{"id":885,"date":"2012-11-02T16:01:02","date_gmt":"2012-11-02T14:01:02","guid":{"rendered":"http:\/\/oldblogs.uct.ac.za\/blog\/big-bytes\/2012\/11\/02\/aws-and-starcluster"},"modified":"2022-09-26T20:24:26","modified_gmt":"2022-09-26T18:24:26","slug":"aws-and-mits-starcluster","status":"publish","type":"post","link":"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/","title":{"rendered":"AWS and MIT&#8217;s StarCluster"},"content":{"rendered":"We've been playing about with Amazon Web Service cloud based\r\ninfrastructure for the last few weeks and thought we'd share this.\r\nUsing\u00a0<a href=\"http:\/\/star.mit.edu\/cluster\/\">StarCluster<\/a>\u00a0and following this\u00a0<a href=\"http:\/\/www.youtube.com\/embed\/2Ym7epCYnSk\">very cool demo<\/a>\u00a0we launched a 3 node cluster\r\non Amazon\u2019s Elastic Compute Cloud infrastructure within the space of\r\nabout 10 minutes.\r\n\r\nYou'll need an Amazon account (i.e. you give Amazon your credit card\r\ndetails) and create a private key pair via their website.\u00a0 You then\r\nlaunch a small machine instance of StarCluster to act as the coordination\r\nserver.\u00a0 Installation of StarCluster is a single command.\u00a0 To configure\r\nthe 'personality' of the cluster one modifies the configuration file\r\n(about 2 lines).\u00a0 To set up permissions you need to copy your key to the\r\ncoordination server and reference this key in the config file.\r\n\r\nStarting the cluster is also one command, as is adding or deleting\r\nnodes.\u00a0 In about 5 minutes we had a head node and a worker node. \u00a0We decided to add a second worker node which took about 4 minutes.\u00a0 StarCluster uses Oracle\r\nGrid Engine and works in a very standard manner.\u00a0 We were able to\r\ncompile and submit an OpenMPI job in the space of about 60 seconds and\r\nit ran perfectly.\r\n\r\n<img src=\"https:\/\/ucthpc.uct.ac.za\/wp-content\/uploads\/2015\/07\/starcluster.jpg\" alt=\"dashboard AWS\" border=\"0\" \/>\r\n\r\nHowever the coolest bit is the ability to\u00a0<a href=\"http:\/\/aws.amazon.com\/ec2\/spot-instances\/\">'bid' for Amazon spot\r\ninstances<\/a>.\u00a0 StarCluster\r\nallows one to look at the spot instance price history over time to allow\r\nyou to make an informed bid in $\/hour.\u00a0 You can launch your cluster\r\nbased on this bid and as resources become available so your nodes are\r\nprovisioned.\u00a0 As long as your bid is (just) over the average price\r\nyou're pretty much guaranteed a reasonably priced compute cluster for as\r\nlong as you want.\r\n\r\n<img src=\"https:\/\/ucthpc.uct.ac.za\/wp-content\/uploads\/2015\/07\/bid.jpg\" alt=\"bid\" border=\"0\" \/>\r\n\r\nAbove is the current hourly value of an 8 core Nehalem server with two 2050 NVIDIA GPU cards.\r\n\r\nWe're now looking at ways to scale our current (and pending) infrastructure into this space.","protected":false},"excerpt":{"rendered":"<p>We&#8217;ve been playing about with Amazon Web Service cloud based<br \/>\ninfrastructure for the last few weeks and thought we&#8217;d share this.&nbsp;<br \/>\nUsing&nbsp;<a href=\"http:\/\/star.mit.edu\/cluster\/\">StarCluster<\/a>&nbsp;and following this&nbsp;<a href=\"http:\/\/www.youtube.com\/embed\/2Ym7epCYnSk\">very cool demo<\/a>&nbsp;we launched a 3 node cluster<br \/>\non Amazon&rsquo;s Elastic Compute Cloud infrastructure within the space of<br \/>\nabout 10 minutes.<\/p>\n<p>You&#8217;ll need an Amazon account (i.e. you give Amazon your credit card<br \/>\ndetails) and create a private key pair via their website.&nbsp; You then<br \/>\nlaunch a small machine instance of StarCluster to act as the coordination<br \/>\n server.&nbsp; Installation of StarCluster is a single command.&nbsp; To configure<br \/>\n the &#8216;personality&#8217; of the cluster one modifies the configuration file<br \/>\n(about 2 lines).&nbsp; To set up permissions you need to copy your key to the<br \/>\n coordination server and reference this key in the config file.<\/p>\n<p>Starting the cluster is also one command, as is adding or deleting<br \/>\nnodes.&nbsp; In about 5 minutes we had a head node and a worker node. &nbsp;We decided to add a second worker node which took about 4 minutes.&nbsp; StarCluster uses Oracle<br \/>\nGrid Engine and works in a very standard manner.&nbsp; We were able to<br \/>\ncompile and submit an OpenMPI job in the space of about 60 seconds and<br \/>\nit ran perfectly.<\/p>\n<p><img decoding=\"async\" src=\"http:\/\/blogs.uct.ac.za\/gallery\/1253\/starcluster.jpg\" border=\"0\" alt=\"dashboard AWS\"><\/p>\n<p>However the coolest bit is the ability to&nbsp;<a href=\"http:\/\/aws.amazon.com\/ec2\/spot-instances\/\">&#8216;bid&#8217; for Amazon spot<br \/>\ninstances<\/a>.&nbsp; StarCluster<br \/>\nallows one to look at the spot instance price history over time to allow<br \/>\nyou to make an informed bid in $\/hour.&nbsp; You can launch your cluster<br \/>\nbased on this bid and as resources become available so your nodes are<br \/>\nprovisioned.&nbsp; As long as your bid is (just) over the average price<br \/>\nyou&#8217;re pretty much guaranteed a reasonably priced compute cluster for as<br \/>\n long as you want.<\/p>\n<p><img decoding=\"async\" src=\"http:\/\/blogs.uct.ac.za\/gallery\/1253\/bid.jpg\" border=\"0\" alt=\"bid\">&nbsp;<\/p>\n<p>Above is the current hourly value of an 8 core Nehalem server with two 2050 NVIDIA GPU cards.<\/p>\n<p>We&#8217;re now looking at ways to scale our current (and pending) infrastructure into this space.<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[4],"tags":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v21.4 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>AWS and MIT&#039;s StarCluster - UCT HPC<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AWS and MIT&#039;s StarCluster - UCT HPC\" \/>\n<meta property=\"og:description\" content=\"We&#039;ve been playing about with Amazon Web Service cloud based  infrastructure for the last few weeks and thought we&#039;d share this.&nbsp;  Using&nbsp;StarCluster&nbsp;and following this&nbsp;very cool demo&nbsp;we launched a 3 node cluster  on Amazon&rsquo;s Elastic Compute Cloud infrastructure within the space of  about 10 minutes. You&#039;ll need an Amazon account (i.e. you give Amazon your credit card  details) and create a private key pair via their website.&nbsp; You then  launch a small machine instance of StarCluster to act as the coordination  server.&nbsp; Installation of StarCluster is a single command.&nbsp; To configure  the &#039;personality&#039; of the cluster one modifies the configuration file  (about 2 lines).&nbsp; To set up permissions you need to copy your key to the  coordination server and reference this key in the config file. Starting the cluster is also one command, as is adding or deleting  nodes.&nbsp; In about 5 minutes we had a head node and a worker node. &nbsp;We decided to add a second worker node which took about 4 minutes.&nbsp; StarCluster uses Oracle  Grid Engine and works in a very standard manner.&nbsp; We were able to  compile and submit an OpenMPI job in the space of about 60 seconds and  it ran perfectly.However the coolest bit is the ability to&nbsp;&#039;bid&#039; for Amazon spot  instances.&nbsp; StarCluster  allows one to look at the spot instance price history over time to allow  you to make an informed bid in $\/hour.&nbsp; You can launch your cluster  based on this bid and as resources become available so your nodes are  provisioned.&nbsp; As long as your bid is (just) over the average price  you&#039;re pretty much guaranteed a reasonably priced compute cluster for as  long as you want.&nbsp;Above is the current hourly value of an 8 core Nehalem server with two 2050 NVIDIA GPU cards.We&#039;re now looking at ways to scale our current (and pending) infrastructure into this space.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/\" \/>\n<meta property=\"og:site_name\" content=\"UCT HPC\" \/>\n<meta property=\"article:published_time\" content=\"2012-11-02T14:01:02+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2022-09-26T18:24:26+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/ucthpc.uct.ac.za\/wp-content\/uploads\/2015\/07\/starcluster.jpg\" \/>\n<meta name=\"author\" content=\"Andrew Lewis\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Andrew Lewis\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/\"},\"author\":{\"name\":\"Andrew Lewis\",\"@id\":\"https:\/\/ucthpc.uct.ac.za\/#\/schema\/person\/c183ad1c0a1063124a72d63963ae9c7e\"},\"headline\":\"AWS and MIT&#8217;s StarCluster\",\"datePublished\":\"2012-11-02T14:01:02+00:00\",\"dateModified\":\"2022-09-26T18:24:26+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/\"},\"wordCount\":313,\"publisher\":{\"@id\":\"https:\/\/ucthpc.uct.ac.za\/#organization\"},\"articleSection\":[\"hpc\"],\"inLanguage\":\"en-ZA\"},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/\",\"url\":\"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/\",\"name\":\"AWS and MIT's StarCluster - UCT HPC\",\"isPartOf\":{\"@id\":\"https:\/\/ucthpc.uct.ac.za\/#website\"},\"datePublished\":\"2012-11-02T14:01:02+00:00\",\"dateModified\":\"2022-09-26T18:24:26+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/#breadcrumb\"},\"inLanguage\":\"en-ZA\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/ucthpc.uct.ac.za\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"AWS and MIT&#8217;s StarCluster\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/ucthpc.uct.ac.za\/#website\",\"url\":\"https:\/\/ucthpc.uct.ac.za\/\",\"name\":\"UCT HPC\",\"description\":\"University of Cape Town High Performance Computing\",\"publisher\":{\"@id\":\"https:\/\/ucthpc.uct.ac.za\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/ucthpc.uct.ac.za\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"en-ZA\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/ucthpc.uct.ac.za\/#organization\",\"name\":\"University of Cape Town High Performance Computing\",\"url\":\"https:\/\/ucthpc.uct.ac.za\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-ZA\",\"@id\":\"https:\/\/ucthpc.uct.ac.za\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/ucthpc.uct.ac.za\/wp-content\/uploads\/2015\/09\/logocircless.png\",\"contentUrl\":\"https:\/\/ucthpc.uct.ac.za\/wp-content\/uploads\/2015\/09\/logocircless.png\",\"width\":450,\"height\":423,\"caption\":\"University of Cape Town High Performance Computing\"},\"image\":{\"@id\":\"https:\/\/ucthpc.uct.ac.za\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/ucthpc.uct.ac.za\/#\/schema\/person\/c183ad1c0a1063124a72d63963ae9c7e\",\"name\":\"Andrew Lewis\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-ZA\",\"@id\":\"https:\/\/ucthpc.uct.ac.za\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/9652c9c73beeab594b8dc2383a880048?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/9652c9c73beeab594b8dc2383a880048?s=96&d=mm&r=g\",\"caption\":\"Andrew Lewis\"},\"sameAs\":[\"http:\/\/blogs.uct.ac.za\/blog\/big-bytes\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"AWS and MIT's StarCluster - UCT HPC","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/","og_locale":"en_US","og_type":"article","og_title":"AWS and MIT's StarCluster - UCT HPC","og_description":"We've been playing about with Amazon Web Service cloud based  infrastructure for the last few weeks and thought we'd share this.&nbsp;  Using&nbsp;StarCluster&nbsp;and following this&nbsp;very cool demo&nbsp;we launched a 3 node cluster  on Amazon&rsquo;s Elastic Compute Cloud infrastructure within the space of  about 10 minutes. You'll need an Amazon account (i.e. you give Amazon your credit card  details) and create a private key pair via their website.&nbsp; You then  launch a small machine instance of StarCluster to act as the coordination  server.&nbsp; Installation of StarCluster is a single command.&nbsp; To configure  the 'personality' of the cluster one modifies the configuration file  (about 2 lines).&nbsp; To set up permissions you need to copy your key to the  coordination server and reference this key in the config file. Starting the cluster is also one command, as is adding or deleting  nodes.&nbsp; In about 5 minutes we had a head node and a worker node. &nbsp;We decided to add a second worker node which took about 4 minutes.&nbsp; StarCluster uses Oracle  Grid Engine and works in a very standard manner.&nbsp; We were able to  compile and submit an OpenMPI job in the space of about 60 seconds and  it ran perfectly.However the coolest bit is the ability to&nbsp;'bid' for Amazon spot  instances.&nbsp; StarCluster  allows one to look at the spot instance price history over time to allow  you to make an informed bid in $\/hour.&nbsp; You can launch your cluster  based on this bid and as resources become available so your nodes are  provisioned.&nbsp; As long as your bid is (just) over the average price  you're pretty much guaranteed a reasonably priced compute cluster for as  long as you want.&nbsp;Above is the current hourly value of an 8 core Nehalem server with two 2050 NVIDIA GPU cards.We're now looking at ways to scale our current (and pending) infrastructure into this space.","og_url":"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/","og_site_name":"UCT HPC","article_published_time":"2012-11-02T14:01:02+00:00","article_modified_time":"2022-09-26T18:24:26+00:00","og_image":[{"url":"https:\/\/ucthpc.uct.ac.za\/wp-content\/uploads\/2015\/07\/starcluster.jpg"}],"author":"Andrew Lewis","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Andrew Lewis","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/#article","isPartOf":{"@id":"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/"},"author":{"name":"Andrew Lewis","@id":"https:\/\/ucthpc.uct.ac.za\/#\/schema\/person\/c183ad1c0a1063124a72d63963ae9c7e"},"headline":"AWS and MIT&#8217;s StarCluster","datePublished":"2012-11-02T14:01:02+00:00","dateModified":"2022-09-26T18:24:26+00:00","mainEntityOfPage":{"@id":"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/"},"wordCount":313,"publisher":{"@id":"https:\/\/ucthpc.uct.ac.za\/#organization"},"articleSection":["hpc"],"inLanguage":"en-ZA"},{"@type":"WebPage","@id":"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/","url":"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/","name":"AWS and MIT's StarCluster - UCT HPC","isPartOf":{"@id":"https:\/\/ucthpc.uct.ac.za\/#website"},"datePublished":"2012-11-02T14:01:02+00:00","dateModified":"2022-09-26T18:24:26+00:00","breadcrumb":{"@id":"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/#breadcrumb"},"inLanguage":"en-ZA","potentialAction":[{"@type":"ReadAction","target":["https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/ucthpc.uct.ac.za\/index.php\/2012\/11\/02\/aws-and-mits-starcluster\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/ucthpc.uct.ac.za\/"},{"@type":"ListItem","position":2,"name":"AWS and MIT&#8217;s StarCluster"}]},{"@type":"WebSite","@id":"https:\/\/ucthpc.uct.ac.za\/#website","url":"https:\/\/ucthpc.uct.ac.za\/","name":"UCT HPC","description":"University of Cape Town High Performance Computing","publisher":{"@id":"https:\/\/ucthpc.uct.ac.za\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/ucthpc.uct.ac.za\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"en-ZA"},{"@type":"Organization","@id":"https:\/\/ucthpc.uct.ac.za\/#organization","name":"University of Cape Town High Performance Computing","url":"https:\/\/ucthpc.uct.ac.za\/","logo":{"@type":"ImageObject","inLanguage":"en-ZA","@id":"https:\/\/ucthpc.uct.ac.za\/#\/schema\/logo\/image\/","url":"https:\/\/ucthpc.uct.ac.za\/wp-content\/uploads\/2015\/09\/logocircless.png","contentUrl":"https:\/\/ucthpc.uct.ac.za\/wp-content\/uploads\/2015\/09\/logocircless.png","width":450,"height":423,"caption":"University of Cape Town High Performance Computing"},"image":{"@id":"https:\/\/ucthpc.uct.ac.za\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/ucthpc.uct.ac.za\/#\/schema\/person\/c183ad1c0a1063124a72d63963ae9c7e","name":"Andrew Lewis","image":{"@type":"ImageObject","inLanguage":"en-ZA","@id":"https:\/\/ucthpc.uct.ac.za\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/9652c9c73beeab594b8dc2383a880048?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/9652c9c73beeab594b8dc2383a880048?s=96&d=mm&r=g","caption":"Andrew Lewis"},"sameAs":["http:\/\/blogs.uct.ac.za\/blog\/big-bytes"]}]}},"_links":{"self":[{"href":"https:\/\/ucthpc.uct.ac.za\/index.php\/wp-json\/wp\/v2\/posts\/885"}],"collection":[{"href":"https:\/\/ucthpc.uct.ac.za\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ucthpc.uct.ac.za\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ucthpc.uct.ac.za\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/ucthpc.uct.ac.za\/index.php\/wp-json\/wp\/v2\/comments?post=885"}],"version-history":[{"count":4,"href":"https:\/\/ucthpc.uct.ac.za\/index.php\/wp-json\/wp\/v2\/posts\/885\/revisions"}],"predecessor-version":[{"id":4328,"href":"https:\/\/ucthpc.uct.ac.za\/index.php\/wp-json\/wp\/v2\/posts\/885\/revisions\/4328"}],"wp:attachment":[{"href":"https:\/\/ucthpc.uct.ac.za\/index.php\/wp-json\/wp\/v2\/media?parent=885"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ucthpc.uct.ac.za\/index.php\/wp-json\/wp\/v2\/categories?post=885"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ucthpc.uct.ac.za\/index.php\/wp-json\/wp\/v2\/tags?post=885"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}