HeteroOS: OS Design for Heterogeneous Memory Management in Datacenters

Sudarsun Kannan, Ada Gavrilovska, Vishal Gupta, Karsten Schwan

Research output: Contribution to journalArticlepeer-review

6 Scopus citations


Heterogeneous memory management combined with server virtualization in datacenters is expected to increase the software and OS management complexity. State-of-the-art solutions rely exclusively on the hypervisor (VMM) for expensive page hotness tracking and migrations, limiting the benefits from heterogeneity. To address this, we design HeteroOS, a novel application-transparent OS-level solution for managing memory heterogeneity in virtualized systems. The HeteroOS design first makes the guest-OSes heterogeneityaware, and then extracts rich OS-level information about applications' memory usage to place data in the 'right' memory, avoiding page migrations. When such proactive placements are not possible, HeteroOS combines the power of the guest-OSes' information about applications with the VMM's hardware control to track for hotness and migrate only performance-critical pages. Finally, HeteroOS also designs an efficient heterogeneous memory sharing across multiple guest-VMs. Evaluation of HeteroOS with memory, storage, and network-intensive datacenter applications show up to 2x performance improvement compared to the state-of-the-art VMMexclusive approach.

Original languageEnglish (US)
Pages (from-to)13-26
Number of pages14
JournalOperating Systems Review (ACM)
Issue number1
StatePublished - Aug 28 2018
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Hardware and Architecture
  • Computer Networks and Communications


  • 3D-stacked DRAM
  • Heterogeneous Memory
  • Hypervisor
  • Non-volatile memory
  • Operating Systems
  • Virtual Memory
  • Virtualization


Dive into the research topics of 'HeteroOS: OS Design for Heterogeneous Memory Management in Datacenters'. Together they form a unique fingerprint.

Cite this