mirrors/unikernels
1
0
Fork 0
mirror of https://github.com/cetic/unikernels.git synced 2024-10-18 23:22:35 +07:00
Code Issues Packages Projects Releases Wiki Activity

Update README concerning UDP performance issues

Browse Source
This commit is contained in:
Gaetan Longree 2018-06-14 11:11:25 +02:00 committed by GitHub
parent 872f7122cf
commit 8974d85843
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -481,6 +481,8 @@ Note that at the 600 queries per second mark, the latency became too important a
Over the 900 queries per second mark, the data retrieved showed that the unikernel application refused to process requests beyond this throughput. Thus, the remainder of the container statistics have been excluded. As explained later in the analysis, this could be due to a bug in the UDP library implementation of the IncludeOS project (reported to developers, see [issue #1772](https://github.com/hioa-cs/IncludeOS/issues/1772) & [issue #3](https://github.com/cetic/unikernels/issues/3)). Over the 900 queries per second mark, the data retrieved showed that the unikernel application refused to process requests beyond this throughput. Thus, the remainder of the container statistics have been excluded. As explained later in the analysis, this could be due to a bug in the UDP library implementation of the IncludeOS project (reported to developers, see [issue #1772](https://github.com/hioa-cs/IncludeOS/issues/1772) & [issue #3](https://github.com/cetic/unikernels/issues/3)).
**NOTE: The performance issues encountered were caused by serial output being performed during execution. Supressing the output allowed higher throughput from the server as was evidenced** [**here**](https://github.com/hioa-cs/IncludeOS/issues/1772)**.**
#### Web Server #### Web Server
For the web server test, a similar stress testing was conducted. The methodology is once again to increase the number of requests per second. Starting at 100 requests per second over a 5-minute period, the number of requests is incremented by steps of 100 until the web service stops responding. For the web server test, a similar stress testing was conducted. The methodology is once again to increase the number of requests per second. Starting at 100 requests per second over a 5-minute period, the number of requests is incremented by steps of 100 until the web service stops responding.