[
https://issues.apache.org/jira/browse/YARN-5814?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15670054#comment-15670054
]
Bingxue Qiu commented on YARN-5814:
-----------------------------------
Thanks [~gtCarrera9] for your suggestions:
1. For the writer design issues, We have implemented writer by kafka and a mr
job (for HA) pull data to the realtime nodes of druid. But I'm not so sure this
method is also fit for others. After all tranquility is more simple. I will
give the design of them later. we can choose to implement one or both of them.
2. For the table design, it may not be fit for using timeline.entity table to
hold general timeline entities including container data in druid
implementation. In HBase implementation, we can store general timeline entities
with column family in entity table and scan them by rowkey. But druid is fixed
schema column storage, if we need ad-hoc/agg in real-time, timeline.entity
table maybe a wide table with many columns. It would bring the data redundancy
and generate many rows and increase cache miss. That's why we consider to add
these tables but not timeline.entity
Please feel free to give your suggestions. Thanks!
> Add druid as storage backend in YARN Timeline Service
> ------------------------------------------------------
>
> Key: YARN-5814
> URL: https://issues.apache.org/jira/browse/YARN-5814
> Project: Hadoop YARN
> Issue Type: New Feature
> Components: ATSv2
> Affects Versions: 3.0.0-alpha2
> Reporter: Bingxue Qiu
> Attachments: Add-Druid-in-YARN-Timeline-Service.pdf
>
>
> h3. Introduction
> I propose to add druid as storage backend in YARN Timeline Service.
> We run more than 6000 applications and generate 450 million metrics daily in
> Alibaba Clusters with thousands of nodes. We need to collect and store
> meta/events/metrics data, online analyze the utilization reports of various
> dimensions and display the trends of allocation/usage resources for cluster
> by joining and aggregating data. It helps us to manage and optimize the
> cluster by tracking resource utilization.
> To achieve our goal we have changed to use druid as the storage instead of
> HBase and have achieved sub-second OLAP performance in our production
> environment for few months.
> h3. Analysis
> Currently YARN Timeline Service only supports aggregating metrics at a) flow
> level by FlowRunCoprocessor and b) application level metrics aggregating by
> AppLevelTimelineCollector, offline (time-based periodic) aggregation for
> flows/users/queues for reporting and analysis is planned but not yet
> implemented. YARN Timeline Service chooses Apache HBase as the primary
> storage backend. As we all know that HBase doesn't fit for OLAP.
> For arbitrary exploration of data,such as online analyze the utilization
> reports of various dimensions(Queue,Flow,Users,Application,CPU,Memory) by
> joining and aggregating data, Druid's custom column format enables ad-hoc
> queries without pre-computation. The format also enables fast scans on
> columns, which is important for good aggregation performance.
> To achieve our goal that support to online analyze the utilization reports of
> various dimensions, display the variation trends of allocation/usage
> resources for cluster, and arbitrary exploration of data, we propose to add
> druid storage and implement DruidWriter /DruidReader in YARN Timeline Service.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
