Anfeng Li

I'm facing similar issues with ~1k to ~10k jobs, each job having ~100 to ~1000 input/output files. Though I am not using a distributed filesystem but a local ZFS pool,...

BTW, I noticed some time ago that the scheduler (both ILP and greedy) seems to become lazy after running for several hours and schedule new jobs much slower than in...

Digging further I found the root cause of my issue. The cause is not file metadata checking (this is actually expected since I am not using a distributed filesystem but...

Well, some observations still show that it is sequential. I may need further investigation.

One can indeed package any pypi package as a conda package if needed. But if the conda version of a package is not released officially by its developers, additional packaging...

> I am observing the same symptoms - after about 20k jobs, Snakemake takes a minute to submit the next (small) set of jobs. > > I am _not_ seeing...

> @laf070810 Are you using checkpoints in your pipeline? I've done some debugging with PDB. My issue is somewhere inside `update_checkpoint_dependencies()`. If you aren't, I should probably make a different...

Closing this issue as it seems to be a device-specific problem. The issue disappeared after banning a specific NFS client, though we have no idea about what's wrong with that...