antoniopetrole
antoniopetrole
Hey @liang8283 . So some more context and I added some files to look at. It seems like the issue is the same thing that happens with gpssh. You pass...
Tagging @foreyes per request
@yjhjstz Wow I can't believe I forgot to upload the ddl, I've attached it to this comment. Also I shared the coredump with @edespino directly, I don't want to share...
@foreyes You can reach out to @edespino for the subset of core files, he will be distributing it amongst the core maintainers for analysis. Thanks for looking into this!
So I've gotten the green light to go ahead and try to recreate this issue in our dev environment. If I manage to do this then the next step will...
Just want to give everyone an update, I've yet to be able to recreate this in our development environment. I still have a few more things to try and validate...
@foreyes I'll take a look at this either later today or tomorrow. We collect and store metrics around memory, disk, and CPU utilization so we should have data on this....
Just realized I never replied to this, apologies for that things have been super busy. Just wanted to add some context that Greg Spiegelberg found. He went through all of...
@edespino Yes we have specific directories where core files are dumped and I believe we have the core files for all of the times segments have gone down since we...
@foreyes Thank you! I understand that this is a complex issue with a lot of moving parts