Fix ZSTD compression error "dst buffer too small"

When ZSTD compression is used for AO CO tables, insertion of data may cause an
error "Destination buffer is too small". This happens when compressed data is
larger than uncompressed input data.

This commit adds handling of this situation: do not change output buffer and
return size used equal to source size. The caller (e.g.,
'cdbappendonlystoragewrite.c') is able to handle such output; in this case, it
copies data from input to output itself.

configure

@@ -13158,7 +13158,7 @@ fi
 
 fi
 
-# Check for zstd.h
+# Check for zstd.h and zstd_errors.h
 if test "$with_zstd" = yes; then
   ac_fn_c_check_header_mongrel "$LINENO" "zstd.h" "ac_cv_header_zstd_h" "$ac_includes_default"
 if test "x$ac_cv_header_zstd_h" = xyes; then :
@@ -13168,6 +13168,14 @@ else
 fi
 
 
+  ac_fn_c_check_header_mongrel "$LINENO" "zstd_errors.h" "ac_cv_header_zstd_errors_h" "$ac_includes_default"
+if test "x$ac_cv_header_zstd_errors_h" = xyes; then :
+
+else
+  as_fn_error $? "header file <zstd_errors.h> is required for zstd support" "$LINENO" 5
+fi
+
+
 fi
 
 if test "$with_gssapi" = yes ; then

configure.in

@@ -1542,6 +1542,7 @@ fi
 # Check for zstd.h
 if test "$with_zstd" = yes; then
   AC_CHECK_HEADER(zstd.h, [], [AC_MSG_ERROR([header file <zstd.h> is required for zstd support])])
+  AC_CHECK_HEADER(zstd_errors.h, [], [AC_MSG_ERROR([header file <zstd_errors.h> is required for zstd support])])
 fi
 
 if test "$with_gssapi" = yes ; then
@@ -1648,7 +1649,7 @@ fi
 
 if test "$PORTNAME" = "win32" ; then
    AC_CHECK_HEADERS(crtdefs.h)
-fi 
+fi
 
 # OpenBSD requires libexecinfo from ports for backtrace() as it's a glibc addition
 if test "$PORTNAME" = "openbsd"; then

gpcontrib/zstd/zstd_compression.c

@@ -16,6 +16,7 @@
 #include "utils/builtins.h"
 
 #include <zstd.h>
+#include <zstd_errors.h>
 
 Datum zstd_constructor(PG_FUNCTION_ARGS);
 Datum zstd_destructor(PG_FUNCTION_ARGS);
@@ -83,6 +84,12 @@ zstd_destructor(PG_FUNCTION_ARGS)
 	PG_RETURN_VOID();
 }
 
+/*
+ * zstd compression implementation
+ *
+ * Note that when compression fails due to algorithm inefficiency,
+ * dst_used is set so src_sz, but the output buffer contents are left unchanged
+ */
 Datum
 zstd_compress(PG_FUNCTION_ARGS)
 {
@@ -104,7 +111,16 @@ zstd_compress(PG_FUNCTION_ARGS)
 
 	if (ZSTD_isError(dst_length_used))
 	{
-		elog(ERROR, "%s", ZSTD_getErrorName(dst_length_used));
+		if (ZSTD_getErrorCode(dst_length_used) == ZSTD_error_dstSize_tooSmall) {
+			/*
+			 * This error is returned when "compressed" output is bigger than
+			 * uncompressed input.
+			 * The caller can detect this by checking dst_used >= src_size
+			 */
+			dst_length_used = src_sz;
+		}
+		else
+			elog(ERROR, "%s", ZSTD_getErrorName(dst_length_used));
 	}
 
 	*dst_used = (int32) dst_length_used;