First CE Matters: On the Importance of Long Term Properties on Memory Failure Prediction

Dynamic random access memory failures are a threat to the reliability of data centres as they lead to data loss and system crashes. Timely predictions of memory failures allow for taking preventive measures such as server migration and memory replacement. Thereby, memory failure prediction prevents...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bogatinovski, Jasmin, Yu, Qiao, Cardoso, Jorge, Kao, Odej
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Bogatinovski, Jasmin
Yu, Qiao
Cardoso, Jorge
Kao, Odej
description Dynamic random access memory failures are a threat to the reliability of data centres as they lead to data loss and system crashes. Timely predictions of memory failures allow for taking preventive measures such as server migration and memory replacement. Thereby, memory failure prediction prevents failures from externalizing, and it is a vital task to improve system reliability. In this paper, we revisited the problem of memory failure prediction. We analyzed the correctable errors (CEs) from hardware logs as indicators for a degraded memory state. As memories do not always work with full occupancy, access to faulty memory parts is time distributed. Following this intuition, we observed that important properties for memory failure prediction are distributed through long time intervals. In contrast, related studies, to fit practical constraints, frequently only analyze the CEs from the last fixed-size time interval while ignoring the predating information. Motivated by the observed discrepancy, we study the impact of including the overall (long-range) CE evolution and propose novel features that are calculated incrementally to preserve long-range properties. By coupling the extracted features with machine learning methods, we learn a predictive model to anticipate upcoming failures three hours in advance while improving the average relative precision and recall for 21% and 19% accordingly. We evaluated our methodology on real-world memory failures from the server fleet of a large cloud provider, justifying its validity and practicality.
doi_str_mv 10.48550/arxiv.2212.10441
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2212_10441</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2212_10441</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-55c5171850e8659a4205f0e771862c9016c6434913d4b98559765c5e4080aaa93</originalsourceid><addsrcrecordid>eNotz7FOwzAQBmAvDKjwAEzcCyTYie3EbChqoFKrMmRgi470ApaaOLoYRN-eUDqd9J_-X_qEuFMy1aUx8gH5x3-nWaayVEmt1bV4qz3PEao17DBG4vkR9iPET4LNMAWOOHYEoYdtGD-gIR7glcNEHD3NEEbY0RD4BDX64xfT8qSD76IP44246vE40-3lrkRTr5vqJdnunzfV0zZBW6jEmM6oQpVGUmmNQ51J00sqlshmnZPKdlbn2qn8oN_dYnCFXSqkZSkR0eUrcf8_e6a1E_sB-dT-EdszMf8FqT1Jpw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>First CE Matters: On the Importance of Long Term Properties on Memory Failure Prediction</title><source>arXiv.org</source><creator>Bogatinovski, Jasmin ; Yu, Qiao ; Cardoso, Jorge ; Kao, Odej</creator><creatorcontrib>Bogatinovski, Jasmin ; Yu, Qiao ; Cardoso, Jorge ; Kao, Odej</creatorcontrib><description>Dynamic random access memory failures are a threat to the reliability of data centres as they lead to data loss and system crashes. Timely predictions of memory failures allow for taking preventive measures such as server migration and memory replacement. Thereby, memory failure prediction prevents failures from externalizing, and it is a vital task to improve system reliability. In this paper, we revisited the problem of memory failure prediction. We analyzed the correctable errors (CEs) from hardware logs as indicators for a degraded memory state. As memories do not always work with full occupancy, access to faulty memory parts is time distributed. Following this intuition, we observed that important properties for memory failure prediction are distributed through long time intervals. In contrast, related studies, to fit practical constraints, frequently only analyze the CEs from the last fixed-size time interval while ignoring the predating information. Motivated by the observed discrepancy, we study the impact of including the overall (long-range) CE evolution and propose novel features that are calculated incrementally to preserve long-range properties. By coupling the extracted features with machine learning methods, we learn a predictive model to anticipate upcoming failures three hours in advance while improving the average relative precision and recall for 21% and 19% accordingly. We evaluated our methodology on real-world memory failures from the server fleet of a large cloud provider, justifying its validity and practicality.</description><identifier>DOI: 10.48550/arxiv.2212.10441</identifier><language>eng</language><subject>Computer Science - Distributed, Parallel, and Cluster Computing</subject><creationdate>2022-11</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2212.10441$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2212.10441$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Bogatinovski, Jasmin</creatorcontrib><creatorcontrib>Yu, Qiao</creatorcontrib><creatorcontrib>Cardoso, Jorge</creatorcontrib><creatorcontrib>Kao, Odej</creatorcontrib><title>First CE Matters: On the Importance of Long Term Properties on Memory Failure Prediction</title><description>Dynamic random access memory failures are a threat to the reliability of data centres as they lead to data loss and system crashes. Timely predictions of memory failures allow for taking preventive measures such as server migration and memory replacement. Thereby, memory failure prediction prevents failures from externalizing, and it is a vital task to improve system reliability. In this paper, we revisited the problem of memory failure prediction. We analyzed the correctable errors (CEs) from hardware logs as indicators for a degraded memory state. As memories do not always work with full occupancy, access to faulty memory parts is time distributed. Following this intuition, we observed that important properties for memory failure prediction are distributed through long time intervals. In contrast, related studies, to fit practical constraints, frequently only analyze the CEs from the last fixed-size time interval while ignoring the predating information. Motivated by the observed discrepancy, we study the impact of including the overall (long-range) CE evolution and propose novel features that are calculated incrementally to preserve long-range properties. By coupling the extracted features with machine learning methods, we learn a predictive model to anticipate upcoming failures three hours in advance while improving the average relative precision and recall for 21% and 19% accordingly. We evaluated our methodology on real-world memory failures from the server fleet of a large cloud provider, justifying its validity and practicality.</description><subject>Computer Science - Distributed, Parallel, and Cluster Computing</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz7FOwzAQBmAvDKjwAEzcCyTYie3EbChqoFKrMmRgi470ApaaOLoYRN-eUDqd9J_-X_qEuFMy1aUx8gH5x3-nWaayVEmt1bV4qz3PEao17DBG4vkR9iPET4LNMAWOOHYEoYdtGD-gIR7glcNEHD3NEEbY0RD4BDX64xfT8qSD76IP44246vE40-3lrkRTr5vqJdnunzfV0zZBW6jEmM6oQpVGUmmNQ51J00sqlshmnZPKdlbn2qn8oN_dYnCFXSqkZSkR0eUrcf8_e6a1E_sB-dT-EdszMf8FqT1Jpw</recordid><startdate>20221121</startdate><enddate>20221121</enddate><creator>Bogatinovski, Jasmin</creator><creator>Yu, Qiao</creator><creator>Cardoso, Jorge</creator><creator>Kao, Odej</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20221121</creationdate><title>First CE Matters: On the Importance of Long Term Properties on Memory Failure Prediction</title><author>Bogatinovski, Jasmin ; Yu, Qiao ; Cardoso, Jorge ; Kao, Odej</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-55c5171850e8659a4205f0e771862c9016c6434913d4b98559765c5e4080aaa93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Distributed, Parallel, and Cluster Computing</topic><toplevel>online_resources</toplevel><creatorcontrib>Bogatinovski, Jasmin</creatorcontrib><creatorcontrib>Yu, Qiao</creatorcontrib><creatorcontrib>Cardoso, Jorge</creatorcontrib><creatorcontrib>Kao, Odej</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bogatinovski, Jasmin</au><au>Yu, Qiao</au><au>Cardoso, Jorge</au><au>Kao, Odej</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>First CE Matters: On the Importance of Long Term Properties on Memory Failure Prediction</atitle><date>2022-11-21</date><risdate>2022</risdate><abstract>Dynamic random access memory failures are a threat to the reliability of data centres as they lead to data loss and system crashes. Timely predictions of memory failures allow for taking preventive measures such as server migration and memory replacement. Thereby, memory failure prediction prevents failures from externalizing, and it is a vital task to improve system reliability. In this paper, we revisited the problem of memory failure prediction. We analyzed the correctable errors (CEs) from hardware logs as indicators for a degraded memory state. As memories do not always work with full occupancy, access to faulty memory parts is time distributed. Following this intuition, we observed that important properties for memory failure prediction are distributed through long time intervals. In contrast, related studies, to fit practical constraints, frequently only analyze the CEs from the last fixed-size time interval while ignoring the predating information. Motivated by the observed discrepancy, we study the impact of including the overall (long-range) CE evolution and propose novel features that are calculated incrementally to preserve long-range properties. By coupling the extracted features with machine learning methods, we learn a predictive model to anticipate upcoming failures three hours in advance while improving the average relative precision and recall for 21% and 19% accordingly. We evaluated our methodology on real-world memory failures from the server fleet of a large cloud provider, justifying its validity and practicality.</abstract><doi>10.48550/arxiv.2212.10441</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2212.10441
ispartof
issn
language eng
recordid cdi_arxiv_primary_2212_10441
source arXiv.org
subjects Computer Science - Distributed, Parallel, and Cluster Computing
title First CE Matters: On the Importance of Long Term Properties on Memory Failure Prediction
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T06%3A36%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=First%20CE%20Matters:%20On%20the%20Importance%20of%20Long%20Term%20Properties%20on%20Memory%20Failure%20Prediction&rft.au=Bogatinovski,%20Jasmin&rft.date=2022-11-21&rft_id=info:doi/10.48550/arxiv.2212.10441&rft_dat=%3Carxiv_GOX%3E2212_10441%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true