John Wilkes

Physical Deployability Matters

Jeffrey C. Mogul, John Wilkes

While many network research papers address issues of deployability, with a few exceptions, this has been limited to protocol compatibility or switch-resource constraints, such as flow table sizes. We argue that good network designs must also consider the costs and complexities of …

us (code pays fourni par la source)

Simulations of Criticality Control Overpack Container Compaction at the Waste Isolation Pilot Plant

Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States), Benjamin Reedlunn, USDOE National Nuclear Security Administration (NNSA), James Bean et autres

Criticality Control Overpack (CCO) containers are being considered for the disposal of defense-related nuclear waste at the Waste Isolation Pilot Plant (WIPP). At WIPP, these containers would be placed in underground disposal rooms, which will naturally close and compact the containers closer …

us (code pays fourni par la source)

Data-driven networking research

Jeffrey C. Mogul, Priya Mahadevan, Christophe Diot, John Wilkes et autres

We in Google's various networking teams would like to increase our collaborations with academic researchers related to data-driven networking research. There are some significant constraints on our ability to directly share data, which are not always widely-understood in the academic community; this …

us (code pays fourni par la source)

A portable BCPL library

John Wilkes

Too often, programs written in BCPL are difficult to port from one system to another, not because of the language, but because of differences between ‘standard’ libraries. Almost without exception, the definitions of these libraries are loose, woolly and inaccurate – the …

Borg

Muhammad Tirmazi, Adam Barker, Nan Deng, Md E. Haque et autres

This paper analyzes a newly-published trace that covers 8 different Borg [35] clusters for the month of May 2019. The trace enables researchers to explore how scheduling works in large-scale production compute clusters. We highlight how Borg has evolved and perform a …

us, gb (code pays fourni par la source)

Autopilot

Krzysztof Rzaḑca, Paweł Findeisen, Jacek Świderski, Przemyslaw Zych et autres

In many public and private Cloud systems, users need to specify a limit for the amount of resources (CPU cores and RAM) to provision for their workloads. A job that exceeds its limits might be throttled or killed, resulting in delaying or …

us, pl (code pays fourni par la source)

Autopilot: Workload Autoscaling at Google Scale

Krzysztof Rzaḑca, Paweł Findeisen, Jacek Świderski, Przemyslaw Zych et autres

Nines are Not Enough

Jeffrey C. Mogul, John Wilkes

Cloud customers want strong, understandable promises (Service Level Objectives, or SLOs) that their applications will run reliably and with adequate performance, but cloud providers don't want to offer them, because they are technically hard to meet in the face of arbitrary customer …

us (code pays fourni par la source)

JSSPP 2018 Keynote

John Wilkes

Ensuring that users in a computation cluster can receive strong guarantees about immediate resource availability is surprisingly hard to do without wasting significant amounts of resources. The Google Flex system gives administrators a way to define resource pools that provide a range …

Replacing Mud Pulse Telemetry with an Electromagnetic System

Iain Lunney, John K. Thompson, John Wilkes, Matthew Chong et autres

Abstract In the budgeting of all major development projects, there is always a desire to capture the financial and operational opportunities of all new and existing technologies; however, this can be difficult if not proven to be viable in advance of the …

gb (code pays fourni par la source)

Keynotes

Nelly Bencomo, Mark Patton, Ragunathan Rajkumar, John Wilkes

These keynotes discussing the following: The role of models@run.time in Autonomic Systems; Columbus smart cities initiative; Connected and automated vehicles: the future of surface transportation? and Building warehouse-scale computers.

gb, us (code pays fourni par la source)

DieHard: Reliable Scheduling to Survive Correlated Failures in Cloud Data Centers

Mina Sedaghat, Eddie Wadbro, John Wilkes, Sara De Luna et autres

In large scale data centers, a single fault can lead to correlated failures of several physical machines and the tasks running on them, simultaneously. Such correlated failures can severely damage the reliability of a service or a job. This paper models the …

se, us (code pays fourni par la source)