agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
54+ messages / 4 participants
[nested] [flat]

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH 2/2] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-02-04 10:39  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-02-04 10:39 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index dd629668540..757b240a3c8 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += nbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1087,7 +1047,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.0


--------------AD4B53627CEDABF9E8CC5B3C--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v2 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-03-04 09:10  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-03-04 09:10 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Discussion: https://www.postgresql.org/message-id/9ec25819-0a8a-d51a-17dc-4150bb3cca3b%40iki.fi
---
 src/backend/commands/copyfromparse.c     | 119 ++++++++---------------
 src/include/commands/copyfrom_internal.h |   3 +-
 2 files changed, 40 insertions(+), 82 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index ce24a1528bd..c2efe7e0782 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -46,21 +46,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (raw_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		raw_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -118,7 +103,7 @@ static int	CopyGetData(CopyFromState cstate, void *databuf,
 						int minread, int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
-static bool CopyLoadRawBuf(CopyFromState cstate);
+static bool CopyLoadRawBuf(CopyFromState cstate, int minread);
 static int	CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes);
 
 void
@@ -209,7 +194,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				ereport(ERROR,
 						(errcode_for_file_access(),
 						 errmsg("could not read from COPY file: %m")));
-			if (bytesread == 0)
+			if (bytesread < maxread)
 				cstate->reached_eof = true;
 			break;
 		case COPY_FRONTEND:
@@ -278,6 +263,8 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			break;
 		case COPY_CALLBACK:
 			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			if (bytesread < minread)
+				cstate->reached_eof = true;
 			break;
 	}
 
@@ -329,14 +316,13 @@ CopyGetInt16(CopyFromState cstate, int16 *val)
 /*
  * CopyLoadRawBuf loads some more data into raw_buf
  *
- * Returns true if able to obtain at least one more byte, else false.
+ * Returns true if able to obtain at least 'minread' bytes, else false.
  *
  * If RAW_BUF_BYTES(cstate) > 0, the unprocessed bytes are moved to the start
- * of the buffer and then we load more data after that.  This case occurs only
- * when a multibyte character crosses a bufferload boundary.
+ * of the buffer and then we load more data after that.
  */
 static bool
-CopyLoadRawBuf(CopyFromState cstate)
+CopyLoadRawBuf(CopyFromState cstate, int minread)
 {
 	int			nbytes = RAW_BUF_BYTES(cstate);
 	int			inbytes;
@@ -347,14 +333,15 @@ CopyLoadRawBuf(CopyFromState cstate)
 				nbytes);
 
 	inbytes = CopyGetData(cstate, cstate->raw_buf + nbytes,
-						  1, RAW_BUF_SIZE - nbytes);
+						  minread, RAW_BUF_SIZE - nbytes);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_index = 0;
 	cstate->raw_buf_len = nbytes;
 	cstate->bytes_processed += inbytes;
 	pgstat_progress_update_param(PROGRESS_COPY_BYTES_PROCESSED, cstate->bytes_processed);
-	return (inbytes > 0);
+
+	return (inbytes >= minread);
 }
 
 /*
@@ -389,7 +376,7 @@ CopyReadBinaryData(CopyFromState cstate, char *dest, int nbytes)
 			/* Load more data if buffer is empty. */
 			if (RAW_BUF_BYTES(cstate) == 0)
 			{
-				if (!CopyLoadRawBuf(cstate))
+				if (!CopyLoadRawBuf(cstate, 1))
 					break;		/* EOF */
 			}
 
@@ -678,7 +665,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				cstate->raw_buf_index = cstate->raw_buf_len;
-			} while (CopyLoadRawBuf(cstate));
+			} while (CopyLoadRawBuf(cstate, 1));
 		}
 	}
 	else
@@ -747,7 +734,6 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_raw_buf;
 	int			raw_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
 	bool		hit_eof = false;
 	bool		result = false;
 	char		mblen_str[2];
@@ -794,6 +780,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_raw_buf = cstate->raw_buf;
 	raw_buf_ptr = cstate->raw_buf_index;
 	copy_buf_len = cstate->raw_buf_len;
+	hit_eof = cstate->reached_eof;
 
 	for (;;)
 	{
@@ -801,38 +788,40 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (raw_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (raw_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			/*
-			 * Try to read some more data.  This will certainly reset
-			 * raw_buf_index to zero, and raw_buf_ptr must go with it.
-			 */
-			if (!CopyLoadRawBuf(cstate))
-				hit_eof = true;
-			raw_buf_ptr = 0;
-			copy_buf_len = cstate->raw_buf_len;
+				/*
+				 * Try to read some more data.  This will certainly reset
+				 * raw_buf_index to zero, and raw_buf_ptr must go with it.
+				 */
+				if (!CopyLoadRawBuf(cstate, COPY_READ_LINE_LOOKAHEAD))
+					hit_eof = true;
+				raw_buf_ptr = 0;
+				copy_buf_len = cstate->raw_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (copy_buf_len <= 0)
+			if (copy_buf_len - raw_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -841,20 +830,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -888,14 +863,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of raw_buf.
+				 * Look at the next character.  If we're at EOF, c2 will wind
+				 * up as '\0' because of the guaranteed pad of raw_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_raw_buf[raw_buf_ptr];
 
 				if (c == '\n')
@@ -961,7 +931,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -976,16 +945,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				raw_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_raw_buf[raw_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1008,9 +970,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_raw_buf[raw_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
@@ -1095,7 +1055,6 @@ not_end_of_copy:
 			mblen_str[0] = c;
 			mblen = pg_encoding_mblen(cstate->file_encoding, mblen_str);
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(mblen - 1);
 			IF_NEED_REFILL_AND_EOF_BREAK(mblen - 1);
 			raw_buf_ptr += mblen - 1;
 		}
diff --git a/src/include/commands/copyfrom_internal.h b/src/include/commands/copyfrom_internal.h
index 705f5b615be..c088c4facdb 100644
--- a/src/include/commands/copyfrom_internal.h
+++ b/src/include/commands/copyfrom_internal.h
@@ -70,8 +70,7 @@ typedef struct CopyFromStateData
 	CopySource	copy_src;		/* type of copy source */
 	FILE	   *copy_file;		/* used if copy_src == COPY_FILE */
 	StringInfo	fe_msgbuf;		/* used if copy_src == COPY_NEW_FE */
-	bool		reached_eof;	/* true if we read to end of copy data (not
-								 * all copy_src types maintain this) */
+	bool		reached_eof;	/* true if we read to end of copy data */
 
 	EolType		eol_type;		/* EOL type of input */
 	int			file_encoding;	/* file or remote side's character encoding */
-- 
2.30.1


--------------5F54C02640018A10FACC0C96--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v3 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-04-01 20:22  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-04-01 20:22 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

Reviewed-by: John Naylor
Discussion: https://www.postgresql.org/message-id/89627a2a-c123-a8aa-267e-5d168feb73dd%40iki.fi
---
 src/backend/commands/copyfromparse.c | 111 +++++++++------------------
 1 file changed, 35 insertions(+), 76 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index 0813424768..b52abc1520 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -90,21 +90,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (input_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		input_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -159,7 +144,7 @@ static Datum CopyReadBinaryAttribute(CopyFromState cstate, FmgrInfo *flinfo,
 
 /* Low-level communications functions */
 static int	CopyGetData(CopyFromState cstate, void *databuf,
-						int minread, int maxread);
+						int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
 static void CopyLoadInputBuf(CopyFromState cstate);
@@ -230,9 +215,8 @@ ReceiveCopyBinaryHeader(CopyFromState cstate)
 /*
  * CopyGetData reads data from the source (file or frontend)
  *
- * We attempt to read at least minread, and at most maxread, bytes from
- * the source.  The actual number of bytes read is returned; if this is
- * less than minread, EOF was detected.
+ * We attempt to read at maxread bytes from the source.  The actual
+ * number of bytes read is returned; if this is 0, EOF was detected.
  *
  * Note: when copying from the frontend, we expect a proper EOF mark per
  * protocol; if the frontend simply drops the connection, we raise error.
@@ -241,7 +225,7 @@ ReceiveCopyBinaryHeader(CopyFromState cstate)
  * NB: no data conversion is applied here.
  */
 static int
-CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
+CopyGetData(CopyFromState cstate, void *databuf, int maxread)
 {
 	int			bytesread = 0;
 
@@ -257,7 +241,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				cstate->raw_reached_eof = true;
 			break;
 		case COPY_FRONTEND:
-			while (maxread > 0 && bytesread < minread && !cstate->raw_reached_eof)
+			while (maxread > 0 && bytesread == 0 && !cstate->raw_reached_eof)
 			{
 				int			avail;
 
@@ -321,7 +305,9 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			}
 			break;
 		case COPY_CALLBACK:
-			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			bytesread = cstate->data_source_cb(databuf, 1, maxread);
+			if (bytesread == 0)
+				cstate->raw_reached_eof = true;
 			break;
 	}
 
@@ -605,7 +591,7 @@ CopyLoadRawBuf(CopyFromState cstate)
 
 	/* Load more data */
 	inbytes = CopyGetData(cstate, cstate->raw_buf + cstate->raw_buf_len,
-						  1, RAW_BUF_SIZE - cstate->raw_buf_len);
+						  RAW_BUF_SIZE - cstate->raw_buf_len);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_len = nbytes;
@@ -990,7 +976,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				inbytes = CopyGetData(cstate, cstate->input_buf,
-									  1, INPUT_BUF_SIZE);
+									  INPUT_BUF_SIZE);
 			} while (inbytes > 0);
 			cstate->input_buf_index = 0;
 			cstate->input_buf_len = 0;
@@ -1047,8 +1033,7 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_input_buf;
 	int			input_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
-	bool		hit_eof = false;
+	bool		hit_eof;
 	bool		result = false;
 
 	/* CSV variables */
@@ -1098,6 +1083,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_input_buf = cstate->input_buf;
 	input_buf_ptr = cstate->input_buf_index;
 	copy_buf_len = cstate->input_buf_len;
+	hit_eof = cstate->input_reached_eof;
 
 	for (;;)
 	{
@@ -1105,35 +1091,37 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead max three bytes in one iteration of the loop
+		 * (for the sequence \.<CR><NL>), so make sure we have at least four
+		 * bytes in the buffer.  Note that we always guarantee that there is
+		 * one \0 in the buffer, after last valid byte; the lookaheads below
+		 * rely on that.
 		 */
-		if (input_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (input_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			CopyLoadInputBuf(cstate);
-			/* update our local variables */
-			hit_eof = cstate->input_reached_eof;
-			input_buf_ptr = cstate->input_buf_index;
-			copy_buf_len = cstate->input_buf_len;
+				CopyLoadInputBuf(cstate);
+				/* update our local variables */
+				hit_eof = cstate->input_reached_eof;
+				input_buf_ptr = cstate->input_buf_index;
+				copy_buf_len = cstate->input_buf_len;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (INPUT_BUF_BYTES(cstate) <= 0)
+			if (copy_buf_len - input_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -1142,20 +1130,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -1189,14 +1163,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of input_buf.
+				 * Look at the next character.  If we're at EOF, c will wind
+				 * up as '\0' because of the guaranteed pad of input_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_input_buf[input_buf_ptr];
 
 				if (c == '\n')
@@ -1262,7 +1231,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -1277,16 +1245,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				input_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_input_buf[input_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1309,9 +1270,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_input_buf[input_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
-- 
2.30.2


--------------11E1AF537C24312AF77A7698--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* [PATCH v4 1/1] Simplify COPY FROM parsing by forcing lookahead.
@ 2021-04-06 17:48  Heikki Linnakangas <[email protected]>
  0 siblings, 0 replies; 54+ messages in thread

From: Heikki Linnakangas @ 2021-04-06 17:48 UTC (permalink / raw)

Now that we don't support the old-style COPY protocol anymore, we can
force four bytes of lookahead like was suggested in an existing comment,
and simplify the loop in CopyReadLineText().

FIXME: This fails with sequence "\.<NL><some invalid bytes>". We
should detect the end-of-copy marker \. and stop reading without
complaining about the garbage after the end-of-copy marker. That
doesn't work if we force 4 bytes of lookahead; the invalid byte
sequence fits in the lookahead window, so we will try to convert it.

Reviewed-by: John Naylor
Discussion: https://www.postgresql.org/message-id/89627a2a-c123-a8aa-267e-5d168feb73dd%40iki.fi
---
 src/backend/commands/copyfromparse.c | 112 +++++++++------------------
 1 file changed, 36 insertions(+), 76 deletions(-)

diff --git a/src/backend/commands/copyfromparse.c b/src/backend/commands/copyfromparse.c
index 0813424768..6b140531ed 100644
--- a/src/backend/commands/copyfromparse.c
+++ b/src/backend/commands/copyfromparse.c
@@ -90,21 +90,6 @@
  * empty statements.  See http://www.cit.gu.edu.au/~anthony/info/C/C.macros.
  */
 
-/*
- * This keeps the character read at the top of the loop in the buffer
- * even if there is more than one read-ahead.
- */
-#define IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(extralen) \
-if (1) \
-{ \
-	if (input_buf_ptr + (extralen) >= copy_buf_len && !hit_eof) \
-	{ \
-		input_buf_ptr = prev_raw_ptr; /* undo fetch */ \
-		need_data = true; \
-		continue; \
-	} \
-} else ((void) 0)
-
 /* This consumes the remainder of the buffer and breaks */
 #define IF_NEED_REFILL_AND_EOF_BREAK(extralen) \
 if (1) \
@@ -159,7 +144,7 @@ static Datum CopyReadBinaryAttribute(CopyFromState cstate, FmgrInfo *flinfo,
 
 /* Low-level communications functions */
 static int	CopyGetData(CopyFromState cstate, void *databuf,
-						int minread, int maxread);
+						int maxread);
 static inline bool CopyGetInt32(CopyFromState cstate, int32 *val);
 static inline bool CopyGetInt16(CopyFromState cstate, int16 *val);
 static void CopyLoadInputBuf(CopyFromState cstate);
@@ -230,9 +215,8 @@ ReceiveCopyBinaryHeader(CopyFromState cstate)
 /*
  * CopyGetData reads data from the source (file or frontend)
  *
- * We attempt to read at least minread, and at most maxread, bytes from
- * the source.  The actual number of bytes read is returned; if this is
- * less than minread, EOF was detected.
+ * We attempt to read at most maxread bytes from the source.  The actual
+ * number of bytes read is returned; if this is 0, EOF was detected.
  *
  * Note: when copying from the frontend, we expect a proper EOF mark per
  * protocol; if the frontend simply drops the connection, we raise error.
@@ -241,7 +225,7 @@ ReceiveCopyBinaryHeader(CopyFromState cstate)
  * NB: no data conversion is applied here.
  */
 static int
-CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
+CopyGetData(CopyFromState cstate, void *databuf, int maxread)
 {
 	int			bytesread = 0;
 
@@ -257,7 +241,7 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 				cstate->raw_reached_eof = true;
 			break;
 		case COPY_FRONTEND:
-			while (maxread > 0 && bytesread < minread && !cstate->raw_reached_eof)
+			while (maxread > 0 && bytesread == 0 && !cstate->raw_reached_eof)
 			{
 				int			avail;
 
@@ -321,7 +305,9 @@ CopyGetData(CopyFromState cstate, void *databuf, int minread, int maxread)
 			}
 			break;
 		case COPY_CALLBACK:
-			bytesread = cstate->data_source_cb(databuf, minread, maxread);
+			bytesread = cstate->data_source_cb(databuf, 1, maxread);
+			if (bytesread == 0)
+				cstate->raw_reached_eof = true;
 			break;
 	}
 
@@ -605,7 +591,7 @@ CopyLoadRawBuf(CopyFromState cstate)
 
 	/* Load more data */
 	inbytes = CopyGetData(cstate, cstate->raw_buf + cstate->raw_buf_len,
-						  1, RAW_BUF_SIZE - cstate->raw_buf_len);
+						  RAW_BUF_SIZE - cstate->raw_buf_len);
 	nbytes += inbytes;
 	cstate->raw_buf[nbytes] = '\0';
 	cstate->raw_buf_len = nbytes;
@@ -990,7 +976,7 @@ CopyReadLine(CopyFromState cstate)
 			do
 			{
 				inbytes = CopyGetData(cstate, cstate->input_buf,
-									  1, INPUT_BUF_SIZE);
+									  INPUT_BUF_SIZE);
 			} while (inbytes > 0);
 			cstate->input_buf_index = 0;
 			cstate->input_buf_len = 0;
@@ -1047,8 +1033,7 @@ CopyReadLineText(CopyFromState cstate)
 	char	   *copy_input_buf;
 	int			input_buf_ptr;
 	int			copy_buf_len;
-	bool		need_data = false;
-	bool		hit_eof = false;
+	bool		hit_eof;
 	bool		result = false;
 
 	/* CSV variables */
@@ -1098,6 +1083,7 @@ CopyReadLineText(CopyFromState cstate)
 	copy_input_buf = cstate->input_buf;
 	input_buf_ptr = cstate->input_buf_index;
 	copy_buf_len = cstate->input_buf_len;
+	hit_eof = cstate->input_reached_eof;
 
 	for (;;)
 	{
@@ -1105,35 +1091,38 @@ CopyReadLineText(CopyFromState cstate)
 		char		c;
 
 		/*
-		 * Load more data if needed.  Ideally we would just force four bytes
-		 * of read-ahead and avoid the many calls to
-		 * IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(), but the COPY_OLD_FE protocol
-		 * does not allow us to read too far ahead or we might read into the
-		 * next data, so we read-ahead only as far we know we can.  One
-		 * optimization would be to read-ahead four byte here if
-		 * cstate->copy_src != COPY_OLD_FE, but it hardly seems worth it,
-		 * considering the size of the buffer.
+		 * Load more data if needed.
+		 *
+		 * We need to look ahead at most three bytes in one iteration of the
+		 * loop (for the sequence \.<CR><NL>), so make sure we have at least
+		 * four bytes in the buffer.  Note that we always guarantee that there
+		 * is one \0 in the buffer, after last valid byte; the lookaheads
+		 * below rely on that.
 		 */
-		if (input_buf_ptr >= copy_buf_len || need_data)
+#define COPY_READ_LINE_LOOKAHEAD	4
+		if (input_buf_ptr + COPY_READ_LINE_LOOKAHEAD >= copy_buf_len)
 		{
-			REFILL_LINEBUF;
+			if (!hit_eof)
+			{
+				REFILL_LINEBUF;
 
-			CopyLoadInputBuf(cstate);
-			/* update our local variables */
-			hit_eof = cstate->input_reached_eof;
-			input_buf_ptr = cstate->input_buf_index;
-			copy_buf_len = cstate->input_buf_len;
+				CopyLoadInputBuf(cstate);
+				/* update our local variables */
+				input_buf_ptr = cstate->input_buf_index;
+				copy_buf_len = cstate->input_buf_len;
+				hit_eof = cstate->input_reached_eof;
+				continue;
+			}
 
 			/*
 			 * If we are completely out of data, break out of the loop,
 			 * reporting EOF.
 			 */
-			if (INPUT_BUF_BYTES(cstate) <= 0)
+			if (copy_buf_len - input_buf_ptr <= 0)
 			{
 				result = true;
 				break;
 			}
-			need_data = false;
 		}
 
 		/* OK to fetch a character */
@@ -1142,20 +1131,6 @@ CopyReadLineText(CopyFromState cstate)
 
 		if (cstate->opts.csv_mode)
 		{
-			/*
-			 * If character is '\\' or '\r', we may need to look ahead below.
-			 * Force fetch of the next character if we don't already have it.
-			 * We need to do this before changing CSV state, in case one of
-			 * these characters is also the quote or escape character.
-			 *
-			 * Note: old-protocol does not like forced prefetch, but it's OK
-			 * here since we cannot validly be at EOF.
-			 */
-			if (c == '\\' || c == '\r')
-			{
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-			}
-
 			/*
 			 * Dealing with quotes and escapes here is mildly tricky. If the
 			 * quote char is also the escape char, there's no problem - we
@@ -1189,14 +1164,9 @@ CopyReadLineText(CopyFromState cstate)
 				cstate->eol_type == EOL_CRNL)
 			{
 				/*
-				 * If need more data, go back to loop top to load it.
-				 *
-				 * Note that if we are at EOF, c will wind up as '\0' because
-				 * of the guaranteed pad of input_buf.
+				 * Look at the next character.  If we're at EOF, c will wind
+				 * up as '\0' because of the guaranteed pad of input_buf.
 				 */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-
-				/* get next char */
 				c = copy_input_buf[input_buf_ptr];
 
 				if (c == '\n')
@@ -1262,7 +1232,6 @@ CopyReadLineText(CopyFromState cstate)
 		{
 			char		c2;
 
-			IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
 			IF_NEED_REFILL_AND_EOF_BREAK(0);
 
 			/* -----
@@ -1277,16 +1246,9 @@ CopyReadLineText(CopyFromState cstate)
 			{
 				input_buf_ptr++;	/* consume the '.' */
 
-				/*
-				 * Note: if we loop back for more data here, it does not
-				 * matter that the CSV state change checks are re-executed; we
-				 * will come back here with no important state changed.
-				 */
 				if (cstate->eol_type == EOL_CRNL)
 				{
-					/* Get the next character */
-					IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-					/* if hit_eof, c2 will become '\0' */
+					/* Get next character.  If hit_eof, c2 will become '\0' */
 					c2 = copy_input_buf[input_buf_ptr++];
 
 					if (c2 == '\n')
@@ -1309,9 +1271,7 @@ CopyReadLineText(CopyFromState cstate)
 					}
 				}
 
-				/* Get the next character */
-				IF_NEED_REFILL_AND_NOT_EOF_CONTINUE(0);
-				/* if hit_eof, c2 will become '\0' */
+				/* Get next character.  If hit_eof, c2 will become '\0' */
 				c2 = copy_input_buf[input_buf_ptr++];
 
 				if (c2 != '\r' && c2 != '\n')
-- 
2.30.2


--------------1601CF8503AB8D78BE138DD6--





^ permalink  raw  reply  [nested|flat] 54+ messages in thread

* Re: [HACKERS] Should logtape.c blocks be of type long?
@ 2023-09-22 04:46  Michael Paquier <[email protected]>
  0 siblings, 1 reply; 54+ messages in thread

From: Michael Paquier @ 2023-09-22 04:46 UTC (permalink / raw)
  To: Peter Geoghegan <[email protected]>; +Cc: Tom Lane <[email protected]>; pgsql-hackers

On Sun, Feb 26, 2017 at 10:04:20AM -0800, Peter Geoghegan wrote:
> I think it's worth being consistent about a restriction like this, as
> Robert said. Given that fixing this issue will not affect the machine
> code generated by compilers for the majority of platforms we support,
> doing so seems entirely worthwhile to me.

(Reviving an old thread, fives years later..)

As far as I can see, no patches have been sent to do that, and the
changes required to replace long by int64 in the logtape and tuplesort
code are rather minimal as long as some care is taken with all the
internals of logtape (correct me of course if I'm wrong).  I really
don't see why we shouldn't do the switch based on the argument of
Windows not being able to handle more than 16TB worth of blocks as
things stand because of long in these code paths.

So, attached is a patch to change these longs to int64.  Any thoughts?
--
Michael


Attachments:

  [text/x-diff] logtape-int64.patch (14.6K, ../../[email protected]/2-logtape-int64.patch)
  download | inline diff:
diff --git a/src/include/utils/logtape.h b/src/include/utils/logtape.h
index 5420a24ac9..2de7add81c 100644
--- a/src/include/utils/logtape.h
+++ b/src/include/utils/logtape.h
@@ -51,7 +51,7 @@ typedef struct TapeShare
 	 * Currently, all the leader process needs is the location of the
 	 * materialized tape's first block.
 	 */
-	long		firstblocknumber;
+	int64		firstblocknumber;
 } TapeShare;
 
 /*
@@ -70,8 +70,8 @@ extern void LogicalTapeWrite(LogicalTape *lt, const void *ptr, size_t size);
 extern void LogicalTapeRewindForRead(LogicalTape *lt, size_t buffer_size);
 extern void LogicalTapeFreeze(LogicalTape *lt, TapeShare *share);
 extern size_t LogicalTapeBackspace(LogicalTape *lt, size_t size);
-extern void LogicalTapeSeek(LogicalTape *lt, long blocknum, int offset);
-extern void LogicalTapeTell(LogicalTape *lt, long *blocknum, int *offset);
-extern long LogicalTapeSetBlocks(LogicalTapeSet *lts);
+extern void LogicalTapeSeek(LogicalTape *lt, int64 blocknum, int offset);
+extern void LogicalTapeTell(LogicalTape *lt, int64 *blocknum, int *offset);
+extern int64 LogicalTapeSetBlocks(LogicalTapeSet *lts);
 
 #endif							/* LOGTAPE_H */
diff --git a/src/backend/utils/sort/logtape.c b/src/backend/utils/sort/logtape.c
index f31878bdee..604fd00308 100644
--- a/src/backend/utils/sort/logtape.c
+++ b/src/backend/utils/sort/logtape.c
@@ -94,9 +94,9 @@
  */
 typedef struct TapeBlockTrailer
 {
-	long		prev;			/* previous block on this tape, or -1 on first
+	int64		prev;			/* previous block on this tape, or -1 on first
 								 * block */
-	long		next;			/* next block on this tape, or # of valid
+	int64		next;			/* next block on this tape, or # of valid
 								 * bytes on last block (if < 0) */
 } TapeBlockTrailer;
 
@@ -153,10 +153,10 @@ struct LogicalTape
 	 * When concatenation of worker tape BufFiles is performed, an offset to
 	 * the first block in the unified BufFile space is applied during reads.
 	 */
-	long		firstBlockNumber;
-	long		curBlockNumber;
-	long		nextBlockNumber;
-	long		offsetBlockNumber;
+	int64		firstBlockNumber;
+	int64		curBlockNumber;
+	int64		nextBlockNumber;
+	int64		offsetBlockNumber;
 
 	/*
 	 * Buffer for current data block(s).
@@ -172,7 +172,7 @@ struct LogicalTape
 	 * order; blocks are consumed from the end of the array (lowest block
 	 * numbers first).
 	 */
-	long	   *prealloc;
+	int64	   *prealloc;
 	int			nprealloc;		/* number of elements in list */
 	int			prealloc_size;	/* number of elements list can hold */
 };
@@ -200,9 +200,9 @@ struct LogicalTapeSet
 	 * blocks that are in unused holes between worker spaces following BufFile
 	 * concatenation.
 	 */
-	long		nBlocksAllocated;	/* # of blocks allocated */
-	long		nBlocksWritten; /* # of blocks used in underlying file */
-	long		nHoleBlocks;	/* # of "hole" blocks left */
+	int64		nBlocksAllocated;	/* # of blocks allocated */
+	int64		nBlocksWritten; /* # of blocks used in underlying file */
+	int64		nHoleBlocks;	/* # of "hole" blocks left */
 
 	/*
 	 * We store the numbers of recycled-and-available blocks in freeBlocks[].
@@ -213,19 +213,19 @@ struct LogicalTapeSet
 	 * LogicalTapeSetForgetFreeSpace().
 	 */
 	bool		forgetFreeSpace;	/* are we remembering free blocks? */
-	long	   *freeBlocks;		/* resizable array holding minheap */
-	long		nFreeBlocks;	/* # of currently free blocks */
+	int64	   *freeBlocks;		/* resizable array holding minheap */
+	int64		nFreeBlocks;	/* # of currently free blocks */
 	Size		freeBlocksLen;	/* current allocated length of freeBlocks[] */
 	bool		enable_prealloc;	/* preallocate write blocks? */
 };
 
 static LogicalTape *ltsCreateTape(LogicalTapeSet *lts);
-static void ltsWriteBlock(LogicalTapeSet *lts, long blocknum, const void *buffer);
-static void ltsReadBlock(LogicalTapeSet *lts, long blocknum, void *buffer);
-static long ltsGetBlock(LogicalTapeSet *lts, LogicalTape *lt);
-static long ltsGetFreeBlock(LogicalTapeSet *lts);
-static long ltsGetPreallocBlock(LogicalTapeSet *lts, LogicalTape *lt);
-static void ltsReleaseBlock(LogicalTapeSet *lts, long blocknum);
+static void ltsWriteBlock(LogicalTapeSet *lts, int64 blocknum, const void *buffer);
+static void ltsReadBlock(LogicalTapeSet *lts, int64 blocknum, void *buffer);
+static int64 ltsGetBlock(LogicalTapeSet *lts, LogicalTape *lt);
+static int64 ltsGetFreeBlock(LogicalTapeSet *lts);
+static int64 ltsGetPreallocBlock(LogicalTapeSet *lts, LogicalTape *lt);
+static void ltsReleaseBlock(LogicalTapeSet *lts, int64 blocknum);
 static void ltsInitReadBuffer(LogicalTape *lt);
 
 
@@ -235,7 +235,7 @@ static void ltsInitReadBuffer(LogicalTape *lt);
  * No need for an error return convention; we ereport() on any error.
  */
 static void
-ltsWriteBlock(LogicalTapeSet *lts, long blocknum, const void *buffer)
+ltsWriteBlock(LogicalTapeSet *lts, int64 blocknum, const void *buffer)
 {
 	/*
 	 * BufFile does not support "holes", so if we're about to write a block
@@ -263,8 +263,8 @@ ltsWriteBlock(LogicalTapeSet *lts, long blocknum, const void *buffer)
 	if (BufFileSeekBlock(lts->pfile, blocknum) != 0)
 		ereport(ERROR,
 				(errcode_for_file_access(),
-				 errmsg("could not seek to block %ld of temporary file",
-						blocknum)));
+				 errmsg("could not seek to block %lld of temporary file",
+						(long long) blocknum)));
 	BufFileWrite(lts->pfile, buffer, BLCKSZ);
 
 	/* Update nBlocksWritten, if we extended the file */
@@ -279,13 +279,13 @@ ltsWriteBlock(LogicalTapeSet *lts, long blocknum, const void *buffer)
  * module should never attempt to read a block it doesn't know is there.
  */
 static void
-ltsReadBlock(LogicalTapeSet *lts, long blocknum, void *buffer)
+ltsReadBlock(LogicalTapeSet *lts, int64 blocknum, void *buffer)
 {
 	if (BufFileSeekBlock(lts->pfile, blocknum) != 0)
 		ereport(ERROR,
 				(errcode_for_file_access(),
-				 errmsg("could not seek to block %ld of temporary file",
-						blocknum)));
+				 errmsg("could not seek to block %lld of temporary file",
+						(long long) blocknum)));
 	BufFileReadExact(lts->pfile, buffer, BLCKSZ);
 }
 
@@ -303,7 +303,7 @@ ltsReadFillBuffer(LogicalTape *lt)
 	do
 	{
 		char	   *thisbuf = lt->buffer + lt->nbytes;
-		long		datablocknum = lt->nextBlockNumber;
+		int64		datablocknum = lt->nextBlockNumber;
 
 		/* Fetch next block number */
 		if (datablocknum == -1L)
@@ -333,20 +333,20 @@ ltsReadFillBuffer(LogicalTape *lt)
 	return (lt->nbytes > 0);
 }
 
-static inline unsigned long
-left_offset(unsigned long i)
+static inline uint64
+left_offset(uint64 i)
 {
 	return 2 * i + 1;
 }
 
-static inline unsigned long
-right_offset(unsigned long i)
+static inline uint64
+right_offset(uint64 i)
 {
 	return 2 * i + 2;
 }
 
-static inline unsigned long
-parent_offset(unsigned long i)
+static inline uint64
+parent_offset(uint64 i)
 {
 	return (i - 1) / 2;
 }
@@ -354,7 +354,7 @@ parent_offset(unsigned long i)
 /*
  * Get the next block for writing.
  */
-static long
+static int64
 ltsGetBlock(LogicalTapeSet *lts, LogicalTape *lt)
 {
 	if (lts->enable_prealloc)
@@ -367,14 +367,14 @@ ltsGetBlock(LogicalTapeSet *lts, LogicalTape *lt)
  * Select the lowest currently unused block from the tape set's global free
  * list min heap.
  */
-static long
+static int64
 ltsGetFreeBlock(LogicalTapeSet *lts)
 {
-	long	   *heap = lts->freeBlocks;
-	long		blocknum;
-	long		heapsize;
-	long		holeval;
-	unsigned long holepos;
+	int64	   *heap = lts->freeBlocks;
+	int64		blocknum;
+	int64		heapsize;
+	int64		holeval;
+	uint64		holepos;
 
 	/* freelist empty; allocate a new block */
 	if (lts->nFreeBlocks == 0)
@@ -398,9 +398,9 @@ ltsGetFreeBlock(LogicalTapeSet *lts)
 	heapsize = lts->nFreeBlocks;
 	while (true)
 	{
-		unsigned long left = left_offset(holepos);
-		unsigned long right = right_offset(holepos);
-		unsigned long min_child;
+		uint64		left = left_offset(holepos);
+		uint64		right = right_offset(holepos);
+		uint64		min_child;
 
 		if (left < heapsize && right < heapsize)
 			min_child = (heap[left] < heap[right]) ? left : right;
@@ -427,7 +427,7 @@ ltsGetFreeBlock(LogicalTapeSet *lts)
  * Refill the preallocation list with blocks from the tape set's free list if
  * necessary.
  */
-static long
+static int64
 ltsGetPreallocBlock(LogicalTapeSet *lts, LogicalTape *lt)
 {
 	/* sorted in descending order, so return the last element */
@@ -437,7 +437,7 @@ ltsGetPreallocBlock(LogicalTapeSet *lts, LogicalTape *lt)
 	if (lt->prealloc == NULL)
 	{
 		lt->prealloc_size = TAPE_WRITE_PREALLOC_MIN;
-		lt->prealloc = (long *) palloc(sizeof(long) * lt->prealloc_size);
+		lt->prealloc = (int64 *) palloc(sizeof(int64) * lt->prealloc_size);
 	}
 	else if (lt->prealloc_size < TAPE_WRITE_PREALLOC_MAX)
 	{
@@ -445,8 +445,8 @@ ltsGetPreallocBlock(LogicalTapeSet *lts, LogicalTape *lt)
 		lt->prealloc_size *= 2;
 		if (lt->prealloc_size > TAPE_WRITE_PREALLOC_MAX)
 			lt->prealloc_size = TAPE_WRITE_PREALLOC_MAX;
-		lt->prealloc = (long *) repalloc(lt->prealloc,
-										 sizeof(long) * lt->prealloc_size);
+		lt->prealloc = (int64 *) repalloc(lt->prealloc,
+										  sizeof(int64) * lt->prealloc_size);
 	}
 
 	/* refill preallocation list */
@@ -466,10 +466,10 @@ ltsGetPreallocBlock(LogicalTapeSet *lts, LogicalTape *lt)
  * Return a block# to the freelist.
  */
 static void
-ltsReleaseBlock(LogicalTapeSet *lts, long blocknum)
+ltsReleaseBlock(LogicalTapeSet *lts, int64 blocknum)
 {
-	long	   *heap;
-	unsigned long holepos;
+	int64	   *heap;
+	uint64		holepos;
 
 	/*
 	 * Do nothing if we're no longer interested in remembering free space.
@@ -486,12 +486,12 @@ ltsReleaseBlock(LogicalTapeSet *lts, long blocknum)
 		 * If the freelist becomes very large, just return and leak this free
 		 * block.
 		 */
-		if (lts->freeBlocksLen * 2 * sizeof(long) > MaxAllocSize)
+		if (lts->freeBlocksLen * 2 * sizeof(int64) > MaxAllocSize)
 			return;
 
 		lts->freeBlocksLen *= 2;
-		lts->freeBlocks = (long *) repalloc(lts->freeBlocks,
-											lts->freeBlocksLen * sizeof(long));
+		lts->freeBlocks = (int64 *) repalloc(lts->freeBlocks,
+											 lts->freeBlocksLen * sizeof(int64));
 	}
 
 	/* create a "hole" at end of minheap array */
@@ -502,7 +502,7 @@ ltsReleaseBlock(LogicalTapeSet *lts, long blocknum)
 	/* sift up to insert blocknum */
 	while (holepos != 0)
 	{
-		unsigned long parent = parent_offset(holepos);
+		uint64		parent = parent_offset(holepos);
 
 		if (heap[parent] < blocknum)
 			break;
@@ -566,7 +566,7 @@ LogicalTapeSetCreate(bool preallocate, SharedFileSet *fileset, int worker)
 	lts->nHoleBlocks = 0L;
 	lts->forgetFreeSpace = false;
 	lts->freeBlocksLen = 32;	/* reasonable initial guess */
-	lts->freeBlocks = (long *) palloc(lts->freeBlocksLen * sizeof(long));
+	lts->freeBlocks = (int64 *) palloc(lts->freeBlocksLen * sizeof(int64));
 	lts->nFreeBlocks = 0;
 	lts->enable_prealloc = preallocate;
 
@@ -609,7 +609,7 @@ LogicalTape *
 LogicalTapeImport(LogicalTapeSet *lts, int worker, TapeShare *shared)
 {
 	LogicalTape *lt;
-	long		tapeblocks;
+	int64		tapeblocks;
 	char		filename[MAXPGPATH];
 	BufFile    *file;
 	int64		filesize;
@@ -789,7 +789,7 @@ LogicalTapeWrite(LogicalTape *lt, const void *ptr, size_t size)
 		if (lt->pos >= (int) TapeBlockPayloadSize)
 		{
 			/* Buffer full, dump it out */
-			long		nextBlockNumber;
+			int64		nextBlockNumber;
 
 			if (!lt->dirty)
 			{
@@ -1086,7 +1086,7 @@ LogicalTapeBackspace(LogicalTape *lt, size_t size)
 	seekpos = (size_t) lt->pos; /* part within this block */
 	while (size > seekpos)
 	{
-		long		prev = TapeBlockGetTrailer(lt->buffer)->prev;
+		int64		prev = TapeBlockGetTrailer(lt->buffer)->prev;
 
 		if (prev == -1L)
 		{
@@ -1100,10 +1100,10 @@ LogicalTapeBackspace(LogicalTape *lt, size_t size)
 		ltsReadBlock(lt->tapeSet, prev, lt->buffer);
 
 		if (TapeBlockGetTrailer(lt->buffer)->next != lt->curBlockNumber)
-			elog(ERROR, "broken tape, next of block %ld is %ld, expected %ld",
-				 prev,
-				 TapeBlockGetTrailer(lt->buffer)->next,
-				 lt->curBlockNumber);
+			elog(ERROR, "broken tape, next of block %lld is %lld, expected %lld",
+				 (long long) prev,
+				 (long long) (TapeBlockGetTrailer(lt->buffer)->next),
+				 (long long) lt->curBlockNumber);
 
 		lt->nbytes = TapeBlockPayloadSize;
 		lt->curBlockNumber = prev;
@@ -1130,7 +1130,7 @@ LogicalTapeBackspace(LogicalTape *lt, size_t size)
  * LogicalTapeTell().
  */
 void
-LogicalTapeSeek(LogicalTape *lt, long blocknum, int offset)
+LogicalTapeSeek(LogicalTape *lt, int64 blocknum, int offset)
 {
 	Assert(lt->frozen);
 	Assert(offset >= 0 && offset <= TapeBlockPayloadSize);
@@ -1159,7 +1159,7 @@ LogicalTapeSeek(LogicalTape *lt, long blocknum, int offset)
  * the position for a seek after freezing.  Not clear if anyone needs that.
  */
 void
-LogicalTapeTell(LogicalTape *lt, long *blocknum, int *offset)
+LogicalTapeTell(LogicalTape *lt, int64 *blocknum, int *offset)
 {
 	if (lt->buffer == NULL)
 		ltsInitReadBuffer(lt);
@@ -1179,7 +1179,7 @@ LogicalTapeTell(LogicalTape *lt, long *blocknum, int *offset)
  * This should not be called while there are open write buffers; otherwise it
  * may not account for buffered data.
  */
-long
+int64
 LogicalTapeSetBlocks(LogicalTapeSet *lts)
 {
 	return lts->nBlocksWritten - lts->nHoleBlocks;
diff --git a/src/backend/utils/sort/tuplesort.c b/src/backend/utils/sort/tuplesort.c
index c7a6c03f97..5ed76bb80b 100644
--- a/src/backend/utils/sort/tuplesort.c
+++ b/src/backend/utils/sort/tuplesort.c
@@ -296,7 +296,7 @@ struct Tuplesortstate
 	bool		eof_reached;	/* reached EOF (needed for cursors) */
 
 	/* markpos_xxx holds marked position for mark and restore */
-	long		markpos_block;	/* tape block# (only used if SORTEDONTAPE) */
+	int64		markpos_block;	/* tape block# (only used if SORTEDONTAPE) */
 	int			markpos_offset; /* saved "current", or offset in tape block */
 	bool		markpos_eof;	/* saved "eof_reached" */
 
@@ -903,7 +903,7 @@ tuplesort_free(Tuplesortstate *state)
 	MemoryContext oldcontext = MemoryContextSwitchTo(state->base.sortcontext);
 
 #ifdef TRACE_SORT
-	long		spaceUsed;
+	int64		spaceUsed;
 
 	if (state->tapeset)
 		spaceUsed = LogicalTapeSetBlocks(state->tapeset);
@@ -928,13 +928,13 @@ tuplesort_free(Tuplesortstate *state)
 	if (trace_sort)
 	{
 		if (state->tapeset)
-			elog(LOG, "%s of worker %d ended, %ld disk blocks used: %s",
+			elog(LOG, "%s of worker %d ended, %lld disk blocks used: %s",
 				 SERIAL(state) ? "external sort" : "parallel external sort",
-				 state->worker, spaceUsed, pg_rusage_show(&state->ru_start));
+				 state->worker, (long long) spaceUsed, pg_rusage_show(&state->ru_start));
 		else
-			elog(LOG, "%s of worker %d ended, %ld KB used: %s",
+			elog(LOG, "%s of worker %d ended, %lld KB used: %s",
 				 SERIAL(state) ? "internal sort" : "unperformed parallel sort",
-				 state->worker, spaceUsed, pg_rusage_show(&state->ru_start));
+				 state->worker, (long long) spaceUsed, pg_rusage_show(&state->ru_start));
 	}
 
 	TRACE_POSTGRESQL_SORT_DONE(state->tapeset != NULL, spaceUsed);


  [application/pgp-signature] signature.asc (833B, ../../[email protected]/3-signature.asc)
  download

^ permalink  raw  reply  [nested|flat] 54+ messages in thread