消息系统的发展历程
大数据实时数据流处理流程
云原生架构特点
1.存储和计算分离
2.节点对等
3.独立扩展
4.灵活扩容
5.快速容错
企业级流存储层:Apache BookKeeper
BookKeeper分布式日志/流存储具有特性:
1.低延时、高吞吐、持久化
2.强一致
3.高可用
4.I/O隔离
企业级特性:大集群、多租户
原生的跨地域复制
Pulsar介绍:
Apache Pulsar is a cloud-native event streaming platform
Connect, Store, and Process real-time event streams
Connect: Pulsar clients, IO connectors, Protocol handlers
Store: Apache BookKeeper, Tiered storage
Process:
Pulsar Functions - Lightweight serverless computation
Spark / Flink - Unified data processing
Presto - Interactive queries
Tenant & Namespace
Pulsar Architecture
Apache BookKeeper
BookKeeper — 稳定的 IO 质量
Namespace Bundles
Load Manager - Assign bundles to brokers
Topic Lookup
HTTP Topic Lookup
Topic Lookup with Proxies
Geo-Replication
Geo-replication w/o Global ZK
Aggregation Pattern