Abstract
Due to the durability of NVM, we are facing the great challenge of performing efficient memory defragmentation on persistent heaps. To address the problem, we propose an Online Persistent Memory Defragmentation (OPMD) method to manage persistent heaps. Employing two segment trees to track memory allocation and deallocation operations, our method can amortize the cost of global scan, and determine the most valuable objects needed to be moved in logarithmic time. OPMD adopts software transactional memory to move objects and updates object references in constant time using object metadata. We conduct extensive experiments to test the impact of OPMD on the throughput of the operations of linked list and hash table.
Original language | English |
---|---|
Title of host publication | NVMSA 2017 - 6th IEEE Non-Volatile Memory Systems and Applications Symposium |
Publisher | IEEE |
ISBN (Electronic) | 9781538617687 |
DOIs | |
Publication status | Published - 10 Oct 2017 |
Event | 6th IEEE Non-Volatile Memory Systems and Applications Symposium, NVMSA 2017 - Hsinchu, Taiwan Duration: 16 Aug 2017 → 18 Aug 2017 |
Conference
Conference | 6th IEEE Non-Volatile Memory Systems and Applications Symposium, NVMSA 2017 |
---|---|
Country/Territory | Taiwan |
City | Hsinchu |
Period | 16/08/17 → 18/08/17 |
Keywords
- Memory Defragmentation
- NVM
- Persistent heaps
ASJC Scopus subject areas
- Hardware and Architecture