https://community.splunk.com/t5/Getting-Data-In/Predict-that-the-sql-text-will-consume-high-resources/m-p/452666#M95037 <P>yes , I am using Splunk MLTK.<BR /> Is it recommended to do it with Clustering algorithm K-means</P> Mon, 01 Jul 2019 07:15:27 GMT swetar 2019-07-01T07:15:27Z https://community.splunk.com/t5/Getting-Data-In/Predict-that-the-sql-text-will-consume-high-resources/m-p/452664#M95035 <P>Hi everyone,<BR /> Req# Predict that the sql text running in the system will consume high resources. <BR /> I wanted to predict this based on the temp space and undo table space used by the query.<BR /> I am thinking to use Clustering algo.<BR /> Can anyone suggest me, which algo should I use. </P> <P>Thanks</P> Mon, 01 Jul 2019 04:30:05 GMT https://community.splunk.com/t5/Getting-Data-In/Predict-that-the-sql-text-will-consume-high-resources/m-p/452664#M95035 swetar 2019-07-01T04:30:05Z https://community.splunk.com/t5/Getting-Data-In/Predict-that-the-sql-text-will-consume-high-resources/m-p/452665#M95036 <P>Are you using MLTK ?</P> Mon, 01 Jul 2019 06:59:02 GMT https://community.splunk.com/t5/Getting-Data-In/Predict-that-the-sql-text-will-consume-high-resources/m-p/452665#M95036 DavidHourani 2019-07-01T06:59:02Z https://community.splunk.com/t5/Getting-Data-In/Predict-that-the-sql-text-will-consume-high-resources/m-p/452666#M95037 <P>yes , I am using Splunk MLTK.<BR /> Is it recommended to do it with Clustering algorithm K-means</P> Mon, 01 Jul 2019 07:15:27 GMT https://community.splunk.com/t5/Getting-Data-In/Predict-that-the-sql-text-will-consume-high-resources/m-p/452666#M95037 swetar 2019-07-01T07:15:27Z https://community.splunk.com/t5/Getting-Data-In/Predict-that-the-sql-text-will-consume-high-resources/m-p/452667#M95038 <P>yeah that makes sense if you have multiple queries and you wish to classify them, is that what you're trying to achieve ? </P> Mon, 01 Jul 2019 07:22:09 GMT https://community.splunk.com/t5/Getting-Data-In/Predict-that-the-sql-text-will-consume-high-resources/m-p/452667#M95038 DavidHourani 2019-07-01T07:22:09Z https://community.splunk.com/t5/Getting-Data-In/Predict-that-the-sql-text-will-consume-high-resources/m-p/452668#M95039 <P>Yes there will be multiple queries. I wanted to classify bad sql ( bad sql meaning, sql which are going to consume more than 80% temp or consuming high io)</P> Mon, 01 Jul 2019 07:37:40 GMT https://community.splunk.com/t5/Getting-Data-In/Predict-that-the-sql-text-will-consume-high-resources/m-p/452668#M95039 swetar 2019-07-01T07:37:40Z https://community.splunk.com/t5/Getting-Data-In/Predict-that-the-sql-text-will-consume-high-resources/m-p/452669#M95040 <P>In that case try <STRONG>BDSCAN</STRONG> could be better than fitting into a set number of clusters.<BR /> <A href="https://docs.splunk.com/Documentation/MLApp/4.3.0/User/Algorithms#DBSCAN">https://docs.splunk.com/Documentation/MLApp/4.3.0/User/Algorithms#DBSCAN</A></P> Mon, 01 Jul 2019 07:49:52 GMT https://community.splunk.com/t5/Getting-Data-In/Predict-that-the-sql-text-will-consume-high-resources/m-p/452669#M95040 DavidHourani 2019-07-01T07:49:52Z