DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yi, Shushu | ko |
dc.contributor.author | Pan, Xiurui | ko |
dc.contributor.author | Li, Qiao | ko |
dc.contributor.author | Li, Qiang | ko |
dc.contributor.author | Wang, Chenxi | ko |
dc.contributor.author | Mao, Bo | ko |
dc.contributor.author | Jung, Myoungsoo | ko |
dc.contributor.author | Zhang, Jie | ko |
dc.date.accessioned | 2024-09-11T19:00:10Z | - |
dc.date.available | 2024-09-11T19:00:10Z | - |
dc.date.created | 2024-06-16 | - |
dc.date.issued | 2024-07-10 | - |
dc.identifier.citation | 2024 USENIX Annual Technical Conference, ATC 2024 | - |
dc.identifier.uri | http://hdl.handle.net/10203/322919 | - |
dc.description.abstract | All-flash array (AFA) is a popular approach to aggregate the capacity of multiple solid-state drives (SSDs) while guaranteeing fault tolerance. Unfortunately, existing AFA engines inflict substantial software overheads on the I/O path, such as the user-kernel context switches and AFA internal tasks (e.g., parity preparation), thereby failing to adopt next-generation high-performance SSDs. Tackling this challenge, we propose ScalaAFA, a unique holistic design of AFA engine that can extend the throughput of next-generation SSD arrays in scale with low CPU costs. We incorporate ScalaAFA into user space to avoid user-kernel context switches while harnessing SSD built-in resources for handling AFA internal tasks. Specifically, in adherence to the lock-free principle of existing user-space storage framework, ScalaAFA substitutes the traditional locks with an efficient message-passing-based permission management scheme to facilitate inter-thread synchronization. Considering the CPU burden imposed by background I/O and parity computation, ScalaAFA proposes to offload these tasks to SSDs. To mitigate host-SSD communication overheads in offloading, ScalaAFA takes a novel data placement policy that enables transparent data gathering and in-situ parity computation. ScalaAFA also addresses two AFA intrinsic issues, metadata persistence and write amplification, by thoroughly exploiting SSD architectural innovations. Comprehensive evaluation results indicate that ScalaAFA can achieve 2.5× write throughput and reduce average write latency by a significant 52.7%, compared to the state-of-the-art AFA engines. | - |
dc.language | English | - |
dc.publisher | USENIX | - |
dc.title | ScalaAFA: Constructing User-Space All-Flash Array Engine with Holistic Designs | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.citation.publicationname | 2024 USENIX Annual Technical Conference, ATC 2024 | - |
dc.identifier.conferencecountry | US | - |
dc.identifier.conferencelocation | Santa Clara, CA | - |
dc.contributor.localauthor | Jung, Myoungsoo | - |
dc.contributor.nonIdAuthor | Yi, Shushu | - |
dc.contributor.nonIdAuthor | Pan, Xiurui | - |
dc.contributor.nonIdAuthor | Li, Qiao | - |
dc.contributor.nonIdAuthor | Li, Qiang | - |
dc.contributor.nonIdAuthor | Wang, Chenxi | - |
dc.contributor.nonIdAuthor | Mao, Bo | - |
dc.contributor.nonIdAuthor | Zhang, Jie | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.