envoyproxy/envoy

perf: thread local stat caching

Open

#509 opened on Feb 25, 2017

View on GitHub
 (0 comments) (2 reactions) (0 assignees)C++ (5,373 forks)batch import
area/perfhelp wanted

Repository metrics

Stars
 (27,997 stars)
PR merge metrics
 (Avg merge 8d) (378 merged PRs in 30d)

Description

Running Envoy on very high core count boxes is going to lead to atomic contention for counters and gauges. We should implement the option of doing thread local caching of the stats, and then flushing them to the central global representation.

Contributor guide

Research direction
Examine the current stats implementation in Envoy, focusing on counters and gauges. Design a thread local caching mechanism to batch updates and reduce atomic contention. Consider flushing strategies (e.g., periodic, on demand) and thread safe aggregation. Evaluate impact on memory and performance.
Tech stack
cpp
Domain
backendinfrastructure
Issue type
Performance
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
C++multi threadingatomic operations
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30