bpfCP: Efficient and Extensible Process Checkpointing via eBPF

Live migration, snapshotting, and accelerated startup of applications or containers have long been implemented using checkpoint and restore primitives. To save or 'checkpoint', it is necessary to dump not only its userspace state, but also a large amount of state in the kernel. The current widely used implementation on Linux relies heavily on the /proc file system and special system call interfaces, but these suffer from poor performance and lack extensibility. In this paper, we propose bpfCP, a process checkpointing scheme that dumps in-kernel state via eBPF programs, which improves performance and extensibility. Our preliminary evaluation shows that bpfCP can achieve significant performance improvements in dumping multiple types of in-kernel state of processes.

Authors

Institutions

Publication Details

Published
2025-08-19
DOI
https://doi.org/10.1145/3748355.3748373
Primary Topic
Business Process Modeling and Analysis
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

bpfCP: Efficient and Extensible Process Checkpointing via eBPF

Stephen Kell, J. Deng
Business Process Modeling and Analysis
article

bpfCP: Efficient and Extensible Process Checkpointing via eBPF

Stephen Kell, J. Deng
article en

Abstract

Live migration, snapshotting, and accelerated startup of applications or containers have long been implemented using checkpoint and restore primitives. To save or 'checkpoint', it is necessary to dump not only its userspace state, but also a large amount of state in the kernel. The current widely used implementation on Linux relies heavily on the /proc file system and special system call interfaces, but these suffer from poor performance and lack extensibility. In this paper, we propose bpfCP, a process checkpointing scheme that dumps in-kernel state via eBPF programs, which improves performance and extensibility. Our preliminary evaluation shows that bpfCP can achieve significant performance improvements in dumping multiple types of in-kernel state of processes.

King's College London (GB)
Openalex Percentile: Top 65%
Business Process Modeling and Analysis
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.