Skip to content

log/tests: Added test for using log in multithread env#23982

Closed
aclamk wants to merge 1 commit intoceph:masterfrom
aclamk:log-multithread-test
Closed

log/tests: Added test for using log in multithread env#23982
aclamk wants to merge 1 commit intoceph:masterfrom
aclamk:log-multithread-test

Conversation

@aclamk
Copy link
Copy Markdown
Contributor

@aclamk aclamk commented Sep 7, 2018

This is to judge performance of logging in case of multithread environments.
Created to evaluate performance boost and best ConcreteEntry size in #23721.

Signed-off-by: Adam Kupczyk akupczyk@redhat.com

Signed-off-by: Adam Kupczyk <akupczyk@redhat.com>
buffers[i] = std::string(buf_size, (char)rand());

for (size_t i = 0; i < 200000; i++) {
buffers[rand() % buf_cnt] = buffers[rand() % buf_cnt];
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What is this really measuring? I'm not really seeing a trend from https://gist.github.com/aclamk/aeb0faf22c271fddabc81c5efe9fa1e5

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@batrick The test I made was faulty.
The intention was to measure impact on page tables and tls walks.
The actual result was totally garbled because rand() does protect its context with mutex. This caused all wierd results.

Please ignore this result for now.

@batrick batrick added the common label Sep 11, 2018
@aclamk aclamk closed this Sep 13, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants