JointConf: Jointly autotuning configuration parameters for modularized graph databases. Issue 12 (29th July 2022)
- Record Type:
- Journal Article
- Title:
- JointConf: Jointly autotuning configuration parameters for modularized graph databases. Issue 12 (29th July 2022)
- Main Title:
- JointConf: Jointly autotuning configuration parameters for modularized graph databases
- Authors:
- Dou, Hui
Mei, Jicheng
Zhang, Yiwen
Chen, Pengfei
Zheng, Zibin - Abstract:
- Abstract: To support different application scenarios, graph databases (GDBs) usually provide a large number of performance‐related parameters for developers. Since manually configuring is both time‐consuming and cost‐intensive, automatically tuning configurations parameters to achieve a better performance has been an urgent need. Besides, considering various graph management requirements, GDBs begin to utilize the modular architecture to interoperate with a wide range of storage and index backends. Due to the complicated interactions among different modules, sequentially tuning each software with previous solutions may fall into a local optimal and it is necessary to jointly autotune the cross‐module configuration parameters. Toward this challenging target, we propose JointConf —a new black‐box approach of jointly autotuning configuration parameters for modularized GDBs. To address the formulated high‐dimensional black‐box optimization problem, JointConf utilizes the recently proposed BO_dropout algorithm. Inspired by the dropout algorithm in neural networks, BO_dropout explores efficient dimension dropout to achieve a high‐dimensional Bayesian optimization. We evaluate the effectiveness of JointConf on a local distributed JanusGraph cluster with three different graph query benchmark applications and experimental results show its advantages over the four baseline search‐based approaches. The necessity of jointly tuning for modularized GDBs is also verified in ourAbstract: To support different application scenarios, graph databases (GDBs) usually provide a large number of performance‐related parameters for developers. Since manually configuring is both time‐consuming and cost‐intensive, automatically tuning configurations parameters to achieve a better performance has been an urgent need. Besides, considering various graph management requirements, GDBs begin to utilize the modular architecture to interoperate with a wide range of storage and index backends. Due to the complicated interactions among different modules, sequentially tuning each software with previous solutions may fall into a local optimal and it is necessary to jointly autotune the cross‐module configuration parameters. Toward this challenging target, we propose JointConf —a new black‐box approach of jointly autotuning configuration parameters for modularized GDBs. To address the formulated high‐dimensional black‐box optimization problem, JointConf utilizes the recently proposed BO_dropout algorithm. Inspired by the dropout algorithm in neural networks, BO_dropout explores efficient dimension dropout to achieve a high‐dimensional Bayesian optimization. We evaluate the effectiveness of JointConf on a local distributed JanusGraph cluster with three different graph query benchmark applications and experimental results show its advantages over the four baseline search‐based approaches. The necessity of jointly tuning for modularized GDBs is also verified in our experiments. Abstract : The manuscript entitled "JointConf: Jointly autotuning configuration parameters for modularized graph databases" by Hui Dou, Jicheng Mei, Yiwen Zhang, Pengfei Chen, and Zibin Zheng focuses on how to jointly autotune configuration parameters for modularized GDBs. An approach named JointConf is proposed to achieve this challenging target and the graphical abstract image shows its framework. Experimental results conducted on a local distributed JanusGraph cluster with three graph query benchmark applications show the advantages of JointConf over four baseline search‐based approaches. … (more)
- Is Part Of:
- Journal of software. Volume 34:Issue 12(2022)
- Journal:
- Journal of software
- Issue:
- Volume 34:Issue 12(2022)
- Issue Display:
- Volume 34, Issue 12 (2022)
- Year:
- 2022
- Volume:
- 34
- Issue:
- 12
- Issue Sort Value:
- 2022-0034-0012-0000
- Page Start:
- n/a
- Page End:
- n/a
- Publication Date:
- 2022-07-29
- Subjects:
- Bayesian optimization -- configuration parameters -- dropout -- modularized graph databases
Software engineering -- Periodicals
Computer software -- Development -- Periodicals
Software maintenance -- Periodicals
005.1 - Journal URLs:
- http://onlinelibrary.wiley.com/journal/10.1002/(ISSN)2047-7481 ↗
http://onlinelibrary.wiley.com/ ↗ - DOI:
- 10.1002/smr.2495 ↗
- Languages:
- English
- ISSNs:
- 2047-7473
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 24536.xml