Releases: projectcalico/tiger-bench
Releases · projectcalico/tiger-bench
v0.6.0
v0.5.0
What's Changed
- Patch qperf and build from source by @lwr20 in #20
- Ensure that TestPort is defaulted in Perf tests by @lwr20 in #19
- Parameterise registry details in CI, and add retries to aws authenticator install by @lwr20 in #23
- Add e2e test by @lwr20 in #24
- Add optional 'idle policy' to standing config by @lwr20 in #25
- label each pod with at least as many labels as policies by @tomastigera in #26
- Modified CI to run tests on pull requests with label by @lwr20 in #27
- Add ref input to checkout step in Build of images by @lwr20 in #28
- Use Command and Args properly by @lwr20 in #29
- Test built images in e2e by @lwr20 in #31
Full Changelog: v0.4.0...v0.5.0
v0.4.0
What's Changed
- NFtables support by @frozenprocess in #8
- fix build by @lwr20 in #15
- Run as non-root, add security contexts by @lwr20 in #16
- Add service latency test by @lwr20 in #14
- Fix tests by @lwr20 in #17
New Contributors
- @frozenprocess made their first contribution in #8
Full Changelog: https://github.com/projectcalico/tiger-bench/commits/v0.4.0
v0.3.0
v0.2.1
v0.2.0
v0.1.3
v0.1.2
v0.1.0
First release!
tiger-bench has the following features:
- can update your calico installation to change dataplane or encapsulation
- can update your calico installation to add a CPU limit to calico-node
- can create "standing config" in a namespace to load up the cluster. Pods/services/networkpolicies
- this is done in parallel on 10 threads for speed.
- can run a test repeatedly to measure latency and throughput
- this test is done for pod-pod (direct) and pod-service-pod
- and write a json file containing a statistical summary of the results
- can clean up the namespace after the test is done
See README.md for instructions.