I am using SAS Release 9.4 TS1M3 on Red Hat EL 7.2. I am new to SAS; in fact, I help manage the applications on our research clusters, and am not a SAS user. I've a researcher who runs SAS on our clusters, and she is receiving the "ERROR: The SAS System stopped processing this step because of insufficient memory" message in one of her compute jobs. We're trying to figure out if it's an issue in her code, or an issue in our SAS configuration.
This is one of the procedures that causes the error:
Proc mixed data=temp1 noclprint covtest plots(maxpoints=none);
title "Model 7";
class year families;
model income_constant =families year2 year2*year2 families*year2 families*year2*year2/s ;
random intercept families / subject=year ;
repeated /type=sp(pow)(year3) sub=intercept;
weight weightvar;
format families families. ;
run;
The output in the SAS log is:
WARNING: The R matrix depends on observation order within subjects. Omitting observations from the analysis because of missing values can affect this matrix. Consider using a classification effect in the REPEATED statement to determine ordering in the R matrix. NOTE: 440948 observations are not included because of missing values. NOTE: 38 observations are not included because of negative or zero weights. ERROR: The SAS System stopped processing this step because of insufficient memory. NOTE: The PROCEDURE MIXED printed page 2. NOTE: PROCEDURE MIXED used (Total process time): real time 44.52 seconds user cpu time 17.14 seconds system cpu time 20.56 seconds memory 16456514.29k OS Memory 16467496.00k Timestamp 10/16/2018 09:42:32 AM Step Count 8 Switch Count 0 Page Faults 2 Page Reclaims 10509 Page Swaps 0 Voluntary Context Switches 209 Involuntary Context Switches 41 Block Input Operations 1816 Block Output Operations 2650776
I've tried setting the various memory settings to either max or 0; I've run this on compute nodes with various RAM sizes: 128GB; 384GB; I even tried it on a node with 4TB of RAM. In any case SAS always claims that the "OS Memory" is 16.4GB. Any help would be most appreciated.
It could be that the model is not specified correctly--the code looks odds to me, but we'd need sufficient detail about the study design to sort that out.
Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 16. Read more here about why you should contribute and what is in it for you!
ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.
Find more tutorials on the SAS Users YouTube channel.