Rack level scheduling for containerized workloads

Show simple item record

dc.contributor.author Xu, Qiumin
dc.contributor.author Malladi, Krishna T.
dc.contributor.author Awasthi, Manu
dc.contributor.other 12th International Conference on Networking, Architecture, and Storage (NAS 2017)
dc.coverage.spatial Shenzhen, CN
dc.date.accessioned 2017-09-19T17:42:31Z
dc.date.available 2017-09-19T17:42:31Z
dc.date.issued 2017-08-07
dc.identifier.citation Xu, Qiumin; Malladi, Krishna T. and Awasthi, Manu; , "Rack level scheduling for containerized workloads", in the 12th International Conference on Networking, Architecture, and Storage (NAS 2017), Shenzhen, CN, Aug. 7-9, 2017. en_US
dc.identifier.uri https://repository.iitgn.ac.in/handle/123456789/3148
dc.identifier.uri https://doi.org/10.1109/NAS.2017.8026873
dc.description.abstract High performance SSDs have become ubiquitous in warehouse scale computing. Increased adoptions can be attributed to their high bandwidth, low latency and excellent random I/O performance. Owing to this high performance, multiple I/O intensive services can now be co-located on the same server. SSDs also introduce periodic latency spikes due to garbage collection. This, combined with multi-tenancy increases latency unpredictability since co-located applications now compete for CPU, memory, and disk bandwidth. The combination of these latency spikes and unpredictability lead to long tail latencies that can significantly decrease the system performance at scale. In this paper, we present a rack-level scheduling algorithm, which dynamically detects and shifts workloads with long tail latencies within servers in the same rack. Different from the global resource management methods, rack-level scheduling utilizes lightweight containers to minimize data movement and message passing overheads, leading to a much more efficient solution to reduce tail latency.With the algorithms implemented in the storage driver of the containerization infrastructure, it becomes viable to deploy and migrate applications in existing server racks without extensive modifications to storage, OS and other subsystems.
dc.description.statementofresponsibility by Qiumin Xu, Krishna T. Malladi and Manu Awasthi.
dc.language.iso en en_US
dc.subject Servers
dc.subject Nonvolatile memory
dc.subject Bandwidth
dc.subject Containers
dc.subject Monitoring
dc.subject Scheduling algorithms
dc.subject Resource management
dc.title Rack level scheduling for containerized workloads en_US
dc.type Article en_US

Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


My Account