Omnisc'IO: A Grammar-Based Approach to Spatial and Temporal I/O Patterns Prediction

Dorier, Matthieu; Ibrahim, Shadi; Antoniu, Gabriel; Ross, Rob

doi:10.1109/sc.2014.56

Cited by 31 publications

(19 citation statements)

References 25 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper extends our previous work [15] by (1) proposing StarSequitur, an extension to Nevll-Manning's Sequitur that keeps the grammar size bounded in case of periodic sequences, and is able to predict futur incoming symbols, (2) making Omnisc'IO capable of predicting any number of future I/O operations, (3) improving Omnisc'IO's predictions capability by weighting predictions when several are available and (4) we performed extensive experiments that demonstrate the substantial benefit of StarSequitur, including the accurate predication of any sequence of N future operations, and bounded grammar sizes. 1) The context in which the operation is executed is extracted by recording the call stack of the program (upper-left part of Figure 1(a)).…”

Section: Introductionsupporting

confidence: 89%

Using Formal Grammars to Predict I/O Behaviors in HPC: The Omnisc'IO Approach

Dorier

Ibrahim

Antoniu

et al. 2016

IEEE Trans. Parallel Distrib. Syst.

Self Cite

View full text Add to dashboard Cite

The increasing gap between the computation performance of post-petascale machines and the performance of their I/O subsystem has motivated many I/O optimizations including prefetching, caching, and scheduling. In order to further improve these techniques, modeling and predicting spatial and temporal I/O patterns of HPC applications as they run has become crucial. In this paper we present Omnisc'IO, an approach that builds a grammar-based model of the I/O behavior of HPC applications and uses it to predict when future I/O operations will occur, and where and how much data will be accessed. To infer grammars, Omnisc'IO is based on StarSequitur, a novel algorithm extending Nevill-Manning's Sequitur algorithm. Omnisc'IO is transparently integrated into the POSIX and MPI I/O stacks and does not require any modification in applications or higher-level I/O libraries. It works without any prior knowledge of the application and converges to accurate predictions of any N future I/O operations within a couple of iterations. Its implementation is efficient in both computation time and memory footprint.

show abstract

Section: Introductionsupporting

confidence: 89%

Using Formal Grammars to Predict I/O Behaviors in HPC: The Omnisc'IO Approach

Dorier

Ibrahim

Antoniu

et al. 2016

IEEE Trans. Parallel Distrib. Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…An example of a computational experimentation application from computational systems biology that is organized this way is the MOLNs virtual cluster provisioning system for scalable cloud-native simulation of gene regulatory networks [Drawert et al, 2015]. MOLNs is part of the Stochastic Simulation Service, StochSS [Drawert et al, 2016]. It exposes an API for depositing and accessing simulation output files either at a shared filesystem served from instance or block storage attached to the cluster master node, or in object storage.…”

Section: Example: a Semi-supervised Model Exploration Workflowmentioning

confidence: 99%

Adapting the Secretary Hiring Problem for Optimal Hot-Cold Tier Placement Under Top-K Workloads

Blamey

Wrede

Karlsson

et al. 2019

2019 19th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)

View full text Add to dashboard Cite

Top-K queries are an established heuristic in information retrieval. This paper presents an approach for optimal tiered storage allocation under stream processing workloads using this heuristic: those requiring the analysis of only the top-K ranked most relevant, or most interesting, documents from a fixed-length stream, stream window, or batch job. In this workflow, documents are analyzed for relevance with a userspecified interestingness function, on which they are ranked, the top-K being selected (and hence stored) for further processing. This workflow allows human in the loop systems, including supervised machine learning, to prioritize documents. This scenario bears similarity to the classic Secretary Hiring Problem (SHP), and the expected rate of document writes, and document lifetime, can be modelled as a function of document index. We present parameter-based algorithms for storage tier placement, minimizing document storage and transport costs. We show that optimal parameter values are a function of these costs. It is possible to model application IO characteristics analytically for this class of workloads. When combined with tiered storage, the tractability of the probabilistic model of IO makes it possible to optimize (and budget for) storage tier allocation a priori, without needing to monitor the application. This contrasts with (often complex) existing work on tiered storage optimization, which is either tightly coupled to specific use cases, or requires active monitoring of application IO load (a reactive approach)ill-suited to long-running or one-off operations common in the scientific computing domain. We evaluate our model with a tracedriven simulation of a bio-chemical model exploration, and give case studies for two cloud storage case studies.

show abstract

“…At runtime, techniques can typically only use information from operations already performed. To predict future accesses, the technique proposed by Dorier et al [8] named Omnisc'IO, intercepts I/O operations and builds a grammar. The approach employed by Tang et al [9] periodically analyzes previous accesses and applies a rule library to predict future accesses (for prefetching).…”

Section: Related Workmentioning

confidence: 99%

Detecting I/O Access Patterns of HPC Workloads at Runtime

Bez

Boito

Nou

et al. 2019

2019 31st International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)

View full text Add to dashboard Cite

In this paper, we seek to guide optimization and tuning strategies by identifying the application's I/O access pattern. We evaluate three machine learning techniques to automatically detect the I/O access pattern of HPC applications at runtime: decision trees, random forests, and neural networks. We focus on the detection using metrics from file-level accesses as seen by the clients, I/O nodes, and parallel file system servers. We evaluated these detection strategies in a case study in which the accurate detection of the current access pattern is fundamental to adjust a parameter of an I/O scheduling algorithm. We demonstrate that such approaches correctly classify the access pattern, regarding file layout and spatiality of accesses-into the most common ones used by the community and by I/O benchmarking tools to test new I/O optimization-with up to 99% precision. Furthermore, when applied to our study case, it guides a tuning mechanism to achieve 99% of the performance of an Oracle solution.

show abstract

Omnisc'IO: A Grammar-Based Approach to Spatial and Temporal I/O Patterns Prediction

Cited by 31 publications

References 25 publications

Using Formal Grammars to Predict I/O Behaviors in HPC: The Omnisc'IO Approach

Using Formal Grammars to Predict I/O Behaviors in HPC: The Omnisc'IO Approach

Adapting the Secretary Hiring Problem for Optimal Hot-Cold Tier Placement Under Top-K Workloads

Detecting I/O Access Patterns of HPC Workloads at Runtime

Contact Info

Product

Resources

About