diff --git a/doc/src/sgml/ref/pg_verify_checksums.sgml b/doc/src/sgml/ref/pg_verify_checksums.sgml
index 905b8f1222..4ad6edcde6 100644
--- a/doc/src/sgml/ref/pg_verify_checksums.sgml
+++ b/doc/src/sgml/ref/pg_verify_checksums.sgml
@@ -37,9 +37,8 @@ PostgreSQL documentation
Description
pg_verify_checksums verifies data checksums in a
- PostgreSQL cluster. The server must be shut
- down cleanly before running pg_verify_checksums.
- The exit status is zero if there are no checksum errors, otherwise nonzero.
+ PostgreSQL cluster. The exit status is zero if
+ there are no checksum errors, otherwise nonzero.
diff --git a/src/bin/pg_verify_checksums/pg_verify_checksums.c b/src/bin/pg_verify_checksums/pg_verify_checksums.c
index f0e09bea20..9519133e5e 100644
--- a/src/bin/pg_verify_checksums/pg_verify_checksums.c
+++ b/src/bin/pg_verify_checksums/pg_verify_checksums.c
@@ -1,7 +1,7 @@
/*
* pg_verify_checksums
*
- * Verifies page level checksums in an offline cluster
+ * Verifies page level checksums in a cluster
*
* Copyright (c) 2010-2018, PostgreSQL Global Development Group
*
@@ -26,10 +26,13 @@
static int64 files = 0;
static int64 blocks = 0;
static int64 badblocks = 0;
+static int64 skippedblocks = 0;
static ControlFileData *ControlFile;
+static XLogRecPtr checkpointLSN;
static char *only_relfilenode = NULL;
static bool verbose = false;
+static bool online = false;
static const char *progname;
@@ -122,10 +125,17 @@ scan_file(const char *fn, BlockNumber segmentno)
PageHeader header = (PageHeader) buf.data;
int f;
BlockNumber blockno;
+ bool block_retry = false;
f = open(fn, O_RDONLY | PG_BINARY, 0);
if (f < 0)
{
+ if (online && errno == ENOENT)
+ {
+ /* File was removed in the meantime */
+ return;
+ }
+
fprintf(stderr, _("%s: could not open file \"%s\": %s\n"),
progname, fn, strerror(errno));
exit(1);
@@ -140,26 +150,106 @@ scan_file(const char *fn, BlockNumber segmentno)
if (r == 0)
break;
+ if (r < 0)
+ {
+ fprintf(stderr, _("%s: could not read block %u in file \"%s\": %s\n"),
+ progname, blockno, fn, strerror(errno));
+ return;
+ }
if (r != BLCKSZ)
{
- fprintf(stderr, _("%s: could not read block %u in file \"%s\": read %d of %d\n"),
- progname, blockno, fn, r, BLCKSZ);
- exit(1);
+ if (block_retry)
+ {
+ /* We already tried once to reread the block, bail out */
+ fprintf(stderr, _("%s: could not read block %u in file \"%s\": read %d of %d\n"),
+ progname, blockno, fn, r, BLCKSZ);
+ exit(1);
+ }
+
+ /*
+ * Retry the block. It's possible that we read the block while it
+ * was extended or shrinked, so it it ends up looking torn to us.
+ */
+
+ /*
+ * Seek back by the amount of bytes we read to the beginning of
+ * the failed block.
+ */
+ if (lseek(f, -r, SEEK_CUR) == -1)
+ {
+ fprintf(stderr, _("%s: could not lseek in file \"%s\": %m\n"),
+ progname, fn);
+ exit(1);
+ }
+
+ /* Set flag so we know a retry was attempted */
+ block_retry = true;
+
+ /* Reset loop to validate the block again */
+ blockno--;
+
+ continue;
}
- blocks++;
/* New pages have no checksum yet */
if (PageIsNew(header))
+ {
+ skippedblocks++;
continue;
+ }
+
+ blocks++;
csum = pg_checksum_page(buf.data, blockno + segmentno * RELSEG_SIZE);
if (csum != header->pd_checksum)
{
+ /*
+ * Retry the block on the first failure. If the verification is
+ * done while the instance is online, it is possible that we read
+ * the first 4K page of the block just before postgres updated the
+ * entire block so it ends up looking torn to us. We only need to
+ * retry once because the LSN should be updated to something we can
+ * ignore on the next pass. If the error happens again then it is
+ * a true validation failure.
+ */
+ if (!block_retry)
+ {
+ /* Seek to the beginning of the failed block */
+ if (lseek(f, -BLCKSZ, SEEK_CUR) == -1)
+ {
+ fprintf(stderr, _("%s: could not lseek in file \"%s\": %m\n"),
+ progname, fn);
+ exit(1);
+ }
+
+ /* Set flag so we know a retry was attempted */
+ block_retry = true;
+
+ /* Reset loop to validate the block again */
+ blockno--;
+
+ continue;
+ }
+
+ /*
+ * The checksum verification failed on retry as well. Check if the
+ * page has been modified since the checkpoint and skip it in this
+ * case.
+ */
+ if (PageGetLSN(buf.data) > checkpointLSN)
+ {
+ block_retry = false;
+ blocks--;
+ skippedblocks++;
+ continue;
+ }
+
if (ControlFile->data_checksum_version == PG_DATA_CHECKSUM_VERSION)
fprintf(stderr, _("%s: checksum verification failed in file \"%s\", block %u: calculated checksum %X but block contains %X\n"),
progname, fn, blockno, csum, header->pd_checksum);
badblocks++;
}
+ block_retry = false;
}
if (verbose)
@@ -195,6 +285,12 @@ scan_directory(const char *basedir, const char *subdir)
snprintf(fn, sizeof(fn), "%s/%s", path, de->d_name);
if (lstat(fn, &st) < 0)
{
+ if (online && errno == ENOENT)
+ {
+ /* File was removed in the meantime */
+ continue;
+ }
+
fprintf(stderr, _("%s: could not stat file \"%s\": %s\n"),
progname, fn, strerror(errno));
exit(1);
@@ -328,7 +424,7 @@ main(int argc, char *argv[])
exit(1);
}
- /* Check if cluster is running */
+ /* Check if checksums are enabled */
ControlFile = get_controlfile(DataDir, progname, &crc_ok);
if (!crc_ok)
{
@@ -336,12 +432,10 @@ main(int argc, char *argv[])
exit(1);
}
+ /* Check if cluster is running */
if (ControlFile->state != DB_SHUTDOWNED &&
ControlFile->state != DB_SHUTDOWNED_IN_RECOVERY)
- {
- fprintf(stderr, _("%s: cluster must be shut down to verify checksums\n"), progname);
- exit(1);
- }
+ online = true;
if (ControlFile->data_checksum_version == 0)
{
@@ -349,6 +443,9 @@ main(int argc, char *argv[])
exit(1);
}
+ /* Get checkpoint LSN */
+ checkpointLSN = ControlFile->checkPoint;
+
/* Scan all files */
scan_directory(DataDir, "global");
scan_directory(DataDir, "base");
@@ -358,6 +455,8 @@ main(int argc, char *argv[])
printf(_("Data checksum version: %d\n"), ControlFile->data_checksum_version);
printf(_("Files scanned: %s\n"), psprintf(INT64_FORMAT, files));
printf(_("Blocks scanned: %s\n"), psprintf(INT64_FORMAT, blocks));
+ if (skippedblocks > 0)
+ printf(_("Blocks skipped: %s\n"), psprintf(INT64_FORMAT, skippedblocks));
printf(_("Bad checksums: %s\n"), psprintf(INT64_FORMAT, badblocks));
if (badblocks > 0)
diff --git a/src/bin/pg_verify_checksums/t/002_actions.pl b/src/bin/pg_verify_checksums/t/002_actions.pl
index 0e1725d9f2..bd22415f4a 100644
--- a/src/bin/pg_verify_checksums/t/002_actions.pl
+++ b/src/bin/pg_verify_checksums/t/002_actions.pl
@@ -5,7 +5,7 @@ use strict;
use warnings;
use PostgresNode;
use TestLib;
-use Test::More tests => 36;
+use Test::More tests => 45;
# Initialize node with checksums enabled.
my $node = get_new_node('node_checksum');
@@ -48,10 +48,10 @@ append_to_file "$pgdata/global/99999_vm.123", "";
command_ok(['pg_verify_checksums', '-D', $pgdata],
"succeeds with offline cluster");
-# Checks cannot happen with an online cluster
+# Checksums pass on an online cluster
$node->start;
-command_fails(['pg_verify_checksums', '-D', $pgdata],
- "fails with online cluster");
+command_ok(['pg_verify_checksums', '-D', $pgdata],
+ "succeeds with online cluster");
# Create table to corrupt and get its relfilenode
$node->safe_psql('postgres',
@@ -74,27 +74,6 @@ command_ok(['pg_verify_checksums', '-D', $pgdata,
'-r', $relfilenode_corrupted],
"succeeds for single relfilenode with offline cluster");
-# Time to create some corruption
-open my $file, '+<', "$pgdata/$file_corrupted";
-seek($file, $pageheader_size, 0);
-syswrite($file, '\0\0\0\0\0\0\0\0\0');
-close $file;
-
-# Global checksum checks fail
-$node->command_checks_all([ 'pg_verify_checksums', '-D', $pgdata],
- 1,
- [qr/Bad checksums:.*1/],
- [qr/checksum verification failed/],
- 'fails with corrupted data');
-
-# Checksum checks on single relfilenode fail
-$node->command_checks_all([ 'pg_verify_checksums', '-D', $pgdata, '-r',
- $relfilenode_corrupted],
- 1,
- [qr/Bad checksums:.*1/],
- [qr/checksum verification failed/],
- 'fails for corrupted data on single relfilenode');
-
# Utility routine to check that pg_verify_checksums is able to detect
# correctly-named relation files filled with some corrupted data.
sub fail_corrupt
@@ -129,3 +108,46 @@ fail_corrupt($node, "99990_vm");
fail_corrupt($node, "99990_init.123");
fail_corrupt($node, "99990_fsm.123");
fail_corrupt($node, "99990_vm.123");
+
+# Time to create some corruption
+open my $file, '+<', "$pgdata/$file_corrupted";
+seek($file, $pageheader_size, 0);
+syswrite($file, '\0\0\0\0\0\0\0\0\0');
+close $file;
+
+# Global checksum checks fail
+$node->command_checks_all([ 'pg_verify_checksums', '-D', $pgdata],
+ 1,
+ [qr/Bad checksums:.*1/],
+ [qr/checksum verification failed/],
+ 'fails with corrupted data');
+
+# Checksum checks on single relfilenode fail
+$node->command_checks_all([ 'pg_verify_checksums', '-D', $pgdata, '-r',
+ $relfilenode_corrupted],
+ 1,
+ [qr/Bad checksums:.*1/],
+ [qr/checksum verification failed/],
+ 'fails for corrupted data on single relfilenode');
+
+# Start node again to test online verification correctly finds failures
+$node->stop;
+
+# Global online checksum checks fail
+$node->command_checks_all([ 'pg_verify_checksums', '-D', $pgdata],
+ 1,
+ [qr/Bad checksums:.*1/],
+ [qr/checksum verification failed/],
+ 'fails with corrupted data');
+
+# Online checksum checks on single relfilenode fail
+$node->command_checks_all([ 'pg_verify_checksums', '-D', $pgdata, '-r',
+ $relfilenode_corrupted],
+ 1,
+ [qr/Bad checksums:.*1/],
+ [qr/checksum verification failed/],
+ 'fails for corrupted data on single relfilenode');
+
+# Authorized relation files filled with corrupted data cause the
+# online checksum checks to fail.
+fail_corrupt($node, "99991");