database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-06-26 12:21:12 +03:00
Code Activity

Avoid detoast in texteq/textne/byteaeq/byteane for unequal-length strings.

Browse Source 
We can get the length of a compressed or out-of-line datum without actually
detoasting it.  If the lengths of two strings are unequal, we can then
conclude they are unequal without detoasting.  That saves considerable work
in an admittedly less-common case, without costing anything much when the
optimization doesn't apply.

Noah Misch
This commit is contained in:
Tom Lane
2011-01-18 14:09:22 -05:00
parent 6e1726d082
commit 1b393f4e5d
1 changed files with 75 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

116
src/backend/utils/adt/varlena.c
View File

@ -1451,22 +1451,34 @@ text_cmp(text *arg1, text *arg2)
Datum Datum
texteq(PG_FUNCTION_ARGS) texteq(PG_FUNCTION_ARGS)
{ {
text *arg1 = PG_GETARG_TEXT_PP(0); Datum arg1 = PG_GETARG_DATUM(0);
text *arg2 = PG_GETARG_TEXT_PP(1); Datum arg2 = PG_GETARG_DATUM(1);
bool result; bool result;
Size len1,
len2;
/* /*
* Since we only care about equality or not-equality, we can avoid all the * Since we only care about equality or not-equality, we can avoid all the
* expense of strcoll() here, and just do bitwise comparison. * expense of strcoll() here, and just do bitwise comparison. In fact,
* we don't even have to do a bitwise comparison if we can show the
* lengths of the strings are unequal; which might save us from having
* to detoast one or both values.
*/ */
if (VARSIZE_ANY_EXHDR(arg1) != VARSIZE_ANY_EXHDR(arg2)) len1 = toast_raw_datum_size(arg1);
len2 = toast_raw_datum_size(arg2);
if (len1 != len2)
result = false; result = false;
else else
result = (memcmp(VARDATA_ANY(arg1), VARDATA_ANY(arg2), {
VARSIZE_ANY_EXHDR(arg1)) == 0); text *targ1 = DatumGetTextPP(arg1);
text *targ2 = DatumGetTextPP(arg2);
PG_FREE_IF_COPY(arg1, 0); result = (memcmp(VARDATA_ANY(targ1), VARDATA_ANY(targ2),
PG_FREE_IF_COPY(arg2, 1); len1 - VARHDRSZ) == 0);
PG_FREE_IF_COPY(targ1, 0);
PG_FREE_IF_COPY(targ2, 1);
}
PG_RETURN_BOOL(result); PG_RETURN_BOOL(result);
} }
@ -1474,22 +1486,28 @@ texteq(PG_FUNCTION_ARGS)
Datum Datum
textne(PG_FUNCTION_ARGS) textne(PG_FUNCTION_ARGS)
{ {
text *arg1 = PG_GETARG_TEXT_PP(0); Datum arg1 = PG_GETARG_DATUM(0);
text *arg2 = PG_GETARG_TEXT_PP(1); Datum arg2 = PG_GETARG_DATUM(1);
bool result; bool result;
Size len1,
len2;
/* /* See comment in texteq() */
* Since we only care about equality or not-equality, we can avoid all the len1 = toast_raw_datum_size(arg1);
* expense of strcoll() here, and just do bitwise comparison. len2 = toast_raw_datum_size(arg2);
*/ if (len1 != len2)
if (VARSIZE_ANY_EXHDR(arg1) != VARSIZE_ANY_EXHDR(arg2))
result = true; result = true;
else else
result = (memcmp(VARDATA_ANY(arg1), VARDATA_ANY(arg2), {
VARSIZE_ANY_EXHDR(arg1)) != 0); text *targ1 = DatumGetTextPP(arg1);
text *targ2 = DatumGetTextPP(arg2);
PG_FREE_IF_COPY(arg1, 0); result = (memcmp(VARDATA_ANY(targ1), VARDATA_ANY(targ2),
PG_FREE_IF_COPY(arg2, 1); len1 - VARHDRSZ) != 0);
PG_FREE_IF_COPY(targ1, 0);
PG_FREE_IF_COPY(targ2, 1);
}
PG_RETURN_BOOL(result); PG_RETURN_BOOL(result);
} }
@ -2358,23 +2376,31 @@ SplitIdentifierString(char *rawstring, char separator,
Datum Datum
byteaeq(PG_FUNCTION_ARGS) byteaeq(PG_FUNCTION_ARGS)
{ {
bytea *arg1 = PG_GETARG_BYTEA_PP(0); Datum arg1 = PG_GETARG_DATUM(0);
bytea *arg2 = PG_GETARG_BYTEA_PP(1); Datum arg2 = PG_GETARG_DATUM(1);
int len1,
len2;
bool result; bool result;
Size len1,
len2;
len1 = VARSIZE_ANY_EXHDR(arg1); /*
len2 = VARSIZE_ANY_EXHDR(arg2); * We can use a fast path for unequal lengths, which might save us from
* having to detoast one or both values.
/* fast path for different-length inputs */ */
len1 = toast_raw_datum_size(arg1);
len2 = toast_raw_datum_size(arg2);
if (len1 != len2) if (len1 != len2)
result = false; result = false;
else else
result = (memcmp(VARDATA_ANY(arg1), VARDATA_ANY(arg2), len1) == 0); {
bytea *barg1 = DatumGetByteaPP(arg1);
bytea *barg2 = DatumGetByteaPP(arg2);
PG_FREE_IF_COPY(arg1, 0); result = (memcmp(VARDATA_ANY(barg1), VARDATA_ANY(barg2),
PG_FREE_IF_COPY(arg2, 1); len1 - VARHDRSZ) == 0);
PG_FREE_IF_COPY(barg1, 0);
PG_FREE_IF_COPY(barg2, 1);
}
PG_RETURN_BOOL(result); PG_RETURN_BOOL(result);
} }
@ -2382,23 +2408,31 @@ byteaeq(PG_FUNCTION_ARGS)
Datum Datum
byteane(PG_FUNCTION_ARGS) byteane(PG_FUNCTION_ARGS)
{ {
bytea *arg1 = PG_GETARG_BYTEA_PP(0); Datum arg1 = PG_GETARG_DATUM(0);
bytea *arg2 = PG_GETARG_BYTEA_PP(1); Datum arg2 = PG_GETARG_DATUM(1);
int len1,
len2;
bool result; bool result;
Size len1,
len2;
len1 = VARSIZE_ANY_EXHDR(arg1); /*
len2 = VARSIZE_ANY_EXHDR(arg2); * We can use a fast path for unequal lengths, which might save us from
* having to detoast one or both values.
/* fast path for different-length inputs */ */
len1 = toast_raw_datum_size(arg1);
len2 = toast_raw_datum_size(arg2);
if (len1 != len2) if (len1 != len2)
result = true; result = true;
else else
result = (memcmp(VARDATA_ANY(arg1), VARDATA_ANY(arg2), len1) != 0); {
bytea *barg1 = DatumGetByteaPP(arg1);
bytea *barg2 = DatumGetByteaPP(arg2);
PG_FREE_IF_COPY(arg1, 0); result = (memcmp(VARDATA_ANY(barg1), VARDATA_ANY(barg2),
PG_FREE_IF_COPY(arg2, 1); len1 - VARHDRSZ) != 0);
PG_FREE_IF_COPY(barg1, 0);
PG_FREE_IF_COPY(barg2, 1);
}
PG_RETURN_BOOL(result); PG_RETURN_BOOL(result);
} }