From 21780b4f6530dd7da6dfc99fa34441caf35fc1b7 Mon Sep 17 00:00:00 2001 From: Jelte Fennema Date: Tue, 23 Aug 2022 17:24:27 +0200 Subject: [PATCH] Fix flakyness in ch_benchmarks_1 (#6228) One of our arbitrary config tests would sometimes fail like this in CI: ```diff su_nationkey, cust_nation, l_year; - supp_nation | cust_nation | l_year | revenue ---------------------------------------------------------------------- - 9 | C | 2008 | 3.00 -(1 row) - +ERROR: cannot connect to localhost:10212 to fetch intermediate results +CONTEXT: while executing command on localhost:10211 ``` When looking at the logs it seems like we were running out of connections: ``` 2022-08-23 14:03:52.856 UTC [28122] FATAL: sorry, too many clients already 2022-08-23 14:03:52.860 UTC [21027] ERROR: cannot connect to localhost:10212 to fetch intermediate results ``` This happened with `CitusThreeWorkersManyShards` config. This test on purpose tries to push the limits of Citus quite far. And the `ch_benchmarks_1` test is also run in parallel with a few more ones. So it's not too weird that it ran out of connections. This doubles the connection limit in the arbitrary config tests to hopefully not hit this error again. Example of failed test: https://app.circleci.com/pipelines/github/citusdata/citus/26365/workflows/7a1b5688-85cc-4bc3-ade5-9bd1d83cd0ed/jobs/747908/parallel-runs/1 --- src/test/regress/citus_tests/config.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/test/regress/citus_tests/config.py b/src/test/regress/citus_tests/config.py index 4ebe96143..207279f92 100644 --- a/src/test/regress/citus_tests/config.py +++ b/src/test/regress/citus_tests/config.py @@ -105,7 +105,7 @@ class CitusBaseClusterConfig(object, metaclass=NewInitCaller): "citus.enable_repartition_joins": True, "citus.repartition_join_bucket_count_per_node": 2, "citus.log_distributed_deadlock_detection": True, - "max_connections": 600, + "max_connections": 1200, } self.new_settings = {} self.add_coordinator_to_metadata = False