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

More cluster stats and add epoch stakes cache in retransmit stage #10345

Merged
merged 2 commits into from
Jun 1, 2020

Conversation

sakridge
Copy link
Member

@sakridge sakridge commented May 31, 2020

Problem

Computing epoch stakes can take a long time in retransmit and hog the gossip lock to do duplicate work in multiple threads.

Incomplete metrics for number of packets received/sent in process push requests.

Summary of Changes

Cache the stake information for the epoch and the peer information for a second and only update with 1 thread. retransmit computation goes from ~500ms to less than 10ms.

Add more cluster_info metrics to see picture of all packets into and out of gossip.

Fixes #

@sakridge sakridge changed the title Cluster stats epoch cache More cluster stats and add epoch stakes cache in retransmit stage May 31, 2020
@codecov
Copy link

codecov bot commented May 31, 2020

Codecov Report

Merging #10345 into master will decrease coverage by 0.1%.
The diff coverage is 90.4%.

@@            Coverage Diff            @@
##           master   #10345     +/-   ##
=========================================
- Coverage    81.3%    81.2%   -0.2%     
=========================================
  Files         288      288             
  Lines       66861    66917     +56     
=========================================
- Hits        54403    54378     -25     
- Misses      12458    12539     +81     

@sakridge sakridge added the v1.2 label Jun 1, 2020
@sakridge sakridge merged commit ef37b82 into solana-labs:master Jun 1, 2020
@sakridge sakridge deleted the cluster-stats-epoch-cache branch June 1, 2020 15:37
mergify bot pushed a commit that referenced this pull request Jun 1, 2020
…0345)

* More cluster info metrics for push request/response counts

* Cache staked peers for the epoch

(cherry picked from commit ef37b82)
sakridge added a commit to sakridge/solana that referenced this pull request Jun 8, 2020
…lana-labs#10345)

* More cluster info metrics for push request/response counts

* Cache staked peers for the epoch

(cherry picked from commit ef37b82)
sakridge added a commit that referenced this pull request Jun 9, 2020
* Skip gossip requests with different shred version and split lock (#10240)


(cherry picked from commit 3f508b3)

* More cluster stats and add epoch stakes cache in retransmit stage (#10345)

* More cluster info metrics for push request/response counts

* Cache staked peers for the epoch

(cherry picked from commit ef37b82)

* Cache tvu peers for broadcast (#10373)


(cherry picked from commit 2cf719a)

* Add pull request count metrics (#10421)


(cherry picked from commit 3d2230f)
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

Successfully merging this pull request may close these issues.

2 participants