aboutsummaryrefslogtreecommitdiff
path: root/sys/contrib/openzfs/module/os/freebsd/zfs/arc_os.c
blob: e73efd810e53d3ebfe61e0e062430060302236f2 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
/*
 * CDDL HEADER START
 *
 * The contents of this file are subject to the terms of the
 * Common Development and Distribution License (the "License").
 * You may not use this file except in compliance with the License.
 *
 * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
 * or http://www.opensolaris.org/os/licensing.
 * See the License for the specific language governing permissions
 * and limitations under the License.
 *
 * When distributing Covered Code, include this CDDL HEADER in each
 * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
 * If applicable, add the following below this CDDL HEADER, with the
 * fields enclosed by brackets "[]" replaced with your own identifying
 * information: Portions Copyright [yyyy] [name of copyright owner]
 *
 * CDDL HEADER END
 */

#include <sys/spa.h>
#include <sys/zio.h>
#include <sys/spa_impl.h>
#include <sys/counter.h>
#include <sys/zio_compress.h>
#include <sys/zio_checksum.h>
#include <sys/zfs_context.h>
#include <sys/arc.h>
#include <sys/zfs_refcount.h>
#include <sys/vdev.h>
#include <sys/vdev_trim.h>
#include <sys/vdev_impl.h>
#include <sys/dsl_pool.h>
#include <sys/zio_checksum.h>
#include <sys/multilist.h>
#include <sys/abd.h>
#include <sys/zil.h>
#include <sys/fm/fs/zfs.h>
#include <sys/eventhandler.h>
#include <sys/callb.h>
#include <sys/kstat.h>
#include <sys/zthr.h>
#include <zfs_fletcher.h>
#include <sys/arc_impl.h>
#include <sys/sdt.h>
#include <sys/aggsum.h>
#include <sys/vnode.h>
#include <cityhash.h>
#include <machine/vmparam.h>
#include <sys/vm.h>
#include <sys/vmmeter.h>

#if __FreeBSD_version >= 1300139
static struct sx arc_vnlru_lock;
static struct vnode *arc_vnlru_marker;
#endif

extern struct vfsops zfs_vfsops;

uint_t zfs_arc_free_target = 0;

static void
arc_free_target_init(void *unused __unused)
{
	zfs_arc_free_target = vm_cnt.v_free_target;
}
SYSINIT(arc_free_target_init, SI_SUB_KTHREAD_PAGE, SI_ORDER_ANY,
    arc_free_target_init, NULL);

/*
 * We don't have a tunable for arc_free_target due to the dependency on
 * pagedaemon initialisation.
 */
static int
sysctl_vfs_zfs_arc_free_target(SYSCTL_HANDLER_ARGS)
{
	uint_t val;
	int err;

	val = zfs_arc_free_target;
	err = sysctl_handle_int(oidp, &val, 0, req);
	if (err != 0 || req->newptr == NULL)
		return (err);

	if (val < minfree)
		return (EINVAL);
	if (val > vm_cnt.v_page_count)
		return (EINVAL);

	zfs_arc_free_target = val;

	return (0);
}
SYSCTL_DECL(_vfs_zfs);
/* BEGIN CSTYLED */
SYSCTL_PROC(_vfs_zfs, OID_AUTO, arc_free_target,
    CTLTYPE_UINT | CTLFLAG_MPSAFE | CTLFLAG_RW, 0, sizeof (uint_t),
    sysctl_vfs_zfs_arc_free_target, "IU",
    "Desired number of free pages below which ARC triggers reclaim");
/* END CSTYLED */

int64_t
arc_available_memory(void)
{
	int64_t lowest = INT64_MAX;
	int64_t n __unused;

	/*
	 * Cooperate with pagedaemon when it's time for it to scan
	 * and reclaim some pages.
	 */
	n = PAGESIZE * ((int64_t)freemem - zfs_arc_free_target);
	if (n < lowest) {
		lowest = n;
	}
#if defined(__i386) || !defined(UMA_MD_SMALL_ALLOC)
	/*
	 * If we're on an i386 platform, it's possible that we'll exhaust the
	 * kernel heap space before we ever run out of available physical
	 * memory.  Most checks of the size of the heap_area compare against
	 * tune.t_minarmem, which is the minimum available real memory that we
	 * can have in the system.  However, this is generally fixed at 25 pages
	 * which is so low that it's useless.  In this comparison, we seek to
	 * calculate the total heap-size, and reclaim if more than 3/4ths of the
	 * heap is allocated.  (Or, in the calculation, if less than 1/4th is
	 * free)
	 */
	n = uma_avail() - (long)(uma_limit() / 4);
	if (n < lowest) {
		lowest = n;
	}
#endif

	DTRACE_PROBE1(arc__available_memory, int64_t, lowest);
	return (lowest);
}

/*
 * Return a default max arc size based on the amount of physical memory.
 */
uint64_t
arc_default_max(uint64_t min, uint64_t allmem)
{
	uint64_t size;

	if (allmem >= 1 << 30)
		size = allmem - (1 << 30);
	else
		size = min;
	return (MAX(allmem * 5 / 8, size));
}

/*
 * Helper function for arc_prune_async() it is responsible for safely
 * handling the execution of a registered arc_prune_func_t.
 */
static void
arc_prune_task(void *arg)
{
#ifdef __LP64__
	int64_t nr_scan = (int64_t)arg;
#else
	int64_t nr_scan = (int32_t)arg;
#endif

	arc_reduce_target_size(ptob(nr_scan));
#if __FreeBSD_version >= 1300139
	sx_xlock(&arc_vnlru_lock);
	vnlru_free_vfsops(nr_scan, &zfs_vfsops, arc_vnlru_marker);
	sx_xunlock(&arc_vnlru_lock);
#else
	vnlru_free(nr_scan, &zfs_vfsops);
#endif
}

/*
 * Notify registered consumers they must drop holds on a portion of the ARC
 * buffered they reference.  This provides a mechanism to ensure the ARC can
 * honor the arc_meta_limit and reclaim otherwise pinned ARC buffers.  This
 * is analogous to dnlc_reduce_cache() but more generic.
 *
 * This operation is performed asynchronously so it may be safely called
 * in the context of the arc_reclaim_thread().  A reference is taken here
 * for each registered arc_prune_t and the arc_prune_task() is responsible
 * for releasing it once the registered arc_prune_func_t has completed.
 */
void
arc_prune_async(int64_t adjust)
{
	int64_t *adjustptr;

#ifndef __LP64__
	if (adjust > __LONG_MAX)
		adjust = __LONG_MAX;
#endif

	adjustptr = (void *)adjust;
	taskq_dispatch(arc_prune_taskq, arc_prune_task, adjustptr, TQ_SLEEP);
	ARCSTAT_BUMP(arcstat_prune);
}

uint64_t
arc_all_memory(void)
{
	return (ptob(physmem));
}

int
arc_memory_throttle(spa_t *spa, uint64_t reserve, uint64_t txg)
{
	return (0);
}

uint64_t
arc_free_memory(void)
{
	return (ptob(freemem));
}

static eventhandler_tag arc_event_lowmem = NULL;

static void
arc_lowmem(void *arg __unused, int howto __unused)
{
	int64_t free_memory, to_free;

	arc_no_grow = B_TRUE;
	arc_warm = B_TRUE;
	arc_growtime = gethrtime() + SEC2NSEC(arc_grow_retry);
	free_memory = arc_available_memory();
	to_free = (arc_c >> arc_shrink_shift) - MIN(free_memory, 0);
	DTRACE_PROBE2(arc__needfree, int64_t, free_memory, int64_t, to_free);
	arc_reduce_target_size(to_free);

	/*
	 * It is unsafe to block here in arbitrary threads, because we can come
	 * here from ARC itself and may hold ARC locks and thus risk a deadlock
	 * with ARC reclaim thread.
	 */
	if (curproc == pageproc)
		arc_wait_for_eviction(to_free);
	else
		arc_wait_for_eviction(0);
}

void
arc_lowmem_init(void)
{
	arc_event_lowmem = EVENTHANDLER_REGISTER(vm_lowmem, arc_lowmem, NULL,
	    EVENTHANDLER_PRI_FIRST);
#if __FreeBSD_version >= 1300139
	arc_vnlru_marker = vnlru_alloc_marker();
	sx_init(&arc_vnlru_lock, "arc vnlru lock");
#endif
}

void
arc_lowmem_fini(void)
{
	if (arc_event_lowmem != NULL)
		EVENTHANDLER_DEREGISTER(vm_lowmem, arc_event_lowmem);
#if __FreeBSD_version >= 1300139
	if (arc_vnlru_marker != NULL) {
		vnlru_free_marker(arc_vnlru_marker);
		sx_destroy(&arc_vnlru_lock);
	}
#endif
}

void
arc_register_hotplug(void)
{
}

void
arc_unregister_hotplug(void)
{
}