Improve the performance of LIKE/regex estimation in non-C locales, by making

make_greater_string() try harder to generate a string that's actually greater
than its input string.  Before we just assumed that making a string that was
memcmp-greater was enough, but it is easy to generate examples where this is
not so when the locale is not C.  Instead, loop until the relevant comparison
function agrees that the generated string is greater than the input.

Unfortunately this is probably not enough to guarantee that the generated
string is greater than all extensions of the input, so we cannot relax the
restriction to C locale for the LIKE/regex index optimization.  But it should
at least improve the odds of getting a useful selectivity estimate in
prefix_selectivity().  Per example from Guillaume Smet.

Backpatch to 8.1, mainly because that's what the complainant is using...

diff --git a/src/backend/optimizer/path/indxpath.c b/src/backend/optimizer/path/indxpath.c
index a20e5603653444a07b2616d805accbf4b757d2ac..c14b141e7c139926e4df0e9c4b3ec97b5f349a1f 100644 (file)
--- a/src/backend/optimizer/path/indxpath.c
+++ b/src/backend/optimizer/path/indxpath.c
@@ -2668,6 +2668,7 @@ prefix_quals(Node *leftop, Oid opfamily,
        Oid                     datatype;
        Oid                     oproid;
        Expr       *expr;
+       FmgrInfo        ltproc;
        Const      *greaterstr;
 
        Assert(pstatus != Pattern_Prefix_None);
@@ -2759,13 +2760,14 @@ prefix_quals(Node *leftop, Oid opfamily,
         * "x < greaterstr".
         *-------
         */
-       greaterstr = make_greater_string(prefix_const);
+       oproid = get_opfamily_member(opfamily, datatype, datatype,
+                                                                BTLessStrategyNumber);
+       if (oproid == InvalidOid)
+               elog(ERROR, "no < operator for opfamily %u", opfamily);
+       fmgr_info(get_opcode(oproid), &ltproc);
+       greaterstr = make_greater_string(prefix_const, &ltproc);
        if (greaterstr)
        {
-               oproid = get_opfamily_member(opfamily, datatype, datatype,
-                                                                        BTLessStrategyNumber);
-               if (oproid == InvalidOid)
-                       elog(ERROR, "no < operator for opfamily %u", opfamily);
                expr = make_opclause(oproid, BOOLOID, false,
                                                         (Expr *) leftop, (Expr *) greaterstr);
                result = lappend(result,

diff --git a/src/backend/utils/adt/selfuncs.c b/src/backend/utils/adt/selfuncs.c
index 0bac71bd0b4082dd06b59d3bc912c00e32dc8865..409e6d1379ebcc42dedd327d5a2ffdf3bbeafbb3 100644 (file)
--- a/src/backend/utils/adt/selfuncs.c
+++ b/src/backend/utils/adt/selfuncs.c
@@ -4302,17 +4302,17 @@ prefix_selectivity(VariableStatData *vardata,
         *      "x < greaterstr".
         *-------
         */
-       greaterstrcon = make_greater_string(prefixcon);
+       cmpopr = get_opfamily_member(opfamily, vartype, vartype,
+                                                                BTLessStrategyNumber);
+       if (cmpopr == InvalidOid)
+               elog(ERROR, "no < operator for opfamily %u", opfamily);
+       fmgr_info(get_opcode(cmpopr), &opproc);
+
+       greaterstrcon = make_greater_string(prefixcon, &opproc);
        if (greaterstrcon)
        {
                Selectivity topsel;
 
-               cmpopr = get_opfamily_member(opfamily, vartype, vartype,
-                                                                        BTLessStrategyNumber);
-               if (cmpopr == InvalidOid)
-                       elog(ERROR, "no < operator for opfamily %u", opfamily);
-               fmgr_info(get_opcode(cmpopr), &opproc);
-
                topsel = ineq_histogram_selectivity(vardata, &opproc, false,
                                                                                        greaterstrcon->constvalue,
                                                                                        greaterstrcon->consttype);
@@ -4589,8 +4589,17 @@ pattern_selectivity(Const *patt, Pattern_Type ptype)
  * in the form of a Const pointer; else return NULL.
  *
  * The key requirement here is that given a prefix string, say "foo",
- * we must be able to generate another string "fop" that is greater
- * than all strings "foobar" starting with "foo".
+ * we must be able to generate another string "fop" that is greater than
+ * all strings "foobar" starting with "foo".  We can test that we have
+ * generated a string greater than the prefix string, but in non-C locales
+ * that is not a bulletproof guarantee that an extension of the string might
+ * not sort after it; an example is that "foo " is less than "foo!", but it
+ * is not clear that a "dictionary" sort ordering will consider "foo!" less
+ * than "foo bar".  Therefore, this function should be used only for
+ * estimation purposes when working in a non-C locale.
+ *
+ * The caller must provide the appropriate "less than" comparison function
+ * for testing the strings.
  *
  * If we max out the righthand byte, truncate off the last character
  * and start incrementing the next.  For example, if "z" were the last
@@ -4599,20 +4608,15 @@ pattern_selectivity(Const *patt, Pattern_Type ptype)
  *
  * This could be rather slow in the worst case, but in most cases we
  * won't have to try more than one or two strings before succeeding.
- *
- * NOTE: at present this assumes we are in the C locale, so that simple
- * bytewise comparison applies.  However, we might be in a multibyte
- * encoding such as UTF8, so we do have to watch out for generating
- * invalid encoding sequences.
  */
 Const *
-make_greater_string(const Const *str_const)
+make_greater_string(const Const *str_const, FmgrInfo *ltproc)
 {
        Oid                     datatype = str_const->consttype;
        char       *workstr;
        int                     len;
 
-       /* Get the string and a modifiable copy */
+       /* Get a modifiable copy of the string in C-string format */
        if (datatype == NAMEOID)
        {
                workstr = DatumGetCString(DirectFunctionCall1(nameout,
@@ -4660,8 +4664,18 @@ make_greater_string(const Const *str_const)
                        else
                                workstr_const = string_to_bytea_const(workstr, len);
 
-                       pfree(workstr);
-                       return workstr_const;
+                       if (DatumGetBool(FunctionCall2(ltproc,
+                                                                                  str_const->constvalue,
+                                                                                  workstr_const->constvalue)))
+                       {
+                               /* Successfully made a string larger than the input */
+                               pfree(workstr);
+                               return workstr_const;
+                       }
+
+                       /* No good, release unusable value and try again */
+                       pfree(DatumGetPointer(workstr_const->constvalue));
+                       pfree(workstr_const);
                }
 
                /* restore last byte so we don't confuse pg_mbcliplen */

diff --git a/src/include/utils/selfuncs.h b/src/include/utils/selfuncs.h
index 42264af5cc09f97f6ecec5e31f8292ed1c210954..8e3c559308201a3439c7392971e20eb41edcfa5a 100644 (file)
--- a/src/include/utils/selfuncs.h
+++ b/src/include/utils/selfuncs.h
@@ -118,7 +118,7 @@ extern Pattern_Prefix_Status pattern_fixed_prefix(Const *patt,
                                         Pattern_Type ptype,
                                         Const **prefix,
                                         Const **rest);
-extern Const *make_greater_string(const Const *str_const);
+extern Const *make_greater_string(const Const *str_const, FmgrInfo *ltproc);
 
 extern Datum eqsel(PG_FUNCTION_ARGS);
 extern Datum neqsel(PG_FUNCTION_ARGS);