Skip to main content
Fig. 21 | Journal of Big Data

Fig. 21

From: Comparison of sort algorithms in Hadoop and PCJ

Fig. 21

Strong scaling of the Hadoop and PCJ implementations of TeraSort benchmark for various number of records. Each map and reduce task in Hadoop was requested with 10 GB of memory. The compute nodes were placed on the same nodes as datanodes. The results for PCJ were gathered using 1, 2, 4 and 8 nodes (with 80 threads per node; Xn80t) and using 8 nodes (with 10, 20, 40 and 80 threads per node; 8nXt)

Back to article page