summaryrefslogtreecommitdiffstats
path: root/src/include/storage/buf_internals.h
blob: dbb0aef4c59fc91923bb289c83172cb855aa40b7 (plain)
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
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
/*-------------------------------------------------------------------------
 *
 * buf_internals.h
 *	  Internal definitions for buffer manager and the buffer replacement
 *	  strategy.
 *
 *
 * Portions Copyright (c) 1996-2022, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * src/include/storage/buf_internals.h
 *
 *-------------------------------------------------------------------------
 */
#ifndef BUFMGR_INTERNALS_H
#define BUFMGR_INTERNALS_H

#include "port/atomics.h"
#include "storage/buf.h"
#include "storage/bufmgr.h"
#include "storage/condition_variable.h"
#include "storage/latch.h"
#include "storage/lwlock.h"
#include "storage/shmem.h"
#include "storage/smgr.h"
#include "storage/spin.h"
#include "utils/relcache.h"

/*
 * Buffer state is a single 32-bit variable where following data is combined.
 *
 * - 18 bits refcount
 * - 4 bits usage count
 * - 10 bits of flags
 *
 * Combining these values allows to perform some operations without locking
 * the buffer header, by modifying them together with a CAS loop.
 *
 * The definition of buffer state components is below.
 */
#define BUF_REFCOUNT_ONE 1
#define BUF_REFCOUNT_MASK ((1U << 18) - 1)
#define BUF_USAGECOUNT_MASK 0x003C0000U
#define BUF_USAGECOUNT_ONE (1U << 18)
#define BUF_USAGECOUNT_SHIFT 18
#define BUF_FLAG_MASK 0xFFC00000U

/* Get refcount and usagecount from buffer state */
#define BUF_STATE_GET_REFCOUNT(state) ((state) & BUF_REFCOUNT_MASK)
#define BUF_STATE_GET_USAGECOUNT(state) (((state) & BUF_USAGECOUNT_MASK) >> BUF_USAGECOUNT_SHIFT)

/*
 * Flags for buffer descriptors
 *
 * Note: BM_TAG_VALID essentially means that there is a buffer hashtable
 * entry associated with the buffer's tag.
 */
#define BM_LOCKED				(1U << 22)	/* buffer header is locked */
#define BM_DIRTY				(1U << 23)	/* data needs writing */
#define BM_VALID				(1U << 24)	/* data is valid */
#define BM_TAG_VALID			(1U << 25)	/* tag is assigned */
#define BM_IO_IN_PROGRESS		(1U << 26)	/* read or write in progress */
#define BM_IO_ERROR				(1U << 27)	/* previous I/O failed */
#define BM_JUST_DIRTIED			(1U << 28)	/* dirtied since write started */
#define BM_PIN_COUNT_WAITER		(1U << 29)	/* have waiter for sole pin */
#define BM_CHECKPOINT_NEEDED	(1U << 30)	/* must write for checkpoint */
#define BM_PERMANENT			(1U << 31)	/* permanent buffer (not unlogged,
											 * or init fork) */
/*
 * The maximum allowed value of usage_count represents a tradeoff between
 * accuracy and speed of the clock-sweep buffer management algorithm.  A
 * large value (comparable to NBuffers) would approximate LRU semantics.
 * But it can take as many as BM_MAX_USAGE_COUNT+1 complete cycles of
 * clock sweeps to find a free buffer, so in practice we don't want the
 * value to be very large.
 */
#define BM_MAX_USAGE_COUNT	5

/*
 * Buffer tag identifies which disk block the buffer contains.
 *
 * Note: the BufferTag data must be sufficient to determine where to write the
 * block, without reference to pg_class or pg_tablespace entries.  It's
 * possible that the backend flushing the buffer doesn't even believe the
 * relation is visible yet (its xact may have started before the xact that
 * created the rel).  The storage manager must be able to cope anyway.
 *
 * Note: if there's any pad bytes in the struct, INIT_BUFFERTAG will have
 * to be fixed to zero them, since this struct is used as a hash key.
 */
typedef struct buftag
{
	RelFileNode rnode;			/* physical relation identifier */
	ForkNumber	forkNum;
	BlockNumber blockNum;		/* blknum relative to begin of reln */
} BufferTag;

#define CLEAR_BUFFERTAG(a) \
( \
	(a).rnode.spcNode = InvalidOid, \
	(a).rnode.dbNode = InvalidOid, \
	(a).rnode.relNode = InvalidOid, \
	(a).forkNum = InvalidForkNumber, \
	(a).blockNum = InvalidBlockNumber \
)

#define INIT_BUFFERTAG(a,xx_rnode,xx_forkNum,xx_blockNum) \
( \
	(a).rnode = (xx_rnode), \
	(a).forkNum = (xx_forkNum), \
	(a).blockNum = (xx_blockNum) \
)

#define BUFFERTAGS_EQUAL(a,b) \
( \
	RelFileNodeEquals((a).rnode, (b).rnode) && \
	(a).blockNum == (b).blockNum && \
	(a).forkNum == (b).forkNum \
)

/*
 * The shared buffer mapping table is partitioned to reduce contention.
 * To determine which partition lock a given tag requires, compute the tag's
 * hash code with BufTableHashCode(), then apply BufMappingPartitionLock().
 * NB: NUM_BUFFER_PARTITIONS must be a power of 2!
 */
#define BufTableHashPartition(hashcode) \
	((hashcode) % NUM_BUFFER_PARTITIONS)
#define BufMappingPartitionLock(hashcode) \
	(&MainLWLockArray[BUFFER_MAPPING_LWLOCK_OFFSET + \
		BufTableHashPartition(hashcode)].lock)
#define BufMappingPartitionLockByIndex(i) \
	(&MainLWLockArray[BUFFER_MAPPING_LWLOCK_OFFSET + (i)].lock)

/*
 *	BufferDesc -- shared descriptor/state data for a single shared buffer.
 *
 * Note: Buffer header lock (BM_LOCKED flag) must be held to examine or change
 * tag, state or wait_backend_pgprocno fields.  In general, buffer header lock
 * is a spinlock which is combined with flags, refcount and usagecount into
 * single atomic variable.  This layout allow us to do some operations in a
 * single atomic operation, without actually acquiring and releasing spinlock;
 * for instance, increase or decrease refcount.  buf_id field never changes
 * after initialization, so does not need locking.  freeNext is protected by
 * the buffer_strategy_lock not buffer header lock.  The LWLock can take care
 * of itself.  The buffer header lock is *not* used to control access to the
 * data in the buffer!
 *
 * It's assumed that nobody changes the state field while buffer header lock
 * is held.  Thus buffer header lock holder can do complex updates of the
 * state variable in single write, simultaneously with lock release (cleaning
 * BM_LOCKED flag).  On the other hand, updating of state without holding
 * buffer header lock is restricted to CAS, which ensures that BM_LOCKED flag
 * is not set.  Atomic increment/decrement, OR/AND etc. are not allowed.
 *
 * An exception is that if we have the buffer pinned, its tag can't change
 * underneath us, so we can examine the tag without locking the buffer header.
 * Also, in places we do one-time reads of the flags without bothering to
 * lock the buffer header; this is generally for situations where we don't
 * expect the flag bit being tested to be changing.
 *
 * We can't physically remove items from a disk page if another backend has
 * the buffer pinned.  Hence, a backend may need to wait for all other pins
 * to go away.  This is signaled by storing its own pgprocno into
 * wait_backend_pgprocno and setting flag bit BM_PIN_COUNT_WAITER.  At present,
 * there can be only one such waiter per buffer.
 *
 * We use this same struct for local buffer headers, but the locks are not
 * used and not all of the flag bits are useful either. To avoid unnecessary
 * overhead, manipulations of the state field should be done without actual
 * atomic operations (i.e. only pg_atomic_read_u32() and
 * pg_atomic_unlocked_write_u32()).
 *
 * Be careful to avoid increasing the size of the struct when adding or
 * reordering members.  Keeping it below 64 bytes (the most common CPU
 * cache line size) is fairly important for performance.
 *
 * Per-buffer I/O condition variables are currently kept outside this struct in
 * a separate array.  They could be moved in here and still fit within that
 * limit on common systems, but for now that is not done.
 */
typedef struct BufferDesc
{
	BufferTag	tag;			/* ID of page contained in buffer */
	int			buf_id;			/* buffer's index number (from 0) */

	/* state of the tag, containing flags, refcount and usagecount */
	pg_atomic_uint32 state;

	int			wait_backend_pgprocno;	/* backend of pin-count waiter */
	int			freeNext;		/* link in freelist chain */
	LWLock		content_lock;	/* to lock access to buffer contents */
} BufferDesc;

/*
 * Concurrent access to buffer headers has proven to be more efficient if
 * they're cache line aligned. So we force the start of the BufferDescriptors
 * array to be on a cache line boundary and force the elements to be cache
 * line sized.
 *
 * XXX: As this is primarily matters in highly concurrent workloads which
 * probably all are 64bit these days, and the space wastage would be a bit
 * more noticeable on 32bit systems, we don't force the stride to be cache
 * line sized on those. If somebody does actual performance testing, we can
 * reevaluate.
 *
 * Note that local buffer descriptors aren't forced to be aligned - as there's
 * no concurrent access to those it's unlikely to be beneficial.
 *
 * We use a 64-byte cache line size here, because that's the most common
 * size. Making it bigger would be a waste of memory. Even if running on a
 * platform with either 32 or 128 byte line sizes, it's good to align to
 * boundaries and avoid false sharing.
 */
#define BUFFERDESC_PAD_TO_SIZE	(SIZEOF_VOID_P == 8 ? 64 : 1)

typedef union BufferDescPadded
{
	BufferDesc	bufferdesc;
	char		pad[BUFFERDESC_PAD_TO_SIZE];
} BufferDescPadded;

#define GetBufferDescriptor(id) (&BufferDescriptors[(id)].bufferdesc)
#define GetLocalBufferDescriptor(id) (&LocalBufferDescriptors[(id)])

#define BufferDescriptorGetBuffer(bdesc) ((bdesc)->buf_id + 1)

#define BufferDescriptorGetIOCV(bdesc) \
	(&(BufferIOCVArray[(bdesc)->buf_id]).cv)
#define BufferDescriptorGetContentLock(bdesc) \
	((LWLock*) (&(bdesc)->content_lock))

extern PGDLLIMPORT ConditionVariableMinimallyPadded *BufferIOCVArray;

/*
 * The freeNext field is either the index of the next freelist entry,
 * or one of these special values:
 */
#define FREENEXT_END_OF_LIST	(-1)
#define FREENEXT_NOT_IN_LIST	(-2)

/*
 * Functions for acquiring/releasing a shared buffer header's spinlock.  Do
 * not apply these to local buffers!
 */
extern uint32 LockBufHdr(BufferDesc *desc);
#define UnlockBufHdr(desc, s)	\
	do {	\
		pg_write_barrier(); \
		pg_atomic_write_u32(&(desc)->state, (s) & (~BM_LOCKED)); \
	} while (0)


/*
 * The PendingWriteback & WritebackContext structure are used to keep
 * information about pending flush requests to be issued to the OS.
 */
typedef struct PendingWriteback
{
	/* could store different types of pending flushes here */
	BufferTag	tag;
} PendingWriteback;

/* struct forward declared in bufmgr.h */
typedef struct WritebackContext
{
	/* pointer to the max number of writeback requests to coalesce */
	int		   *max_pending;

	/* current number of pending writeback requests */
	int			nr_pending;

	/* pending requests */
	PendingWriteback pending_writebacks[WRITEBACK_MAX_PENDING_FLUSHES];
} WritebackContext;

/* in buf_init.c */
extern PGDLLIMPORT BufferDescPadded *BufferDescriptors;
extern PGDLLIMPORT WritebackContext BackendWritebackContext;

/* in localbuf.c */
extern PGDLLIMPORT BufferDesc *LocalBufferDescriptors;

/* in bufmgr.c */

/*
 * Structure to sort buffers per file on checkpoints.
 *
 * This structure is allocated per buffer in shared memory, so it should be
 * kept as small as possible.
 */
typedef struct CkptSortItem
{
	Oid			tsId;
	Oid			relNode;
	ForkNumber	forkNum;
	BlockNumber blockNum;
	int			buf_id;
} CkptSortItem;

extern PGDLLIMPORT CkptSortItem *CkptBufferIds;

/*
 * Internal buffer management routines
 */
/* bufmgr.c */
extern void WritebackContextInit(WritebackContext *context, int *max_pending);
extern void IssuePendingWritebacks(WritebackContext *context);
extern void ScheduleBufferTagForWriteback(WritebackContext *context, BufferTag *tag);

/* freelist.c */
extern BufferDesc *StrategyGetBuffer(BufferAccessStrategy strategy,
									 uint32 *buf_state);
extern void StrategyFreeBuffer(BufferDesc *buf);
extern bool StrategyRejectBuffer(BufferAccessStrategy strategy,
								 BufferDesc *buf);

extern int	StrategySyncStart(uint32 *complete_passes, uint32 *num_buf_alloc);
extern void StrategyNotifyBgWriter(int bgwprocno);

extern Size StrategyShmemSize(void);
extern void StrategyInitialize(bool init);
extern bool have_free_buffer(void);

/* buf_table.c */
extern Size BufTableShmemSize(int size);
extern void InitBufTable(int size);
extern uint32 BufTableHashCode(BufferTag *tagPtr);
extern int	BufTableLookup(BufferTag *tagPtr, uint32 hashcode);
extern int	BufTableInsert(BufferTag *tagPtr, uint32 hashcode, int buf_id);
extern void BufTableDelete(BufferTag *tagPtr, uint32 hashcode);

/* localbuf.c */
extern PrefetchBufferResult PrefetchLocalBuffer(SMgrRelation smgr,
												ForkNumber forkNum,
												BlockNumber blockNum);
extern BufferDesc *LocalBufferAlloc(SMgrRelation smgr, ForkNumber forkNum,
									BlockNumber blockNum, bool *foundPtr);
extern void MarkLocalBufferDirty(Buffer buffer);
extern void DropRelFileNodeLocalBuffers(RelFileNode rnode, ForkNumber forkNum,
										BlockNumber firstDelBlock);
extern void DropRelFileNodeAllLocalBuffers(RelFileNode rnode);
extern void AtEOXact_LocalBuffers(bool isCommit);

#endif							/* BUFMGR_INTERNALS_H */