Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Investigate project application errors #20

Open
amereghe opened this issue Jul 30, 2017 · 2 comments
Open

Investigate project application errors #20

amereghe opened this issue Jul 30, 2017 · 2 comments

Comments

@amereghe
Copy link

Some SixTrack result produced by BOINC volunteers end up in error state.

A brief statistics on current results in error state still in DB (~40k) show that:

# N, error ID, error message
 1444  194 (0x000000C2) EXIT_ABORTED_BY_CLIENT
 2201 -186 (0xFFFFFF46) ERR_RESULT_DOWNLOAD
 3064  196 (0x000000C4) EXIT_DISK_LIMIT_EXCEEDED
 4377 -185 (0xFFFFFF47) ERR_RESULT_START
 7449    0 (0x00000000)
 7732  200 (0x000000C8) EXIT_UNSTARTED_LATE
11767  203 (0x000000CB) EXIT_ABORTED_VIA_GUI

Error code 200 seems to be related to short tasks, biasing the stats of the hosts, such that the host is flooded with tasks which will never start in due time - reported by R.Haselgrove

Proposed mitigation actions:

  • improve accuracy of rsc_fpops_est;
  • improve algorithm in validator to flag outliers;
@amereghe
Copy link
Author

Proposed changes in validator (just conditional statement):

from:

fracturn = turnx/(mturn*n*2.0);
outlier = 0;
if(fracturn <= 0.1) {
r1.runtime_outlier = 1;
// r2.runtime_outlier = 1; // const
outlier = 1;
}

to

fracturn = turnx/(mturn*n*2.0);
outlier = 0;
if(fracturn < 1.0) {
r1.runtime_outlier = 1;
// r2.runtime_outlier = 1; // const
outlier = 1;
}

@amereghe
Copy link
Author

SNOW ticket

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant