet in the evicted state, it will be put there.
3248 arc_buf_evict(arc_buf_t
*buf
)
3251 kmutex_t
*hash_lock
;
3254 mutex_enter(&buf
->b_evict_lock
);
3258 * We are in arc_do_user_evicts().
3260 ASSERT(buf
->b_data
== NULL
);
3261 mutex_exit(&buf
->b_evict_lock
);
3263 } else if (buf
->b_data
== NULL
) {
3264 arc_buf_t copy
= *buf
; /* structure assignment */
3266 * We are on the eviction list; process this buffer now
3267 * but let arc_do_user_evicts() do the reaping.
3269 buf
->b_efunc
= NULL
;
3270 mutex_exit(&buf
->b_evict_lock
);
3271 VERIFY(copy
.b_efunc(©
) == 0);
3274 hash_lock
= HDR_LOCK(hdr
);
3275 mutex_enter(hash_lock
);
3277 ASSERT3P(hash_lock
, ==, HDR_LOCK(hdr
));
3279 ASSERT3U(refcount_count(&hdr
->b_refcnt
), <, hdr
->b_datacnt
);
3280 ASSERT(hdr
->b_state
== arc_mru
|| hdr
->b_state
== arc_mfu
);
3283 * Pull this buffer off of the hdr
3286 while (*bufp
!= buf
)
3287 bufp
= &(*bufp
)->b_next
;
3288 *bufp
= buf
->b_next
;
3290 ASSERT(buf
->b_data
!= NULL
);
3291 arc_buf_destroy(buf
, FALSE
, FALSE
);
3293 if (hdr
->b_datacnt
== 0) {
3294 arc_state_t
*old_state
= hdr
->b_state
;
3295 arc_state_t
*evicted_state
;
3297 ASSERT(hdr
->b_buf
== NULL
);
3298 ASSERT(refcount_is_zero(&hdr
->b_refcnt
));
3301 (old_state
== arc_mru
) ? arc_mru_ghost
: arc_mfu_ghost
;
3303 mutex_enter(&old_state
->arcs_mtx
);
3304 mutex_enter(&evicted_state
->arcs_mtx
);
3306 arc_change_state(evicted_state
, hdr
, hash_lock
);
3307 ASSERT(HDR_IN_HASH_TABLE(hdr
));
3308 hdr
->b_flags
|= ARC_IN_HASH_TABLE
;
3309 hdr
->b_flags
&= ~ARC_BUF_AVAILABLE
;
3311 mutex_exit(&evicted_state
->arcs_mtx
);
3312 mutex_exit(&old_state
->arcs_mtx
);
3314 mutex_exit(hash_lock
);
3315 mutex_exit(&buf
->b_evict_lock
);
3317 VERIFY(buf
->b_efunc(buf
) == 0);
3318 buf
->b_efunc
= NULL
;
3319 buf
->b_private
= NULL
;
3322 kmem_cache_free(buf_cache
, buf
);
3327 * Release this buffer from the cache. This must be done
3328 * after a read and prior to modifying the buffer contents.
3329 * If the buffer has more than one reference, we must make
3330 * a new hdr for the buffer.
3333 arc_release(arc_buf_t
*buf
, void *tag
)
3336 kmutex_t
*hash_lock
= NULL
;
3337 l2arc_buf_hdr_t
*l2hdr
;
3338 uint64_t buf_size
= 0;
3341 * It would be nice to assert that if it's DMU metadata (level >
3342 * 0 || it's the dnode file), then it must be syncing context.
3343 * But we don't know that information at this level.
3346 mutex_enter(&buf
->b_evict_lock
);
3349 /* this buffer is not on any list */
3350 ASSERT(refcount_count(&hdr
->b_refcnt
) > 0);
3352 if (hdr
->b_state
== arc_anon
) {
3353 /* this buffer is already released */
3354 ASSERT(buf
->b_efunc
== NULL
);
3356 hash_lock
= HDR_LOCK(hdr
);
3357 mutex_enter(hash_lock
);
3359 ASSERT3P(hash_lock
, ==, HDR_LOCK(hdr
));
3362 l2hdr
= hdr
->b_l2hdr
;
3364 mutex_enter(&l2arc_buflist_mtx
);
3365 hdr
->b_l2hdr
= NULL
;
3366 buf_size
= hdr
->b_size
;
3370 * Do we have more than one buf?
3372 if (hdr
->b_datacnt
> 1) {
3373 arc_buf_hdr_t
*nhdr
;
3375 uint64_t blksz
= hdr
->b_size
;
3376 uint64_t spa
= hdr
->b_spa
;
3377 arc_buf_contents_t type
= hdr
->b_type
;
3378 uint32_t flags
= hdr
->b_flags
;
3380 ASSERT(hdr
->b_buf
!= buf
|| buf
->b_next
!= NULL
);
3382 * Pull the data off of this hdr and attach it to
3383 * a new anonymous hdr.
3385 (void) remove_reference(hdr
, hash_lock
, tag
);
3387 while (*bufp
!= buf
)
3388 bufp
= &(*bufp
)->b_next
;
3389 *bufp
= buf
->b_next
;
3392 ASSERT3U(hdr
->b_state
->arcs_size
, >=, hdr
->b_size
);
3393 atomic_add_64(&hdr
->b_state
->arcs_size
, -hdr
->b_size
);
3394 if (refcount_is_zero(&hdr
->b_refcnt
)) {
3395 uint64_t *size
= &hdr
->b_state
->arcs_lsize
[hdr
->b_type
];
3396 ASSERT3U(*size
, >=, hdr
->b_size
);
3397 atomic_add_64(size
, -hdr
->b_size
);
3401 * We're releasing a duplicate user data buffer, update
3402 * our statistics accordingly.
3404 if (hdr
->b_type
== ARC_BUFC_DATA
) {
3405 ARCSTAT_BUMPDOWN(arcstat_duplicate_buffers
);
3406 ARCSTAT_INCR(arcstat_duplicate_buffers_size
,
3409 hdr
->b_datacnt
-= 1;
3410 arc_cksum_verify(buf
);
3412 mutex_exit(hash_lock
);
3414 nhdr
= kmem_cache_alloc(hdr_cache
, KM_PUSHPAGE
);
3415 nhdr
->b_size
= blksz
;
3417 nhdr
->b_type
= type
;
3419 nhdr
->b_state
= arc_anon
;
3420 nhdr
->b_arc_access
= 0;
3421 nhdr
->b_flags
= flags
& ARC_L2_WRITING
;
3422 nhdr
->b_l2hdr
= NULL
;
3423 nhdr
->b_datacnt
= 1;
3424 nhdr
->b_freeze_cksum
= NULL
;
3425 (void) refcount_add(&nhdr
->b_refcnt
, tag
);
3427 mutex_exit(&buf
->b_evict_lock
);
3428 atomic_add_64(&arc_anon
->arcs_size
, blksz
);
3430 mutex_exit(&buf
->b_evict_lock
);
3431 ASSERT(refcount_count(&hdr
->b_refcnt
) == 1);
3432 ASSERT(!list_link_active(&hdr
->b_arc_node
));
3433 ASSERT(!HDR_IO_IN_PROGRESS(hdr
));
3434 if (hdr
->b_state
!= arc_anon
)
3435 arc_change_state(arc_anon
, hdr
, hash_lock
);
3436 hdr
->b_arc_access
= 0;
3438 mutex_exit(hash_lock
);
3440 buf_discard_identity(hdr
);
3443 buf
->b_efunc
= NULL
;
3444 buf
->b_private
= NULL
;
3447 list_remove(l2hdr
->b_dev
->l2ad_buflist
, hdr
);
3448 kmem_free(l2hdr
, sizeof (l2arc_buf_hdr_t
));
3449 ARCSTAT_INCR(arcstat_l2_size
, -buf_size
);
3450 mutex_exit(&l2arc_buflist_mtx
);
3455 * Release this buffer. If it does not match the provided BP, fill it
3456 * with that block's contents.
3460 arc_release_bp(arc_buf_t
*buf
, void *tag
, blkptr_t
*bp
, spa_t
*spa
,
3463 arc_release(buf
, tag
);
3468 arc_released(arc_buf_t
*buf
)
3472 mutex_enter(&buf
->b_evict_lock
);
3473 released
= (buf
->b_data
!= NULL
&& buf
->b_hdr
->b_state
== arc_anon
);
3474 mutex_exit(&buf
->b_evict_lock
);
3479 arc_has_callback(arc_buf_t
*buf
)
3483 mutex_enter(&buf
->b_evict_lock
);
3484 callback
= (buf
->b_efunc
!= NULL
);
3485 mutex_exit(&buf
->b_evict_lock
);
3491 arc_referenced(arc_buf_t
*buf
)
3495 mutex_enter(&buf
->b_evict_lock
);
3496 referenced
= (refcount_count(&buf
->b_hdr
->b_refcnt
));
3497 mutex_exit(&buf
->b_evict_lock
);
3498 return (referenced
);
3503 arc_write_ready(zio_t
*zio
)
3505 arc_write_callback_t
*callback
= zio
->io_private
;
3506 arc_buf_t
*buf
= callback
->awcb_buf
;
3507 arc_buf_hdr_t
*hdr
= buf
->b_hdr
;
3509 ASSERT(!refcount_is_zero(&buf
->b_hdr
->b_refcnt
));
3510 callback
->awcb_ready(zio
, buf
, callback
->awcb_private
);
3513 * If the IO is already in progress, then this is a re-write
3514 * attempt, so we need to thaw and re-compute the cksum.
3515 * It is the responsibility of the callback to handle the
3516 * accounting for any re-write attempt.
3518 if (HDR_IO_IN_PROGRESS(hdr
)) {
3519 mutex_enter(&hdr
->b_freeze_lock
);
3520 if (hdr
->b_freeze_cksum
!= NULL
) {
3521 kmem_free(hdr
->b_freeze_cksum
, sizeof (zio_cksum_t
));
3522 hdr
->b_freeze_cksum
= NULL
;
3524 mutex_exit(&hdr
->b_freeze_lock
);
3526 arc_cksum_compute(buf
, B_FALSE
);
3527 hdr
->b_flags
|= ARC_IO_IN_PROGRESS
;
3531 arc_write_done(zio_t
*zio
)
3533 arc_write_callback_t
*callback
= zio
->io_private
;
3534 arc_buf_t
*buf
= callback
->awcb_buf
;
3535 arc_buf_hdr_t
*hdr
= buf
->b_hdr
;
3537 ASSERT(hdr
->b_acb
== NULL
);
3539 if (zio
->io_error
== 0) {
3540 hdr
->b_dva
= *BP_IDENTITY(zio
->io_bp
);
3541 hdr
->b_birth
= BP_PHYSICAL_BIRTH(zio
->io_bp
);
3542 hdr
->b_cksum0
= zio
->io_bp
->blk_cksum
.zc_word
[0];
3544 ASSERT(BUF_EMPTY(hdr
));
3548 * If the block to be written was all-zero, we may have
3549 * compressed it away. In this case no write was performed
3550 * so there will be no dva/birth/checksum. The buffer must
3551 * therefore remain anonymous (and uncached).
3553 if (!BUF_EMPTY(hdr
)) {
3554 arc_buf_hdr_t
*exists
;
3555 kmutex_t
*hash_lock
;
3557 ASSERT(zio
->io_error
== 0);
3559 arc_cksum_verify(buf
);
3561 exists
= buf_hash_insert(hdr
, &hash_lock
);
3564 * This can only happen if we overwrite for
3565 * sync-to-convergence, because we remove
3566 * buffers from the hash table when we arc_free().
3568 if (zio
->io_flags
& ZIO_FLAG_IO_REWRITE
) {
3569 if (!BP_EQUAL(&zio
->io_bp_orig
, zio
->io_bp
))
3570 panic("bad overwrite, hdr=%p exists=%p",
3571 (void *)hdr
, (void *)exists
);
3572 ASSERT(refcount_is_zero(&exists
->b_refcnt
));
3573 arc_change_state(arc_anon
, exists
, hash_lock
);
3574 mutex_exit(hash_lock
);
3575 arc_hdr_destroy(exists
);
3576 exists
= buf_hash_insert(hdr
, &hash_lock
);
3577 ASSERT3P(exists
, ==, NULL
);
3580 ASSERT(hdr
->b_datacnt
== 1);
3581 ASSERT(hdr
->b_state
== arc_anon
);
3582 ASSERT(BP_GET_DEDUP(zio
->io_bp
));
3583 ASSERT(BP_GET_LEVEL(zio
->io_bp
) == 0);
3586 hdr
->b_flags
&= ~ARC_IO_IN_PROGRESS
;
3587 /* if it's not anon, we are doing a scrub */
3588 if (!exists
&& hdr
->b_state
== arc_anon
)
3589 arc_access(hdr
, hash_lock
);
3590 mutex_exit(hash_lock
);
3592 hdr
->b_flags
&= ~ARC_IO_IN_PROGRESS
;
3595 ASSERT(!refcount_is_zero(&hdr
->b_refcnt
));
3596 callback
->awcb_done(zio
, buf
, callback
->awcb_private
);
3598 kmem_free(callback
, sizeof (arc_write_callback_t
));
3602 arc_write(zio_t
*pio
, spa_t
*spa
, uint64_t txg
,
3603 blkptr_t
*bp
, arc_buf_t
*buf
, boolean_t l2arc
, const zio_prop_t
*zp
,
3604 arc_done_func_t
*ready
, arc_done_func_t
*done
, void *private,
3605 int priority
, int zio_flags
, const zbookmark_t
*zb
)
3607 arc_buf_hdr_t
*hdr
= buf
->b_hdr
;
3608 arc_write_callback_t
*callback
;
3611 ASSERT(ready
!= NULL
);
3612 ASSERT(done
!= NULL
);
3613 ASSERT(!HDR_IO_ERROR(hdr
));
3614 ASSERT((hdr
->b_flags
& ARC_IO_IN_PROGRESS
) == 0);
3615 ASSERT(hdr
->b_acb
== NULL
);
3617 hdr
->b_flags
|= ARC_L2CACHE
;
3618 callback
= kmem_zalloc(sizeof (arc_write_callback_t
), KM_PUSHPAGE
);
3619 callback
->awcb_ready
= ready
;
3620 callback
->awcb_done
= done
;
3621 callback
->awcb_private
= private;
3622 callback
->awcb_buf
= buf
;
3624 zio
= zio_write(pio
, spa
, txg
, bp
, buf
->b_data
, hdr
->b_size
, zp
,
3625 arc_write_ready
, arc_write_done
, callback
, priority
, zio_flags
, zb
);
3631 arc_memory_throttle(uint64_t reserve
, uint64_t inflight_data
, uint64_t txg
)
3634 uint64_t available_memory
;
3636 /* Easily reclaimable memory (free + inactive + arc-evictable) */
3637 available_memory
= ptob(spl_kmem_availrmem()) + arc_evictable_memory();
3639 if (available_memory
<= zfs_write_limit_max
) {
3640 ARCSTAT_INCR(arcstat_memory_throttle_count
, 1);
3641 DMU_TX_STAT_BUMP(dmu_tx_memory_reclaim
);
3645 if (inflight_data
> available_memory
/ 4) {
3646 ARCSTAT_INCR(arcstat_memory_throttle_count
, 1);
3647 DMU_TX_STAT_BUMP(dmu_tx_memory_inflight
);
3655 arc_tempreserve_clear(uint64_t reserve
)
3657 atomic_add_64(&arc_tempreserve
, -reserve
);
3658 ASSERT((int64_t)arc_tempreserve
>= 0);
3662 arc_tempreserve_space(uint64_t reserve
, uint64_t txg
)
3669 * Once in a while, fail for no reason. Everything should cope.
3671 if (spa_get_random(10000) == 0) {
3672 dprintf("forcing random failure\n");
3676 if (reserve
> arc_c
/4 && !arc_no_grow
)
3677 arc_c
= MIN(arc_c_max
, reserve
* 4);
3678 if (reserve
> arc_c
) {
3679 DMU_TX_STAT_BUMP(dmu_tx_memory_reserve
);
3684 * Don't count loaned bufs as in flight dirty data to prevent long
3685 * network delays from blocking transactions that are ready to be
3686 * assigned to a txg.
3688 anon_size
= MAX((int64_t)(arc_anon
->arcs_size
- arc_loaned_bytes
), 0);
3691 * Writes will, almost always, require additional memory allocations
3692 * in order to compress/encrypt/etc the data. We therefor need to
3693 * make sure that there is sufficient available memory for this.
3695 if ((error
= arc_memory_throttle(reserve
, anon_size
, txg
)))
3699 * Throttle writes when the amount of dirty data in the cache
3700 * gets too large. We try to keep the cache less than half full
3701 * of dirty blocks so that our sync times don't grow too large.
3702 * Note: if two requests come in concurrently, we might let them
3703 * both succeed, when one of them should fail. Not a huge deal.
3706 if (reserve
+ arc_tempreserve
+ anon_size
> arc_c
/ 2 &&
3707 anon_size
> arc_c
/ 4) {
3708 dprintf("failing, arc_tempreserve=%lluK anon_meta=%lluK "
3709 "anon_data=%lluK tempreserve=%lluK arc_c=%lluK\n",
3710 arc_tempreserve
>>10,
3711 arc_anon
->arcs_lsize
[ARC_BUFC_METADATA
]>>10,
3712 arc_anon
->arcs_lsize
[ARC_BUFC_DATA
]>>10,
3713 reserve
>>10, arc_c
>>10);
3714 DMU_TX_STAT_BUMP(dmu_tx_dirty_throttle
);
3717 atomic_add_64(&arc_tempreserve
, reserve
);
3722 arc_kstat_update_state(arc_state_t
*state
, kstat_named_t
*size
,
3723 kstat_named_t
*evict_data
, kstat_named_t
*evict_metadata
)
3725 size
->value
.ui64
= state
->arcs_size
;
3726 evict_data
->value
.ui64
= state
->arcs_lsize
[ARC_BUFC_DATA
];
3727 evict_metadata
->value
.ui64
= state
->arcs_lsize
[ARC_BUFC_METADATA
];
3731 arc_kstat_update(kstat_t
*ksp
, int rw
)
3733 arc_stats_t
*as
= ksp
->ks_data
;
3735 if (rw
== KSTAT_WRITE
) {
3738 arc_kstat_update_state(arc_anon
,
3739 &as
->arcstat_anon_size
,
3740 &as
->arcstat_anon_evict_data
,
3741 &as
->arcstat_anon_evict_metadata
);
3742 arc_kstat_update_state(arc_mru
,
3743 &as
->arcstat_mru_size
,
3744 &as
->arcstat_mru_evict_data
,
3745 &as
->arcstat_mru_evict_metadata
);
3746 arc_kstat_update_state(arc_mru_ghost
,
3747 &as
->arcstat_mru_ghost_size
,
3748 &as
->arcstat_mru_ghost_evict_data
,
3749 &as
->arcstat_mru_ghost_evict_metadata
);
3750 arc_kstat_update_state(arc_mfu
,
3751 &as
->arcstat_mfu_size
,
3752 &as
->arcstat_mfu_evict_data
,
3753 &as
->arcstat_mfu_evict_metadata
);
3754 arc_kstat_update_state(arc_mfu_ghost
,
3755 &as
->arcstat_mfu_ghost_size
,
3756 &as
->arcstat_mfu_ghost_evict_data
,
3757 &as
->arcstat_mfu_ghost_evict_metadata
);
3766 mutex_init(&arc_reclaim_thr_lock
, NULL
, MUTEX_DEFAULT
, NULL
);
3767 cv_init(&arc_reclaim_thr_cv
, NULL
, CV_DEFAULT
, NULL
);
3769 /* Convert seconds to clock ticks */
3770 arc_min_prefetch_lifespan
= 1 * hz
;
3772 /* Start out with 1/8 of all memory */
3773 arc_c
= physmem
* PAGESIZE
/ 8;
3777 * On architectures where the physical memory can be larger
3778 * than the addressable space (intel in 32-bit mode), we may
3779 * need to limit the cache to 1/8 of VM size.
3781 arc_c
= MIN(arc_c
, vmem_size(heap_arena
, VMEM_ALLOC
| VMEM_FREE
) / 8);
3783 * Register a shrinker to support synchronous (direct) memory
3784 * reclaim from the arc. This is done to prevent kswapd from
3785 * swapping out pages when it is preferable to shrink the arc.
3787 spl_register_shrinker(&arc_shrinker
);
3790 /* set min cache to 1/32 of all memory, or 64MB, whichever is more */
3791 arc_c_min
= MAX(arc_c
/ 4, 64<<20);
3792 /* set max to 1/2 of all memory */
3793 arc_c_max
= MAX(arc_c
* 4, arc_c_max
);
3796 * Allow the tunables to override our calculations if they are
3797 * reasonable (ie. over 64MB)
3799 if (zfs_arc_max
> 64<<20 && zfs_arc_max
< physmem
* PAGESIZE
)
3800 arc_c_max
= zfs_arc_max
;
3801 if (zfs_arc_min
> 64<<20 && zfs_arc_min
<= arc_c_max
)
3802 arc_c_min
= zfs_arc_min
;
3805 arc_p
= (arc_c
>> 1);
3807 /* limit meta-data to 1/4 of the arc capacity */
3808 arc_meta_limit
= arc_c_max
/ 4;
3811 /* Allow the tunable to override if it is reasonable */
3812 if (zfs_arc_meta_limit
> 0 && zfs_arc_meta_limit
<= arc_c_max
)
3813 arc_meta_limit
= zfs_arc_meta_limit
;
3815 if (arc_c_min
< arc_meta_limit
/ 2 && zfs_arc_min
== 0)
3816 arc_c_min
= arc_meta_limit
/ 2;
3818 if (zfs_arc_grow_retry
> 0)
3819 arc_grow_retry
= zfs_arc_grow_retry
;
3821 if (zfs_arc_shrink_shift
> 0)
3822 arc_shrink_shift
= zfs_arc_shrink_shift
;
3824 if (zfs_arc_p_min_shift
> 0)
3825 arc_p_min_shift
= zfs_arc_p_min_shift
;
3827 if (zfs_arc_meta_prune
> 0)
3828 arc_meta_prune
= zfs_arc_meta_prune
;
3830 /* if kmem_flags are set, lets try to use less memory */
3831 if (kmem_debugging())
3833 if (arc_c
< arc_c_min
)
3836 arc_anon
= &ARC_anon
;
3838 arc_mru_ghost
= &ARC_mru_ghost
;
3840 arc_mfu_ghost
= &ARC_mfu_ghost
;
3841 arc_l2c_only
= &ARC_l2c_only
;
3844 mutex_init(&arc_anon
->arcs_mtx
, NULL
, MUTEX_DEFAULT
, NULL
);
3845 mutex_init(&arc_mru
->arcs_mtx
, NULL
, MUTEX_DEFAULT
, NULL
);
3846 mutex_init(&arc_mru_ghost
->arcs_mtx
, NULL
, MUTEX_DEFAULT
, NULL
);
3847 mutex_init(&arc_mfu
->arcs_mtx
, NULL
, MUTEX_DEFAULT
, NULL
);
3848 mutex_init(&arc_mfu_ghost
->arcs_mtx
, NULL
, MUTEX_DEFAULT
, NULL
);
3849 mutex_init(&arc_l2c_only
->arcs_mtx
, NULL
, MUTEX_DEFAULT
, NULL
);
3851 list_create(&arc_mru
->arcs_list
[ARC_BUFC_METADATA
],
3852 sizeof (arc_buf_hdr_t
), offsetof(arc_buf_hdr_t
, b_arc_node
));
3853 list_create(&arc_mru
->arcs_list
[ARC_BUFC_DATA
],
3854 sizeof (arc_buf_hdr_t
), offsetof(arc_buf_hdr_t
, b_arc_node
));
3855 list_create(&arc_mru_ghost
->arcs_list
[ARC_BUFC_METADATA
],
3856 sizeof (arc_buf_hdr_t
), offsetof(arc_buf_hdr_t
, b_arc_node
));
3857 list_create(&arc_mru_ghost
->arcs_list
[ARC_BUFC_DATA
],
3858 sizeof (arc_buf_hdr_t
), offsetof(arc_buf_hdr_t
, b_arc_node
));
3859 list_create(&arc_mfu
->arcs_list
[ARC_BUFC_METADATA
],
3860 sizeof (arc_buf_hdr_t
), offsetof(arc_buf_hdr_t
, b_arc_node
));
3861 list_create(&arc_mfu
->arcs_list
[ARC_BUFC_DATA
],
3862 sizeof (arc_buf_hdr_t
), offsetof(arc_buf_hdr_t
, b_arc_node
));
3863 list_create(&arc_mfu_ghost
->arcs_list
[ARC_BUFC_METADATA
],
3864 sizeof (arc_buf_hdr_t
), offsetof(arc_buf_hdr_t
, b_arc_node
));
3865 list_create(&arc_mfu_ghost
->arcs_list
[ARC_BUFC_DATA
],
3866 sizeof (arc_buf_hdr_t
), offsetof(arc_buf_hdr_t
, b_arc_node
));
3867 list_create(&arc_l2c_only
->arcs_list
[ARC_BUFC_METADATA
],
3868 sizeof (arc_buf_hdr_t
), offsetof(arc_buf_hdr_t
, b_arc_node
));
3869 list_create(&arc_l2c_only
->arcs_list
[ARC_BUFC_DATA
],
3870 sizeof (arc_buf_hdr_t
), offsetof(arc_buf_hdr_t
, b_arc_node
));
3874 arc_thread_exit
= 0;
3875 list_create(&arc_prune_list
, sizeof (arc_prune_t
),
3876 offsetof(arc_prune_t
, p_node
));
3877 arc_eviction_list
= NULL
;
3878 mutex_init(&arc_prune_mtx
, NULL
, MUTEX_DEFAULT
, NULL
);
3879 mutex_init(&arc_eviction_mtx
, NULL
, MUTEX_DEFAULT
, NULL
);
3880 bzero(&arc_eviction_hdr
, sizeof (arc_buf_hdr_t
));
3882 arc_ksp
= kstat_create("zfs", 0, "arcstats", "misc", KSTAT_TYPE_NAMED
,
3883 sizeof (arc_stats
) / sizeof (kstat_named_t
), KSTAT_FLAG_VIRTUAL
);
3885 if (arc_ksp
!= NULL
) {
3886 arc_ksp
->ks_data
= &arc_stats
;
3887 arc_ksp
->ks_update
= arc_kstat_update
;
3888 kstat_install(arc_ksp
);
3891 (void) thread_create(NULL
, 0, arc_adapt_thread
, NULL
, 0, &p0
,
3892 TS_RUN
, minclsyspri
);
3897 if (zfs_write_limit_max
== 0)
3898 zfs_write_limit_max
= ptob(physmem
) >> zfs_write_limit_shift
;
3900 zfs_write_limit_shift
= 0;
3901 mutex_init(&zfs_write_limit_lock
, NULL
, MUTEX_DEFAULT
, NULL
);
3909 mutex_enter(&arc_reclaim_thr_lock
);
3911 spl_unregister_shrinker(&arc_shrinker
);
3912 #endif /* _KERNEL */
3914 arc_thread_exit
= 1;
3915 while (arc_thread_exit
!= 0)
3916 cv_wait(&arc_reclaim_thr_cv
, &arc_reclaim_thr_lock
);
3917 mutex_exit(&arc_reclaim_thr_lock
);
3923 if (arc_ksp
!= NULL
) {
3924 kstat_delete(arc_ksp
);
3928 mutex_enter(&arc_prune_mtx
);
3929 while ((p
= list_head(&arc_prune_list
)) != NULL
) {
3930 list_remove(&arc_prune_list
, p
);
3931 refcount_remove(&p
->p_refcnt
, &arc_prune_list
);
3932 refcount_destroy(&p
->p_refcnt
);
3933 kmem_free(p
, sizeof (*p
));
3935 mutex_exit(&arc_prune_mtx
);
3937 list_destroy(&arc_prune_list
);
3938 mutex_destroy(&arc_prune_mtx
);
3939 mutex_destroy(&arc_eviction_mtx
);
3940 mutex_destroy(&arc_reclaim_thr_lock
);
3941 cv_destroy(&arc_reclaim_thr_cv
);
3943 list_destroy(&arc_mru
->arcs_list
[ARC_BUFC_METADATA
]);
3944 list_destroy(&arc_mru_ghost
->arcs_list
[ARC_BUFC_METADATA
]);
3945 list_destroy(&arc_mfu
->arcs_list
[ARC_BUFC_METADATA
]);
3946 list_destroy(&arc_mfu_ghost
->arcs_list
[ARC_BUFC_METADATA
]);
3947 list_destroy(&arc_mru
->arcs_list
[ARC_BUFC_DATA
]);
3948 list_destroy(&arc_mru_ghost
->arcs_list
[ARC_BUFC_DATA
]);
3949 list_destroy(&arc_mfu
->arcs_list
[ARC_BUFC_DATA
]);
3950 list_destroy(&arc_mfu_ghost
->arcs_list
[ARC_BUFC_DATA
]);
3952 mutex_destroy(&arc_anon
->arcs_mtx
);
3953 mutex_destroy(&arc_mru
->arcs_mtx
);
3954 mutex_destroy(&arc_mru_ghost
->arcs_mtx
);
3955 mutex_destroy(&arc_mfu
->arcs_mtx
);
3956 mutex_destroy(&arc_mfu_ghost
->arcs_mtx
);
3957 mutex_destroy(&arc_l2c_only
->arcs_mtx
);
3959 mutex_destroy(&zfs_write_limit_lock
);
3963 ASSERT(arc_loaned_bytes
== 0);
3969 * The level 2 ARC (L2ARC) is a cache layer in-between main memory and disk.
3970 * It uses dedicated storage devices to hold cached data, which are populated
3971 * using large infrequent writes. The main role of this cache is to boost
3972 * the performance of random read workloads. The intended L2ARC devices
3973 * include short-stroked disks, solid state disks, and other media with
3974 * substantially faster read latency than disk.
3976 * +-----------------------+
3978 * +-----------------------+
3981 * l2arc_feed_thread() arc_read()
3985 * +---------------+ |
3987 * +---------------+ |
3992 * +-------+ +-------+
3994 * | cache | | cache |
3995 * +-------+ +-------+
3996 * +=========+ .-----.
3997 * : L2ARC : |-_____-|
3998 * : devices : | Disks |
3999 * +=========+ `-_____-'
4001 * Read requests are satisfied from the following sources, in order:
4004 * 2) vdev cache of L2ARC devices
4006 * 4) vdev cache of disks
4009 * Some L2ARC device types exhibit extremely slow write performance.
4010 * To accommodate for this there are some significant differences between
4011 * the L2ARC and traditional cache design:
4013 * 1. There is no eviction path from the ARC to the L2ARC. Evictions from
4014 * the ARC behave as usual, freeing buffers and placing headers on ghost
4015 * lists. The ARC does not send buffers to the L2ARC during eviction as
4016 * this would add inflated write latencies for all ARC memory pressure.
4018 * 2. The L2ARC attempts to cache data from the ARC before it is evicted.
4019 * It does this by periodically scanning buffers from the eviction-end of
4020 * the MFU and MRU ARC lists, copying them to the L2ARC devices if they are
4021 * not already there. It scans until a headroom of buffers is satisfied,
4022 * which itself is a buffer for ARC eviction. The thread that does this is
4023 * l2arc_feed_thread(), illustrated below; example sizes are included to
4024 * provide a better sense of ratio than this diagram:
4027 * +---------------------+----------+
4028 * ARC_mfu |:::::#:::::::::::::::|o#o###o###|-->. # already on L2ARC
4029 * +---------------------+----------+ | o L2ARC eligible
4030 * ARC_mru |:#:::::::::::::::::::|#o#ooo####|-->| : ARC buffer
4031 * +---------------------+----------+ |
4032 * 15.9 Gbytes ^ 32 Mbytes |
4034 * l2arc_feed_thread()
4036 * l2arc write hand <--[oooo]--'
4040 * +==============================+
4041 * L2ARC dev |####|#|###|###| |####| ... |
4042 * +==============================+
4045 * 3. If an ARC buffer is copied to the L2ARC but then hit instead of
4046 * evicted, then the L2ARC has cached a buffer much sooner than it probably
4047 * needed to, potentially wasting L2ARC device bandwidth and storage. It is
4048 * safe to say that this is an uncommon case, since buffers at the end of
4049 * the ARC lists have moved there due to inactivity.
4051 * 4. If the ARC evicts faster than the L2ARC can maintain a headroom,
4052 * then the L2ARC simply misses copying some buffers. This serves as a
4053 * pressure valve to prevent heavy read workloads from both stalling the ARC
4054 * with waits and clogging the L2ARC with writes. This also helps prevent
4055 * the potential for the L2ARC to churn if it attempts to cache content too
4056 * quickly, such as during backups of the entire pool.
4058 * 5. After system boot and before the ARC has filled main memory, there are
4059 * no evictions from the ARC and so the tails of the ARC_mfu and ARC_mru
4060 * lists can remain mostly static. Instead of searching from tail of these
4061 * lists as pictured, the l2arc_feed_thread() will search from the list heads
4062 * for eligible buffers, greatly increasing its chance of finding them.
4064 * The L2ARC device write speed is also boosted during this time so that
4065 * the L2ARC warms up faster. Since there have been no ARC evictions yet,
4066 * there are no L2ARC reads, and no fear of degrading read performance
4067 * through increased writes.
4069 * 6. Writes to the L2ARC devices are grouped and sent in-sequence, so that
4070 * the vdev queue can aggregate them into larger and fewer writes. Each
4071 * device is written to in a rotor fashion, sweeping writes through
4072 * available space then repeating.
4074 * 7. The L2ARC does not store dirty content. It never needs to flush
4075 * write buffers back to disk based storage.
4077 * 8. If an ARC buffer is written (and dirtied) which also exists in the
4078 * L2ARC, the now stale L2ARC buffer is immediately dropped.
4080 * The performance of the L2ARC can be tweaked by a number of tunables, which
4081 * may be necessary for different workloads:
4083 * l2arc_write_max max write bytes per interval
4084 * l2arc_write_boost extra write bytes during device warmup
4085 * l2arc_noprefetch skip caching prefetched buffers
4086 * l2arc_headroom number of max device writes to precache
4087 * l2arc_feed_secs seconds between L2ARC writing
4089 * Tunables may be removed or added as future performance improvements are
4090 * integrated, and also may become zpool properties.
4092 * There are three key functions that control how the L2ARC warms up:
4094 * l2arc_write_eligible() check if a buffer is eligible to cache
4095 * l2arc_write_size() calculate how much to write
4096 * l2arc_write_interval() calculate sleep delay between writes
4098 * These three functions determine what to write, how much, and how quickly
4103 l2arc_write_eligible(uint64_t spa_guid
, arc_buf_hdr_t
*ab
)
4106 * A buffer is *not* eligible for the L2ARC if it:
4107 * 1. belongs to a different spa.
4108 * 2. is already cached on the L2ARC.
4109 * 3. has an I/O in progress (it may be an incomplete read).
4110 * 4. is flagged not eligible (zfs property).
4112 if (ab
->b_spa
!= spa_guid
|| ab
->b_l2hdr
!= NULL
||
4113 HDR_IO_IN_PROGRESS(ab
) || !HDR_L2CACHE(ab
))
4120 l2arc_write_size(l2arc_dev_t
*dev
)
4124 size
= dev
->l2ad_write
;
4126 if (arc_warm
== B_FALSE
)
4127 size
+= dev
->l2ad_boost
;
4134 l2arc_write_interval(clock_t began
, uint64_t wanted
, uint64_t wrote
)
4136 clock_t interval
, next
, now
;
4139 * If the ARC lists are busy, increase our write rate; if the
4140 * lists are stale, idle back. This is achieved by checking
4141 * how much we previously wrote - if it was more than half of
4142 * what we wanted, schedule the next write much sooner.
4144 if (l2arc_feed_again
&& wrote
> (wanted
/ 2))
4145 interval
= (hz
* l2arc_feed_min_ms
) / 1000;
4147 interval
= hz
* l2arc_feed_secs
;
4149 now
= ddi_get_lbolt();
4150 next
= MAX(now
, MIN(now
+ interval
, began
+ interval
));
4156 l2arc_hdr_stat_add(void)
4158 ARCSTAT_INCR(arcstat_l2_hdr_size
, HDR_SIZE
+ L2HDR_SIZE
);
4159 ARCSTAT_INCR(arcstat_hdr_size
, -HDR_SIZE
);
4163 l2arc_hdr_stat_remove(void)
4165 ARCSTAT_INCR(arcstat_l2_hdr_size
, -(HDR_SIZE
+ L2HDR_SIZE
));
4166 ARCSTAT_INCR(arcstat_hdr_size
, HDR_SIZE
);
4170 * Cycle through L2ARC devices. This is how L2ARC load balances.
4171 * If a device is returned, this also returns holding the spa config lock.
4173 static l2arc_dev_t
*
4174 l2arc_dev_get_next(void)
4176 l2arc_dev_t
*first
, *next
= NULL
;
4179 * Lock out the removal of spas (spa_namespace_lock), then removal
4180 * of cache devices (l2arc_dev_mtx). Once a device has been selected,
4181 * both locks will be dropped and a spa config lock held instead.
4183 mutex_enter(&spa_namespace_lock
);
4184 mutex_enter(&l2arc_dev_mtx
);
4186 /* if there are no vdevs, there is nothing to do */
4187 if (l2arc_ndev
== 0)
4191 next
= l2arc_dev_last
;
4193 /* loop around the list looking for a non-faulted vdev */
4195 next
= list_head(l2arc_dev_list
);
4197 next
= list_next(l2arc_dev_list
, next
);
4199 next
= list_head(l2arc_dev_list
);
4202 /* if we have come back to the start, bail out */
4205 else if (next
== first
)
4208 } while (vdev_is_dead(next
->l2ad_vdev
));
4210 /* if we were unable to find any usable vdevs, return NULL */
4211 if (vdev_is_dead(next
->l2ad_vdev
))
4214 l2arc_dev_last
= next
;
4217 mutex_exit(&l2arc_dev_mtx
);
4220 * Grab the config lock to prevent the 'next' device from being
4221 * removed while we are writing to it.
4224 spa_config_enter(next
->l2ad_spa
, SCL_L2ARC
, next
, RW_READER
);
4225 mutex_exit(&spa_namespace_lock
);
4231 * Free buffers that were tagged for destruction.
4234 l2arc_do_free_on_write(void)
4237 l2arc_data_free_t
*df
, *df_prev
;
4239 mutex_enter(&l2arc_free_on_write_mtx
);
4240 buflist
= l2arc_free_on_write
;
4242 for (df
= list_tail(buflist
); df
; df
= df_prev
) {
4243 df_prev
= list_prev(buflist
, df
);
4244 ASSERT(df
->l2df_data
!= NULL
);
4245 ASSERT(df
->l2df_func
!= NULL
);
4246 df
->l2df_func(df
->l2df_data
, df
->l2df_size
);
4247 list_remove(buflist
, df
);
4248 kmem_free(df
, sizeof (l2arc_data_free_t
));
4251 mutex_exit(&l2arc_free_on_write_mtx
);
4255 * A write to a cache device has completed. Update all headers to allow
4256 * reads from these buffers to begin.
4259 l2arc_write_done(zio_t
*zio
)
4261 l2arc_write_callback_t
*cb
;
4264 arc_buf_hdr_t
*head
, *ab
, *ab_prev
;
4265 l2arc_buf_hdr_t
*abl2
;
4266 kmutex_t
*hash_lock
;
4268 cb
= zio
->io_private
;
4270 dev
= cb
->l2wcb_dev
;
4271 ASSERT(dev
!= NULL
);
4272 head
= cb
->l2wcb_head
;
4273 ASSERT(head
!= NULL
);
4274 buflist
= dev
->l2ad_buflist
;
4275 ASSERT(buflist
!= NULL
);
4276 DTRACE_PROBE2(l2arc__iodone
, zio_t
*, zio
,
4277 l2arc_write_callback_t
*, cb
);
4279 if (zio
->io_error
!= 0)
4280 ARCSTAT_BUMP(arcstat_l2_writes_error
);
4282 mutex_enter(&l2arc_buflist_mtx
);
4285 * All writes completed, or an error was hit.
4287 for (ab
= list_prev(buflist
, head
); ab
; ab
= ab_prev
) {
4288 ab_prev
= list_prev(buflist
, ab
);
4290 hash_lock
= HDR_LOCK(ab
);
4291 if (!mutex_tryenter(hash_lock
)) {
4293 * This buffer misses out. It may be in a stage
4294 * of eviction. Its ARC_L2_WRITING flag will be
4295 * left set, denying reads to this buffer.
4297 ARCSTAT_BUMP(arcstat_l2_writes_hdr_miss
);
4301 if (zio
->io_error
!= 0) {
4303 * Error - drop L2ARC entry.
4305 list_remove(buflist
, ab
);
4308 kmem_free(abl2
, sizeof (l2arc_buf_hdr_t
));
4309 ARCSTAT_INCR(arcstat_l2_size
, -ab
->b_size
);
4313 * Allow ARC to begin reads to this L2ARC entry.
4315 ab
->b_flags
&= ~ARC_L2_WRITING
;
4317 mutex_exit(hash_lock
);
4320 atomic_inc_64(&l2arc_writes_done
);
4321 list_remove(buflist
, head
);
4322 kmem_cache_free(hdr_cache
, head
);
4323 mutex_exit(&l2arc_buflist_mtx
);
4325 l2arc_do_free_on_write();
4327 kmem_free(cb
, sizeof (l2arc_write_callback_t
));
4331 * A read to a cache device completed. Validate buffer contents before
4332 * handing over to the regular ARC routines.
4335 l2arc_read_done(zio_t
*zio
)
4337 l2arc_read_callback_t
*cb
;
4340 kmutex_t
*hash_lock
;
4343 ASSERT(zio
->io_vd
!= NULL
);
4344 ASSERT(zio
->io_flags
& ZIO_FLAG_DONT_PROPAGATE
);
4346 spa_config_exit(zio
->io_spa
, SCL_L2ARC
, zio
->io_vd
);
4348 cb
= zio
->io_private
;
4350 buf
= cb
->l2rcb_buf
;
4351 ASSERT(buf
!= NULL
);
4353 hash_lock
= HDR_LOCK(buf
->b_hdr
);
4354 mutex_enter(hash_lock
);
4356 ASSERT3P(hash_lock
, ==, HDR_LOCK(hdr
));
4359 * Check this survived the L2ARC journey.
4361 equal
= arc_cksum_equal(buf
);
4362 if (equal
&& zio
->io_error
== 0 && !HDR_L2_EVICTED(hdr
)) {
4363 mutex_exit(hash_lock
);
4364 zio
->io_private
= buf
;
4365 zio
->io_bp_copy
= cb
->l2rcb_bp
; /* XXX fix in L2ARC 2.0 */
4366 zio
->io_bp
= &zio
->io_bp_copy
; /* XXX fix in L2ARC 2.0 */
4369 mutex_exit(hash_lock
);
4371 * Buffer didn't survive caching. Increment stats and
4372 * reissue to the original storage device.
4374 if (zio
->io_error
!= 0) {
4375 ARCSTAT_BUMP(arcstat_l2_io_error
);
4377 zio
->io_error
= EIO
;
4380 ARCSTAT_BUMP(arcstat_l2_cksum_bad
);
4383 * If there's no waiter, issue an async i/o to the primary
4384 * storage now. If there *is* a waiter, the caller must
4385 * issue the i/o in a context where it's OK to block.
4387 if (zio
->io_waiter
== NULL
) {
4388 zio_t
*pio
= zio_unique_parent(zio
);
4390 ASSERT(!pio
|| pio
->io_child_type
== ZIO_CHILD_LOGICAL
);
4392 zio_nowait(zio_read(pio
, cb
->l2rcb_spa
, &cb
->l2rcb_bp
,
4393 buf
->b_data
, zio
->io_size
, arc_read_done
, buf
,
4394 zio
->io_priority
, cb
->l2rcb_flags
, &cb
->l2rcb_zb
));
4398 kmem_free(cb
, sizeof (l2arc_read_callback_t
));
4402 * This is the list priority from which the L2ARC will search for pages to
4403 * cache. This is used within loops (0..3) to cycle through lists in the
4404 * desired order. This order can have a significant effect on cache
4407 * Currently the metadata lists are hit first, MFU then MRU, followed by
4408 * the data lists. This function returns a locked list, and also returns
4412 l2arc_list_locked(int list_num
, kmutex_t
**lock
)
4414 list_t
*list
= NULL
;
4416 ASSERT(list_num
>= 0 && list_num
<= 3);
4420 list
= &arc_mfu
->arcs_list
[ARC_BUFC_METADATA
];
4421 *lock
= &arc_mfu
->arcs_mtx
;
4424 list
= &arc_mru
->arcs_list
[ARC_BUFC_METADATA
];
4425 *lock
= &arc_mru
->arcs_mtx
;
4428 list
= &arc_mfu
->arcs_list
[ARC_BUFC_DATA
];
4429 *lock
= &arc_mfu
->arcs_mtx
;
4432 list
= &arc_mru
->arcs_list
[ARC_BUFC_DATA
];
4433 *lock
= &arc_mru
->arcs_mtx
;
4437 ASSERT(!(MUTEX_HELD(*lock
)));
4443 * Evict buffers from the device write hand to the distance specified in
4444 * bytes. This distance may span populated buffers, it may span nothing.
4445 * This is clearing a region on the L2ARC device ready for writing.
4446 * If the 'all' boolean is set, every buffer is evicted.
4449 l2arc_evict(l2arc_dev_t
*dev
, uint64_t distance
, boolean_t all
)
4452 l2arc_buf_hdr_t
*abl2
;
4453 arc_buf_hdr_t
*ab
, *ab_prev
;
4454 kmutex_t
*hash_lock
;
4457 buflist
= dev
->l2ad_buflist
;
4459 if (buflist
== NULL
)
4462 if (!all
&& dev
->l2ad_first
) {
4464 * This is the first sweep through the device. There is
4470 if (dev
->l2ad_hand
>= (dev
->l2ad_end
- (2 * distance
))) {
4472 * When nearing the end of the device, evict to the end
4473 * before the device write hand jumps to the start.
4475 taddr
= dev
->l2ad_end
;
4477 taddr
= dev
->l2ad_hand
+ distance
;
4479 DTRACE_PROBE4(l2arc__evict
, l2arc_dev_t
*, dev
, list_t
*, buflist
,
4480 uint64_t, taddr
, boolean_t
, all
);
4483 mutex_enter(&l2arc_buflist_mtx
);
4484 for (ab
= list_tail(buflist
); ab
; ab
= ab_prev
) {
4485 ab_prev
= list_prev(buflist
, ab
);
4487 hash_lock
= HDR_LOCK(ab
);
4488 if (!mutex_tryenter(hash_lock
)) {
4490 * Missed the hash lock. Retry.
4492 ARCSTAT_BUMP(arcstat_l2_evict_lock_retry
);
4493 mutex_exit(&l2arc_buflist_mtx
);
4494 mutex_enter(hash_lock
);
4495 mutex_exit(hash_lock
);
4499 if (HDR_L2_WRITE_HEAD(ab
)) {
4501 * We hit a write head node. Leave it for
4502 * l2arc_write_done().
4504 list_remove(buflist
, ab
);
4505 mutex_exit(hash_lock
);
4509 if (!all
&& ab
->b_l2hdr
!= NULL
&&
4510 (ab
->b_l2hdr
->b_daddr
> taddr
||
4511 ab
->b_l2hdr
->b_daddr
< dev
->l2ad_hand
)) {
4513 * We've evicted to the target address,
4514 * or the end of the device.
4516 mutex_exit(hash_lock
);
4520 if (HDR_FREE_IN_PROGRESS(ab
)) {
4522 * Already on the path to destruction.
4524 mutex_exit(hash_lock
);
4528 if (ab
->b_state
== arc_l2c_only
) {
4529 ASSERT(!HDR_L2_READING(ab
));
4531 * This doesn't exist in the ARC. Destroy.
4532 * arc_hdr_destroy() will call list_remove()
4533 * and decrement arcstat_l2_size.
4535 arc_change_state(arc_anon
, ab
, hash_lock
);
4536 arc_hdr_destroy(ab
);
4539 * Invalidate issued or about to be issued
4540 * reads, since we may be about to write
4541 * over this location.
4543 if (HDR_L2_READING(ab
)) {
4544 ARCSTAT_BUMP(arcstat_l2_evict_reading
);
4545 ab
->b_flags
|= ARC_L2_EVICTED
;
4549 * Tell ARC this no longer exists in L2ARC.
4551 if (ab
->b_l2hdr
!= NULL
) {
4554 kmem_free(abl2
, sizeof (l2arc_buf_hdr_t
));
4555 ARCSTAT_INCR(arcstat_l2_size
, -ab
->b_size
);
4557 list_remove(buflist
, ab
);
4560 * This may have been leftover after a
4563 ab
->b_flags
&= ~ARC_L2_WRITING
;
4565 mutex_exit(hash_lock
);
4567 mutex_exit(&l2arc_buflist_mtx
);
4569 vdev_space_update(dev
->l2ad_vdev
, -(taddr
- dev
->l2ad_evict
), 0, 0);
4570 dev
->l2ad_evict
= taddr
;
4574 * Find and write ARC buffers to the L2ARC device.
4576 * An ARC_L2_WRITING flag is set so that the L2ARC buffers are not valid
4577 * for reading until they have completed writing.
4580 l2arc_write_buffers(spa_t
*spa
, l2arc_dev_t
*dev
, uint64_t target_sz
)
4582 arc_buf_hdr_t
*ab
, *ab_prev
, *head
;
4583 l2arc_buf_hdr_t
*hdrl2
;
4585 uint64_t passed_sz
, write_sz
, buf_sz
, headroom
;
4587 kmutex_t
*hash_lock
, *list_lock
= NULL
;
4588 boolean_t have_lock
, full
;
4589 l2arc_write_callback_t
*cb
;
4591 uint64_t guid
= spa_load_guid(spa
);
4594 ASSERT(dev
->l2ad_vdev
!= NULL
);
4599 head
= kmem_cache_alloc(hdr_cache
, KM_PUSHPAGE
);
4600 head
->b_flags
|= ARC_L2_WRITE_HEAD
;
4603 * Copy buffers for L2ARC writing.
4605 mutex_enter(&l2arc_buflist_mtx
);
4606 for (try = 0; try <= 3; try++) {
4607 list
= l2arc_list_locked(try, &list_lock
);
4611 * L2ARC fast warmup.
4613 * Until the ARC is warm and starts to evict, read from the
4614 * head of the ARC lists rather than the tail.
4616 headroom
= target_sz
* l2arc_headroom
;
4617 if (arc_warm
== B_FALSE
)
4618 ab
= list_head(list
);
4620 ab
= list_tail(list
);
4622 for (; ab
; ab
= ab_prev
) {
4623 if (arc_warm
== B_FALSE
)
4624 ab_prev
= list_next(list
, ab
);
4626 ab_prev
= list_prev(list
, ab
);
4628 hash_lock
= HDR_LOCK(ab
);
4629 have_lock
= MUTEX_HELD(hash_lock
);
4630 if (!have_lock
&& !mutex_tryenter(hash_lock
)) {
4632 * Skip this buffer rather than waiting.
4637 passed_sz
+= ab
->b_size
;
4638 if (passed_sz
> headroom
) {
4642 mutex_exit(hash_lock
);
4646 if (!l2arc_write_eligible(guid
, ab
)) {
4647 mutex_exit(hash_lock
);
4651 if ((write_sz
+ ab
->b_size
) > target_sz
) {
4653 mutex_exit(hash_lock
);
4659 * Insert a dummy header on the buflist so
4660 * l2arc_write_done() can find where the
4661 * write buffers begin without searching.
4663 list_insert_head(dev
->l2ad_buflist
, head
);
4665 cb
= kmem_alloc(sizeof (l2arc_write_callback_t
),
4667 cb
->l2wcb_dev
= dev
;
4668 cb
->l2wcb_head
= head
;
4669 pio
= zio_root(spa
, l2arc_write_done
, cb
,
4674 * Create and add a new L2ARC header.
4676 hdrl2
= kmem_zalloc(sizeof (l2arc_buf_hdr_t
),
4679 hdrl2
->b_daddr
= dev
->l2ad_hand
;
4681 ab
->b_flags
|= ARC_L2_WRITING
;
4682 ab
->b_l2hdr
= hdrl2
;
4683 list_insert_head(dev
->l2ad_buflist
, ab
);
4684 buf_data
= ab
->b_buf
->b_data
;
4685 buf_sz
= ab
->b_size
;
4688 * Compute and store the buffer cksum before
4689 * writing. On debug the cksum is verified first.
4691 arc_cksum_verify(ab
->b_buf
);
4692 arc_cksum_compute(ab
->b_buf
, B_TRUE
);
4694 mutex_exit(hash_lock
);
4696 wzio
= zio_write_phys(pio
, dev
->l2ad_vdev
,
4697 dev
->l2ad_hand
, buf_sz
, buf_data
, ZIO_CHECKSUM_OFF
,
4698 NULL
, NULL
, ZIO_PRIORITY_ASYNC_WRITE
,
4699 ZIO_FLAG_CANFAIL
, B_FALSE
);
4701 DTRACE_PROBE2(l2arc__write
, vdev_t
*, dev
->l2ad_vdev
,
4703 (void) zio_nowait(wzio
);
4706 * Keep the clock hand suitably device-aligned.
4708 buf_sz
= vdev_psize_to_asize(dev
->l2ad_vdev
, buf_sz
);
4711 dev
->l2ad_hand
+= buf_sz
;
4714 mutex_exit(list_lock
);
4719 mutex_exit(&l2arc_buflist_mtx
);
4722 ASSERT3U(write_sz
, ==, 0);
4723 kmem_cache_free(hdr_cache
, head
);
4727 ASSERT3U(write_sz
, <=, target_sz
);
4728 ARCSTAT_BUMP(arcstat_l2_writes_sent
);
4729 ARCSTAT_INCR(arcstat_l2_write_bytes
, write_sz
);
4730 ARCSTAT_INCR(arcstat_l2_size
, write_sz
);
4731 vdev_space_update(dev
->l2ad_vdev
, write_sz
, 0, 0);
4734 * Bump device hand to the device start if it is approaching the end.
4735 * l2arc_evict() will already have evicted ahead for this case.
4737 if (dev
->l2ad_hand
>= (dev
->l2ad_end
- target_sz
)) {
4738 vdev_space_update(dev
->l2ad_vdev
,
4739 dev
->l2ad_end
- dev
->l2ad_hand
, 0, 0);
4740 dev
->l2ad_hand
= dev
->l2ad_start
;
4741 dev
->l2ad_evict
= dev
->l2ad_start
;
4742 dev
->l2ad_first
= B_FALSE
;
4745 dev
->l2ad_writing
= B_TRUE
;
4746 (void) zio_wait(pio
);
4747 dev
->l2ad_writing
= B_FALSE
;
4753 * This thread feeds the L2ARC at regular intervals. This is the beating
4754 * heart of the L2ARC.
4757 l2arc_feed_thread(void)
4762 uint64_t size
, wrote
;
4763 clock_t begin
, next
= ddi_get_lbolt();
4765 CALLB_CPR_INIT(&cpr
, &l2arc_feed_thr_lock
, callb_generic_cpr
, FTAG
);
4767 mutex_enter(&l2arc_feed_thr_lock
);
4769 while (l2arc_thread_exit
== 0) {
4770 CALLB_CPR_SAFE_BEGIN(&cpr
);
4771 (void) cv_timedwait_interruptible(&l2arc_feed_thr_cv
,
4772 &l2arc_feed_thr_lock
, next
);
4773 CALLB_CPR_SAFE_END(&cpr
, &l2arc_feed_thr_lock
);
4774 next
= ddi_get_lbolt() + hz
;
4777 * Quick check for L2ARC devices.
4779 mutex_enter(&l2arc_dev_mtx
);
4780 if (l2arc_ndev
== 0) {
4781 mutex_exit(&l2arc_dev_mtx
);
4784 mutex_exit(&l2arc_dev_mtx
);
4785 begin
= ddi_get_lbolt();
4788 * This selects the next l2arc device to write to, and in
4789 * doing so the next spa to feed from: dev->l2ad_spa. This
4790 * will return NULL if there are now no l2arc devices or if
4791 * they are all faulted.
4793 * If a device is returned, its spa's config lock is also
4794 * held to prevent device removal. l2arc_dev_get_next()
4795 * will grab and release l2arc_dev_mtx.
4797 if ((dev
= l2arc_dev_get_next()) == NULL
)
4800 spa
= dev
->l2ad_spa
;
4801 ASSERT(spa
!= NULL
);
4804 * If the pool is read-only then force the feed thread to
4805 * sleep a little longer.
4807 if (!spa_writeable(spa
)) {
4808 next
= ddi_get_lbolt() + 5 * l2arc_feed_secs
* hz
;
4809 spa_config_exit(spa
, SCL_L2ARC
, dev
);
4814 * Avoid contributing to memory pressure.
4817 ARCSTAT_BUMP(arcstat_l2_abort_lowmem
);
4818 spa_config_exit(spa
, SCL_L2ARC
, dev
);
4822 ARCSTAT_BUMP(arcstat_l2_feeds
);
4824 size
= l2arc_write_size(dev
);
4827 * Evict L2ARC buffers that will be overwritten.
4829 l2arc_evict(dev
, size
, B_FALSE
);
4832 * Write ARC buffers.
4834 wrote
= l2arc_write_buffers(spa
, dev
, size
);
4837 * Calculate interval between writes.
4839 next
= l2arc_write_interval(begin
, size
, wrote
);
4840 spa_config_exit(spa
, SCL_L2ARC
, dev
);
4843 l2arc_thread_exit
= 0;
4844 cv_broadcast(&l2arc_feed_thr_cv
);
4845 CALLB_CPR_EXIT(&cpr
); /* drops l2arc_feed_thr_lock */
4850 l2arc_vdev_present(vdev_t
*vd
)
4854 mutex_enter(&l2arc_dev_mtx
);
4855 for (dev
= list_head(l2arc_dev_list
); dev
!= NULL
;
4856 dev
= list_next(l2arc_dev_list
, dev
)) {
4857 if (dev
->l2ad_vdev
== vd
)
4860 mutex_exit(&l2arc_dev_mtx
);
4862 return (dev
!= NULL
);
4866 * Add a vdev for use by the L2ARC. By this point the spa has already
4867 * validated the vdev and opened it.
4870 l2arc_add_vdev(spa_t
*spa
, vdev_t
*vd
)
4872 l2arc_dev_t
*adddev
;
4874 ASSERT(!l2arc_vdev_present(vd
));
4877 * Create a new l2arc device entry.
4879 adddev
= kmem_zalloc(sizeof (l2arc_dev_t
), KM_SLEEP
);
4880 adddev
->l2ad_spa
= spa
;
4881 adddev
->l2ad_vdev
= vd
;
4882 adddev
->l2ad_write
= l2arc_write_max
;
4883 adddev
->l2ad_boost
= l2arc_write_boost
;
4884 adddev
->l2ad_start
= VDEV_LABEL_START_SIZE
;
4885 adddev
->l2ad_end
= VDEV_LABEL_START_SIZE
+ vdev_get_min_asize(vd
);
4886 adddev
->l2ad_hand
= adddev
->l2ad_start
;
4887 adddev
->l2ad_evict
= adddev
->l2ad_start
;
4888 adddev
->l2ad_first
= B_TRUE
;
4889 adddev
->l2ad_writing
= B_FALSE
;
4890 list_link_init(&adddev
->l2ad_node
);
4891 ASSERT3U(adddev
->l2ad_write
, >, 0);
4894 * This is a list of all ARC buffers that are still valid on the
4897 adddev
->l2ad_buflist
= kmem_zalloc(sizeof (list_t
), KM_SLEEP
);
4898 list_create(adddev
->l2ad_buflist
, sizeof (arc_buf_hdr_t
),
4899 offsetof(arc_buf_hdr_t
, b_l2node
));
4901 vdev_space_update(vd
, 0, 0, adddev
->l2ad_end
- adddev
->l2ad_hand
);
4904 * Add device to global list
4906 mutex_enter(&l2arc_dev_mtx
);
4907 list_insert_head(l2arc_dev_list
, adddev
);
4908 atomic_inc_64(&l2arc_ndev
);
4909 mutex_exit(&l2arc_dev_mtx
);
4913 * Remove a vdev from the L2ARC.
4916 l2arc_remove_vdev(vdev_t
*vd
)
4918 l2arc_dev_t
*dev
, *nextdev
, *remdev
= NULL
;
4921 * Find the device by vdev
4923 mutex_enter(&l2arc_dev_mtx
);
4924 for (dev
= list_head(l2arc_dev_list
); dev
; dev
= nextdev
) {
4925 nextdev
= list_next(l2arc_dev_list
, dev
);
4926 if (vd
== dev
->l2ad_vdev
) {
4931 ASSERT(remdev
!= NULL
);
4934 * Remove device from global list
4936 list_remove(l2arc_dev_list
, remdev
);
4937 l2arc_dev_last
= NULL
; /* may have been invalidated */
4938 atomic_dec_64(&l2arc_ndev
);
4939 mutex_exit(&l2arc_dev_mtx
);
4942 * Clear all buflists and ARC references. L2ARC device flush.
4944 l2arc_evict(remdev
, 0, B_TRUE
);
4945 list_destroy(remdev
->l2ad_buflist
);
4946 kmem_free(remdev
->l2ad_buflist
, sizeof (list_t
));
4947 kmem_free(remdev
, sizeof (l2arc_dev_t
));
4953 l2arc_thread_exit
= 0;
4955 l2arc_writes_sent
= 0;
4956 l2arc_writes_done
= 0;
4958 mutex_init(&l2arc_feed_thr_lock
, NULL
, MUTEX_DEFAULT
, NULL
);
4959 cv_init(&l2arc_feed_thr_cv
, NULL
, CV_DEFAULT
, NULL
);
4960 mutex_init(&l2arc_dev_mtx
, NULL
, MUTEX_DEFAULT
, NULL
);
4961 mutex_init(&l2arc_buflist_mtx
, NULL
, MUTEX_DEFAULT
, NULL
);
4962 mutex_init(&l2arc_free_on_write_mtx
, NULL
, MUTEX_DEFAULT
, NULL
);
4964 l2arc_dev_list
= &L2ARC_dev_list
;
4965 l2arc_free_on_write
= &L2ARC_free_on_write
;
4966 list_create(l2arc_dev_list
, sizeof (l2arc_dev_t
),
4967 offsetof(l2arc_dev_t
, l2ad_node
));
4968 list_create(l2arc_free_on_write
, sizeof (l2arc_data_free_t
),
4969 offsetof(l2arc_data_free_t
, l2df_list_node
));
4976 * This is called from dmu_fini(), which is called from spa_fini();
4977 * Because of this, we can assume that all l2arc devices have
4978 * already been removed when the pools themselves were removed.
4981 l2arc_do_free_on_write();
4983 mutex_destroy(&l2arc_feed_thr_lock
);
4984 cv_destroy(&l2arc_feed_thr_cv
);
4985 mutex_destroy(&l2arc_dev_mtx
);
4986 mutex_destroy(&l2arc_buflist_mtx
);
4987 mutex_destroy(&l2arc_free_on_write_mtx
);
4989 list_destroy(l2arc_dev_list
);
4990 list_destroy(l2arc_free_on_write
);
4996 if (!(spa_mode_global
& FWRITE
))
4999 (void) thread_create(NULL
, 0, l2arc_feed_thread
, NULL
, 0, &p0
,
5000 TS_RUN
, minclsyspri
);
5006 if (!(spa_mode_global
& FWRITE
))
5009 mutex_enter(&l2arc_feed_thr_lock
);
5010 cv_signal(&l2arc_feed_thr_cv
); /* kick thread out of startup */
5011 l2arc_thread_exit
= 1;
5012 while (l2arc_thread_exit
!= 0)
5013 cv_wait(&l2arc_feed_thr_cv
, &l2arc_feed_thr_lock
);
5014 mutex_exit(&l2arc_feed_thr_lock
);
5017 #if defined(_KERNEL) && defined(HAVE_SPL)
5018 EXPORT_SYMBOL(arc_read
);
5019 EXPORT_SYMBOL(arc_buf_remove_ref
);
5020 EXPORT_SYMBOL(arc_getbuf_func
);
5021 EXPORT_SYMBOL(arc_add_prune_callback
);
5022 EXPORT_SYMBOL(arc_remove_prune_callback
);
5024 module_param(zfs_arc_min
, ulong
, 0444);
5025 MODULE_PARM_DESC(zfs_arc_min
, "Min arc size");
5027 module_param(zfs_arc_max
, ulong
, 0444);
5028 MODULE_PARM_DESC(zfs_arc_max
, "Max arc size");
5030 module_param(zfs_arc_meta_limit
, ulong
, 0444);
5031 MODULE_PARM_DESC(zfs_arc_meta_limit
, "Meta limit for arc size");
5033 module_param(zfs_arc_meta_prune
, int, 0444);
5034 MODULE_PARM_DESC(zfs_arc_meta_prune
, "Bytes of meta data to prune");
5036 module_param(zfs_arc_grow_retry
, int, 0444);
5037 MODULE_PARM_DESC(zfs_arc_grow_retry
, "Seconds before growing arc size");
5039 module_param(zfs_arc_shrink_shift
, int, 0444);
5040 MODULE_PARM_DESC(zfs_arc_shrink_shift
, "log2(fraction of arc to reclaim)");
5042 module_param(zfs_arc_p_min_shift
, int, 0444);
5043 MODULE_PARM_DESC(zfs_arc_p_min_shift
, "arc_c shift to calc min/max arc_p");
5045 module_param(zfs_disable_dup_eviction
, int, 0644);
5046 MODULE_PARM_DESC(zfs_disable_dup_eviction
, "disable duplicate buffer eviction");
5048 module_param(l2arc_write_max
, ulong
, 0444);
5049 MODULE_PARM_DESC(l2arc_write_max
, "Max write bytes per interval");
5051 module_param(l2arc_write_boost
, ulong
, 0444);
5052 MODULE_PARM_DESC(l2arc_write_boost
, "Extra write bytes during device warmup");
5054 module_param(l2arc_headroom
, ulong
, 0444);
5055 MODULE_PARM_DESC(l2arc_headroom
, "Number of max device writes to precache");
5057 module_param(l2arc_feed_secs
, ulong
, 0444);
5058 MODULE_PARM_DESC(l2arc_feed_secs
, "Seconds between L2ARC writing");
5060 module_param(l2arc_feed_min_ms
, ulong
, 0444);
5061 MODULE_PARM_DESC(l2arc_feed_min_ms
, "Min feed interval in milliseconds");
5063 module_param(l2arc_noprefetch
, int, 0444);
5064 MODULE_PARM_DESC(l2arc_noprefetch
, "Skip caching prefetched buffers");
5066 module_param(l2arc_feed_again
, int, 0444);
5067 MODULE_PARM_DESC(l2arc_feed_again
, "Turbo L2ARC warmup");
5069 module_param(l2arc_norw
, int, 0444);
5070 MODULE_PARM_DESC(l2arc_norw
, "No reads during writes");