I’m not too across all the specifics, but I think there’s some kind of parallel gremlin lurking. I can reliably trigger the HDF5 abort by using 4 or 6 ranks, but I’ve been successful with 2, 3, 7, and 8. My guess is it’s some combination of the masking on tiles and the distribution of the files to process over the ranks? Will dig deeper to get a definitive answer though!
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Payu collate not working from "out-of-the-box" access-om2 config | 3 | 46 | 7 January 2026 | |
| Outputting a region using MOM6 diag_table - rather than a single file, I am getting many (one per processor?) | 20 | 295 | 1 December 2025 | |
| Payu generated symlinks don't work with ParallelIO library | 10 | 296 | 19 December 2023 | |
| Restart problem (atmosphere) | 22 | 590 | 24 March 2025 | |
| Automatic UM to netcdf conversion | 3 | 100 | 5 January 2025 |