Storage-Saving Scheduling Policies for Clusters Running Containers

Funari, Ludovico; Petrucci, Luca; Detti, Andrea

doi:10.1109/tcc.2021.3104662

Cited by 5 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To collect data, we practically evaluate the deployment times of 500 images in two formats. Specifically, the images are tested under 50 different bandwidths (ranging from 1Mbps to 100Mbps), and 5 different conversion parallelisms (i.e., 1,2,4,8,16). Each example in the dataset is represented by multiple fields, <image size, category tag, repository name, conversion parallelism, conversion time, converted size, net bandwidth, startup data size, optimal image format>.…”

Section: Image Format Recommendation Systemmentioning

confidence: 99%

“…For layers of images, Sharma et al [31] find that container images have smaller sizes compared to VM images. Funari et al [4] observe the distribution of images in clusters and find that as the number of nodes increases, the effectiveness of layer-level sharing decreases. Zhao et al [12] analyze the layer redundant in the registry and find that images share numerous small-sized layers.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Grained Trace Collection, Analysis, and Management of Diverse Container Images

Huang,

Zhang,

Fan

et al. 2024

IEEE Trans. Comput.

View full text Add to dashboard Cite

Container technology is getting popular in cloud environments due to its lightweight feature and convenient deployment. The container registry plays a critical role in container-based clouds, as many container startups involve downloading layer-structured container images from a container registry. However, the container registry is struggling to efficiently manage images (i.e., transfer and store) with the emergence of diverse services and new image formats. The reason is that the container registry manages images uniformly at layer granularity. On the one hand, such uniform layer-level management probably cannot fit the various requirements of different kinds of containerized services well. On the other hand, new image formats organizing data in blocks or files cannot benefit from such uniform layer-level image management. In this paper, we perform the first analysis of image traces at multiple granularities (i.e., image-, layer-, and file-level) for various services and provide an in-depth comparison of different image formats. The traces are collected from a production-level container registry, amounting to 24 million requests and involving more than 184 TB of transferred data. We provide a number of valuable insights, including request patterns of services, file-level access patterns, and bottlenecks associated with different image formats. Based on these insights, we also propose two optimizations to improve image transfer and application deployment.

show abstract

Section: Image Format Recommendation Systemmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Multi-Grained Trace Collection, Analysis, and Management of Diverse Container Images

Huang,

Zhang,

Fan

et al. 2024

IEEE Trans. Comput.

View full text Add to dashboard Cite

show abstract

“…In our previous work [18] we make use of an efficient SMT solver [77] to derive feasible control signals encoded in a QN performance model, but no optimization was considered (as we do in this paper). Funari et al [78] propose an analytical model for evaluating storage occupancy of clusters hosting containerized applications and various scheduling policies are introduced to prevent the growth of storage utilization as cluster size increases. Tadakamalla et al [79] present a single-queue multiple-server system model (G/G/c) subject to workload surges and scales the number of servers or their capacity to mitigate the effects of such surges.…”

Section: Related Workmentioning

confidence: 99%

Autoscaling Solutions for Cloud Applications Under Dynamic Workloads

Quattrocchi,

Incerto,

Pinciroli

et al. 2024

IEEE Trans. Serv. Comput.

View full text Add to dashboard Cite

Autoscaling systems provide means to automatically change the resources allocated to a software system according to the incoming workload and its actual needs. Public cloud providers offer a variety of autoscaling solutions, ranging from those based on user-written rules to more sophisticated ones. Originally, these solutions were conceived to manage clusters of virtual machines, while more recently, they have also been employed in the operation of containers. This paper analyses the autoscaling solutions provided by three major cloud providers, namely Amazon Web Services, Google Cloud Platform, and Microsoft Azure, and compares them against two solutions we develop based on control theory (ScaleX ) and queuing theory (QN-CTRL). We evaluate the different approaches using both an in-house simulation engine and cloud deployments by feeding them with various synthetic and real-world workloads. Our extensive evaluation collects both simulation results and real measurements by which we can assess that both ScaleX and QN-CTRL outperform industrial techniques in most cases when considering the trade-offs between the service-level-agreement (SLA) violations and the optimal usage of resources.

show abstract