Trigger cluster replication immediately after flush to speed up writes. #848
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
gregoryyoung
added a commit
that referenced
this pull request
Mar 11, 2016
Trigger cluster replication immediately after flush to speed up writes.
|
I was just looking through chaser for related reasons today |
|
Bit trigger happy there GFY! Second PR to fix the build. |
|
Has already done locally :) On Fri, Mar 11, 2016 at 2:18 PM, lscpike notifications@github.com wrote:
Studying for the Turing test |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I think this may only be an issue on Windows. I don't have a Linux box available to test on. The Thread.Sleep(1) causes an average delay of (1/64)/2 seconds delay (8ms) in replication of a cluster. This results in irregular commits to a cluster to take in the region of 10 ms each.
I've removed the sleep and triggered replication from the checkpoint flush event. This reduces writes much closer to the raw flush costs at ~3ms.
I've replaced the existing WaitForFlush with an event as the Monitor.Pulse method has a race between the check for more data and the call to Wait.
I also added a fake type so the queue monitoring on the dashboard shows the replication activity.