v4-0002-1.-Do-not-retry-failed-transaction-due-to-other_sql_.patch

From d9d363c7c298f44063a2aa33530622548ee45cbf Mon Sep 17 00:00:00 2001
From: Rintaro Ikeda <ikedarintaro@ikedarintarous-MacBook-Air.local>
Date: Sun, 8 Jun 2025 23:40:32 +0900
Subject: [PATCH 2/2] 1. Do not retry failed transaction due to
 other_sql_failures. 2. modify documentation and comments. 3. add test.

---
 doc/src/sgml/ref/pgbench.sgml                |  3 +++
 src/bin/pgbench/pgbench.c                    | 26 +++++++++++++++-----
 src/bin/pgbench/t/001_pgbench_with_server.pl | 22 +++++++++++++++++
 3 files changed, 45 insertions(+), 6 deletions(-)

diff --git a/doc/src/sgml/ref/pgbench.sgml b/doc/src/sgml/ref/pgbench.sgml
index dcb8c1c487c..2086dd59cb3 100644
--- a/doc/src/sgml/ref/pgbench.sgml
+++ b/doc/src/sgml/ref/pgbench.sgml
@@ -923,6 +923,9 @@ pgbench <optional> <replaceable>options</replaceable> </optional> <replaceable>d
         serialization failure. This allows all clients specified with -c option
         to continuously apply load to the server, even if some transactions fail.
        </para>
+       <para>
+        Note that this option can not be used together with
+        <option>--exit-on-abort</option>.
       </listitem>
      </varlistentry>
 
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 5db222f2c1e..2333110c29f 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -287,6 +287,9 @@ static int	main_pid;			/* main process id used in log filename */
 /*
  * We cannot retry a transaction after the serialization/deadlock error if its
  * number of tries reaches this maximum; if its value is zero, it is not used.
+ * We can ignore errors including serialization/deadlock errors and other errors
+ * if --continue-on-error is set, but in this case the failed transaction is not
+ * retried.
  */
 static uint32 max_tries = 1;
 
@@ -402,7 +405,8 @@ typedef struct StatsData
 	 *   directly successful transactions (they were successfully completed on
 	 *                                     the first try).
 	 *
-	 * A failed transaction is defined as unsuccessfully retried transactions.
+	 * A failed transaction is defined as unsuccessfully retried transactions
+	 * unless continue-on-error option is specified.
 	 * It can be one of two types:
 	 *
 	 * failed (the number of failed transactions) =
@@ -411,6 +415,11 @@ typedef struct StatsData
 	 *   'deadlock_failures' (they got a deadlock error and were not
 	 *                        successfully retried).
 	 *
+	 * When continue-on-error option is specified,
+	 * failed (the number of failed transactions) =
+	 *   'other_sql_failures' (they got a error when continue-on-error option
+	 * 						   was specified).
+	 *
 	 * If the transaction was retried after a serialization or a deadlock
 	 * error this does not guarantee that this retry was successful. Thus
 	 *
@@ -960,7 +969,7 @@ usage(void)
 		   "                           (default: \"pgbench_log\")\n"
 		   "  --max-tries=NUM          max number of tries to run transaction (default: 1)\n"
 		   "  --continue-on-error\n"
-		   "                           Continue and retry transactions that failed due to errors other than serialization or deadlocks.\n"
+		   "                           continue to process transactions after a trasaction fails due to errors other than serialization or deadlocks.\n"
 		   "  --progress-timestamp     use Unix epoch timestamps for progress\n"
 		   "  --random-seed=SEED       set random seed (\"time\", \"rand\", integer)\n"
 		   "  --sampling-rate=NUM      fraction of transactions to log (e.g., 0.01 for 1%%)\n"
@@ -3258,8 +3267,7 @@ static bool
 canRetryError(EStatus estatus)
 {
 	return (estatus == ESTATUS_SERIALIZATION_ERROR ||
-			estatus == ESTATUS_DEADLOCK_ERROR ||
-			(continue_on_error && estatus == ESTATUS_OTHER_SQL_ERROR));
+			estatus == ESTATUS_DEADLOCK_ERROR);
 }
 
 /*
@@ -4019,7 +4027,7 @@ advanceConnectionState(TState *thread, CState *st, StatsData *agg)
 					if (PQpipelineStatus(st->con) != PQ_PIPELINE_ON)
 						st->state = CSTATE_END_COMMAND;
 				}
-				else if (canRetryError(st->estatus))
+				else if (canRetryError(st->estatus) | continue_on_error)
 					st->state = CSTATE_ERROR;
 				else
 					st->state = CSTATE_ABORTED;
@@ -4111,6 +4119,7 @@ advanceConnectionState(TState *thread, CState *st, StatsData *agg)
 						 * can retry the error.
 						 */
 						st->state = timer_exceeded ? CSTATE_FINISHED :
+							continue_on_error ? CSTATE_FAILURE :
 							doRetry(st, &now) ? CSTATE_RETRY : CSTATE_FAILURE;
 					}
 					else
@@ -6446,7 +6455,8 @@ printResults(StatsData *total,
 
 	/*
 	 * Remaining stats are nonsensical if we failed to execute any xacts due
-	 * to others than serialization or deadlock errors
+	 * to others than serialization or deadlock errors and --continue-on-error
+	 * is not set.
 	 */
 	if (total_cnt <= 0)
 		return;
@@ -7086,6 +7096,7 @@ main(int argc, char **argv)
 				pg_logging_increase_verbosity();
 				break;
 			case 18:			/* continue-on-error */
+				benchmarking_option_set = true;
 				continue_on_error = true;
 				break;
 			default:
@@ -7242,6 +7253,9 @@ main(int argc, char **argv)
 			pg_fatal("an unlimited number of transaction tries can only be used with --latency-limit or a duration (-T)");
 	}
 
+	if (exit_on_abort && continue_on_error)
+		pg_fatal("--exit-on-abort and --continue-on-error are mutually exclusive options");
+
 	/*
 	 * save main process id in the global variable because process id will be
 	 * changed after fork.
diff --git a/src/bin/pgbench/t/001_pgbench_with_server.pl b/src/bin/pgbench/t/001_pgbench_with_server.pl
index 7dd78940300..afb49b554d0 100644
--- a/src/bin/pgbench/t/001_pgbench_with_server.pl
+++ b/src/bin/pgbench/t/001_pgbench_with_server.pl
@@ -1813,6 +1813,28 @@ update counter set i = i+1 returning i \gset
 # Clean up
 $node->safe_psql('postgres', 'DROP TABLE counter;');
 
+# Test --continue-on-error
+$node->safe_psql('postgres',
+	'CREATE TABLE unique_table(i int unique); ' . 'INSERT INTO unique_table VALUES (0);');
+
+$node->pgbench(
+	'-t 10 --continue-on-error --failures-detailed',
+	0,
+	[
+		qr{processed: 0/10\b},
+		qr{other failures: 10\b}
+	],
+	[],
+	'test --continue-on-error',
+	{
+		'002_continue_on_error' => q{
+		insert into unique_table values 0;
+		}
+	});
+
+# Clean up
+$node->safe_psql('postgres', 'DROP TABLE unique_table;');
+
 # done
 $node->safe_psql('postgres', 'DROP TABLESPACE regress_pgbench_tap_1_ts');
 $node->stop;
-- 
2.39.5 (Apple Git-154)