Kong Gateway performance testing benchmarks

Uses: Kong Gateway

Kong Gateway performance testing method and results

Kong tests performance results for Kong Gateway using our public test suite.

The following sections explain the test methodology, results, and configuration.

Test method

The performance tests cover a number of baseline configurations and common use cases for Kong Gateway. The following describes the test cases used and the configuration methodology:

Environment: Kubernetes environment on AWS infrastructure.
Test use cases:
- Basic Kong Gateway proxy.
- Rate limiting a request with no authentication.
- Authentication using the Basic Auth plugin and rate limiting.
- Authentication using the Key Auth plugin and rate limiting.
Routes and Consumers: Each case was tested with two different options: one with one Route and one Consumer, and one with 100 Routes and 100 Consumers, for a total of eight test cases. For test cases that didn’t require authentication, no Consumers were used.
Traffic distribution: Normal distribution across both Routes and Consumers.
Protocol: HTTPS only.
Sample size: Each test case was run five times, each for a duration of 15 minutes. The results are an average of the five different test runs.

Kong Gateway performance benchmark results

Test case	Number of Routes and Consumers	Requests per second (RPS)	P99 (ms)	P95 (ms)
Kong proxy with no plugins	1 Route, 0 Consumers	127257.3	7.11	4.07
Kong proxy with no plugins	100 Routes, 0 Consumers	124402.3	7.39	4.15
Rate limit and no auth	1 Route, 0 Consumers	112025.7	8.38	3.89
Rate limit and no auth	100 Routes, 0 Consumers	108439.2	8.74	4.1
Rate limit and key auth	1 Route, 1 Consumer	97208.2	9.1	4.81
Rate limit and key auth	100 Routes, 100 Consumers	91859.1	9.61	5.11
Rate limit and basic auth	1 Route, 1 Consumer	92862.9	9.64	5.05
Rate limit and basic auth	100 Routes, 100 Consumers	87535.4	10.15	5.54

Test case	Number of Routes and Consumers	Requests per second (RPS)	P99 (ms)	P95 (ms)
Kong proxy with no plugins	1 Route, 0 Consumers	134940.8	6.79	3.7
Kong proxy with no plugins	100 Routes, 0 Consumers	130779.5	7.08	3.79
Rate limit and no auth	1 Route, 0 Consumers	115281.4	8.38	3.87
Rate limit and no auth	100 Routes, 0 Consumers	111324.6	8.57	3.83
Rate limit and key auth	1 Route, 1 Consumer	101822.8	9.09	4.46
Rate limit and key auth	100 Routes, 100 Consumers	96237.6	10.27	4.69
Rate limit and basic auth	1 Route, 1 Consumer	94680.2	9.58	5.04
Rate limit and basic auth	100 Routes, 100 Consumers	89378.4	10.2	5.37

Test case	Number of Routes and Consumers	Requests per second (RPS)	P99 (ms)	P95 (ms)
Kong proxy with no plugins	1 Route, 0 Consumers	142443.4	6.24	3.55
Kong proxy with no plugins	100 Routes, 0 Consumers	137561.7	6.36	3.58
Rate limit and no auth	1 Route, 0 Consumers	120897.4	8.08	3.6
Rate limit and no auth	100 Routes, 0 Consumers	116867.2	8.51	3.78
Rate limit and key auth	1 Route, 1 Consumer	105657.4	8.62	4.38
Rate limit and key auth	100 Routes, 100 Consumers	100047.6	9.12	4.45
Rate limit and basic auth	1 Route, 1 Consumer	98031.6	10.47	5.02
Rate limit and basic auth	100 Routes, 100 Consumers	92548.2	9.8	5.25

Test case	Number of Routes and Consumers	Requests per second (RPS)	P99 (ms)	P95 (ms)
Kong proxy with no plugins	1 Route, 0 Consumers	137358.8	7.25	4.06
Kong proxy with no plugins	100 Routes, 0 Consumers	133953.4	7.2	4.17
Rate limit and no auth	1 Route, 0 Consumers	121737.2	7.69	4.01
Rate limit and no auth	100 Routes, 0 Consumers	117521.4	8.53	4.22
Rate limit and key auth	1 Route, 1 Consumer	103777.6	9.43	4.39
Rate limit and key auth	100 Routes, 100 Consumers	98777.5	9.16	4.79
Rate limit and basic auth	1 Route, 1 Consumer	97397.6	9.69	4.93
Rate limit and basic auth	100 Routes, 100 Consumers	92372.6	10.17	5.31

Test case	Number of Routes and Consumers	Requests per second (RPS)	P99 (ms)	P95 (ms)
Kong proxy with no plugins	1 Route, 0 Consumers	137850.4	6.25	3.82
Kong proxy with no plugins	100 Routes, 0 Consumers	132302.8	6.55	3.99
Rate limit and no auth	1 Route, 0 Consumers	116413.8	7.59	4.56
Rate limit and no auth	100 Routes, 0 Consumers	111615.8	7.62	4.54
Rate limit and key auth	1 Route, 1 Consumer	102261.6	8.47	5.05
Rate limit and key auth	100 Routes, 100 Consumers	96289.6	8.82	5.25
Rate limit and basic auth	1 Route, 1 Consumer	95297.8	8.75	5.66
Rate limit and basic auth	100 Routes, 100 Consumers	89777.4	9.34	5.89

Kong ran these tests in AWS using EC2 machines. We used Kubernetes taints to ensure that Kong Gateway is on its own node while the load testing and observability tools are on their own separate nodes in the same cluster.

Kong Gateway ran on a single dedicated instance of c5.4xlarge, and the two nodes for the observability stack and K6 ran on dedicated c5.metal instances. We used the metal instances for the observability load generation toolchain to ensure they aren’t resource-constrained in any way. Since K6 is very resource-demanding when generating a high amount of traffic during tests, we observed that using smaller or less powerful instances for the toolchain caused the observability load generation tools to be a bottleneck for Kong Gateway performance.

Test configuration

For these tests, we changed the number of worker processes to match the number of available cores to the node running Kong Gateway, which was 16 vCPU. Accordingly, we set the number of processes to 16. This follows Kong’s overall performance guidance. Outside of this change, no other tuning was made.

Conduct your own performance test using Kong’s test suite

You can use Kong’s public test suite repo to help you spin up an EKS cluster with Kong Gateway, Redis, Prometheus, and Grafana installed. Additionally, it will configure K6, a popular open source load testing tool. You can use this test suite to conduct your own performance tests.

Once the cluster is generated, you can apply the provided YAML to configure Kong Gateway for the included test cases, and the observability plugins for metrics scraping by the Prometheus instance already provisioned in the cluster. If you’d rather define your own test scenarios, you can also define the Kong Gateway configuration you want to test and apply it to the cluster.

From there, you can use the included bash scripts to run K6 tests. After the tests complete, you can port-forward into the cluster and view the Grafana dashboard with the performance results.

Next Steps

Establish your own Kong Gateway performance benchmark