{"id":237,"date":"2021-03-25T08:41:55","date_gmt":"2021-03-25T12:41:55","guid":{"rendered":"https:\/\/sites.bu.edu\/casp\/?p=237"},"modified":"2021-03-25T08:41:55","modified_gmt":"2021-03-25T12:41:55","slug":"showans-work-was-accepted-for-presentation-at-the-eurosys-doctoral-workshop-eurodw-2021","status":"publish","type":"post","link":"https:\/\/sites.bu.edu\/casp\/2021\/03\/25\/showans-work-was-accepted-for-presentation-at-the-eurosys-doctoral-workshop-eurodw-2021\/","title":{"rendered":"Showan&#8217;s work was accepted for presentation at the EuroSys Doctoral Workshop (EuroDW 2021)"},"content":{"rendered":"<p>Showan&#8217;s submission &#8220;<strong>Toward Workload-Aware State Management in Streaming Systems<\/strong>&#8221; was accepted for presentation at the 15th <a href=\"https:\/\/2021.eurosys.org\/index.html\">EuroSys<\/a> Doctoral Workshop (<a href=\"https:\/\/eurodw21.github.io\/\">EuroDW 2021<\/a>).<\/p>\n<p>Here&#8217;s the abstract:<\/p>\n<p><span>Modern streaming systems rely on persistent KV stores <\/span><span>to perform stateful processing on data streams. Although <\/span><span>the choice of the state store is crucial for the system\u2019s per<\/span><span>formance, there has been little research in designing state <\/span><span>stores tailored for streaming workloads. Streaming systems <\/span><span>use general-purpose KV stores, such as RocksDB, to manage <\/span><span>state. Being oblivious to workload characteristics of stream-<\/span><span>ing applications, such stores incur unnecessary overheads.<\/span><span>Our methodology to tackle this challenge consists of the fol<\/span><span>lowing steps. First, we have been conducting a thorough study <\/span><span>of streaming state workloads to further the understanding of <\/span><span>their characteristics and differences from traditional work-<\/span><span>loads. Second, we are developing a new benchmark that can <\/span><span>faithfully mimic streaming state workloads and enables re-<\/span><span>searchers to easily evaluate alternative store designs. Our long-<\/span><span>term goal is to design and develop workload-aware streaming <\/span><span>state management to improve the latency and throughput of <\/span><span>streaming analytics.<\/span><\/p>\n<p>We are looking forward to the workshop!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Showan&#8217;s submission &#8220;Toward Workload-Aware State Management in Streaming Systems&#8221; was accepted for presentation at the 15th EuroSys Doctoral Workshop (EuroDW 2021). Here&#8217;s the abstract: Modern streaming systems rely on persistent KV stores to perform stateful processing on data streams. Although the choice of the state store is crucial for the system\u2019s performance, there has been [&hellip;]<\/p>\n","protected":false},"author":18854,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[9,8],"tags":[],"_links":{"self":[{"href":"https:\/\/sites.bu.edu\/casp\/wp-json\/wp\/v2\/posts\/237"}],"collection":[{"href":"https:\/\/sites.bu.edu\/casp\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/sites.bu.edu\/casp\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/sites.bu.edu\/casp\/wp-json\/wp\/v2\/users\/18854"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.bu.edu\/casp\/wp-json\/wp\/v2\/comments?post=237"}],"version-history":[{"count":3,"href":"https:\/\/sites.bu.edu\/casp\/wp-json\/wp\/v2\/posts\/237\/revisions"}],"predecessor-version":[{"id":240,"href":"https:\/\/sites.bu.edu\/casp\/wp-json\/wp\/v2\/posts\/237\/revisions\/240"}],"wp:attachment":[{"href":"https:\/\/sites.bu.edu\/casp\/wp-json\/wp\/v2\/media?parent=237"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sites.bu.edu\/casp\/wp-json\/wp\/v2\/categories?post=237"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sites.bu.edu\/casp\/wp-json\/wp\/v2\/tags?post=237"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}