In HHH-L mode, Hadoop MapReduce runs over HDFS that is integrated with parallel file system (e.g. Lustre). This is a hybrid mode that stores data in both local storage and Lustre. Lustre provides fault-tolerance in this mode. Therefore, HDFS replication is not required. We evaluate our package with this setup and provide performance comparisons here. For detailed configuration and setup, please refer to our userguide.
TestDFSIO Write and TestDFSIO Read
TestDFSIO Write
TestDFSIO Read
Experimental Testbed: Each node in OSU-RI2 has two fourteen Core Xeon E5-2680v4 processors at 2.4 GHz and 512 GB main memory. The nodes support 16x PCI Express Gen3 interfaces and are equipped with Mellanox ConnectX-4 EDR HCAs with PCI Express Gen3 interfaces. The operating system used is CentOS 7.
These experiments are performed in 8 DataNodes with a total of 64 maps and 32 reduces. Each DataNode has a single 2TB HDD, single 400GB PCIe SSD, and 252GB of RAM disk. HDFS block size is kept to 256 MB. Each NodeManager is configured to run with 12 concurrent containers assigning a minimum of 1.5GB memory per container. The NameNode runs in a different node of the Hadoop cluster. 70% of the RAM disk is used for HHH data storage.
The RDMA-IB design improves the write throughput by up to 34% over HDFS-IPoIB (100Gbps). RDMA-IB-BB design has an improvement of 2.81x compared to HDFS-IPoIB (100Gbps). The performance improvement for read throughput is up to 21% over Lustre-IPoIB (100Gbps). RDMA-IB-BB design has an improvement of 51% over Lustre-IPoIB (100Gbps).
RandomWriter and Sort
RandomWriter Execution Time
Sort Execution Time
Experimental Testbed: Each node in OSU-RI2 has two fourteen Core Xeon E5-2680v4 processors at 2.4 GHz and 512 GB main memory. The nodes support 16x PCI Express Gen3 interfaces and are equipped with Mellanox ConnectX-4 EDR HCAs with PCI Express Gen3 interfaces. The operating system used is CentOS 7.
These experiments are performed in 8 DataNodes with a total of 64 maps and 32 reduces. Each DataNode has a single 2TB HDD, single 400GB PCIe SSD, and 252GB of RAM disk. HDFS block size is kept to 256 MB. Each NodeManager is configured to run with 12 concurrent containers assigning a minimum of 1.5GB memory per container. The NameNode runs in a different node of the Hadoop cluster. 70% of the RAM disk is used for HHH data storage.
The RDMA-IB design improves the job execution time of RandomWriter by 39% comapred to HDFS-IPoIB (100Gbps) and 13% compared to Lustre-IPoIB (100Gbps). The RDMA-IB-BB design improves the job execution time of RandomWriter by 53% comapred to HDFS-IPoIB (100Gbps) and 32% compared to Lustre-IPoIB (100Gbps). For Sort, RDMA-IB has an improvement of 44% compared to HDFS-IPoIB (100Gbps) and 50% compared to Lustre-IPoIB (100Gbps). The RDMA-IB-BB design has an improvement of 67% compared to HDFS-IPoIB (100Gbps) and 60% compared to Lustre-IPoIB (100Gbps).
