Hadoop - Past, Present and Future - v1.2

725 views

Published on

A session focused on ramping you up on what Hadoop is, how its works and what it's capable of. We will also look at what Hadoop 2.x and YARN brings to the table and some future projects in the Hadoop space to keep an eye on.

0 Comments
1 Like
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
725
On SlideShare
0
From Embeds
0
Number of Embeds
89
Actions
Shares
0
Downloads
14
Comments
0
Likes
1
Embeds 0
No embeds

No notes for slide

Hadoop - Past, Present and Future - v1.2

  1. 1. 7/12/14   !  Prepared  for:   v Orange  County  Java  Users  Group     !  Presented  by:   v “Big  Data  Joe”  Rossi   v @bigdatajoerossi   Hadoop   Past,  Present  and  Future  
  2. 2. Roadmap   ~1  hour   1-­‐  What  Makes  Up  Hadoop  1.x?   2-­‐  What’s  New  In  Hadoop  2.x?   3-­‐  The  Future  Of  Hadoop  …  
  3. 3. What  Makes  Up  Hadoop  1.x?  
  4. 4. Hadoop  1.0:  HDFS  +  MapReduce   NameNode   DataNode  /  TaskTracker   DataNode  /  TaskTracker   DataNode  /  TaskTracker   DataNode  /  TaskTracker   JobTracker   Client   1-­‐1   1-­‐2  1-­‐3  
  5. 5. Hadoop  1.0:  HDFS  +  MapReduce   NameNode   DataNode  /  TaskTracker   DataNode  /  TaskTracker   DataNode  /  TaskTracker   DataNode  /  TaskTracker   JobTracker   Client   1-­‐1   1-­‐2   1-­‐3   Reduce  Map   2-­‐1   3-­‐2   3-­‐3   4-­‐1   2-­‐3   4-­‐2   2-­‐2   3-­‐1   4-­‐3   Reduce  Map  
  6. 6. MapReduce  v1  LimitaTons   Scalability   Maximum  cluster  size  is  4,000  nodes  and  maximum  concurrent  tasks  is  40,000   Availability   JobTracker  failure  kills  all  queued  and  running  jobs   Resources  ParVVoned  into  Map  and  Reduce   Hard  parTToning  of  Map  and  Reduce  slots  led  to  low  resource  uVlizaVon   No  Support  for  Alternate  Paradigms  /  Services   Only  MapReduce  batch  jobs,  nothing  else  
  7. 7. HADOOP  1.0   Single  Use  System   Batch  Apps   Apache  Hadoop  1.0:  Single  Use  System   HDFS   (redundant,  reliable  storage)   MapReduce   (cluster  resource  management  and  data   processing)   Pig   Hive  
  8. 8. What’s  New  In  Hadoop  2.x?  
  9. 9. YARN  Replaces   MapReduce   Yet  Another  Resource  NegoVator   YARN   YARN  will  be  the  de-­‐facto  distributed   operaVng  system  for  Big  Data  
  10. 10. Store  DATA  in  one  place   YARN:  Taking  Hadoop  Beyond  Batch   Interact  with  that  data  in  MULTIPLE  WAYS   with  Predictable  Performance  and  Quality  of  Service              ApplicaTons  Run  NaTvely  IN  Hadoop   HDFS2   (redundant,  reliable  storage)   YARN   (cluster  resource  management)   BATCH   (MapReduce)   INTERACTIVE   (Tez)   ONLINE   (HBase)   STREAMING   (DataTorrent)   GRAPH   (Giraph)  
  11. 11. Running  all  on  the  same  Hadoop  cluster  to  give   applicaVons  access  to  all  the  same  source  data!   YARN:  ApplicaTons   MapReduce  v2   Stream  Processing   Master-­‐Worker  Online   In-­‐Memory   Apache  Storm  
  12. 12. 2010     2011     2012     2013     2014     Today   YARN:  Moving  Quickly   Conceived  at  Yahoo!   Alpha  Releases  –  2.0   Beta  Releases  –  2.1   GA  Released  –  2.2   100,000+  nodes,  400,000+  jobs  daily   10  million+  hours  of  compute  daily   Version  2.3   Version  2.4  
  13. 13. YARN:  Dr.  Evil  Approved  
  14. 14. YARN:  How  It  Works   ResourceManager   NodeManager   ApplicaVonMaster   NodeManager   NodeManager   NodeManager   Scheduler   Container   Container   Container   Client  
  15. 15. YARN:  What  Has  Changed?   YARN   MRv1   RM   ResourceManager   AM  ApplicaVonMaster   JT   JobTracker   Scheduler   Scheduler   NM  NodeManager   TT  TaskTracker   Container   Map   Reduce   ResourceManager   Scheduler   JobTracker   Scheduler   NodeManager   ApplicaVonMaster   TaskTracker   Map   Reduce   NodeManager   Container   Container   TaskTracker   Map   Reduce  
  16. 16. !  Scale   !  New  programming  models   and  services   !  Improved  cluster  uVlizaVon   !  Agility   !  Backwards  compaVble  with   MapReduce  v1   !  Mixed  workloads  on  the   same  source  of  data   6  Benefits  of  YARN  
  17. 17. The  Future  of  Hadoop   Projects  and  Roadmap  
  18. 18. Speed   Deliver  interacTve  query  performance.   SQL  on  Hadoop   SQL   Support  array  of  SQL  semanTcs  for  analyTc   applicaTons  running  against  Hadoop.   Scale   SQL  interface  to  Hadoop  designed  for  queries   that  scale  from  Terabytes  to  Petabytes    
  19. 19. Hive  on  Apache  Tez   Hortonworks   Next  Gen  SQL  on  Hadoop   Hive  on  Apache  Spark   Cloudera   Cloudera  Impala   Cloudera     Apache  Drill   MapR  
  20. 20. Dynamic  Scaling   On-­‐demand  cluster  size.  Increase  and  decrease   the  size  with  load.   HOYA:  HBase  (NoSQL)  on  YARN   Easier  Deployment   APIs  to  create,  start,  stop  and  delete  HBase   clusters.   Availability   Recover  from  Region  Server  loss  with  a  new   container.  
  21. 21. Machine  Learning   Framework  well  suited  for  building  machine   learning  jobs.   Microsog  REEF   Scalable  /  Fault  Tolerant   Makes  it  easy  to  implement  scalable,  fault-­‐ tolerant  runTme  environments  for  a  range  of   computaTonal  models.   Maintain  State   Users  can  build  jobs  that  uTlize  data  from   where  it’s  needed  and  also  maintain  state  ager   jobs  are  done.   Retainable   Evaluator   ExecuTon   Framework  
  22. 22. Heterogeneous  Storages  in  HDFS   NameNode   Storage   NameNode   SATA   SSD   Fusion   IO  
  23. 23.     !  Apache  Hadoop  2.5   v NodeManager  Restart  w/o  disrupTon   v Dynamic  Resource  ConfiguraTon     !  Apache  Hadoop  2.6   v Memory  As  Storage  Tier   v Support  For  Docker  Containers   Hadoop  Roadmap   Q3  2014   Q4  2014  
  24. 24. I  Know  You  Have   QuesVons  …   No  such  thing  as  a  stupid  quesVon.   Hadoop:  Past,  Present  and  Future  
  25. 25. OC  Big  Data  Meetup     One  Last  Thing  …   meetup.com/ocbigdata   3rd  Wednesday  Of  The  Month   Next:  July  16st  @  5:45P  
  26. 26. Thank  You!   Hadoop:  Past,  Present  and  Future   Big  Data  Joe  Rossi   hkp://bigdatajoe.io/   @bigdatajoerossi  

×