The Tail at Scale.
The article discusses high-latency episodes in large online services and tail-tolerant software techniques that form a predictable whole out of less-predictable parts to reduce the episodes' effect on whole-system performance. The article notes variability in latency distribution or response time to...
| Publicado en: | Communications of the ACM Vol. 56; no. 2; pp. 74 - 81 |
|---|---|
| Autores principales: | , |
| Formato: | Artículo |
| Publicado: |
Association for Computing Machinery
Feb2013
|
| 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=88141551&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 88141551 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 00010782 ACM jtl: Communications of the ACM issn: 00010782 maglogo: N pubinfo: dt: Feb2013 vid: 56 iid: 2 pid: 68 pub: Association for Computing Machinery artinfo: ui: 88141551 10.1145/2408776.2408794 ppf: 74 ppct: 7 formats: tig: atl: The Tail at Scale. aug: au: DEAN, JEFFREY BARROSO, LUIZ ANDRÉ affil: Google Fellow, Systems Infrastructure Group, Google Inc., Mountain View, CA Google Fellow and technical lead of core computing infrastructure, Google Inc., Mountain View, CA su: Web services Distributed computing software Fault-tolerant computing Search engine optimization Google (Web resource) Computer performance Computer software sug: subj: Web services Distributed computing software Fault-tolerant computing Search engine optimization Google (Web resource) Computer performance Computer software ab: The article discusses high-latency episodes in large online services and tail-tolerant software techniques that form a predictable whole out of less-predictable parts to reduce the episodes' effect on whole-system performance. The article notes variability in latency distribution or response time to user actions can be reduced by parallelization of sub-operations across different machines. Topics include system utilization that avoids overprovisioning, performance variability, and the Google search engine. pubtype: Periodical doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2013 holdings: @attributes: islocal: N |
|---|