Remove read_archive_file()'s "count" parameter.

Instead, always try to fill the allocated buffer completely.
The previous coding apparently intended (though it's undocumented)
to read only small amounts of data until we are able to identify the
WAL segment size and begin filtering out unwanted segments.  However
this extra complication has no measurable value according to simple
testing here, and it could easily be a net loss if there is a
substantial amount of non-WAL data in the archive file before the
first WAL file.

Discussion: https://postgr.es/m/3341199.1774221191@sss.pgh.pa.us

diff --git a/src/bin/pg_waldump/archive_waldump.c b/src/bin/pg_waldump/archive_waldump.c
index 50a5eb426fec45cba2cbef83b69170641c76242e..96f4d94449f7faf2675efa2c46dbdfa0ae4afab9 100644 (file)
--- a/src/bin/pg_waldump/archive_waldump.c
+++ b/src/bin/pg_waldump/archive_waldump.c
@@ -89,7 +89,7 @@ typedef struct astreamer_waldump
 
 static ArchivedWALFile *get_archive_wal_entry(const char *fname,
                                                                                          XLogDumpPrivate *privateInfo);
-static bool read_archive_file(XLogDumpPrivate *privateInfo, Size count);
+static bool read_archive_file(XLogDumpPrivate *privateInfo);
 static void setup_tmpwal_dir(const char *waldir);
 static void cleanup_tmpwal_dir_atexit(void);
 
@@ -156,14 +156,11 @@ init_archive_reader(XLogDumpPrivate *privateInfo,
        privateInfo->archive_streamer = streamer;
 
        /*
-        * Allocate a buffer for reading the archive file to facilitate content
-        * decoding; read requests must not exceed the allocated buffer size.
+        * Allocate a buffer for reading the archive file to begin content
+        * decoding.
         */
        privateInfo->archive_read_buf = pg_malloc(READ_CHUNK_SIZE);
-
-#ifdef USE_ASSERT_CHECKING
        privateInfo->archive_read_buf_size = READ_CHUNK_SIZE;
-#endif
 
        /*
         * Hash table storing WAL entries read from the archive with an arbitrary
@@ -182,7 +179,7 @@ init_archive_reader(XLogDumpPrivate *privateInfo,
         */
        while (entry == NULL)
        {
-               if (!read_archive_file(privateInfo, XLOG_BLCKSZ))
+               if (!read_archive_file(privateInfo))
                        pg_fatal("could not find WAL in archive \"%s\"",
                                         privateInfo->archive_name);
 
@@ -402,7 +399,7 @@ read_archive_wal_page(XLogDumpPrivate *privateInfo, XLogRecPtr targetPagePtr,
                                                 fname, privateInfo->archive_name,
                                                 (long long int) (count - nbytes),
                                                 (long long int) count);
-                       if (!read_archive_file(privateInfo, READ_CHUNK_SIZE))
+                       if (!read_archive_file(privateInfo))
                                pg_fatal("unexpected end of archive \"%s\" while reading \"%s\": read %lld of %lld bytes",
                                                 privateInfo->archive_name, fname,
                                                 (long long int) (count - nbytes),
@@ -523,7 +520,7 @@ get_archive_wal_entry(const char *fname, XLogDumpPrivate *privateInfo)
                /*
                 * Read more data.  If we reach EOF, the desired file is not present.
                 */
-               if (!read_archive_file(privateInfo, READ_CHUNK_SIZE))
+               if (!read_archive_file(privateInfo))
                        pg_fatal("could not find WAL \"%s\" in archive \"%s\"",
                                         fname, privateInfo->archive_name);
        }
@@ -533,10 +530,6 @@ get_archive_wal_entry(const char *fname, XLogDumpPrivate *privateInfo)
  * Reads a chunk from the archive file and passes it through the streamer
  * pipeline for decompression (if needed) and tar member extraction.
  *
- * count is the maximum amount to try to read this time.  Note that it's
- * measured in raw file bytes, and may have little to do with how much
- * comes out of decompression/extraction.
- *
  * Returns true if successful, false if there is no more data.
  *
  * Callers must be aware that a single call may trigger multiple callbacks
@@ -548,19 +541,17 @@ get_archive_wal_entry(const char *fname, XLogDumpPrivate *privateInfo)
  * within the same call.
  */
 static bool
-read_archive_file(XLogDumpPrivate *privateInfo, Size count)
+read_archive_file(XLogDumpPrivate *privateInfo)
 {
        int                     rc;
 
-       /* The read request must not exceed the allocated buffer size. */
-       Assert(privateInfo->archive_read_buf_size >= count);
-
        /* Fail if we already reached EOF in a prior call. */
        if (privateInfo->archive_fd_eof)
                return false;
 
        /* Try to read some more data. */
-       rc = read(privateInfo->archive_fd, privateInfo->archive_read_buf, count);
+       rc = read(privateInfo->archive_fd, privateInfo->archive_read_buf,
+                         privateInfo->archive_read_buf_size);
        if (rc < 0)
                pg_fatal("could not read file \"%s\": %m",
                                 privateInfo->archive_name);

diff --git a/src/bin/pg_waldump/pg_waldump.h b/src/bin/pg_waldump/pg_waldump.h
index ca0dfd971688bdb0e650a69fcd4b1fc08f672b64..bd46d14f3a88df2ae3e66b212853e78156348443 100644 (file)
--- a/src/bin/pg_waldump/pg_waldump.h
+++ b/src/bin/pg_waldump/pg_waldump.h
@@ -39,10 +39,7 @@ typedef struct XLogDumpPrivate
 
        astreamer  *archive_streamer;
        char       *archive_read_buf;   /* Reusable read buffer for archive I/O */
-
-#ifdef USE_ASSERT_CHECKING
        Size            archive_read_buf_size;
-#endif
 
        /*
         * The buffer for the WAL file the archive streamer is currently reading,