In Lessons from
Giant-Scale services, Brewer addressed several important methods for evaluation
in the aspect of availability for distributed system in giant scale from a generalized
perspective. First, harvest and yield, instead of traditional uptime, are
introduced as metrics in measurement. Second, DQ Principle analysis is used in
terms of fault impact and evaluation of system design (replication vs.
partitioning).
The paper Experiences
with CoralCDN, with operational practices of CoralCDN, Freedman represented how this decentralized network system (proxy, DNS, indexing) can reduce load on the web server This distributed network system typically serves terabytes of data and tens of millions of HTTP requests per day. in addition to high availability, scalability, fault-tolerances, etc., resource management is another big challenge in distributed systems, with limitations in bandwidth, performance, storage, etc., minimized client latency are always desired. Also, security and resource protection cannot be compromised.
Donghan
No comments:
Post a Comment