SD Big Data Monthly Meetup #4 - Session 2 - WANDisco

Post on 29-Jun-2015

185 views 1 download

Tags:

description

How To Achieve Non-Stop Hadoop

Transcript of SD Big Data Monthly Meetup #4 - Session 2 - WANDisco

Non-Stop Hadoop Enterprise Ready Hadoop Presentation for Big Data Meetup October 8, 2014

2   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

WANdisco Background

•  WANdisco: Wide Area Network Distributed Computing –  Enterprise ready, high availability software solutions that enable globally distributed

organizations to meet today’s data challenges of secure storage, scalability and availability •  Leader in tools for software engineers – Subversion

–  Apache Software Foundation sponsor •  Highly successful IPO, London Stock Exchange, June 2012 (LSE:WAND) •  US patented active-active replication technology granted, November 2012 •  Global locations

–  San Ramon (CA) –  Chengdu (China) –  Tokyo (Japan) –  Boston (MA) –  Sheffield (UK) –  Belfast (UK)

3   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Customers

4   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Non-Stop Hadoop

Non-Intrusive Plugin

Provides Continuous Availability In the LAN / Across the WAN

Active/Active

5   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

3 Key Problems For Multi Cluster Hadoop LAN / WAN

6   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Enterprise Ready Hadoop Characteristics of Mission Critical Applications

•  Require 100% Uptime of Hadoop –  SLA’s, Regulatory Compliance

•  Require HDFS to be Deployed Globally –  Share Data Between Data Centers –  Data is Consistent and Not Eventual

•  Ease Administrative Burden –  Reduce Operational Complexity –  Simplify Disaster Recovery –  Lower RTO/RPO

•  Allow Maximum Utilization of Resource –  Within the Data Center –  Across Data Centers

7   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Single Standby •  Inefficient utilization of resource

–  Journal Nodes –  ZooKeeper Nodes –  Standby Node

•  Performance Bottleneck •  Still tied to the beeper •  Limited to LAN scope

Active / Active •  All resources utilized

–  Only NameNode configuration –  Scale as the cluster grows –  All NameNodes active

•  Load balancing •  Set resiliency (# of active NN) •  Global Consistency

Breaking Away from Active/Passive What’s in a NameNode

8   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Standby Datacenter •  Idle Resource

–  Single Data Center Ingest –  Disaster Recovery Only

•  One way synchronization –  DistCp

•  Error Prone –  Clusters can diverge over time

•  Difficult to scale > 2 Data Centers –  Complexity of sharing data

increases

Active / Active •  DR Resource Available

–  Ingest at all Data Centers –  Run Jobs in both Data Centers

•  Replication is Multi-Directional –  active/active

•  Absolute Consistency –  Single HDFS spans locations

•  ‘N’ Data Center support –  Global HDFS allows appropriate

data to be shared

Breaking Away from Active/Passive What’s in a Data Center

9   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

One Cluster Approach

•  Example Applications

–  HBASE –  RT Query –  Map Reduce

•  Poor Resource Management

–  Data Locality Issues –  Network Use –  Complex

Multiple Clusters

10   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Creating Multiple Clusters

•  Example Applications

–  HBASE –  RT Query –  Map Reduce

•  Need to share data between clusters

–  DistCp / Stale Data –  Inefficient use of

storage and or network

–  Some clusters may not be available

Multiple Clusters

11   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Cluster Zones Zoning for Optimal Efficiency

1 100%

HDFS  

Consistency  

12   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Multi Datacenter Hadoop Disaster Recovery

WAN  REPLICATION    

Absolute  Consistency  Maximum  Resource  Use  

Lower  Recovery  Time/Point    

Replicate  Only  What  You  Want  BeCer  UFlizaFon  of  Power/Cooling  

Lower  TCO  LAN  Speed  Performance  

 

Technical Overview Hadoop Powered by WANdisco

14   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Periodic Synchronization DistCp

Parallel Data Ingest Load Balancer, Streaming

Multi Data Center Hadoop Today What's wrong with the status quo

15   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Periodic Synchronization DistCp

Multi Data Center Hadoop Today Hacks currently in use

•  Runs as Map reduce •  DR Data Center is read only •  Over time, Hadoop clusters

become inconsistent •  Manual and labor intensive

process to reconcile differences •  Inefficient use of the network

16   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Parallel Data Ingest Load Balancer, Flume

Multi Data Center Hadoop Today Hacks currently in use

•  Hiccups in either of the Hadoop cluster causes the two file systems to diverge

•  Potential to run out of buffer when WAN is down

•  Requires constant attention and sys-admin hours to keep running

•  Data created on the cluster is not replicated

•  Use of streaming technologies (like flume) for data redirection are only for streaming

17   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

DConE Distributed Coordination Engine

•  WANdisco’s patented WAN capable paxos implementation –  Mathematically proven –  Provides distributed co-ordination of File system metadata

•  Active/Active (All locations) •  Create, Modify, Delete •  Shared nothing (No Leader)

•  No restrictions on distance between datacenters –  US Patent granted for time independent implementation of Paxos

•  Not based on SAN block device synchronization such as EMC SRDF –  SAN block replication has distance limits resulting from the inability of file systems

such as NTFS and ext4 to tolerate long RTTs to block storage –  Possible distribution of corrupted blocks

PAXOS

Paxos is a family of protocols for solving consensus in a network of unreliable processors.

Consensus is the process of agreeing on one result among a group of participants.

This problem becomes difficult when the participants or their communication medium may experience failures.

18   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

•  Majority Quorum –  A fixed number of participants –  The Majority must agree for change

•  Failure –  Failed nodes are unavailable –  Normal operation continue on nodes

with quorum

•  Recovery / Self Healing –  Nodes that rejoin stay in safe mode

until they are caught up

•  Disaster Recovery –  A complete loss can be brought back

from another replica

How DConE Works WANdisco Active/Active Replication

TX  id:  168  TX  id:  169  TX  id:  170  TX  id:  171  TX  id:  172  TX  id:  173  

TX  id:  168  TX  id:  169  TX  id:  170  TX  id:  171  TX  id:  172  TX  id:  173  

TX  id:  168  TX  id:  169  TX  id:  170  TX  id:  171  TX  id:  172  TX  id:  173  

Proposal  170  

Agree  170  

Agree  170  

Proposal  171  Agree  172  Agree  173  

Agree  171  Proposal  172  Proposal  173  

B  

A  

C  Agree  170  Agree  171   Agree  172  

Agree  173  

19   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Architecture of a Non-Stop Hadoop

20   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Use Cases

•  Eliminate The Performance Bottleneck of a Single Active NameNode •  Multi Data-Center Ingest

–  Information doesn't need to be sent to one DC and then copied back to the other using DistCP –  Parallel ingest methods don’t require redirected data streams –  Ingest data at, or close to the source –  Global Analysis (Logs, Click Streams, etc…)

•  Cluster Zones –  Efficient use of resource based on application profile –  HBASE, IMPALA, Storm, Map Reduce, SPARK, etc… –  Heterogeneous Clusters Supported

•  Maximize Data Center Resource Utilization –  All datacenters can be used to run different jobs concurrently

•  Disaster Recovery –  Data is as current as possible (no periodic synchs) –  Virtually zero downtime to recover from regional data center failure –  Regulatory compliance

21   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

•  Optimized hardware profiles for job specific tasks –  Batch –  Real-time –  NoSQL (HBASE)

•  Set replication factors per sub-cluster

•  Use at LAN or WAN scope

•  Resilient to NameNode failures

Use Case: Heterogeneous Hardware

22   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

•  Maximize Resource Utilization –  No idle standby

•  Isolate Dev and Test Clusters –  Share data not resource

•  Carve off hardware for a specific group

–  Prevents a bad map/reduce job from bringing down the cluster

•  Guarantee Consistency and availability of data

–  Data is instantly available

Use Case: Sub-Clusters

23   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Non-Stop Hadoop Demonstration

24   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Q & A

Question and Answer Feel free to submit your questions

25   WWW.WANDISCO.COMREALIZING THE POSSIBILITIES OF BIG DATA

Thank you