From 3350b3740e5960da294384ba9c1806f13b72ba6f Mon Sep 17 00:00:00 2001 From: Neil Conway Date: Wed, 23 Feb 2005 22:46:17 +0000 Subject: [PATCH] This patch optimizes the md5_text() function (which is used to implement the md5() SQL-level function). The old code did the following: 1. de-toast the datum 2. convert it to a cstring via textout() 3. get the length of the cstring via strlen() Since we are treating the datum context as a blob of binary data, the latter two steps are unnecessary. Once the data has been detoasted, we can just use it as-is, and derive its length from the varlena metadata. This patch improves some run-of-the-mill md5() computations by just under 10% in my limited tests, and passes the regression tests. I also noticed that md5_text() wasn't checking the return value of md5_hash(); encountering OOM at precisely the right moment could result in returning a random md5 hash. This patch corrects that. A better fix would be to make md5_hash() only return on success (and/or allocate via palloc()), but since it's used in the frontend as well I don't see an easy way to do that. --- src/backend/libpq/md5.c | 6 +++--- src/backend/utils/adt/varlena.c | 14 ++++++++++---- 2 files changed, 13 insertions(+), 7 deletions(-) diff --git a/src/backend/libpq/md5.c b/src/backend/libpq/md5.c index 16649abe24..3c7fcd6912 100644 --- a/src/backend/libpq/md5.c +++ b/src/backend/libpq/md5.c @@ -14,7 +14,7 @@ * Portions Copyright (c) 1994, Regents of the University of California * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/libpq/md5.c,v 1.27 2004/12/31 21:59:50 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/libpq/md5.c,v 1.28 2005/02/23 22:46:17 neilc Exp $ */ @@ -289,8 +289,8 @@ bytesToHex(uint8 b[16], char *s) * characters. you thus need to provide an array * of 33 characters, including the trailing '\0'. * - * RETURNS 0 on failure (out of memory for internal buffers) or - * non-zero on success. + * RETURNS false on failure (out of memory for internal buffers) or + * true on success. * * STANDARDS MD5 is described in RFC 1321. * diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c index a2570a66bb..26fcab20d3 100644 --- a/src/backend/utils/adt/varlena.c +++ b/src/backend/utils/adt/varlena.c @@ -8,7 +8,7 @@ * * * IDENTIFICATION - * $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.118 2004/12/31 22:01:22 pgsql Exp $ + * $PostgreSQL: pgsql/src/backend/utils/adt/varlena.c,v 1.119 2005/02/23 22:46:17 neilc Exp $ * *------------------------------------------------------------------------- */ @@ -2310,16 +2310,22 @@ to_hex64(PG_FUNCTION_ARGS) Datum md5_text(PG_FUNCTION_ARGS) { - char *buff = PG_TEXT_GET_STR(PG_GETARG_TEXT_P(0)); - size_t len = strlen(buff); + text *in_text = PG_GETARG_TEXT_P(0); + size_t len; char *hexsum; text *result_text; + /* Calculate the length of the buffer using varlena metadata */ + len = VARSIZE(in_text) - VARHDRSZ; + /* leave room for the terminating '\0' */ hexsum = (char *) palloc(MD5_HASH_LEN + 1); /* get the hash result */ - md5_hash((void *) buff, len, hexsum); + if (md5_hash(VARDATA(in_text), len, hexsum) == false) + ereport(ERROR, + (errcode(ERRCODE_OUT_OF_MEMORY), + errmsg("out of memory"))); /* convert to text and return it */ result_text = PG_STR_GET_TEXT(hexsum);