Download as PDF, PPTX
Uploaded byGeoffrey Fox
HPC-ABDS: The Case for an Integrating Apache Big Data Stack with HPC
The document discusses the integration of Apache Big Data Stack (ABDS) with High Performance Computing (HPC) to enhance data analytics capabilities. It presents a framework (HPC-ABDS) that combines over 120 projects from the Apache ecosystem with strong HPC features such as resource management and parallel programming. Several use cases demonstrate the application of this integration in fields like genomics, deep learning, and network science.
HPC-ABDS: The Case for an Integrating Apache Big Data Stack with HPC
- 1.
- 2. Enhanced Apache Big Data Stack ABDS • ~120 Capabilities • >40 Apache •Green layers have strong HPC Integration opportunities • Goal • Functionality of ABDS • Performance of HPC
- 3. Broad Layers in HPC‐ABDS• Workflow‐Orchestration • Application and Analytics •High level Programming • Basic Programming model and runtime – SPMD, Streaming, MapReduce, MPI • Inter process communication – Collectives, point to point, publish‐subscribe • In memory databases/caches • Object‐relational mapping • SQL and NoSQL, File management • Data Transport • Cluster Resource Management (Yarn, Slurm, SGE) • File systems(HDFS, Lustre …) • DevOps (Puppet, Chef …) • IaaS Management from HPC to hypervisors (OpenStack) • Cross Cutting – Message Protocols – Distributed Coordination – Security & Privacy – Monitoring
- 6. Getting High Performance on Data Analytics (e.g. Mahout, R …) • On the systems side, we have two principles – The Apache Big Data Stack with ~120 projects has important broad functionality with a vital large support organization –HPC including MPI has striking success in delivering high performance with however a fragile sustainability model • There are key systems abstractions which are levels in HPC‐ABDS software stack where Apache approach needs careful integration with HPC – Resource management – Storage – Programming model ‐‐ horizontal scaling parallelism – Collective and Point to Point communication – Support of iteration – Data interface (not just key‐value) • In application areas, we define application abstractions to support – Graphs/network – Geospatial – Images etc.
- 7. 4 Forms of MapReduce 7 (a) Map Only (d)Loosely Synchronous (c) Iterative MapReduce (b) Classic MapReduce Input map reduce Input map reduce Iterations Input Output map Pij BLAST Analysis Parametric sweep Pleasingly Parallel High Energy Physics (HEP) Histograms Distributed search Classic MPI PDE Solvers and particle dynamics Domain of MapReduce and Iterative Extensions Science Clouds MPI Giraph Expectation maximization Clustering e.g. Kmeans Linear Algebra, Page Rank (a) Map Only (d) Loosely Synchronous (c) Iterative MapReduce (b) Classic MapReduce InputInput mapmap reducereduce InputInput mapmap reducereduce IterationsIterations InputInput OutputOutput mapmap Pij BLAST Analysis Parametric sweep Pleasingly Parallel High Energy Physics (HEP) Histograms Distributed search Classic MPI PDE Solvers and particle dynamics Domain of MapReduce and Iterative Extensions Science Clouds MPI Giraph Expectation maximization Clustering e.g. Kmeans Linear Algebra, Page Rank MPI is Map followed by Point to Point or Collective Communication – as in style c) plus d)
- 8. HPC‐ABDS Hourglass HPC ABDS System (Middleware) High performance Applications • HPC Yarn for Resource management • Horizontally scalable parallel programming model •Collective and Point to Point communication • Support of iteration System Abstractions/standards • Data format • Storage 120 Software Projects Application Abstractions/standards Graphs, Networks, Images, Geospatial …. SPIDAL (Scalable Parallel Interoperable Data Analytics Library) or High performance Mahout, R, Matlab …..
- 9.
- 10. We are sort of working on Use Cases with HPC‐ABDS • Use Case 10 Internet of Things: Yarn, Storm, ActiveMQ • Use Case 19, 20 Genomics. Hadoop, Iterative MapReduce, MPI, Much better analytics than Mahout •Use Case 26 Deep Learning. High performance distributed GPU (optimized collectives) with Python front end (planned) • Variant of Use Case 26, 27 Image classification using Kmeans: Iterative MapReduce • Use Case 28 Twitter with optimized index for Hbase, Hadoop and Iterative MapReduce • Use Case 30 Network Science. MPI and Giraph for network structure and dynamics (planned) • Use Case 39 Particle Physics. Iterative MapReduce (wrote proposal) • Use Case 43 Radar Image Analysis. Hadoop for multiple individual images moving to Iterative MapReduce for global integration over “all” images • Use Case 44 Radar Images. Running on Amazon
- 11. Features of Harp Hadoop Plug in • Hadoop Plugin (on Hadoop 1.2.1 and Hadoop 2.2.0) • Hierarchical data abstraction on arrays, key‐values and graphs for easy programming expressiveness. •Collective communication model to support various communication operations on the data abstractions. • Caching with buffer management for memory allocation required from computation and communication • BSP style parallelism • Fault tolerance with check‐pointing
- 12. Architecture YARN MapReduce V2 Harp MapReduce ApplicationsMap‐Collective ApplicationsApplication Framework Resource Manager
- 13. Performance on Madrid Cluster (8 nodes) 0 200 400 600 800 1000 1200 1400 1600 100m 500 10m 5k 1m 50k Execution Time (s) Problem Size K‐Means Clustering Harp v.s. Hadoop on Madrid Hadoop 24 coresHarp 24 cores Hadoop 48 cores Harp 48 cores Hadoop 96 cores Harp 96 cores Note compute same in each case as product of centers times points identical Increasing CommunicationIdentical Computation
- 14. Mahout and Hadoop MR – Slow due to MapReduce Python slow as Scripting SparkIterative MapReduce, non optimal communication Harp Hadoop plug in with ~MPI collectives MPI fastest as C not JavaIncreasing Communication Identical Computation
- 15.
- 16. Use case 28: Truthy: Information diffusion research from Twitter Data • Building blocks: – Yarn –Parallel query evaluation using Hadoop MapReduce – Related hashtag mining algorithm using Hadoop MapReduce: – Meme daily frequency generation using MapReduce over index tables – Parallel force‐directed graph layout algorithm using Twister (Harp) iterative MapReduce
- 17.
- 18. 0 200 400 600 800 1000 1200 1400 1600 1800 2000 24 48 96 Total execution time (s) number of mappers Different KmeansImplementation Total execution time vs. mapper number Hadoop 100m,500 Hadoop 10m,5000 Hadoop 1m,50000 Harp 100m,500 Harp 10m,5000 Harp 1m,50000 Pig HD1 100m,500 Pig HD1 10m,5000 Pig HD1 1m,50000 Pig Yarn 100m,500 Pig Yarn 10m,5000 Pig Yarn 1m,50000 Pig Performance Hadoop Harp‐Hadoop Pig +HD1 (Hadoop) Pig + Yarn
- 19. Lines of Code Pig Kmeans Hadoop Kmeans Pig IndexedHBase meme‐cooccur‐ count IndexedHBase meme‐cooccur‐ count Java ~345780 152 ~434 Pig 10 0 10 0 Python / Bash ~40 0 0 28 Total Lines 395 780 162 462
- 20. DACIDR for Gene Analysis (Use Case 19,20) • Deterministic Annealing Clustering and Interpolative Dimension Reduction Method (DACIDR) • Use Hadoop for pleasingly parallel applications, and Twister (replacing by Yarn) for iterative MapReduce applications •Sequences – Cluster Centers • Add Existing data and find Phylogenetic Tree All‐Pair Sequence Alignment Streaming Pairwise Clustering Multidimensional Scaling Visualization Simplified Flow Chart of DACIDR
- 21.
- 22. Lessons / Insights • Integrate (don’t compete) HPC with “Commodity Big data” (Google to Amazon to Enterprise data Analytics) – i.e. improve Mahout; don’t compete with it –Use Hadoop plug‐ins rather than replacing Hadoop – Enhanced Apache Big Data Stack HPC‐ABDS has 120 members – please improve! • HPC‐ABDS+ Integration areas include – file systems, – cluster resource management, – file and object data management, – inter process and thread communication, – analytics libraries, – Workflow – monitoring