Fast in-memory CRIU for docker containers

Abstract

Server systems with large amounts of physical memory can benefit from using some of the available memory capacity for in-memory snapshots of the ongoing computations. In-memory snapshots are useful for services such as scaling of new workload instances, debugging, during scheduling, etc., which do not require snapshot persistence across node crashes/reboots. Since increasingly more frequently servers run containerized workloads, using technologies such as Docker, the snapshot, and the subsequent snapshot restore mechanisms, would be applied at granularity of containers. However, CRIU, the current approach to snapshot/restore containers, suffers from expensive filesystem write/read operations on image files containing memory pages, which dominate the runtime costs and impact the potential benefits of manipulating in-memory process state. In this paper, we demonstrate that these overheads can be eliminated by using MVAS-kernel support for multiple independent virtual address spaces (VAS), designed specifically for machines with large memory capacities. The resulting VAS-CRIU stores application memory as a separate snapshot address space in DRAM and avoids costly file system operations. This accelerates the snapshot/restore of address spaces by two orders of magnitude, resulting in an overall reduction in snapshot time by up to 10× and restore time by up to 9×. We demonstrate the utility of VAS-CRIU for container management services such as fine-grained snapshot generation and container instance scaling.

Prebaking Functions to Warm the Serverless Cold Start

“…In addition to that, we plan to evaluate the checkpoint/restore as a service including aspects such as the performance to deal with even bigger function code sizes and concurrent snapshots. Finally, we plan to adopt the recently released version of the CRIU tool, that does not require the execution of previleged operations and to experiment with in-memory optimization on CRIU to speed-up snapshot restore [26].…”

COSCO: Container Orchestration Using Co-Simulation and Gradient Based Optimization for Fog Computing Environments

“…Flask is a web application REST client which allows interfacing between hosts and the server. To migrate a container, we use the Checkpoint/Restore In Userspace (CRIU) [49] tool. For each migration decision (a t j , h i ) ∈ D(A t ), a checkpoint of a t j is created which is equivalent to a snapshot of the container.…”

Toward a Live BBU Container Migration in Wireless Networks

“…In general, the migration procedure can be achieved by check pointing the state of running processes in a container and restoring these processes in user space at the current node or at a different node in the network infrastructure. CRIU stores snapshots of container processes as momentary protocol buffer (protobuf) images in a file system [50]. To access the state of processes during the check pointing phase, CRIU uses the /proc file system to collect running threads and child/dependent processes.…”