Learning-Assisted Write Latency Optimization for Mobile Storage

I/O activities of mobile storage are highly synchronous. Flash garbage collection activities in mobile storage introduce extra delay to write requests and negatively impact on user perceived-latency. Runtime write demand is subject to correlation between multiple parameters, such as network connecti...

Full description

Saved in:
Bibliographic Details
Main Authors: Tsai, Wei-Chu, Wu, Sung-Ming, Chang, Li-Pin
Format: Conference Proceeding
Language:English
Subjects:
Correlation
Global Positioning System
Mobile storage
NAND flash
Optimization
Prediction algorithms
Smart phones
smartphones
Training
Wireless fidelity
XG-Boost
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 6
container_issue
container_start_page 1
container_title
container_volume
creator Tsai, Wei-Chu
Wu, Sung-Ming
Chang, Li-Pin
description I/O activities of mobile storage are highly synchronous. Flash garbage collection activities in mobile storage introduce extra delay to write requests and negatively impact on user perceived-latency. Runtime write demand is subject to correlation between multiple parameters, such as network connectivity, GPS coordinates, and current time. We propose predicting write demand with a learning algorithm, XGBoost, and conducting background, rate-based garbage collection to optimize write latency without premature, excessive flash erasure. Our method reduced the 99-th percentile write latency by 56% compared to on-demand garbage collection and decreased flash erase count by 51% compared to unconditional background garbage collection.
doi_str_mv 10.1109/RTCSA.2019.8864577
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_8864577</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8864577</ieee_id><sourcerecordid>8864577</sourcerecordid><originalsourceid>FETCH-LOGICAL-i118t-97571b70bbe30308d46a9f7bbc8343781fcbbfb2ae7ceb333a2e7afa0076b8e33</originalsourceid><addsrcrecordid>eNotz0FLwzAUwPEoCM65L6CXfoHWvLy2LzlJKTqFysBNPI6kexmRrR1pLvPTe3Cn_-0HfyEeQBYA0jx9btp1UygJptC6LiuiK3EHpDQgGDLXYqZQVTmghFuxmKYfKSUCkVFqJp47tnEIwz5vpilMiXfZdwyJs84mHvpztjqlcAy_NoVxyPwYs4_RhQNn6zRGu-d7cePtYeLFpXPx9fqyad_ybrV8b5suDwA65YYqAkfSOUaJUu_K2hpPzvUaSyQNvnfOO2WZenaIaBWT9VZKqp1mxLl4_HcDM29PMRxtPG8vv_gHApdKNw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Learning-Assisted Write Latency Optimization for Mobile Storage</title><source>IEEE Xplore All Conference Series</source><creator>Tsai, Wei-Chu ; Wu, Sung-Ming ; Chang, Li-Pin</creator><creatorcontrib>Tsai, Wei-Chu ; Wu, Sung-Ming ; Chang, Li-Pin</creatorcontrib><description>I/O activities of mobile storage are highly synchronous. Flash garbage collection activities in mobile storage introduce extra delay to write requests and negatively impact on user perceived-latency. Runtime write demand is subject to correlation between multiple parameters, such as network connectivity, GPS coordinates, and current time. We propose predicting write demand with a learning algorithm, XGBoost, and conducting background, rate-based garbage collection to optimize write latency without premature, excessive flash erasure. Our method reduced the 99-th percentile write latency by 56% compared to on-demand garbage collection and decreased flash erase count by 51% compared to unconditional background garbage collection.</description><identifier>EISSN: 2325-1301</identifier><identifier>EISBN: 1728131979</identifier><identifier>EISBN: 9781728131979</identifier><identifier>DOI: 10.1109/RTCSA.2019.8864577</identifier><language>eng</language><publisher>IEEE</publisher><subject>Correlation ; Global Positioning System ; Mobile storage ; NAND flash ; Optimization ; Prediction algorithms ; Smart phones ; smartphones ; Training ; Wireless fidelity ; XG-Boost</subject><ispartof>2019 IEEE 25th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA), 2019, p.1-6</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8864577$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,23930,23931,25140,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8864577$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Tsai, Wei-Chu</creatorcontrib><creatorcontrib>Wu, Sung-Ming</creatorcontrib><creatorcontrib>Chang, Li-Pin</creatorcontrib><title>Learning-Assisted Write Latency Optimization for Mobile Storage</title><title>2019 IEEE 25th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)</title><addtitle>RTCSA</addtitle><description>I/O activities of mobile storage are highly synchronous. Flash garbage collection activities in mobile storage introduce extra delay to write requests and negatively impact on user perceived-latency. Runtime write demand is subject to correlation between multiple parameters, such as network connectivity, GPS coordinates, and current time. We propose predicting write demand with a learning algorithm, XGBoost, and conducting background, rate-based garbage collection to optimize write latency without premature, excessive flash erasure. Our method reduced the 99-th percentile write latency by 56% compared to on-demand garbage collection and decreased flash erase count by 51% compared to unconditional background garbage collection.</description><subject>Correlation</subject><subject>Global Positioning System</subject><subject>Mobile storage</subject><subject>NAND flash</subject><subject>Optimization</subject><subject>Prediction algorithms</subject><subject>Smart phones</subject><subject>smartphones</subject><subject>Training</subject><subject>Wireless fidelity</subject><subject>XG-Boost</subject><issn>2325-1301</issn><isbn>1728131979</isbn><isbn>9781728131979</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2019</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotz0FLwzAUwPEoCM65L6CXfoHWvLy2LzlJKTqFysBNPI6kexmRrR1pLvPTe3Cn_-0HfyEeQBYA0jx9btp1UygJptC6LiuiK3EHpDQgGDLXYqZQVTmghFuxmKYfKSUCkVFqJp47tnEIwz5vpilMiXfZdwyJs84mHvpztjqlcAy_NoVxyPwYs4_RhQNn6zRGu-d7cePtYeLFpXPx9fqyad_ybrV8b5suDwA65YYqAkfSOUaJUu_K2hpPzvUaSyQNvnfOO2WZenaIaBWT9VZKqp1mxLl4_HcDM29PMRxtPG8vv_gHApdKNw</recordid><startdate>201908</startdate><enddate>201908</enddate><creator>Tsai, Wei-Chu</creator><creator>Wu, Sung-Ming</creator><creator>Chang, Li-Pin</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201908</creationdate><title>Learning-Assisted Write Latency Optimization for Mobile Storage</title><author>Tsai, Wei-Chu ; Wu, Sung-Ming ; Chang, Li-Pin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i118t-97571b70bbe30308d46a9f7bbc8343781fcbbfb2ae7ceb333a2e7afa0076b8e33</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Correlation</topic><topic>Global Positioning System</topic><topic>Mobile storage</topic><topic>NAND flash</topic><topic>Optimization</topic><topic>Prediction algorithms</topic><topic>Smart phones</topic><topic>smartphones</topic><topic>Training</topic><topic>Wireless fidelity</topic><topic>XG-Boost</topic><toplevel>online_resources</toplevel><creatorcontrib>Tsai, Wei-Chu</creatorcontrib><creatorcontrib>Wu, Sung-Ming</creatorcontrib><creatorcontrib>Chang, Li-Pin</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore Digital Library</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tsai, Wei-Chu</au><au>Wu, Sung-Ming</au><au>Chang, Li-Pin</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Learning-Assisted Write Latency Optimization for Mobile Storage</atitle><btitle>2019 IEEE 25th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)</btitle><stitle>RTCSA</stitle><date>2019-08</date><risdate>2019</risdate><spage>1</spage><epage>6</epage><pages>1-6</pages><eissn>2325-1301</eissn><eisbn>1728131979</eisbn><eisbn>9781728131979</eisbn><abstract>I/O activities of mobile storage are highly synchronous. Flash garbage collection activities in mobile storage introduce extra delay to write requests and negatively impact on user perceived-latency. Runtime write demand is subject to correlation between multiple parameters, such as network connectivity, GPS coordinates, and current time. We propose predicting write demand with a learning algorithm, XGBoost, and conducting background, rate-based garbage collection to optimize write latency without premature, excessive flash erasure. Our method reduced the 99-th percentile write latency by 56% compared to on-demand garbage collection and decreased flash erase count by 51% compared to unconditional background garbage collection.</abstract><pub>IEEE</pub><doi>10.1109/RTCSA.2019.8864577</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2325-1301
ispartof 2019 IEEE 25th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA), 2019, p.1-6
issn 2325-1301
language eng
recordid cdi_ieee_primary_8864577
source IEEE Xplore All Conference Series
subjects Correlation
Global Positioning System
Mobile storage
NAND flash
Optimization
Prediction algorithms
Smart phones
smartphones
Training
Wireless fidelity
XG-Boost
title Learning-Assisted Write Latency Optimization for Mobile Storage
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T18%3A46%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Learning-Assisted%20Write%20Latency%20Optimization%20for%20Mobile%20Storage&rft.btitle=2019%20IEEE%2025th%20International%20Conference%20on%20Embedded%20and%20Real-Time%20Computing%20Systems%20and%20Applications%20(RTCSA)&rft.au=Tsai,%20Wei-Chu&rft.date=2019-08&rft.spage=1&rft.epage=6&rft.pages=1-6&rft.eissn=2325-1301&rft_id=info:doi/10.1109/RTCSA.2019.8864577&rft.eisbn=1728131979&rft.eisbn_list=9781728131979&rft_dat=%3Cieee_CHZPO%3E8864577%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i118t-97571b70bbe30308d46a9f7bbc8343781fcbbfb2ae7ceb333a2e7afa0076b8e33%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=8864577&rfr_iscdi=true