上一页 1 ··· 13 14 15 16 17 18 19 20 21 ··· 53 下一页

Amazon Aurora: Design Considerations for High Throughput Cloud-Native Relational Databases

摘要: INTRODUCTION 面对的问题,3个方面, In modern distributed cloud services, resilience and scalability are increasingly achieved by decoupling compute from storage 阅读全文
posted @ 2017-05-25 15:35 fxjwind 阅读(1104) 评论(0) 推荐(0) 编辑

Calcite - StreamingSQL

摘要: https://calcite.apache.org/docs/stream.html Calcite’s SQL is an extension to standard SQL, not another ‘SQL-like’ language. The distinction is important, for several reasons: Streaming SQL is ... 阅读全文
posted @ 2017-04-27 17:17 fxjwind 阅读(2474) 评论(0) 推荐(0) 编辑

Flink - ShipStrategyType

摘要: 对于DataStream,可以选择如下的Strategy, /** * Sets the partitioning of the {@link DataStream} so that the output elements * are broadcasted to every parallel instance of the next operation. ... 阅读全文
posted @ 2017-04-14 10:55 fxjwind 阅读(818) 评论(0) 推荐(0) 编辑

Flink - Scheduler

摘要: Job资源分配的过程, 在submitJob中,会生成ExecutionGraph 最终调用到, executionGraph.scheduleForExecution(scheduler) 接着,ExecutionGraph public void scheduleForExecution(SlotProvider slotProvider) throws JobException... 阅读全文
posted @ 2017-04-13 15:13 fxjwind 阅读(1316) 评论(0) 推荐(0) 编辑

Flink – SlotSharingGroup

摘要: SlotSharingGroup 表示不同的task可以共享slot,但是这是soft的约束,即也可以不在一个slot 默认情况下,整个StreamGraph都会用一个默认的“default” SlotSharingGroup,即所有的JobVertex的task都可以共用一个slot /** * A slot sharing units defines which dif... 阅读全文
posted @ 2017-04-13 12:17 fxjwind 阅读(6433) 评论(0) 推荐(0) 编辑

Flink – JobManager.submitJob

摘要: JobManager作为actor, case SubmitJob(jobGraph, listeningBehaviour) => val client = sender() val jobInfo = new JobInfo(client, listeningBehaviour, System.currentTimeMillis(), jo... 阅读全文
posted @ 2017-04-05 17:25 fxjwind 阅读(2331) 评论(0) 推荐(0) 编辑

Flink - StreamJob

摘要: 先看最简单的例子, final StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment(); DataStream> stream = env.addSource(...); stream .map(new MapFunction() {...}) .add... 阅读全文
posted @ 2017-04-01 13:51 fxjwind 阅读(2606) 评论(0) 推荐(0) 编辑

Flink – WindowedStream

摘要: 在WindowedStream上可以执行,如reduce,aggregate,min,max等操作 关键是要理解windowOperator对KVState的运用,因为window是用它来存储window buffer的 采用不同的KVState,会有不同的效果,如ReduceState,ListState Reduce /** * Applies the gi... 阅读全文
posted @ 2017-03-21 17:27 fxjwind 阅读(2578) 评论(0) 推荐(0) 编辑

Flink - watermark生成

摘要: 参考,Flink - Generating Timestamps / Watermarks watermark,只有在有window的情况下才用到,所以在window operator前加上assignTimestampsAndWatermarks即可 不一定需要从source发出 1. 首先,so 阅读全文
posted @ 2017-03-16 18:07 fxjwind 阅读(4670) 评论(0) 推荐(0) 编辑

Copycat - StateMachine

摘要: 看下用户注册StateMachine的过程, MapStateMachine::new这会构造一个supplier 在build中,传入初始化ServerContext ServerContext中, reset逻辑中, 这里看到stateContext的定义, 也是一个单线程,所以这里有两个thr 阅读全文
posted @ 2017-03-16 16:41 fxjwind 阅读(411) 评论(0) 推荐(0) 编辑
上一页 1 ··· 13 14 15 16 17 18 19 20 21 ··· 53 下一页