diff options
Diffstat (limited to 'src/backend/commands')
| -rw-r--r-- | src/backend/commands/analyze.c | 6 | ||||
| -rw-r--r-- | src/backend/commands/tablecmds.c | 4 |
2 files changed, 5 insertions, 5 deletions
diff --git a/src/backend/commands/analyze.c b/src/backend/commands/analyze.c index 8536332030..e066c59278 100644 --- a/src/backend/commands/analyze.c +++ b/src/backend/commands/analyze.c @@ -67,7 +67,7 @@ typedef struct AnlIndexData /* Default statistics target (GUC parameter) */ -int default_statistics_target = 10; +int default_statistics_target = 100; /* A few variables that don't seem worth passing around as parameters */ static int elevel = -1; @@ -1531,10 +1531,10 @@ std_typanalyze(VacAttrStats *stats) * error in bin size f, and error probability gamma, the minimum * random sample size is * r = 4 * k * ln(2*n/gamma) / f^2 - * Taking f = 0.5, gamma = 0.01, n = 1 million rows, we obtain + * Taking f = 0.5, gamma = 0.01, n = 10^6 rows, we obtain * r = 305.82 * k * Note that because of the log function, the dependence on n is - * quite weak; even at n = 1 billion, a 300*k sample gives <= 0.59 + * quite weak; even at n = 10^12, a 300*k sample gives <= 0.66 * bin size error with probability 0.99. So there's no real need to * scale for n, which is a good thing because we don't necessarily * know it at this point. diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c index dcf85637af..8b276ae7fc 100644 --- a/src/backend/commands/tablecmds.c +++ b/src/backend/commands/tablecmds.c @@ -3942,9 +3942,9 @@ ATExecSetStatistics(Relation rel, const char *colName, Node *newValue) errmsg("statistics target %d is too low", newtarget))); } - else if (newtarget > 1000) + else if (newtarget > 10000) { - newtarget = 1000; + newtarget = 10000; ereport(WARNING, (errcode(ERRCODE_INVALID_PARAMETER_VALUE), errmsg("lowering statistics target to %d", |