Efficient scheduling algorithms for real-time distributed systems

Author(s):  
Apurva Shah ◽  
Ketan Kotecha
2021 ◽  
Vol 40 (2) ◽  
pp. 65-69
Author(s):  
Richard Wai

Modern day cloud native applications have become broadly representative of distributed systems in the wild. However, unlike traditional distributed system models with conceptually static designs, cloud-native systems emphasize dynamic scaling and on-line iteration (CI/CD). Cloud-native systems tend to be architected around a networked collection of distinct programs ("microservices") that can be added, removed, and updated in real-time. Typically, distinct containerized programs constitute individual microservices that then communicate among the larger distributed application through heavy-weight protocols. Common communication stacks exchange JSON or XML objects over HTTP, via TCP/TLS, and incur significant overhead, particularly when using small size message sizes. Additionally, interpreted/JIT/VM-based languages such as Javascript (NodeJS/Deno), Java, and Python are dominant in modern microservice programs. These language technologies, along with the high-overhead messaging, can impose superlinear cost increases (hardware demands) on scale-out, particularly towards hyperscale and/or with latency-sensitive workloads.


1982 ◽  
Vol 7 (1) ◽  
pp. 11-20 ◽  
Author(s):  
D.M. Berry ◽  
C. Ghezzi ◽  
D. Mandrioli ◽  
F. Tisato

Sign in / Sign up

Export Citation Format

Share Document