1. Shark:SQL and Rich Analytics at Scale
Presentaed By
Kirti Dighe
Drushti Gawade

2. What is Shark? Built on the top of the RDD and spark
A new data analysis system
Built on the top of the RDD and spark
Compatible with Apache Hive data, metastores, and queries(HiveQL, UDFs, etc)
Similar speedups of up to 100x
Supports low-latency, interactive queries through in-memory computation
Supports both SQL and complex analytics such as machine learning

3. Shark Architecture Diagram of Architecture
Used to query an existing Hive warehouse returns result much faster without modification
Diagram of Architecture

4. Spark Support partial DAG execution Optimization of joint algorithm
Features of shark
Supports general computation
Provides in-memory storage abstraction-RDD
Engine is optimized for low latency

5. RDD Sparks main abstraction-RDD
Collection stored in external storage system or derived data set
Contains arbitrary data types
Benefits of RDD’s
Return at the speed of DRAM
Use of lineage
Speedy recovery
Immutable-foundation for relational processing.

6. Fault tolerance guarantees
Shark can tolerate the loss of any set of worker nodes.
Recovery is parallelized across the cluster.
The deterministic nature of RDDs also enables straggler mitigation
Recovery works even in queries that combine SQL and machine learning UDFs

7. Executing sql over RDDs
Process of executing sql queries which includes
Query parsing
Logical plan generation
Physical plan generation

8. Engine extension Partial DAG execution(PDE) Static query optimization
Dynamic query optimization
Modification of statistics
Example of statistics
Partition size record count
List of “heavy hitters”
Approximate histogram

9. Join Optimization Skew handling and degree parallelism
Task scheduling overhead

10. Columnar Memory Store
Simply catching records as JVM objects is insuffiecient
Shark employs column oriented storage , a partition of columns is one MaoReduce “record”
Benefits: compact representation, cpu efficient compression, cache locality

11. Machine learning support
Shark supports machine learning-first class citizen
Programming model design to express machine learning algorithm:
1. Language Integration
Shark allows queries to perform logistic regression over a user database.
Ex: Data analysis pipeline that performs logistic regression over database.

12. 2. Execution Engine Integration
Common abstraction allows machine learning computation and SQl queries to share workers and cached data.
Enables end to end fault tolerance

13. Implementation Minimize tail latency CPU cost processing of each
How to improve Query Processing Speed
Minimize tail latency
CPU cost processing of each
Memory-based shuffle
Temporary object creation
Bytecode compilation of expression evaluation

14. Experiments Evaluation of the shark using database
Pavlo et al. Benchmark: 2.1 TB of data reproducing Pavlo et
al.’s comparison of MapReduce vs. analytical DBMSs [25].
TPC-H Dataset: 100 GB and 1 TB datasets generated by the DBGEN program [29].
Real Hive Warehouse: 1.7 TB of sampled Hive warehouse data from an early industrial user of Shark.
Machine Learning Dataset: 100 GB synthetic dataset to measure
the performance of machine learning algorithms.
Shark perform 100x faster than hive

15. Methodology and cluster setup
Amazon EC2 with 100m2.4xlarge nodes
8 virtual code
68 GB of memory
1.6 TB of local storage
Pavlo etal. Benchmarks
1 GB/node ranking table
20 GB/node uservisits table
Selection Query (cluster index)
SELECT pageURL, pageRank
FROM rankings WHERE pageRank > X;

16. Aggregation Queries
SELECT sourceIP, SUM(adRevenue)
FROM uservisits GROUP BY sourceIP;
SELECT SUBSTR(sourceIP, 1, 7), SUM(adRevenue)
FROM uservisits GROUP BY SUBSTR(sourceIP, 1, 7);

17. Join Query
SELECT INTO Temp sourceIP, AVG(pageRank), SUM(adRevenue) as totalRevenue FROM rankings AS R, uservisits AS UV WHERE R.pageURL = UV.destURL AND UV.visitDate BETWEEN Date(’ ’) AND Date(’ ’) GROUP BY UV.sourceIP;
Join query runtime from Join stategies
Pavlo Benchmark chosen by optimizers

18. Data Loading Micro-Benchmarks
To query data in HDFS directly,which means its data ingress rate is at least as fast as Hadoop’s.
Micro-Benchmarks
Aggregation performance
SELECT [GROUP_BY_COLUMN], COUNT(*) FROM lineitem GROUP BY [GROUP_BY_COLUMN]

19. Join selection at runtime
Fault tolerence
Measuring sharks performance in presence of node failures –simulate failures and measure query performance, before,during and after failure recovery.

20. Real hive warehouse
1. Query 1 computes summary statistics in 12 dimensions for users of a specific customer on a specific day.
2. Query 2 counts the number of sessions and distinct customer/client combination grouped by countries with filter cates on eight columns.
3. Query 3 counts the number of sessions and distinct users for
all but 2 countries.
4. Query 4 computes summary statistics in 7 dimensions grouping
by a column, and showing the top groups sorted in descending
order.

21. Machine learning Algorithms
Compare performance of shark running the same work flow in Hive and Hadoop
Workflow consisted of three steps:
1)Selecting the data of interesr from the warehouse using SQL
2)Extracting Features
3)Applying Iterartive Algorithms
Logistic Regresion
K-Means Clustering

22. Logistic Regression,pre-iterarion runtime(seconds)
K-means Cllustering,pre-iteration algorithm

23. Conclusion
Warehouse combining relational queries and complex analytics
Generalizes map reduce using both
Traditional Databse Techniques
Novel Partial DAG Execution
Shark faster than Hive and Hadoop