{"id":441,"date":"2006-04-04T13:31:27","date_gmt":"2006-04-04T20:31:27","guid":{"rendered":"tag:www.computerworld.com:\/\/8fa90481485cbecd073c149d6071b71d"},"modified":"2006-04-04T13:31:27","modified_gmt":"2006-04-04T20:31:27","slug":"the-changing-face-of-performance-statistics","status":"publish","type":"post","link":"https:\/\/planet.mcb.guru\/?p=441","title":{"rendered":"The changing face of performance statistics"},"content":{"rendered":"<p>I read <a href=\"http:\/\/www.computerworld.com\/blogs\/node\/2160\">Robert's post yesterday<\/a> on the way companies are changing the way they measure performance from the current per-MHz\/GHz to performance per watt. Robert's comments were based on the front page story yesterday, <a href=\"http:\/\/computerworld.com\/hardwaretopics\/hardware\/story\/0,10801,110072,00.html\">Power struggle: How IT managers cope with the data center power demands<\/a>. <\/p>\n<p>The result got me thinking about how we measure performance and what the yardstick should be. <\/p>\n<p>My first comment is that power has long been a problem for data center managers, and I'm not going to repeat my own feelings and findings on the use (and often waste) of power, or the eco-friendly options that are available. I won't make the comment either about Sun's T1 CPU (Niagara) which was designed with high performance and low power requirements in mind and Sun's aptly named the servers <a href=\"http:\/\/www.sun.com\/servers\/coolthreads\/t1000\/\">CoolThreads<\/a>. OK, I just made the comment anyway, but it nicely leads me on to part of the point I want to make.<\/p>\n\n<!--\n<rdf:RDF xmlns:rdf=\"http:\/\/www.w3.org\/1999\/02\/22-rdf-syntax-ns#\" xmlns:dc=\"http:\/\/purl.org\/dc\/elements\/1.1\/\" xmlns:trackback=\"http:\/\/madskills.com\/public\/xml\/rss\/module\/trackback\/\">\n<rdf:Description rdf:about=\"http:\/\/www.computerworld.com\/blogs\/node\/2177\" dc:identifier=\"http:\/\/www.computerworld.com\/blogs\/node\/2177\" dc:title=\"The changing face of performance statistics\" trackback:ping=\"http:\/\/www.computerworld.com\/blogs\/trackback\/2177\" \/>\n<\/rdf:RDF>\n-->\n<p><a href=\"http:\/\/feeds.feedburner.com\/~a\/Computerworld\/MartinMCBrown?a=lrrWo4\"><img src=\"http:\/\/feeds.feedburner.com\/~a\/Computerworld\/MartinMCBrown?i=lrrWo4\" border=\"0\"><\/img><\/a><\/p><img src=\"http:\/\/feeds.feedburner.com\/Computerworld\/MartinMCBrown?g=123\"\/>","protected":false},"excerpt":{"rendered":"<p>I read <a href=\"http:\/\/www.computerworld.com\/blogs\/node\/2160\">Robert&#8217;s post yesterday<\/a> on the way companies are changing the way they measure performance from the current per-MHz\/GHz to performance per watt. Robert&#8217;s comments were based on the front page story yesterday, <a href=\"http:\/\/computerworld.com\/hardwaretopics\/hardware\/story\/0,10801,110072,00.html\">Power struggle: How IT managers cope with the data center power demands<\/a>. <\/p>\n<p>The result got me thinking about how we measure performance and what the yardstick should be. <\/p>\n<p>My first comment is that power has long been a problem for data center managers, and I&#8217;m not going to repeat my own feelings and findings on the use (and often waste) of power, or the eco-friendly options that are available. I won&#8217;t make the comment either about Sun&#8217;s T1 CPU (Niagara) which was designed with high performance and low power requirements in mind and Sun&#8217;s aptly named the servers <a href=\"http:\/\/www.sun.com\/servers\/coolthreads\/t1000\/\">CoolThreads<\/a>. OK, I just made the comment anyway, but it nicely leads me on to part of the point I want to make.<\/p>\n<p><!--\n<rdf:RDF xmlns:rdf=\"http:\/\/www.w3.org\/1999\/02\/22-rdf-syntax-ns#\" xmlns:dc=\"http:\/\/purl.org\/dc\/elements\/1.1\/\" xmlns:trackback=\"http:\/\/madskills.com\/public\/xml\/rss\/module\/trackback\/\">\n<rdf:Description rdf:about=\"http:\/\/www.computerworld.com\/blogs\/node\/2177\" dc:identifier=\"http:\/\/www.computerworld.com\/blogs\/node\/2177\" dc:title=\"The changing face of performance statistics\" trackback:ping=\"http:\/\/www.computerworld.com\/blogs\/trackback\/2177\" \/>\n<\/rdf:RDF>\n--><\/p>\n<p><a href=\"http:\/\/feeds.feedburner.com\/~a\/Computerworld\/MartinMCBrown?a=lrrWo4\"><img decoding=\"async\" src=\"http:\/\/feeds.feedburner.com\/~a\/Computerworld\/MartinMCBrown?i=lrrWo4\" border=\"0\"><\/img><\/a><\/p>\n<p><img decoding=\"async\" src=\"http:\/\/feeds.feedburner.com\/Computerworld\/MartinMCBrown?g=123\"\/><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[],"tags":[27],"_links":{"self":[{"href":"https:\/\/planet.mcb.guru\/index.php?rest_route=\/wp\/v2\/posts\/441"}],"collection":[{"href":"https:\/\/planet.mcb.guru\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/planet.mcb.guru\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/planet.mcb.guru\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/planet.mcb.guru\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=441"}],"version-history":[{"count":0,"href":"https:\/\/planet.mcb.guru\/index.php?rest_route=\/wp\/v2\/posts\/441\/revisions"}],"wp:attachment":[{"href":"https:\/\/planet.mcb.guru\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=441"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/planet.mcb.guru\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=441"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/planet.mcb.guru\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=441"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}