Conference paper Open Access

User-space I/O for μs-level storage devices

Anastasios Papagiannis; Giorgos Saloustros; Manolis Marazakis; Angelos Bilas


Dublin Core Export

<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:creator>Anastasios Papagiannis</dc:creator>
  <dc:creator>Giorgos Saloustros</dc:creator>
  <dc:creator>Manolis Marazakis</dc:creator>
  <dc:creator>Angelos Bilas</dc:creator>
  <dc:date>2016-10-06</dc:date>
  <dc:description>System software overheads in the I/O path, including VFS and file system code, become more pronounced with emerging low-latency storage devices. Currently, these overheads constitute the main bottleneck in the I/O path and they limit efficiency of modern storage systems. In this paper we present Iris, a new I/O path for applications, that minimizes overheads from system software in the common I/O path. The main idea is the separation of the control and data planes. The control plane consists of an unmodified Linux kernel and is responsible for handling data plane initialization and the normal processing path through the kernel for non-file related operations. The data plane is a lightweight mechanism to provide direct access to storage devices with minimum
overheads and without sacrificing strong protection semantics. Iris requires neither hardware support from the storage devices nor changes in user applications. We evaluate our early prototype and we find that it achieves on a single core up to 1.7× and 2.2× better read and write random IOPS, respectively, compared to the xfs and ext4 file systems. It also scales with the number of cores; using 4 cores Iris achieves 1.84× and 1.96× better read and write random IOPS, respectively.</dc:description>
  <dc:identifier>https://zenodo.org/record/803970</dc:identifier>
  <dc:identifier>10.1007/978-3-319-46079-6_44</dc:identifier>
  <dc:identifier>oai:zenodo.org:803970</dc:identifier>
  <dc:relation>info:eu-repo/grantAgreement/EC/H2020/671553/</dc:relation>
  <dc:relation>doi:10.1145/3041710.3041713</dc:relation>
  <dc:rights>info:eu-repo/semantics/openAccess</dc:rights>
  <dc:rights>https://creativecommons.org/licenses/by-nc-nd/4.0/</dc:rights>
  <dc:subject>NVM</dc:subject>
  <dc:subject>I/O</dc:subject>
  <dc:subject>storage systems</dc:subject>
  <dc:subject>low latency</dc:subject>
  <dc:subject>protection</dc:subject>
  <dc:subject>European Union</dc:subject>
  <dc:subject>Horizon 2020</dc:subject>
  <dc:subject>Euratom</dc:subject>
  <dc:subject>Euratom research &amp; training programme 2014-2018</dc:subject>
  <dc:title>User-space I/O for μs-level storage devices</dc:title>
  <dc:type>info:eu-repo/semantics/conferencePaper</dc:type>
  <dc:type>publication-conferencepaper</dc:type>
</oai_dc:dc>

Share

Cite as