Towards characterizing cloud backend workloads: insights from Google compute clusters

By Asit K. Mishra, Joseph L. Hellerstein, W. Cirne, Chita R. Das. PERV, 2010

435 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Hardware and Architecture, Information Systems

View Paper: https://www.semanticscholar.org/paper/40528e881a5a896466970650a7c8d7a41b2004ff

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Hardware and Architecture

In Information Systems

Citations in the corpus

Borg: the next generation (2020, neutral): “An early 7-hour long precursor to the Borg traces [21] was analyzed in [25].”
Omega: flexible, scalable schedulers for large compute clusters (2013, background): “These results are broadly similar to other analyses of cluster traces from Yahoo [17], Facebook [7] and Google [20, 24, 25, 29].”
Workload characterization and prediction in the cloud: A multiple time series approach (2012, background): “More recently, some work has been done toward characterizing the workload in a cloud environment [10], [11], [12], [13].”
Joint VM placement and routing for data center traffic engineering (2012, methodology): “We construct a synthesized workload by emulating the DC traffic based on existing traffic measurement studies [21], [22], [23], [24], [25].”
A Hierarchical Framework of Cloud Resource Allocation and Power Management Using Deep Reinforcement Learning (2017, background): “e key enablers of the large-scale cloud computing paradigm. To support such a feature, an efﬁcient and robust scheme of VM allocation and management is critical. Due to the time-variance of workloads [1,2], it is desirable to perform cloud resource allocation and management in an online adaptive man”
Large-scale cluster management at Google with Borg (2015, background): “Several recent studies have analyzed cluster traces from Yahoo!, Google, and Facebook [20, 52, 63, 68, 70, 80, 82], and illustrate the challenges of scale and heterogeneity inherent in these modern datacenters and workloads.”
Interactive Analytical Processing in Big Data Systems: A Cross-Industry Study of MapReduce Workloads (2012, background): “A cross-workload comparison is thus far absent, and use cases beyond the technology industry have not been described.”
Bubble-up: Increasing utilization in modern warehouse scale computers via sensible co-locations (2011, methodology): “Based on the resource requirement, the cluster manager uses an algorithm similar to bin-packing to place each task in a cluster of machines [25].”