Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Revisit output buffer flushing #59

Open
WJCIV opened this issue Jan 27, 2016 · 1 comment
Open

Revisit output buffer flushing #59

WJCIV opened this issue Jan 27, 2016 · 1 comment

Comments

@WJCIV
Copy link
Collaborator

WJCIV commented Jan 27, 2016

Output is currently going into buffers. We need to spend more time figuring out when to flush those buffers. Doing so after every write is inefficient and undermines the point of using a buffer in the first place, but not flushing often enough will add latency.

@pwatchara
Copy link

It is possible to have a case where an upstream operator infrequently sends tuples to its downstream(s) and this may result in high latency due to tuple accumulation in the output buffer(s).

Is there an alternative way to address this, given that currently writing WritableByteChannel is done only after the buffer is detected full (OutputBuffer.bufferIsFull()) ?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants