diff options
Diffstat (limited to 'src/backend/commands/analyze.c')
| -rw-r--r-- | src/backend/commands/analyze.c | 46 |
1 files changed, 23 insertions, 23 deletions
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 5f9674699e2..38560d11273 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -408,7 +408,7 @@ do_analyze_rel(Relation onerel, VacuumStmt *vacstmt, /* * Open all indexes of the relation, and see if there are any analyzable - * columns in the indexes. We do not analyze index columns if there was + * columns in the indexes. We do not analyze index columns if there was * an explicit column list in the ANALYZE command, however. If we are * doing a recursive scan, we don't want to touch the parent's indexes at * all. @@ -465,7 +465,7 @@ do_analyze_rel(Relation onerel, VacuumStmt *vacstmt, /* * Determine how many rows we need to sample, using the worst case from - * all analyzable columns. We use a lower bound of 100 rows to avoid + * all analyzable columns. We use a lower bound of 100 rows to avoid * possible overflow in Vitter's algorithm. (Note: that will also be the * target in the corner case where there are no analyzable columns.) */ @@ -500,7 +500,7 @@ do_analyze_rel(Relation onerel, VacuumStmt *vacstmt, &totalrows, &totaldeadrows); /* - * Compute the statistics. Temporary results during the calculations for + * Compute the statistics. Temporary results during the calculations for * each column are stored in a child context. The calc routines are * responsible to make sure that whatever they store into the VacAttrStats * structure is allocated in anl_context. @@ -557,7 +557,7 @@ do_analyze_rel(Relation onerel, VacuumStmt *vacstmt, /* * Emit the completed stats rows into pg_statistic, replacing any - * previous statistics for the target columns. (If there are stats in + * previous statistics for the target columns. (If there are stats in * pg_statistic for columns we didn't process, we leave them alone.) */ update_attstats(RelationGetRelid(onerel), inh, @@ -609,7 +609,7 @@ do_analyze_rel(Relation onerel, VacuumStmt *vacstmt, } /* - * Report ANALYZE to the stats collector, too. However, if doing + * Report ANALYZE to the stats collector, too. However, if doing * inherited stats we shouldn't report, because the stats collector only * tracks per-table stats. */ @@ -871,7 +871,7 @@ examine_attribute(Relation onerel, int attnum, Node *index_expr) return NULL; /* - * Create the VacAttrStats struct. Note that we only have a copy of the + * Create the VacAttrStats struct. Note that we only have a copy of the * fixed fields of the pg_attribute tuple. */ stats = (VacAttrStats *) palloc0(sizeof(VacAttrStats)); @@ -881,7 +881,7 @@ examine_attribute(Relation onerel, int attnum, Node *index_expr) /* * When analyzing an expression index, believe the expression tree's type * not the column datatype --- the latter might be the opckeytype storage - * type of the opclass, which is not interesting for our purposes. (Note: + * type of the opclass, which is not interesting for our purposes. (Note: * if we did anything with non-expression index columns, we'd need to * figure out where to get the correct type info from, but for now that's * not a problem.) It's not clear whether anyone will care about the @@ -920,7 +920,7 @@ examine_attribute(Relation onerel, int attnum, Node *index_expr) } /* - * Call the type-specific typanalyze function. If none is specified, use + * Call the type-specific typanalyze function. If none is specified, use * std_typanalyze(). */ if (OidIsValid(stats->attrtype->typanalyze)) @@ -996,7 +996,7 @@ BlockSampler_Next(BlockSampler bs) * If we are to skip, we should advance t (hence decrease K), and * repeat the same probabilistic test for the next block. The naive * implementation thus requires an anl_random_fract() call for each block - * number. But we can reduce this to one anl_random_fract() call per + * number. But we can reduce this to one anl_random_fract() call per * selected block, by noting that each time the while-test succeeds, * we can reinterpret V as a uniform random number in the range 0 to p. * Therefore, instead of choosing a new V, we just adjust p to be @@ -1126,7 +1126,7 @@ acquire_sample_rows(Relation onerel, int elevel, /* * We ignore unused and redirect line pointers. DEAD line * pointers should be counted as dead, because we need vacuum to - * run to get rid of them. Note that this rule agrees with the + * run to get rid of them. Note that this rule agrees with the * way that heap_page_prune() counts things. */ if (!ItemIdIsNormal(itemid)) @@ -1171,7 +1171,7 @@ acquire_sample_rows(Relation onerel, int elevel, * is the safer option. * * A special case is that the inserting transaction might - * be our own. In this case we should count and sample + * be our own. In this case we should count and sample * the row, to accommodate users who load a table and * analyze it in one transaction. (pgstat_report_analyze * has to adjust the numbers we send to the stats @@ -1213,7 +1213,7 @@ acquire_sample_rows(Relation onerel, int elevel, /* * The first targrows sample rows are simply copied into the * reservoir. Then we start replacing tuples in the sample - * until we reach the end of the relation. This algorithm is + * until we reach the end of the relation. This algorithm is * from Jeff Vitter's paper (see full citation below). It * works by repeatedly computing the number of tuples to skip * before selecting a tuple, which replaces a randomly chosen @@ -1272,7 +1272,7 @@ acquire_sample_rows(Relation onerel, int elevel, qsort((void *) rows, numrows, sizeof(HeapTuple), compare_rows); /* - * Estimate total numbers of rows in relation. For live rows, use + * Estimate total numbers of rows in relation. For live rows, use * vac_estimate_reltuples; for dead rows, we have no source of old * information, so we have to assume the density is the same in unseen * pages as in the pages we scanned. @@ -1595,7 +1595,7 @@ acquire_inherited_sample_rows(Relation onerel, int elevel, * Statistics are stored in several places: the pg_class row for the * relation has stats about the whole relation, and there is a * pg_statistic row for each (non-system) attribute that has ever - * been analyzed. The pg_class values are updated by VACUUM, not here. + * been analyzed. The pg_class values are updated by VACUUM, not here. * * pg_statistic rows are just added or updated normally. This means * that pg_statistic will probably contain some deleted rows at the @@ -1999,7 +1999,7 @@ compute_minimal_stats(VacAttrStatsP stats, /* * If the value is toasted, we want to detoast it just once to * avoid repeated detoastings and resultant excess memory usage - * during the comparisons. Also, check to see if the value is + * during the comparisons. Also, check to see if the value is * excessively wide, and if so don't detoast at all --- just * ignore the value. */ @@ -2119,7 +2119,7 @@ compute_minimal_stats(VacAttrStatsP stats, * We assume (not very reliably!) that all the multiply-occurring * values are reflected in the final track[] list, and the other * nonnull values all appeared but once. (XXX this usually - * results in a drastic overestimate of ndistinct. Can we do + * results in a drastic overestimate of ndistinct. Can we do * any better?) *---------- */ @@ -2156,7 +2156,7 @@ compute_minimal_stats(VacAttrStatsP stats, * Decide how many values are worth storing as most-common values. If * we are able to generate a complete MCV list (all the values in the * sample will fit, and we think these are all the ones in the table), - * then do so. Otherwise, store only those values that are + * then do so. Otherwise, store only those values that are * significantly more common than the (estimated) average. We set the * threshold rather arbitrarily at 25% more than average, with at * least 2 instances in the sample. @@ -2324,7 +2324,7 @@ compute_scalar_stats(VacAttrStatsP stats, /* * If the value is toasted, we want to detoast it just once to * avoid repeated detoastings and resultant excess memory usage - * during the comparisons. Also, check to see if the value is + * during the comparisons. Also, check to see if the value is * excessively wide, and if so don't detoast at all --- just * ignore the value. */ @@ -2369,7 +2369,7 @@ compute_scalar_stats(VacAttrStatsP stats, * accumulate ordering-correlation statistics. * * To determine which are most common, we first have to count the - * number of duplicates of each value. The duplicates are adjacent in + * number of duplicates of each value. The duplicates are adjacent in * the sorted list, so a brute-force approach is to compare successive * datum values until we find two that are not equal. However, that * requires N-1 invocations of the datum comparison routine, which are @@ -2378,7 +2378,7 @@ compute_scalar_stats(VacAttrStatsP stats, * that are adjacent in the sorted order; otherwise it could not know * that it's ordered the pair correctly.) We exploit this by having * compare_scalars remember the highest tupno index that each - * ScalarItem has been found equal to. At the end of the sort, a + * ScalarItem has been found equal to. At the end of the sort, a * ScalarItem's tupnoLink will still point to itself if and only if it * is the last item of its group of duplicates (since the group will * be ordered by tupno). @@ -2498,7 +2498,7 @@ compute_scalar_stats(VacAttrStatsP stats, * Decide how many values are worth storing as most-common values. If * we are able to generate a complete MCV list (all the values in the * sample will fit, and we think these are all the ones in the table), - * then do so. Otherwise, store only those values that are + * then do so. Otherwise, store only those values that are * significantly more common than the (estimated) average. We set the * threshold rather arbitrarily at 25% more than average, with at * least 2 instances in the sample. Also, we won't suppress values @@ -2653,7 +2653,7 @@ compute_scalar_stats(VacAttrStatsP stats, /* * The object of this loop is to copy the first and last values[] - * entries along with evenly-spaced values in between. So the + * entries along with evenly-spaced values in between. So the * i'th value is values[(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 @@ -2764,7 +2764,7 @@ compute_scalar_stats(VacAttrStatsP stats, * qsort_arg comparator for sorting ScalarItems * * Aside from sorting the items, we update the tupnoLink[] array - * whenever two ScalarItems are found to contain equal datums. The array + * whenever two ScalarItems are found to contain equal datums. The array * is indexed by tupno; for each ScalarItem, it contains the highest * tupno that that item's datum has been found to be equal to. This allows * us to avoid additional comparisons in compute_scalar_stats(). |