Extending Intel PML for hardware-assisted working set size estimation of VMs

Bitchebe, Stella; Mvondo, Djob; Réveillère, Laurent; Palma, Noël De; Tchana, Alain

doi:10.1145/3453933.3454018

Cited by 5 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the hypervisor, Intel introduced PML, the hardware feature that we study in the present paper. Bitchebe et al [16] showed that PML can decrease both VM live migration and checkpointing duration. The authors also extended PML to also log read pages in order to efficiently estimate VM working set size.…”

Section: F Coexistence With the Hypervisormentioning

confidence: 99%

See 1 more Smart Citation

Out of Hypervisor (OoH): When Nested Virtualization Becomes Practical

Bitchebe¹,

Tchana²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

This paper introduces Out of Hypervisor (OoH), a new research axis close to nested virtualization. Instead of emulating a full virtual hardware inside a VM to support a hypevisor, OoH principle is to individually expose current hypervisor-oriented hardware virtualization features to the guest OS so that its processes could also take benefit from those features. In fact, several hardware virtualization features such as Intel PML, SPP, CAT and EPT which currently can only be used by the hypervisor also be beneficial for processes which run inside the VM. We illustrate OoH with Intel PML (Page Modification Logging), a feature which allows efficient dirty page tracking for improving VM live migration. According to the fact that dirty page tracking is at the heart of process checkpointing (CRIU) and concurrent garbage collection (Boehm), we present two OoH PML designs namely Shadow PML (SPML) and Extended PML (EPML). The former requires no hardware changes but incur significant overhead, justifying EPML which extends PML. We evaluated and compared SPML and EPML with /proc and userfaultfd, two default solutions in Linux. We do this using a key value store database as the benchmark. The results show that EPML reduces CRIU checkpointing time by about 14% while leading to a negligible overhead (of about 0.5%) compared to SPML, /proc and userfaultfd.

show abstract

Section: F Coexistence With the Hypervisormentioning

confidence: 99%

“…Xen and KVM, two popular opensource hypervisors, currently support PML when the machine provides it. Bitchebe et al [16] empirically validated the benefits of PML in accelerating VM live migration and checkpointing.…”

Section: Introductionmentioning

confidence: 99%