Author’s | Date | Workloads | Data size | Parameters | Hardware |
---|---|---|---|---|---|
Lin et al. [20] | 2013 | K-means PageRank | 10,000 to 20 mil points 1 mil to 10 mil points | Log analysis | Nodes—6, 2 CPU cores 4 GB memory per node Nodes—4, 16 CPU cores 48 GB memory per node |
Satish and Rohan [18] | 2015 | K-means | 62–1240 MB | Default | Virtual machine Nodes—2, 4 GB RAM and 500 GB (HD) |
Yasir Samadi et al. [7] | 2016 | Micro Benchmarks Web Search SQL Machine Learning | 18–328 MB 5000 to 12 * 10e4 pages | 3 | Virtual machine Disk (SDD)—40 GB |
Petridis et al. [21] | 2017 | K-means shuffling and sort-by-Key | 400Â GB | 12 | Barcelona supercomputing center |
Mavridis et al. [17] | 2017 | Spark SQL and Spark Hive | 1.1 GB, 1.5  GB and 11  GB | Log analysis | Virtual machine—6 Memory—8 GB Master node—8 cores Salve node—4 cores |
Yasir Samadi et al. [9] | 2018 | Micro Benchmarks Web Search SQL Machine Learning | 1  GB, 5 GB and 8 GB | 3 | Virtual machine Disk(SDD)—40  GB |
Proposed experiments | 2020 | WordCount and TeraSort | 50–600 GB | 18 | SNCC, Production Cluster CPU cores—80 Total Storage—60 TB Master node—1 Slaves nodes—9 |