Dominant Resource Fairness: Fair Allocation of Multiple Resource Types

Authors: Ali Ghodsi, Matei Zaharia, Benjamin Hindman, Andy Konwinski, Scott Shenker, Ion Stoica
Venue:   NSDI 2011

This work presents a very computationally efficient scheduling algorithm in the context of data centers. The problem is presented as fair resource allocation, but the goal is accomplished through choosing which task to schedule (and how many of each). This done by assigning each task with a resource vector of it's requirements, and a corresponding vector of available resources. The algorithm considers each job's allocation via it's dominant resource. For example, if a job uses 1 CPU and 1 GB of memory, but there are 4 CPUs and 8GB of memory, it would be dominated by it's CPU usage (1/4 > 1/8). Tasks are continually scheduled such that the job with the lowest dominant resource share will be given priority. The algorithm takes O(log(n)) for n tasks. The work presents 4 main properties, and was well as 4 other "nice to have". I'll briefly cover some of what I believe are particularly important.

1. Strategy-proofness: It's impossible to claim you need more of a resource and achieve a greater share of resources. This will actually only result in less efficiency, as you'll be using a greater share of resources.

2. Pareto Efficiency: It's not possible to increase the allocation of a user without decreasing the allocation of another user(s). This means the system is effectively maximally occupied.

3. Population/Resource Monotonicity: Essentially, we can't decrease a job's resources because another job has completed a task, or the system's available resources have increased.

4. Sharing Incentive: The algorithm will outperform a blind (1/n) partitioning scheme of all resources.

Max-min Fairness:

This paper is very well cited (900+ as of writing), and has lot of other interesting work that has in turn cited it. Overall, a very good read and direction for future reading.

Comments

Post a Comment

Popular posts from this blog

Fundamental Latency Trade-offs in Architecting DRAM Caches (Alloy Cache)

Authors: Moinuddin K. Qureshi and Gabriel H. Loh Venue:    MICRO 2012 The authors present a new architecture for DRAM cache which targets optimizing latency rather than hit rate. The authors show that for every optimization made to improve hit rate, one must also consider the added cache latency, thus resulting in a new "break even hit rate". The authors compare to three key baselines: an infeasibly large SRAM-tag array, the prior "LH-Cache", and a ideal latency-optimized cache. They find that "unoptimizations" improve latency, while minimally impacting hit-rate. Their final result is a cache which boosts performance 35% improvement over the baseline, and nearly 20% better than the previous LH-cache. The specific contributions are: Moving to a direct mapped cache provides significant improvement (by reducing latency) Combining tag-store and data-store into a single entity improves performance 21% Implementing a small per-core predictor enhances per...
Read more

ZCOMP: Reducing DNN Cross-Layer Memory Footprint Using Vector Extensions

Authors: Berkin Akin, Zeshan A. Christi, and Alaa R. Alameldeen Venue: MICRO, 2019 With accelerators dominating the deep learning space in architecture conferences, this paper stands out as it focuses on reducing DNN inference/training overhead while using a CPU. An obvious question is, with the wide-spread use of GPUs/TPUs for deep learning, why should we focus on optimizing CPUs for deep learning. In a recent paper published at HPCA 2019, Facebook claims that CPUs are preferred for applications where a tight integration is required between DNN and non-DNN tasks. Also, Intel's recent AVX512 has specialized support for DNNs in the form of new instructions called Vector Neural Network Instructions (VNNI). Broadly, optimizing DNNs can be viewed from two different perspectives; computation, and communication. This paper targets reducing communication overhead, more specifically, activation or feature-map communication overhead by compressing them. Compressing activations/weights...
Read more

AutoFDO: Automatic Feedback-Directed Optimization for Warehouse-Scale Applications

Authors: Dehao Chen, David Xinliang Li, Tipp Moseley Venue:    CGO 2016 This paper presents AutoFDO, a system used which profiles warehouse-scale applications, and applies feedback to the compilation for the next release. AutoFDO works by profiling and storing profiles in an aggregate database, annotating the profiles via an intermediate representation, and finally providing feedback. On average, this technique boosts performance by around 10% and works well even with stale releases. For profiles to be useful, they must be in an intermediate representation. This is built from binary-level profile, which uses LBR to map instruction frequencies. By using these frequencies, program counters, and the source, a source profile can be generated. The source profile can be used to build an annotated call-graph with edge frequencies, with some inaccuracy. These annotated call-graphs can then be used as feedback to the compiler. Because of the size of the applications and scale of d...
Read more