DRAM Errors in the Wild: A Large-Scale Field Study.
Errors in dynamic random access memory (DRAM) are a common form of hardware failure in modern compute clusters. Failures are costly both in terms of hardware replacement costs and service disruption. While a large body of work exists on DRAM in laboratory conditions, little has been reported on real...
| Publicado en: | Communications of the ACM Vol. 54; no. 2; pp. 100 - 108 |
|---|---|
| Autores principales: | , , |
| Formato: | Artículo |
| Publicado: |
Association for Computing Machinery
Feb2011
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=59631547&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 59631547 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 00010782 ACM jtl: Communications of the ACM issn: 00010782 maglogo: N pubinfo: dt: Feb2011 vid: 54 iid: 2 pid: 68 pub: Association for Computing Machinery artinfo: ui: 59631547 10.1145/1897816.1897844 ppf: 100 ppct: 8 formats: tig: atl: DRAM Errors in the Wild: A Large-Scale Field Study. aug: au: Schroeder, Bianca Pinheiro, Eduardo Weber, Wolf-Dietrich affil: Computer Science Department, University of Toronto, Toronto, Canada. Google Inc., Mountain View, CA. su: Dynamic random access memory Error rates Client/server computing Integrated circuits Field research Computer systems sug: subj: Dynamic random access memory Error rates Client/server computing Integrated circuits Field research Computer systems ab: Errors in dynamic random access memory (DRAM) are a common form of hardware failure in modern compute clusters. Failures are costly both in terms of hardware replacement costs and service disruption. While a large body of work exists on DRAM in laboratory conditions, little has been reported on real DRAM failures in large production clusters. In this paper, we analyze measurements of memory errors in a large fleet of commodity servers over a period of 2.5 years. The collected data covers multiple vendors, DRAM capacities and technologies, and comprises many millions of dual in-line memory module (DIMM) days. The goal of this paper is to answer questions such as the following: How common are memory errors in practice? What are their statistical properties? How are they affected by external factors, such as temperature and utilization, and by chipspecific factors, such as chip density, memory technology, and DIMM age? We find that DRAM error behavior in the field differs in many key aspects from commonly held assumptions. For example, we observe DRAM error rates that are orders of magnitude higher than previously reported, with 25,000- 70,000 errors per billion device hours per Mb and more than 8% of DIMMs affected by errors per year. We provide strong evidence that memory errors are dominated by hard errors, rather than soft errors, which previous work suspects to be the dominant error mode. We find that temperature, known to strongly impact DIMM error rates in lab conditions, has a surprisingly small effect on error behavior in the field, when taking all other factors into account. Finally, unlike commonly feared, we do not observe any indication that newer generations of DIMMs have worse error behavior. pubtype: Periodical doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2011 holdings: @attributes: islocal: N |
|---|