An End-to-End Automatic Cloud Database Tuning System Using Deep Reinforcement Learning

Zhang, Ji; Liu, Yu; Zhou, Ke; Li, Guoliang; Zhang, Xiao; Cheng, Bin; Xing, Jiashu; Wang, Yangtao; Cheng, Tianheng; Liu, Li; Ran, Minwei; Li, Zekang

doi:10.1145/3299869.3300085

Cited by 221 publications

(180 citation statements)

References 34 publications

Supporting

Mentioning

154

Contrasting

Unclassified

Order By: Relevance

“…Therefore, Cao et al [19] develop two versions of an enhanced multi-objective simulated annealing approach to solve configuration optimization problem with multiple hard constraints, while Wang et al [39] provide a control-theoretic approach to continuously tune a distributed application. Further, based on the reward function calculated with observations, an enhanced reinforcement learning approach is proposed in [20] to online tune configurations for web systems, while Zhang et al [21] design an end-to-end automatic cloud database tuning system using deep reinforcement learning. The most related work to our paper is [22].…”

Section: Black-box Methodsmentioning

confidence: 99%

“…These baseline algorithms are also widely used in tuning hyper-parameters for machine learning models. Therefore, these algorithms are already widely utilized as baseline black-box optimization algorithms in previous work such as [17], [21], [30]. In the following, we provide a brief introduction of each algorithm and give a short description of their hyper-parameter settings in our experiments if necessary.…”

Section: Baseline Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Hdconfigor: Automatically Tuning High Dimensional Configuration Parameters for Log Search Engines

2020

View full text Add to dashboard Cite

Search engines are nowadays widely applied to store and analyze logs generated by largescale distributed systems. To adapt to various workload scenarios, log search engines such as Elasticsearch usually expose a large number of performance-related configuration parameters. As manual configuring is time consuming and labor intensive, automatically tuning configuration parameters to optimize performance has been an urgent need. However, it is challenging because: 1) Due to the complex implementation, the relationship between performance and configuration parameters is difficult to model and thus the objective function is actually a black box; 2) In addition to application parameters, JVM and kernel parameters are also closely related to the performance and together they construct a high dimensional configuration space; 3) To iteratively search for the best configuration, a tool is necessary to automatically deploy the newly generated configuration and launch tests to measure the corresponding performance. To address these challenges, this paper designs and implements HDConfigor, an automatic holistic configuration parameter tuning tool for log search engines. In order to solve the high dimensional optimization problem, we propose a modified Random EMbedding Bayesian Optimization algorithm (mREMBO) in HDConfigor which is a black-box approach. Instead of directly using a black-box optimization algorithm such as Bayesian optimization (BO), mREMBO first generates a lower dimensional embedded space through introducing a random embedding matrix and then performs BO in this embedded space. Therefore, HDConfigor is able to find a competitive configuration automatically and quickly. We evaluate HDConfigor in an Elasticsearch cluster with different workload scenarios. Experimental results show that compared with the default configuration, the best relative median indexing results achieved by mREMBO can reach 2.07×. In addition, under the same number of trials, mREMBO is able to find a configuration with at least a further 10.31% improvement in throughput compared to Random search, Simulated Annealing and BO. INDEX TERMS Log search engine, configuration parameter tuning, black-box optimization, Bayesian optimization, random embedding.

show abstract

Section: Black-box Methodsmentioning

confidence: 99%

Section: Baseline Algorithmsmentioning

confidence: 99%

Hdconfigor: Automatically Tuning High Dimensional Configuration Parameters for Log Search Engines

2020

View full text Add to dashboard Cite

show abstract

“…Table 1 compares the most relevant state-of-the-art approaches. Alvaro [16], OtterTune [1], and CDBTune [42] use several regressors to tune a set of parameters. However, they train the models in the way of maximizing one objective, i.e., predicting local optimal performance.…”

Section: Motivation and Challengesmentioning

confidence: 99%

“…In contrast, Ernest [35] is designed to predict any unknown parameters in the topology but capable of predicting only vcore parameter. Yet, these regression models either (Gaussian Process [1] and multi-layer Neural Network [42]) face a deterioration accuracy due to overfitting and require many samples for model building or (Linear regression [16], Ernest [35]) are simple but achieves unsatisfactory accuracy. We contribute to apply a novel accurate model and develop an adaptive sampling to mitigate the training cost, as follows.…”

Section: Motivation and Challengesmentioning

confidence: 99%

d-Simplexed: Adaptive Delaunay Triangulation for Performance Modeling and Prediction on Big Data Analytics

Chen

Goetsch

Hoque

et al. 2019

IEEE Trans. Big Data

View full text Add to dashboard Cite

Big Data processing systems (e.g., Spark) have a number of resource configuration parameters, such as memory size, CPU allocation, and the number of running nodes. Regular users and even expert administrators struggle to understand the mutual relation between different parameter configurations and the overall performance of the system. In this paper, we address this challenge by proposing a performance prediction framework, called d-Simplexed, to build performance models with varied configurable parameters on Spark. We take inspiration from the field of Computational Geometry to construct a d-dimensional mesh using Delaunay Triangulation over a selected set of features. From this mesh, we predict execution time for various feature configurations. To minimize the time and resources in building a bootstrap model with a large number of configuration values, we propose an adaptive sampling technique to allow us to collect as few training points as required. Our evaluation on a cluster of computers using WordCount, PageRank, Kmeans, and Join workloads in HiBench benchmarking suites shows that we can achieve less than 5% error rate for estimation accuracy by sampling less than 1% of data.

show abstract

“…Por fim, propõe apenas ações locais, uma vez que gera ações de sintonia considerando apenas parâmetros, e nenhum outro tipo de ação de sintonia fina é considerado durante o processo de geração e seleção das ações. Esta mesma estratégia ainda foi estendida também para predizer parâmetros em ambientes virtualizados [56].…”

Section: Técnicas De Aprendizado De Máquinaunclassified

Combinação E Seleção Automática De Ações De Sintonia Fina

OLIVEIRA¹

View full text Add to dashboard Cite

show abstract

An End-to-End Automatic Cloud Database Tuning System Using Deep Reinforcement Learning

Cited by 221 publications

References 34 publications

Hdconfigor: Automatically Tuning High Dimensional Configuration Parameters for Log Search Engines

Hdconfigor: Automatically Tuning High Dimensional Configuration Parameters for Log Search Engines

d-Simplexed: Adaptive Delaunay Triangulation for Performance Modeling and Prediction on Big Data Analytics

Combinação E Seleção Automática De Ações De Sintonia Fina

Contact Info

Product

Resources

About