You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@openwhisk.apache.org by gi...@git.apache.org on 2017/05/15 20:38:24 UTC
[GitHub] tysonnorris opened a new issue #2245: new ContainerPool aggressively restarts containers under load
tysonnorris opened a new issue #2245: new ContainerPool aggressively restarts containers under load
URL: https://github.com/apache/incubator-openwhisk/issues/2245
<!--
Do NOT share passwords, credentials or other confidential information.
Before creating a new issue, please check if there is one already open that
fits the defect you are reporting.
If you open an issue and realize later it is a duplicate of a pre-existing
open issue, please close yours and add a comment to the other.
Issues can be created for either defects or enhancement requests. If you are a committer than please add the labels "bug" or "feature". If you are not a committer please make clear in the comments which one it is, so that committers can add these labels later.
If you are reporting a defect, please edit the issue description to include the
information shown below.
If you are reporting an enhancement request, please include information on what you are trying to achieve and why that enhancement would help you.
For more information about reporting issues, see
https://github.com/apache/incubator-openwhisk/blob/master/CONTRIBUTING.md#raising-issues
Use the commands below to provide key information from your environment:
You do not have to include this information if this is a feature request.
-->
## Environment details:
* local deployment, Mac OS
* docker 17.03 (server 17.05 on docker-machine)
## Steps to reproduce the issue:
1. use [https://github.com/markusthoemmes/openwhisk-performance] to run throughput test (tests/throughput.sh)
2. run throughput test:
```./throughput.sh https://192.168.99.100 "$(cat ~/git/forks/tysonnorris/openwhisk/ansible/files/auth.guest)" 10 1000```
3. in a separate terminal check for nodesjsaction containers - notice they are constantly recreated
```docker ps | grep nodejs```
## Provide the expected results and outputs:
Expected: Don't restart containers when scheduling activation for an action that already has max warm containers that are all busy. Instead, requeue the activation for later.
## Provide the actual results and outputs:
1. Per above, notice the containers are restarting constantly, even though there is only a single action being exercised
2. Notice throughput latency is way up, compared to 4 concurrent users.
```
[Mon May 15 2017 20:24:41 GMT+0000 (UTC)] INFO Requests: 0 (0%), requests per second: 0, mean latency: 0 ms
[Mon May 15 2017 20:24:46 GMT+0000 (UTC)] INFO Requests: 10 (1%), requests per second: 2, mean latency: 2904.3 ms
[Mon May 15 2017 20:24:51 GMT+0000 (UTC)] INFO Requests: 20 (2%), requests per second: 2, mean latency: 4631.8 ms
[Mon May 15 2017 20:24:56 GMT+0000 (UTC)] INFO Requests: 28 (3%), requests per second: 2, mean latency: 4242.9 ms
[Mon May 15 2017 20:25:01 GMT+0000 (UTC)] INFO Requests: 36 (4%), requests per second: 2, mean latency: 5887.2 ms
[Mon May 15 2017 20:25:06 GMT+0000 (UTC)] INFO Requests: 50 (5%), requests per second: 3, mean latency: 5270.4 ms
[Mon May 15 2017 20:25:11 GMT+0000 (UTC)] INFO Requests: 60 (6%), requests per second: 2, mean latency: 4091.2 ms
[Mon May 15 2017 20:25:16 GMT+0000 (UTC)] INFO Requests: 70 (7%), requests per second: 2, mean latency: 4556.8 ms
[Mon May 15 2017 20:25:21 GMT+0000 (UTC)] INFO Requests: 84 (8%), requests per second: 3, mean latency: 4444.2 ms
[Mon May 15 2017 20:25:26 GMT+0000 (UTC)] INFO Requests: 94 (9%), requests per second: 2, mean latency: 4195.4 ms
```
## Additional information you deem important:
n/a
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
With regards,
Apache Git Services