前言

主要讲了有一定consistency保证的情况下有很不错性能的DB方案Causal Consistency, 其中notion of dependency一定程度上解决了写在不同servers上异步的特点

一、geo-replication

1.1 Spanner

– 通过Paxos保证强consistency
– Two phase commit
– no one site can --write on its own
– but has read transactions, consistent, fairly fast

1.2 Memchche

– 写操作只能通过primary site完成
– read非常快

1.3 新的需求

– 写操作可以再任何server上进行
– 先满足performance再满足consistency

二、预备方案One

每个server都可以有写操作，然后再同步给其它server
这个属于"eventually consistent" design

特点

clients may see updates in different orders
if no writes for long enough, all clients see same data
a pretty loose spec, many ways to implement, easy to get good performance
used in deployed systems, e.g. Dynamo and Cassandra
but can be tricky for app programmers

Example

  C1 uploads photo, adds reference to public list:C1: put(photo) put(list)C2 reads:C2:                       get(list) get(photo)

这里C2是不一定能看到photo的，因为在C1的put(photo) put(list)两个操作不能保证按照原来的顺序传到其它的每个server

决定哪一个write是最近的这个很难做到，但是要做到eventual consistency是需要让每个server都choose the same value

时间比对是一个解决方案，后面再跟上一个server的unique id保证同一时间的两个writes可以区别开来

不过每个server自己的时钟其实是会有差异，这个差异甚至可能是小时级别的，这样可能会prevents any other update for an hour

改进的时间对比方案
each server implements a “Lamport clock” or “logical clock”

 Tmax = highest v# seen (from self and others)T = max(Tmax + 1, wall-clock time)

if some server has a fast clock, everyone who sees a version from that server will advance their Lamport clock

三、预备方案Two

provide a sync(k, v#) operation
– sync() does not return until every datacenter has at least v# for k
这是一个"eventual plus barriers"方案
但是这会变得slow，因为需要等待其它datacenter

– it’s a straightforward, efficient design
– if you don’t need transactions, the semantics are pretty good
– it makes the photo list example work though requires some thought to get order and sync()s right
– read performance is excellent

四、COPS

– we want to forward puts asynchronously (no sync() or waiting)
– we want each shard to forward puts independently (no central log server)

引入了context的概念，也就是每个写操作都包括其dependenc

Example

get(X)->v2context: Xv2
get(Y)->v4context: Xv2, Yv4
put(Z, -)->v3client sends Xv2, Yv4 to shard server along with new Zcontext: Xv2, Yv4, Zv3

问题

这种dependency需要cops aware of，也就是有时候回出现dependency missing的情况
ever-growing client contexts
put(K)->vN sends context, then clears context, replaces with KvN so next put(), e.g. put(L), depends only on KvN
ordered puts/gets aren’t sufficient
a photo list with an ACL (Access Control List)
get(ACL), then get(list)
someone deletes you from ACL, then adds a photo between the two get()s
通过COPS-GT get_trans() approach 解决

五、limitations

conflicting writes are a serious difficulty
awkward for clients to track causality
limited notion of “transaction”
significant overhead to track, communicate, obey causal dependencies

总结

Causal Consistency处于envetual consistency以及strongly consistent之间，没有太多被业界使用

笔记 MIT6.824 Lecture 17: COPS, Causal Consistency相关推荐

CS269I：Incentives in Computer Science 学习笔记 Lecture 17 评分规则和同辈预测（诚实预报和反馈激励）
Lecture 17 Scoring Rules and Peer Prediction(Incentivizing Honest Forecasts and Feedback)(评分规则和同辈预测( ...
mit6.824 2022 lab2
MIT6.824 2022 Raft Raft leader election log persistence log compaction 整体测试后面发现的问题参考代码汇总博客:MIT6.8 ...
MIT6.824环境搭建:wls+vs code
MIT6.824环境搭建:wls+vs code 背景尝试学习MIT 6.824分布式系统,他们的实验使用的是go语言,并且不支持window.打算使用wls+vs code搭建开发环境.这里做记录 ...
MIT6.824 lab4B实验记录
Background 主要是完成一个可以根据group数量,动态调整shard所属的group的分布式kv键值引擎.其中shard->group的配置由shardctrler集群来管理,底层也是 ...
【原】Coursera—Andrew Ng机器学习—课程笔记 Lecture 17—Large Scale Machine Learning 大规模机器学习...
Lecture17 Large Scale Machine Learning大规模机器学习 17.1 大型数据集的学习 Learning With Large Datasets 如果有一个低方差的模型 ...
谷粒商城笔记+踩坑（17）——【认证模块】登录，用户名密码登录+微博社交登录+SpringSession+xxl-sso单点登录
导航: 谷粒商城笔记+踩坑汇总篇目录 5. 用户名密码登录 5.1[认证模块]登录业务 5.1.1 模型类,接收用户名密码 5.1.2 feign客户端新增登录功能 5.1.3 LoginContr ...
Web前端教程学习笔记1.2-2022.10.17始
引言部分: 一.拨云见日(HTML.CSS.切图流程.PC企业站布局.PC游戏站布局) 二.溯本求源(扩展HTML.扩展CSS.HTML5新语法.CSS3新语法.兼容与hack) 三.风生水起(弹性布 ...
读书笔记-人月神话17
有多少书,我读过:有多少事,我做过:记录下学习的点点滴滴,每一天. 回顾一下经典,记录一下悟点. 读书笔记-人月神话 - 另外一面
实习笔记Day9(2022.8.17)
一.总结 1.今天小组进行了初步分工,我和另一个同学负责 k-means 聚类及其并行优化这一部分 2.在网上找了一份 k-means 聚类算法实现的c代码进行学习,以加深对其的理解二.学习笔记 1 ...

笔记 MIT6.824 Lecture 17: COPS, Causal Consistency

目录

前言