Error killed running qiime feature-classifier

Hi, I’m trying to run this command:
qiime feature-classifier classify-sklearn --i-classifier silva-138-99-nb-classifier.qza --i-reads rep-seqs16S-tuber_GeP.qza --p-n-jobs 4 --o-classification taxonomy16S_tuber_GeP.qza
After 10 minutes the process stopped saying killed. I’ve tried to amplify the memory space of my virtual machine (VirtualBox) up to 150 GB and exporting the working directory to my Desktop with 100 GB free, but nothing changes. What problem could be?

Hi @Alice_Calvo,

Would you mind sharing more details? Please copy/paste the exact error that you observed. It is always helpful to know as many details as possible. I am also curious about your development environment. Where are you running your virtual machine?

“qiime feature-classifier classify-sklearn --i-classifier silva-138-99-nb-classifier.qza --i-reads rep-seqs16S-tuber_GeP.qza --p-n-jobs 4 --o-classification taxonomy16S_tuber_GeP.qza
Killed”
There wasn’t a code for the error,
I’m running
Sorry for the late answer, I was trying to solve the problem with my boss that say me it’s a ram problem. We weren’t able to solve it because adding ram to my virtualbox the PC stop working well, for example my dashboard stopped working. My laptop is an HP with windows 10

It sounds like you may have allocated more RAM than your PC had available and/or are trying to parallelize the job beyond your means. The goal is to find the sweet spot - allocate as much RAM as possible, but not too much (same with the --p-n-jobs parameter). I don’t have too much experience running jobs in VirtualBox, so I will do some experiments myself first so I don’t steer you in the wrong direction.

Hi, @Alice_Calvo,

I’ll give a high-level explanation of how I recommend troubleshooting your issues. Please let me know how it goes and if you need more details.

  • Check how much free RAM you have on your PC and use this information to determine how much RAM you should allocate to your VM.

    • This article explains how to check the amount of RAM you have available on your PC. Note that you need to know how much free RAM you have available (not just the total capacity). E.g., you computer may have 16 GB of RAM, but the amount of free RAM will depend on how much is being used at any given time. My suggestion would be to allocate the amount of free RAM minus at least 1 GB to your VM. E.g., if you have 10 GB of free RAM, allocate a maximum of 9 GB to the VM, leaving at least 1 GB free.
  • Check how much available CPU you have on your PC and use this information to determine the value for --p-n-jobs

    • This article explains several different ways to do so. I think the number that’s important here is the number of logical processors. I’m not :100: sure on that and I don’t have a Windows machine to test on. This is the number that you shouldn’t exceed when determining the value for --p-n-jobs.

I hope that helps. Please let me know how you get along.