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
|
/*
* 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
*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2013, 2015 by Delphix. All rights reserved.
* Copyright 2014 HybridCluster. All rights reserved.
*/
#include <sys/dmu.h>
#include <sys/dmu_objset.h>
#include <sys/dmu_tx.h>
#include <sys/dnode.h>
#include <sys/zap.h>
#include <sys/zfeature.h>
uint64_t
dmu_object_alloc(objset_t *os, dmu_object_type_t ot, int blocksize,
dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx)
{
uint64_t object;
uint64_t L1_dnode_count = DNODES_PER_BLOCK <<
(DMU_META_DNODE(os)->dn_indblkshift - SPA_BLKPTRSHIFT);
dnode_t *dn = NULL;
mutex_enter(&os->os_obj_lock);
for (;;) {
object = os->os_obj_next;
/*
* Each time we polish off a L1 bp worth of dnodes (2^12
* objects), move to another L1 bp that's still reasonably
* sparse (at most 1/4 full). Look from the beginning at most
* once per txg, but after that keep looking from here.
* os_scan_dnodes is set during txg sync if enough objects
* have been freed since the previous rescan to justify
* backfilling again. If we can't find a suitable block, just
* keep going from here.
*
* Note that dmu_traverse depends on the behavior that we use
* multiple blocks of the dnode object before going back to
* reuse objects. Any change to this algorithm should preserve
* that property or find another solution to the issues
* described in traverse_visitbp.
*/
if (P2PHASE(object, L1_dnode_count) == 0) {
uint64_t offset;
int error;
if (os->os_rescan_dnodes) {
offset = 0;
os->os_rescan_dnodes = B_FALSE;
} else {
offset = object << DNODE_SHIFT;
}
error = dnode_next_offset(DMU_META_DNODE(os),
DNODE_FIND_HOLE,
&offset, 2, DNODES_PER_BLOCK >> 2, 0);
if (error == 0)
object = offset >> DNODE_SHIFT;
}
os->os_obj_next = ++object;
/*
* XXX We should check for an i/o error here and return
* up to our caller. Actually we should pre-read it in
* dmu_tx_assign(), but there is currently no mechanism
* to do so.
*/
(void) dnode_hold_impl(os, object, DNODE_MUST_BE_FREE,
FTAG, &dn);
if (dn)
break;
if (dmu_object_next(os, &object, B_TRUE, 0) == 0)
os->os_obj_next = object - 1;
}
dnode_allocate(dn, ot, blocksize, 0, bonustype, bonuslen, tx);
dnode_rele(dn, FTAG);
mutex_exit(&os->os_obj_lock);
dmu_tx_add_new_object(tx, os, object);
return (object);
}
int
dmu_object_claim(objset_t *os, uint64_t object, dmu_object_type_t ot,
int blocksize, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx)
{
dnode_t *dn;
int err;
if (object == DMU_META_DNODE_OBJECT && !dmu_tx_private_ok(tx))
return (SET_ERROR(EBADF));
err = dnode_hold_impl(os, object, DNODE_MUST_BE_FREE, FTAG, &dn);
if (err)
return (err);
dnode_allocate(dn, ot, blocksize, 0, bonustype, bonuslen, tx);
dnode_rele(dn, FTAG);
dmu_tx_add_new_object(tx, os, object);
return (0);
}
int
dmu_object_reclaim(objset_t *os, uint64_t object, dmu_object_type_t ot,
int blocksize, dmu_object_type_t bonustype, int bonuslen, dmu_tx_t *tx)
{
dnode_t *dn;
int err;
if (object == DMU_META_DNODE_OBJECT)
return (SET_ERROR(EBADF));
err = dnode_hold_impl(os, object, DNODE_MUST_BE_ALLOCATED,
FTAG, &dn);
if (err)
return (err);
dnode_reallocate(dn, ot, blocksize, bonustype, bonuslen, tx);
dnode_rele(dn, FTAG);
return (err);
}
int
dmu_object_free(objset_t *os, uint64_t object, dmu_tx_t *tx)
{
dnode_t *dn;
int err;
ASSERT(object != DMU_META_DNODE_OBJECT || dmu_tx_private_ok(tx));
err = dnode_hold_impl(os, object, DNODE_MUST_BE_ALLOCATED,
FTAG, &dn);
if (err)
return (err);
ASSERT(dn->dn_type != DMU_OT_NONE);
dnode_free_range(dn, 0, DMU_OBJECT_END, tx);
dnode_free(dn, tx);
dnode_rele(dn, FTAG);
return (0);
}
/*
* Return (in *objectp) the next object which is allocated (or a hole)
* after *object, taking into account only objects that may have been modified
* after the specified txg.
*/
int
dmu_object_next(objset_t *os, uint64_t *objectp, boolean_t hole, uint64_t txg)
{
uint64_t offset = (*objectp + 1) << DNODE_SHIFT;
int error;
error = dnode_next_offset(DMU_META_DNODE(os),
(hole ? DNODE_FIND_HOLE : 0), &offset, 0, DNODES_PER_BLOCK, txg);
*objectp = offset >> DNODE_SHIFT;
return (error);
}
/*
* Turn this object from old_type into DMU_OTN_ZAP_METADATA, and bump the
* refcount on SPA_FEATURE_EXTENSIBLE_DATASET.
*
* Only for use from syncing context, on MOS objects.
*/
void
dmu_object_zapify(objset_t *mos, uint64_t object, dmu_object_type_t old_type,
dmu_tx_t *tx)
{
dnode_t *dn;
ASSERT(dmu_tx_is_syncing(tx));
VERIFY0(dnode_hold(mos, object, FTAG, &dn));
if (dn->dn_type == DMU_OTN_ZAP_METADATA) {
dnode_rele(dn, FTAG);
return;
}
ASSERT3U(dn->dn_type, ==, old_type);
ASSERT0(dn->dn_maxblkid);
dn->dn_next_type[tx->tx_txg & TXG_MASK] = dn->dn_type =
DMU_OTN_ZAP_METADATA;
dnode_setdirty(dn, tx);
dnode_rele(dn, FTAG);
mzap_create_impl(mos, object, 0, 0, tx);
spa_feature_incr(dmu_objset_spa(mos),
SPA_FEATURE_EXTENSIBLE_DATASET, tx);
}
void
dmu_object_free_zapified(objset_t *mos, uint64_t object, dmu_tx_t *tx)
{
dnode_t *dn;
dmu_object_type_t t;
ASSERT(dmu_tx_is_syncing(tx));
VERIFY0(dnode_hold(mos, object, FTAG, &dn));
t = dn->dn_type;
dnode_rele(dn, FTAG);
if (t == DMU_OTN_ZAP_METADATA) {
spa_feature_decr(dmu_objset_spa(mos),
SPA_FEATURE_EXTENSIBLE_DATASET, tx);
}
VERIFY0(dmu_object_free(mos, object, tx));
}
#if defined(_KERNEL) && defined(HAVE_SPL)
EXPORT_SYMBOL(dmu_object_alloc);
EXPORT_SYMBOL(dmu_object_claim);
EXPORT_SYMBOL(dmu_object_reclaim);
EXPORT_SYMBOL(dmu_object_free);
EXPORT_SYMBOL(dmu_object_next);
EXPORT_SYMBOL(dmu_object_zapify);
EXPORT_SYMBOL(dmu_object_free_zapified);
#endif
|
