{"id":559,"date":"2011-06-23T03:50:00","date_gmt":"2011-06-23T03:50:00","guid":{"rendered":"\/blogs\/paul\/post\/MAXDOP-configuration-survey-results.aspx"},"modified":"2013-01-01T19:15:11","modified_gmt":"2013-01-02T03:15:11","slug":"maxdop-configuration-survey-results","status":"publish","type":"post","link":"https:\/\/www.sqlskills.com\/blogs\/paul\/maxdop-configuration-survey-results\/","title":{"rendered":"MAXDOP configuration survey results"},"content":{"rendered":"

\nA month ago I kicked off a survey about MAXDOP setting – see <\/font>here<\/font><\/a> for the survey. I received results for 700 servers around the world! Here they are: <\/font>\n<\/p>\n

\n \"\"<\/font>\n<\/p>\n

\nThe X-axis format is X-Y-Z, where X = number of cores, Y = number of NUMA nodes, Z = MAXDOP setting. I didn't differentiate between hyper-threading or not, or soft vs. hard NUMA.<\/font>\n<\/p>\n

\nThe results are striking – 75% of all systems out there use a server MAXDOP of zero. Now, this doesn't show whether individual queries are using MAXDOP to override that, or resource governor in 2008+ to override that either and I don't have info on the workload for all these servers – so it's not a result we can draw any concrete conclusions from. However, I do find it interesting that such a high proportion are running fine with MAXDOP 0 – my expectation was that there would be a higher proportion of servers with a non-zero MAXDOP setting.<\/font>\n<\/p>\n

\nThere are quite a few 'black and white' configuration rules out there – for instance:<\/font>\n<\/p>\n

    \n
  1. \n
    \n
    \n\tSet MAXDOP to 1 if you're seeing CXPACKET waits as the prevalent wait type.<\/font>\n\t<\/div>\n<\/p><\/div>\n<\/li>\n
  2. \n
    \n
    \n\tSet MAXDOP to 1 for OLTP systems, and don't do anything else.<\/font>\n\t<\/div>\n<\/p><\/div>\n<\/li>\n
  3. \n
    \n
    \n\tOld Microsoft guidance to set MAXDOP to half the number of physical processors.<\/font>\n\t<\/div>\n<\/p><\/div>\n<\/li>\n
  4. \n
    \n
    \n\tSet MAXDOP to the number of cores in the NUMA node.<\/font>\n\t<\/div>\n<\/p><\/div>\n<\/li>\n<\/ol>\n

    \nThese are all incorrect as *rules*. There is no one-size-fits-all rule for MAXDOP – there are only general guidelines. For instance:<\/font>\n<\/p>\n