~ubuntu-branches/debian/sid/postgresql-9.3/sid

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
346
347
348
349
350
351
352
/*-------------------------------------------------------------------------
 *
 * ragetypes_typanalyze.c
 *	  Functions for gathering statistics from range columns
 *
 * For a range type column, histograms of lower and upper bounds, and
 * the fraction of NULL and empty ranges are collected.
 *
 * Both histograms have the same length, and they are combined into a
 * single array of ranges. This has the same shape as the histogram that
 * std_typanalyze would collect, but the values are different. Each range
 * in the array is a valid range, even though the lower and upper bounds
 * come from different tuples. In theory, the standard scalar selectivity
 * functions could be used with the combined histogram.
 *
 * Portions Copyright (c) 1996-2013, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  src/backend/utils/adt/rangetypes_typanalyze.c
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include "catalog/pg_operator.h"
#include "commands/vacuum.h"
#include "utils/builtins.h"
#include "utils/rangetypes.h"

static int float8_qsort_cmp(const void *a1, const void *a2);
static int range_bound_qsort_cmp(const void *a1, const void *a2, void *arg);
static void compute_range_stats(VacAttrStats *stats,
		   AnalyzeAttrFetchFunc fetchfunc, int samplerows, double totalrows);

/*
 * range_typanalyze -- typanalyze function for range columns
 */
Datum
range_typanalyze(PG_FUNCTION_ARGS)
{
	VacAttrStats *stats = (VacAttrStats *) PG_GETARG_POINTER(0);
	TypeCacheEntry *typcache;
	Form_pg_attribute attr = stats->attr;

	/* Get information about range type */
	typcache = range_get_typcache(fcinfo, stats->attrtypid);

	if (attr->attstattarget < 0)
        attr->attstattarget = default_statistics_target;

	stats->compute_stats = compute_range_stats;
	stats->extra_data = typcache;
	/* same as in std_typanalyze */
	stats->minrows = 300 * attr->attstattarget;

	PG_RETURN_BOOL(true);
}

/*
 * Comparison function for sorting float8s, used for range lengths.
 */
static int
float8_qsort_cmp(const void *a1, const void *a2)
{
	const float8 *f1 = (const float8 *) a1;
	const float8 *f2 = (const float8 *) a2;

	if (*f1 < *f2)
		return -1;
	else if (*f1 == *f2)
		return 0;
	else
		return 1;
}

/*
 * Comparison function for sorting RangeBounds.
 */
static int
range_bound_qsort_cmp(const void *a1, const void *a2, void *arg)
{
	RangeBound *b1 = (RangeBound *)a1;
	RangeBound *b2 = (RangeBound *)a2;
	TypeCacheEntry *typcache = (TypeCacheEntry *)arg;

	return range_cmp_bounds(typcache, b1, b2);
}

/*
 * compute_range_stats() -- compute statistics for a range column
 */
static void
compute_range_stats(VacAttrStats *stats, AnalyzeAttrFetchFunc fetchfunc,
					int samplerows, double totalrows)
{
	TypeCacheEntry *typcache = (TypeCacheEntry *) stats->extra_data;
	bool		has_subdiff = OidIsValid(typcache->rng_subdiff_finfo.fn_oid);
	int			null_cnt = 0;
	int			non_null_cnt = 0;
	int			non_empty_cnt = 0;
	int			empty_cnt = 0;
	int			range_no;
	int			slot_idx;
	int			num_bins = stats->attr->attstattarget;
	int			num_hist;
	float8	   *lengths;
	RangeBound *lowers, *uppers;
	double		total_width = 0;

	/* Allocate memory to hold range bounds and lengths of the sample ranges. */
	lowers = (RangeBound *) palloc(sizeof(RangeBound) * samplerows);
	uppers = (RangeBound *) palloc(sizeof(RangeBound) * samplerows);
	lengths = (float8 *) palloc(sizeof(float8) * samplerows);

	/* Loop over the sample ranges. */
	for (range_no = 0; range_no < samplerows; range_no++)
	{
		Datum		value;
		bool		isnull,
					empty;
		RangeType  *range;
		RangeBound	lower,
					upper;
		float8		length;

		vacuum_delay_point();

		value = fetchfunc(stats, range_no, &isnull);
		if (isnull)
		{
			/* range is null, just count that */
			null_cnt++;
			continue;
		}

		/*
		 * XXX: should we ignore wide values, like std_typanalyze does, to
		 * avoid bloating the statistics table?
		 */
		total_width += VARSIZE_ANY(DatumGetPointer(value));

		/* Get range and deserialize it for further analysis. */
		range = DatumGetRangeType(value);
		range_deserialize(typcache, range, &lower, &upper, &empty);

		if (!empty)
		{
			/* Remember bounds and length for further usage in histograms */
			lowers[non_empty_cnt] = lower;
			uppers[non_empty_cnt] = upper;

			if (lower.infinite || upper.infinite)
			{
				/* Length of any kind of an infinite range is infinite */
				length = get_float8_infinity();
			}
			else if (has_subdiff)
			{
				/*
				 * For an ordinary range, use subdiff function between upper
				 * and lower bound values.
				 */
				length = DatumGetFloat8(FunctionCall2Coll(
											&typcache->rng_subdiff_finfo,
											typcache->rng_collation,
											upper.val, lower.val));
			}
			else
			{
				/* Use default value of 1.0 if no subdiff is available. */
				length = 1.0;
			}
			lengths[non_empty_cnt] = length;

			non_empty_cnt++;
		}
		else
			empty_cnt++;

		non_null_cnt++;
	}

	slot_idx = 0;

	/* We can only compute real stats if we found some non-null values. */
	if (non_null_cnt > 0)
	{
		Datum	   *bound_hist_values;
		Datum	   *length_hist_values;
		int			pos,
					posfrac,
					delta,
					deltafrac,
					i;
		MemoryContext old_cxt;
		float4	   *emptyfrac;

		stats->stats_valid = true;
		/* Do the simple null-frac and width stats */
		stats->stanullfrac = (double) null_cnt / (double) samplerows;
		stats->stawidth = total_width / (double) non_null_cnt;
		stats->stadistinct = -1.0;

		/* Must copy the target values into anl_context */
		old_cxt = MemoryContextSwitchTo(stats->anl_context);

		/*
		 * Generate a bounds histogram slot entry if there are at least two
		 * values.
		 */
		if (non_empty_cnt >= 2)
		{
			/* Sort bound values */
			qsort_arg(lowers, non_empty_cnt, sizeof(RangeBound),
					  range_bound_qsort_cmp, typcache);
			qsort_arg(uppers, non_empty_cnt, sizeof(RangeBound),
					  range_bound_qsort_cmp, typcache);

			num_hist = non_empty_cnt;
			if (num_hist > num_bins)
				num_hist = num_bins + 1;

			bound_hist_values = (Datum *) palloc(num_hist * sizeof(Datum));

			/*
			 * The object of this loop is to construct ranges from first and
			 * last entries in lowers[] and uppers[] along with evenly-spaced
			 * values in between. So the i'th value is a range of
			 * lowers[(i * (nvals - 1)) / (num_hist - 1)] and
			 * uppers[(i * (nvals - 1)) / (num_hist - 1)]. But computing that
			 * subscript directly risks integer overflow when the stats target
			 * is more than a couple thousand.  Instead we add
			 * (nvals - 1) / (num_hist - 1) to pos at each step, tracking the
			 * integral and fractional parts of the sum separately.
			 */
			delta = (non_empty_cnt - 1) / (num_hist - 1);
			deltafrac = (non_empty_cnt - 1) % (num_hist - 1);
			pos = posfrac = 0;

			for (i = 0; i < num_hist; i++)
			{
				bound_hist_values[i] = PointerGetDatum(range_serialize(
								typcache, &lowers[pos], &uppers[pos], false));
				pos += delta;
				posfrac += deltafrac;
				if (posfrac >= (num_hist - 1))
				{
					/* fractional part exceeds 1, carry to integer part */
					pos++;
					posfrac -= (num_hist - 1);
				}
			}

			stats->stakind[slot_idx] = STATISTIC_KIND_BOUNDS_HISTOGRAM;
			stats->stavalues[slot_idx] = bound_hist_values;
			stats->numvalues[slot_idx] = num_hist;
			slot_idx++;
		}

		/*
		 * Generate a length histogram slot entry if there are at least two
		 * values.
		 */
		if (non_empty_cnt >= 2)
		{
			/*
			 * Ascending sort of range lengths for further filling of
			 * histogram
			 */
			qsort(lengths, non_empty_cnt, sizeof(float8), float8_qsort_cmp);

			num_hist = non_empty_cnt;
			if (num_hist > num_bins)
				num_hist = num_bins + 1;

			length_hist_values = (Datum *) palloc(num_hist * sizeof(Datum));

			/*
			 * The object of this loop is to copy the first and last lengths[]
			 * entries along with evenly-spaced values in between. So the i'th
			 * value is lengths[(i * (nvals - 1)) / (num_hist - 1)]. But
			 * computing that subscript directly risks integer overflow when the
			 * stats target is more than a couple thousand.  Instead we add
			 * (nvals - 1) / (num_hist - 1) to pos at each step, tracking the
			 * integral and fractional parts of the sum separately.
			 */
			delta = (non_empty_cnt - 1) / (num_hist - 1);
			deltafrac = (non_empty_cnt - 1) % (num_hist - 1);
			pos = posfrac = 0;

			for (i = 0; i < num_hist; i++)
			{
				length_hist_values[i] = Float8GetDatum(lengths[pos]);
				pos += delta;
				posfrac += deltafrac;
				if (posfrac >= (num_hist - 1))
				{
					/* fractional part exceeds 1, carry to integer part */
					pos++;
					posfrac -= (num_hist - 1);
				}
			}
		}
		else
		{
			/*
			 * Even when we don't create the histogram, store an empty array
			 * to mean "no histogram". We can't just leave stavalues NULL,
			 * because get_attstatsslot() errors if you ask for stavalues, and
			 * it's NULL. We'll still store the empty fraction in stanumbers.
			 */
			length_hist_values = palloc(0);
			num_hist = 0;
		}
		stats->staop[slot_idx] = Float8LessOperator;
		stats->stavalues[slot_idx] = length_hist_values;
		stats->numvalues[slot_idx] = num_hist;
		stats->statypid[slot_idx] = FLOAT8OID;
		stats->statyplen[slot_idx] = sizeof(float8);
#ifdef USE_FLOAT8_BYVAL
		stats->statypbyval[slot_idx] = true;
#else
		stats->statypbyval[slot_idx] = false;
#endif
		stats->statypalign[slot_idx] = 'd';

		/* Store the fraction of empty ranges */
		emptyfrac = (float4 *) palloc(sizeof(float4));
		*emptyfrac = ((double) empty_cnt) / ((double) non_null_cnt);
		stats->stanumbers[slot_idx] = emptyfrac;
		stats->numnumbers[slot_idx] = 1;

		stats->stakind[slot_idx] = STATISTIC_KIND_RANGE_LENGTH_HISTOGRAM;
		slot_idx++;

		MemoryContextSwitchTo(old_cxt);
	}
	else if (null_cnt > 0)
	{
		/* We found only nulls; assume the column is entirely null */
		stats->stats_valid = true;
		stats->stanullfrac = 1.0;
		stats->stawidth = 0;		/* "unknown" */
		stats->stadistinct = 0.0;	/* "unknown" */
	}
	/*
	 * We don't need to bother cleaning up any of our temporary palloc's. The
	 * hashtable should also go away, as it used a child memory context.
	 */
}