MROrder: Flexible Job Ordering Optimization for Online MapReduce Workloads

1
MROrder Flexible Job Ordering Optimization for
Online MapReduce Workloads
Shanjiang Tang, Bu-Sung Lee, Bingsheng He
School of Computer Engineering Nanyang
Technological University
30th Aug 2013
2
OutLine

• Background Motivations
• MROrder
• Evaluation
• Conclusion

3
MapReduce Computation Model
Map-Phase Computation
Reduce-Phase Computation
Reduce
Intermediate Result
Output Result
Reduce
Intermediate Result
Output Result
Final Result
Input Data
Reduce
Intermediate Result
Output Result
Reduce
Intermediate Result
Output Result
4
Hadoop Execution Model

• Hadoop is an open-source implementation of
  MapReduce Model.
• The cluster computation resources are divided
  into map slots and reduce slots, which are
  configured by Hadoop administrator in advance.
• A MapReduce job generally consists of map tasks
  and reduce tasks.
• Map tasks have to be allocated with map slots,
  and reduce tasks have to be allocated with reduce
  slots.
• 
  

5
Hadoop Execution Model

• 
  

Map slots
Reduce slots
Map tasks can only run on map slots, reduce
tasks can only run on reduce slots
Map tasks start before reduce tasks
6
Job Order VS Performance
time
Map Phase
Reduce Phase
time
Map Phase
Reduce Phase

• Implication Different Job orders have a
  significant impact on performance results!!!
• 
  

7
Our Goals

• Job ordering Optimization is a non-trivial
  approach to improve the performance of MapReduce
  workloads ( i.e., a batch of MapReduce jobs).
• Our work focuses on job ordering optimization for
  online MapReduce workloads under FIFO scheduler,
  where jobs arriving over time.
• Different performance metrics are considered,
  e.g., makespan, total completion time.
• 
  

8
OutLine

• Background Motivations
• MROrder
• Evaluation
• Conclusion

9
Architecture Overview of MROrder

• 
  

10
Policy Module

• Determine when and how to perform job ordering
  optimization for MapReduce jobs.
• We provide two alternative solutions for
  determine when to perform job ordering
  optimization
• PNJ-Dominated Solution.
• performs job ordering when the number of jobs
  in the queue reaches to a threshold , i.e.,
  .
• TP-Dominated Solution.
• invokes periodically after a time
  interval.
• Notes PNJ -- policy for the number of
  job. TP time-based policy.
• 
  

11
Policy Module

• TP-Dominated solution
• TP-Dominated Solution with Fixed Time Interval
  (TP-FTI).
• perform job ordering periodically within
  fixed time interval
• TP-Dominated Solution with Adaptive Time Interval
  (TP-ATI).
• perform job ordering dynamically with
  adaptive time interval, based on the estimated
  running time of workloads.
• 
  

12
TP-FTI
13
TP-ATI
14
Ordering Engine

• Responsible for performing job ordering
  optimization.
• Two types of job ordering approaches
• Simulation-based Ordering Approach (SIM).
• we develop a Hadoop simulator Hsim to look
  for optimal results. It is a brute-force method.
  
• Algorithm-based Ordering Approach (ALG).
• we provide efficient heuristic job ordering
  algorithms for different performance metrics,
  e.g., makespan, total completion time.
• 
  

15
ALG for Makespan
16
ALG for Total Completion Time
17
OutLine

• Background Motivations
• MROrder
• Evaluation
• Conclusion

18
Experiment Setup

• Enviroments
• A Hadoop cluster consisting of 10 nodes, each
  with two Intel X5675 CPUs, 24GB memory and 56GB
  hard disks.
• Workloads
• Synthetic Facebook Workload.
• we generated it based on previously related
  work. Most of jobs are small-size, aiming to use
  it to evaluate the total completion time.
• Tested Workload.
• Most of its jobs are large-size, we use it
  to evaluate the makespan.

19
TP-FTI VS TP-ATI

• TP-ATI is smarter and works better than
  TP-FTI !

?t the suitable threshold of time period for
time-based policy. PITCT performance improvement
of total completion time.
20
ALG VS SIM

• SIM performs better than ALG, but consumes
  more time especially when the number of jobs are
  large.

21
Performance Improvement by MROrder (Simulation
Result)
Total Completion Time is sensitive to the
small-size dominated jobs !
22
Performance Improvement by MROrder (Real
Experiment Result)
Makespan is sensitive to the large-size
dominated jobs !
23
OutLine

• Background Motivations
• MROrder
• Evaluation
• Conclusion

24
Conclusion

• Job ordering optimization is a non-trivial method
  to improve the efficiency of slots resource
  utilization and perform of MapReduce workloads.
• MROrder is a prototype system for online
  MapReduce workloads, being flexible for various
  performance metrics.
• Experimental results show that MROrder improves
  the performance of MapReduce workloads
  significantly.
• The source code of MROrder is available at
• http//sourceforge.net/projects/mrorder/

25
Ongoing and Future Work

• Integrating MROrder into Hadoop system.
• Considering the performance improvement for other
  schedulers, e.g., Hadoop Fair Scheduler, Capacity
  Scheduler.
• Exploring other alternative approaches to improve
  the cluster utilization and performance of
  MapReduce workloads.

26
Acknowledgement

• This work is supported by the User and Domain
  driven data analytics as a Service framework
  project under the ASTAR Thematic Strategic
  Research Programme (SERC Grant No. 1021580034).

27

•  

Thank You !
Question?
28
Accuracy Evaluation of HSim
29
Impact of Inaccuracy in Estimated Map/Reduce
Tasks Time