1) Message boards : Number crunching : exceeded disk limit (Message 244)
Posted 11 Apr 2015 by LCB001
Post:
My first CMS-devs were also ran on a rig using an SSD and I had the same result.

I thought it might be due lack of space on the ssd and so switched CMS over to two other dualie rigs that use hdds.

What was puzzling was it still happened on one of those even though Boinc has 180GB+ of space available.

This rig was also running 2x Atlas, 2x Edge and 8x SRBase wus plus an Einstein on the gpu.

Once I removed the leftover vdi it has been back to zero errors.

The second rig had no leftovers and no disk space error problems.

Both are due to finish their second CMSs tomorrow and it will be interesting to see what happens then.

I also run T4T, vLHC and Atlas and haven't had this particular problem with them.

I just find it weird that the CMS wus seem to keep running fine but yet cause problems for wus from other projects...
2) Message boards : Number crunching : exceeded disk limit (Message 242)
Posted 10 Apr 2015 by LCB001
Post:
CMS-dev workunits like to leave their disk images behind, check your slots there's probably one or more with only a .vdi left in them.

If you delete the vdi you should be good to go again.

Why this causes other projects to get that exceeded disk space error even if Boinc has lot's of available space left I don't know but it's very annoying...
3) Message boards : Number crunching : Multiple Jobs In A Single Host (Message 240)
Posted 9 Apr 2015 by LCB001
Post:
I had a case recently where tasks were failing because a 5+ GB VM was left in a slot directory where subsequent tasks were run; as they accumulated results the directory exceeded 10 GB, a limit in our set-up, and the tasks failed.

This just happened to me with my first two CMS-dev wu's except it were work from other projects that was getting computation errors due to lack of disk space.

This had me be puzzled until I found the two vdi's left in the slots directory which meant that between the slots and the regular files CMS-dev was taking more than 12.5GB of space on the 128GB ssd I use for Boinc, this without one running at the moment.

Now that I know to keep an eye out for Leftovers it won't be a problem for me but others might be in for an unpleasent surprise if this isn't fixed.



©2020 CERN