A file is not a file

Harter, Tyler; Dragga, Chris; Vaughn, Michael; Arpaci-Dusseau, Andrea C.; Arpaci-Dusseau, Remzi H.

doi:10.1145/2043556.2043564

Cited by 56 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Layer reuse improves the service startup speed by optimizing the pull time, but the effect of layer reuse is very dependent on the number of layers that can be reused locally by the node, and there is a significant upper limit on its optimization effect. Smet et al 12,13 proposed a Docker image layer pre-placement method that connects to a different image layer storage server when a service request arrives and pulls the image layer required to start the service, which does not reduce the data required to build the image, although it optimizes the container startup efficiency at the network transmit level. And Yin et al, 13,14 still did not reduce the data transmission volume, although the storage strategy of the image layer is further optimized at runtime.…”

Section: Layer Reuse Mechanism Methodsmentioning

confidence: 99%

“…Smet et al 12,13 proposed a Docker image layer pre‐placement method that connects to a different image layer storage server when a service request arrives and pulls the image layer required to start the service, which does not reduce the data required to build the image, although it optimizes the container startup efficiency at the network transmit level. And Yin et al, 13,14 still did not reduce the data transmission volume, although the storage strategy of the image layer is further optimized at runtime.…”

Section: Related Workmentioning

confidence: 99%

“…Harter et al 12 developed a benchmark to evaluate the startup time of containerized applications and found that pull time accounted for 76% of container startup time, which means the network transmission time of image files is the leading performance bottleneck affecting Docker startup efficiency. This performance can further deteriorate in specific cases in edge environments affected by limited network resources, congestion, and other factors, which can lead to service unavailability.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An optimal container update method for edge‐cloud collaboration

et al. 2023

View full text Add to dashboard Cite

Emerging computing paradigms provide field‐level service responses for users, for example, edge computing, fog computing, and MEC. Edge virtualization technologies represented by Docker can provide a platform‐independent, low‐resource‐consumption operating environment for edge service. The image‐pulling time of Docker is a crucial factor affecting the start‐up speed of edge services. The layer reuse mechanism of native Docker cannot fully utilize the duplicate data of node local images. In this paper, we propose a chunk reuse mechanism (CRM), which effectively targets node‐local duplicate data during container updates and reduces the volume of data transmission required for image building. We orchestrate the CRM process for cloud and remote‐cloud nodes to ensure that the resource overhead from container update data preparation and image reconstruction is within an acceptable range. The experimental results show that the CRM proposed in this paper can effectively utilize the node local duplicate data in the synchronous update of containers in multiple nodes, reduce the volume of data transmission, and significantly improve container update efficiency.

show abstract

Section: Layer Reuse Mechanism Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An optimal container update method for edge‐cloud collaboration

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Harter et al [22], Considering the slowness of Docker containers and by making changes to the Linux kernel to share a cache, proposed a model for these containers in which it identifies and loads the packages needed to run the software. Other packages are also loaded in a lazy manner.…”

Section: Optimization For the Use Of Prerequisite Packagesmentioning

confidence: 99%

A heuristic-based package-aware function scheduling approach for creating a trade-off between cold start time and cost in FaaS computing environments

et al. 2023

View full text Add to dashboard Cite

With the migration of the enterprise applications to micro-services and containers, cloud service providers, starting with Amazon in 2014, announced a new computational model called function-as-aservice. In these platforms, developers create a set of fine-grained functions with shorter execution times instead of developing coarse-grained software. In addition, the management of system resources and servers is entrusted to cloud service providers. This model has many benefits, such as reducing costs, improving resource utilization, and helping developers focus on the core logic of applications. But still faces many challenges such as balancing cost, balancing performance, programming models, using current dev tools, containers' cold start problem, saving data in caches, security issues, privacy concerns, and scheduling challenges like execution time prediction. In this paper, we focus on scheduling and cold start problems. Compromise occurs when keeping warm operating environments which can reduce cold start times but increase costs. In this study, we propose a dynamic waiting time adjustment approach. We aim to create a trade-off by using four different types of decisions at runtime using a heuristic method and analyzing the function dependency graph, functions' invocation frequency, and other environmental parameters. The proposed method shows a 32% improvement over the fixedtime method (i.e. the method used by Apache OpenWhisk). This comparison is made from the cumulative measurement viewpoint which is a combination of response time, turnaround time, cost, and utilization.

show abstract

“…Often, files are merely named address spaces that contain many internal objects with frequent, crash-consistent updates. Small, random writes are common on both desktop machines [26] and in the cloud through the use of key-value stores, data base backends, such as SQLite [15] and LevelDB [23], revision management systems, and distributed configuration software, such as Zookeeper [4]. On many file systems, efficient crash consistency for these applications is difficult and slow so many applications sacrifice correctness for performance [42].…”

Section: Application Demands On the File Systemmentioning

confidence: 99%

Strata

Kwon

Fingler

Hunt

et al. 2017

Proceedings of the 26th Symposium on Operating Systems Principles

116

View full text Add to dashboard Cite

Current hardware and application storage trends put immense pressure on the operating system's storage subsystem. On the hardware side, the market for storage devices has diversified to a multi-layer storage topology spanning multiple orders of magnitude in cost and performance. Above the file system, applications increasingly need to process small, random IO on vast data sets with low latency, high throughput, and simple crash consistency. File systems designed for a single storage layer cannot support all of these demands together. We present Strata, a cross-media file system that leverages the strengths of one storage media to compensate for weaknesses of another. In doing so, Strata provides performance, capacity, and a simple, synchronous IO model all at once, while having a simpler design than that of file systems constrained by a single storage device. At its heart, Strata uses a log-structured approach with a novel split of responsibilities among user mode, kernel, and storage layers that separates the concerns of scalable, high-performance persistence from storage layer management. We quantify the performance benefits of Strata using a 3-layer storage hierarchy of emulated NVM, a flash-based SSD, and a high-density HDD. Strata has 20-30% better latency and throughput, across several unmodified applications, compared to file systems purpose-built for each layer, while providing synchronous and unified access to the entire storage hierarchy. Finally, Strata achieves up to 2.8× better throughput than a block-based 2-layer cache provided by Linux's logical volume manager. CCS CONCEPTS • Information systems → Hierarchical storage management; Storage class memory; • Software and its engineering → File systems management;

show abstract

A file is not a file

Cited by 56 publications

References 23 publications

An optimal container update method for edge‐cloud collaboration

An optimal container update method for edge‐cloud collaboration

A heuristic-based package-aware function scheduling approach for creating a trade-off between cold start time and cost in FaaS computing environments

Strata

Contact Info

Product

Resources

About