2018
DOI: 10.1109/tce.2018.2859630
|View full text |Cite
|
Sign up to set email alerts
|

S-WAL: Fast and Efficient Write-Ahead Logging for Mobile Devices

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
6

Relationship

1
5

Authors

Journals

citations
Cited by 6 publications
(2 citation statements)
references
References 5 publications
0
2
0
Order By: Relevance
“…This result comes from the fact that the conventional hypervisor frequently incurs file sync calls to guarantee strong consistency on the data of the qcow2-based virtual disk whenever it allocates new data clusters. This procedure negatively affects the performance of the virtual disk because each file sync call usually suspends execution of the hypervisor for upcoming write operations until the modified data are entirely reflected onto the underlying storage device [16], [21], [22]. Furthermore, such file sync calls amplify write/sync operations by triggering journaling of the host filesystem, especially in the Ext4 filesystem, and heavily generating additional journal writes with frequent flush operations [13].…”
Section: Motivation a The Performance Overhead Of The Qcow2-basmentioning
confidence: 99%
“…This result comes from the fact that the conventional hypervisor frequently incurs file sync calls to guarantee strong consistency on the data of the qcow2-based virtual disk whenever it allocates new data clusters. This procedure negatively affects the performance of the virtual disk because each file sync call usually suspends execution of the hypervisor for upcoming write operations until the modified data are entirely reflected onto the underlying storage device [16], [21], [22]. Furthermore, such file sync calls amplify write/sync operations by triggering journaling of the host filesystem, especially in the Ext4 filesystem, and heavily generating additional journal writes with frequent flush operations [13].…”
Section: Motivation a The Performance Overhead Of The Qcow2-basmentioning
confidence: 99%
“…To address this problem, they presented a statement-level logging approach that eliminates the superfluous writes of coarse-grained logging and effectively enhances SQLite write performance. Kang et al also observed that the WAL of SQLite severely sacrifices performance for reliability, dramatically increasing the write traffic [24]. They overcame this challenge by using a write-efficient journaling technique based on data compression.…”
Section: Related Workmentioning
confidence: 99%