MDEV-22929 MariaBackup option to report and/or continue when corruption is encountered

The new option --log-innodb-page-corruption is introduced.

When this option is set, backup is not interrupted if innodb corrupted
page is detected. Instead it logs all found corrupted pages in
innodb_corrupted_pages file in backup directory and finishes with error.

For incremental backup corrupted pages are also copied to .delta file,
because we can't do LSN check for such pages during backup,
innodb_corrupted_pages will also be created in incremental backup
directory.

During --prepare, corrupted pages list is read from the file just after
redo log is applied, and each page from the list is checked if it is allocated
in it's tablespace or not. If it is not allocated, then it is zeroed out,
flushed to the tablespace and removed from the list. If all pages are removed
from the list, then --prepare is finished successfully and
innodb_corrupted_pages file is removed from backup directory. Otherwise
--prepare is finished with error message and innodb_corrupted_pages contains
the list of the pages, which are detected as corrupted during backup, and are
allocated in their tablespaces, what means backup directory contains corrupted
innodb pages, and backup can not be considered as consistent.

For incremental --prepare corrupted pages from .delta files are applied
to the base backup, innodb_corrupted_pages is read from both base in
incremental directories, and the same action is proceded for corrupted
pages list as for full --prepare. innodb_corrupted_pages file is
modified or removed only in base directory.

If DDL happens during backup, it is also processed at the end of backup
to have correct tablespace names in innodb_corrupted_pages.

1 files changed, 35 insertions, 15 deletions

diff --git a/extra/mariabackup/fil_cur.cc b/extra/mariabackup/fil_cur.cc
index b229a37d934..3d48cb3e108 100644
--- a/extra/mariabackup/fil_cur.cc
+++ b/extra/mariabackup/fil_cur.cc
@@ -36,6 +36,7 @@ Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1335  USA
 #include "read_filt.h"
 #include "xtrabackup.h"
 #include "xb0xb.h"
+#include "backup_debug.h"
 
 /* Size of read buffer in pages (640 pages = 10M for 16K sized pages) */
 #define XB_FIL_CUR_PAGES 640
@@ -372,16 +373,15 @@ static bool page_is_corrupted(const byte *page, ulint page_no,
 	return buf_page_is_corrupted(true, page, cursor->page_size, space);
 }
 
-/************************************************************************
-Reads and verifies the next block of pages from the source
+/** Reads and verifies the next block of pages from the source
 file. Positions the cursor after the last read non-corrupted page.
-
+@param[in,out] cursor source file cursor
+@param[out] corrupted_pages adds corrupted pages if
+opt_log_innodb_page_corruption is set
 @return XB_FIL_CUR_SUCCESS if some have been read successfully, XB_FIL_CUR_EOF
 if there are no more pages to read and XB_FIL_CUR_ERROR on error. */
-xb_fil_cur_result_t
-xb_fil_cur_read(
-/*============*/
-	xb_fil_cur_t*	cursor)	/*!< in/out: source file cursor */
+xb_fil_cur_result_t xb_fil_cur_read(xb_fil_cur_t*	cursor,
+                                    CorruptedPages &corrupted_pages)
 {
 	byte*			page;
 	ulint			i;
@@ -455,20 +455,40 @@ read_retry:
 			retry_count--;
 
 			if (retry_count == 0) {
+				const char *ignore_corruption_warn = opt_log_innodb_page_corruption ?
+					" WARNING!!! The corruption is ignored due to"
+					" log-innodb-page-corruption option, the backup can contain"
+					" corrupted data." : "";
 				msg(cursor->thread_n,
 				    "Error: failed to read page after "
 				    "10 retries. File %s seems to be "
-				    "corrupted.", cursor->abs_path);
-				ret = XB_FIL_CUR_ERROR;
+				    "corrupted.%s", cursor->abs_path, ignore_corruption_warn);
 				buf_page_print(page, cursor->page_size);
-				break;
+				if (opt_log_innodb_page_corruption) {
+					corrupted_pages.add_page(cursor->node->name, cursor->node->space->id,
+						page_no);
+					retry_count = 1;
+				}
+				else {
+					ret = XB_FIL_CUR_ERROR;
+					break;
+				}
+			}
+			else {
+				msg(cursor->thread_n, "Database page corruption detected at page "
+				    ULINTPF ", retrying...",
+				    page_no);
+				os_thread_sleep(100000);
+				goto read_retry;
 			}
-			msg(cursor->thread_n, "Database page corruption detected at page "
-			    ULINTPF ", retrying...", 
-			    page_no);
-			os_thread_sleep(100000);
-			goto read_retry;
 		}
+		DBUG_EXECUTE_FOR_KEY("add_corrupted_page_for", cursor->node->space->name,
+			{
+				ulint corrupted_page_no = strtoul(dbug_val, NULL, 10);
+				if (page_no == corrupted_page_no)
+					corrupted_pages.add_page(cursor->node->name, cursor->node->space->id,
+						corrupted_page_no);
+			});
 		cursor->buf_read += page_size;
 		cursor->buf_npages++;
 	}