Hi hackers,
I would like to suggest adding a new option to pgbench, which enables
the client to continue processing transactions even if some errors occur
during a transaction.
Currently, a client stops sending requests when its transaction is
aborted due to reasons other than serialization failures or deadlocks. I
think in some cases, especially when using custom scripts, the client
should be able to rollback the failed transaction and start a new one.
For example, my custom script (insert_to_unique_column.sql) follows:
```
CREATE TABLE IF NOT EXISTS test (col1 serial, col2 int unique);
INSERT INTO test (col2) VALUES (random(0, 50000));
```
Assume we need to continuously apply load to the server using 5 clients
for a certain period of time. However, a client sometimes stops when its
transaction in my custom script is aborted due to a check constraint
violation. As a result, the load on the server is lower than expected,
which is the problem I want to address.
The proposed new option solves this problem. When
--continue-client-on-abort is set to true, the client rolls back the
failed transaction and starts a new one. This allows all 5 clients to
continuously apply load to the server, even if some transactions fail.
```
% bin/pgbench -d postgres -f ../insert_to_unique_column.sql -T 10
--failures-detailed --continue-client-on-error
transaction type: ../custom_script_insert.sql
scaling factor: 1
query mode: simple
number of clients: 1
number of threads: 1
maximum number of tries: 1
duration: 10 s
number of transactions actually processed: 33552
number of failed transactions: 21901 (39.495%)
number of serialization failures: 0 (0.000%)
number of deadlock failures: 0 (0.000%)
number of other failures: 21901 (39.495%)
latency average = 0.180 ms (including failures)
initial connection time = 2.857 ms
tps = 3356.092385 (without initial connection time)
```
I have attached the patch. I would appreciate your feedback.
Best regards,
Rintaro Ikeda
NTT DATA Corporation Japan
From a15432989e2539d55e6ad2f26b3aac7b2221413f Mon Sep 17 00:00:00 2001
From: Rintaro Ikeda <51394766+rinik...@users.noreply.github.com>
Date: Sat, 10 May 2025 16:49:17 +0900
Subject: [PATCH] add continue-client-on-error option to pgbench
---
src/bin/pgbench/pgbench.c | 41 +++++++++++++++++++++++++++++++++++----
1 file changed, 37 insertions(+), 4 deletions(-)
diff --git a/src/bin/pgbench/pgbench.c b/src/bin/pgbench/pgbench.c
index 497a936c141..8eaf6ea38e3 100644
--- a/src/bin/pgbench/pgbench.c
+++ b/src/bin/pgbench/pgbench.c
@@ -440,6 +440,8 @@ typedef struct StatsData
int64 deadlock_failures; /* number of transactions that were not
* successfully retried after a deadlock
* error */
+ int64 other_sql_failures; /* number of failed transactions, which is enabled
+ * if --continue-client-on-error is used */
SimpleStats latency;
SimpleStats lag;
} StatsData;
@@ -770,6 +772,7 @@ static int64 total_weight = 0;
static bool verbose_errors = false; /* print verbose messages of all errors */
static bool exit_on_abort = false; /* exit when any client is aborted */
+static bool continue_on_error = false; /* continue after errors */
/* Builtin test scripts */
typedef struct BuiltinScript
@@ -1467,6 +1470,7 @@ initStats(StatsData *sd, pg_time_usec_t start)
sd->retried = 0;
sd->serialization_failures = 0;
sd->deadlock_failures = 0;
+ sd->other_sql_failures = 0;
initSimpleStats(&sd->latency);
initSimpleStats(&sd->lag);
}
@@ -1516,6 +1520,12 @@ accumStats(StatsData *stats, bool skipped, double lat, double lag,
case ESTATUS_DEADLOCK_ERROR:
stats->deadlock_failures++;
break;
+ case ESTATUS_OTHER_SQL_ERROR:
+ stats->other_sql_failures++;
+ break;
+ case ESTATUS_OTHER_SQL_ERROR:
+ stats->other_sql_failures++;
+ break;
default:
/* internal error which should never occur */
pg_fatal("unexpected error status: %d", estatus);
@@ -3247,7 +3257,8 @@ static bool
canRetryError(EStatus estatus)
{
return (estatus == ESTATUS_SERIALIZATION_ERROR ||
- estatus == ESTATUS_DEADLOCK_ERROR);
+ estatus == ESTATUS_DEADLOCK_ERROR ||
+ (continue_on_error && estatus == ESTATUS_OTHER_SQL_ERROR));
}
/*
@@ -4528,7 +4539,8 @@ static int64
getFailures(const StatsData *stats)
{
return (stats->serialization_failures +
- stats->deadlock_failures);
+ stats->deadlock_failures +
+ stats->other_sql_failures);
}
/*
@@ -4548,6 +4560,8 @@ getResultString(bool skipped, EStatus estatus)
return "serialization";
case ESTATUS_DEADLOCK_ERROR:
return "deadlock";
+ case ESTATUS_OTHER_SQL_ERROR:
+ return "error";
default:
/* internal error which should never occur */
pg_fatal("unexpected error status: %d", estatus);
@@ -4603,6 +4617,7 @@ doLog(TState *thread, CState *st,
int64 skipped = 0;
int64 serialization_failures = 0;
int64 deadlock_failures = 0;
+ int64 other_sql_failures = 0;
int64 retried = 0;
int64 retries = 0;
@@ -4643,10 +4658,12 @@ doLog(TState *thread, CState *st,
{
serialization_failures = agg->serialization_failures;
deadlock_failures = agg->deadlock_failures;
+ other_sql_failures = agg->other_sql_failures;
}
- fprintf(logfile, " " INT64_FORMAT " " INT64_FORMAT,
+ fprintf(logfile, " " INT64_FORMAT " " INT64_FORMAT " " INT64_FORMAT,
serialization_failures,
- deadlock_failures);
+ deadlock_failures,
+ other_sql_failures);
fputc('\n', logfile);
@@ -6285,6 +6302,7 @@ printProgressReport(TState *threads, int64 test_start, pg_time_usec_t now,
cur.serialization_failures +=
threads[i].stats.serialization_failures;
cur.deadlock_failures += threads[i].stats.deadlock_failures;
+ cur.other_sql_failures += threads[i].stats.other_sql_failures;
}
/* we count only actually executed transactions */
@@ -6443,6 +6461,9 @@ printResults(StatsData *total,
printf("number of deadlock failures: " INT64_FORMAT " (%.3f%%)\n",
total->deadlock_failures,
100.0 * total->deadlock_failures / total_cnt);
+ printf("number of other failures: " INT64_FORMAT " (%.3f%%)\n",
+ total->other_sql_failures,
+ 100.0 * total->other_sql_failures / total_cnt);
}
/* it can be non-zero only if max_tries is not equal to one */
@@ -6546,6 +6567,10 @@ printResults(StatsData *total,
sstats->deadlock_failures,
(100.0 * sstats->deadlock_failures /
script_total_cnt));
+ printf(" - number of other failures: " INT64_FORMAT " (%.3f%%)\n",
+ sstats->other_sql_failures,
+ (100.0 * sstats->other_sql_failures /
+ script_total_cnt));
}
/*
@@ -6705,6 +6730,7 @@ main(int argc, char **argv)
{"verbose-errors", no_argument, NULL, 15},
{"exit-on-abort", no_argument, NULL, 16},
{"debug", no_argument, NULL, 17},
+ {"continue-client-on-error", no_argument, NULL, 18},
{NULL, 0, NULL, 0}
};
@@ -7058,6 +7084,12 @@ main(int argc, char **argv)
case 17: /* debug */
pg_logging_increase_verbosity();
break;
+ case 18: /* continue-client-on-error */
+ continue_on_error = true;
+ break;
+ case 18: /* continue-client-on-error */
+ continue_on_error = true;
+ break;
default:
/* getopt_long already emitted a complaint */
pg_log_error_hint("Try \"%s --help\" for more information.", progname);
@@ -7413,6 +7445,7 @@ main(int argc, char **argv)
stats.retried += thread->stats.retried;
stats.serialization_failures += thread->stats.serialization_failures;
stats.deadlock_failures += thread->stats.deadlock_failures;
+ stats.other_sql_failures += thread->stats.other_sql_failures;
latency_late += thread->latency_late;
conn_total_duration += thread->conn_duration;
--
2.39.5 (Apple Git-154)
