In this paper, we propose TeraHeap, a system that eliminates S/D overhead and expensive GC scans for a large portion of the objects in big data frameworks.

TeraHeap provides direct access to objects on the second heap (no S/D). It also reduces GC cost by fencing the garbage collector from scanning the second heap.

Large heaps are expensive (DRAM) and increase GC cost! ▫ DRAM is expensive in dollar cost, energy, and power. ▫ GC requires expensive scans over large heaps.

Duration: 13:47
Posted: May 23, 2023

Jul 17, 2023 · Our evaluation shows that for the same DRAM size, TeraHeap improves performance by up to 73% and 28% compared to native Spark and Giraph, ...

In this work, we propose TeraHeap, a system that eliminates S/D and GC overheads for a large portion of the data in managed big data analytics frameworks.

Jan 31, 2023 · In this paper, we propose HugeHeap, which extends the managed runtime (JVM) to use a second, high-capacity heap over a fast storage device that ...

TeraHeap: Reducing Memory Pressure in Managed Big Data Frameworks ... To read the full-text of this research, you can request a copy directly from the authors.

TeraHeap: Reducing Memory Pressure in Managed Big Data Frameworks · Authors/Contributors: · Iacovos G. Kolokasis. University of Crete, Greece / ICS-FORTH, Greece.

TeraHeap: Reducing Memory Pressure in Managed Big Data Frameworks. Iacovos G. Kolokasis, Giannos Evdorou, Shoaib Akram, Christos Kozanitis, Anastasios ...