Главная
Study mode:
on
1
Intro
2
Distributed Actors
3
Programming Model
4
Executive Summary We're going to look at how we can improve distributed actor
5
Limitations: Scalability
6
Limitations: Latency
7
Partisan
8
Dynamic Overlay Selection
9
Named Channels
10
Affinitized Parallelism
11
Experiments
12
Evaluating Scalability Distributed advertisement counter
13
Increasing Scalability
14
Reducing Latency: Microbenchmarks
15
Increasing Throughput: Echo Service
16
Increasing Throughput: KVS Service
17
Takeaways Distributed actor systems limited by implementation assumptions
18
Questions?
Description:
Explore the design and implementation of PARTISAN, an alternative runtime system for distributed actor applications, in this conference talk from USENIX ATC '19. Delve into how PARTISAN improves scalability and reduces latency through dynamic overlay selection, named channels, and affinitized parallelism. Learn about the limitations of current distributed actor systems and how PARTISAN addresses these issues. Examine experimental results demonstrating significant improvements in scalability, throughput, and latency compared to Distributed Erlang. Gain insights into the potential impact of PARTISAN on distributed systems development and performance optimization.

Scaling the Distributed Actor Runtime - PARTISAN

USENIX
Add to list
0:00 / 0:00