Alexander Gallego
Alexander Gallego
@piyushredpanda - i don't think that matters because the cluster *never* actually upgraded, so the global barrier shouldn't come into play.
@kargh - this `redpanda.service: main process exited, code=killed, status=4/ILL` what processor are you using?
@kargh can you decomision one node since the cluster is unstable and run an FIO test on the same device to get a hardware profile (16KiB pages, seq read,write, 10G...
@kargh thanks for all these notes.... this is *even* MORE suspicious if that is the case. hmmmm... any insight ont he app behavior. btw eng team has today and tomorrow...
this is definitely a bug w/ redpanda `Segmentation fault on shard 58` cc: @piyushredpanda and @mattschumpert @kargh - any 'demo' app we can run on our CI to test? seems...
last q @kargh what is the CPU to memory ratio, is it at least 2G/core?
this sounds ideal tbh. so definitely a bug on our side. let us dig next week.
Is the stress test itself that it only does historical reads. Or is the stress test mixed. Wanting to understand cover letter
@BenPope should this be elavated to `DEBUG` or `TRACE` ``` INFO 2022-11-09 21:51:58,069 [shard 0] rpc - server.cc:127 - kafka rpc protocol - Error[applying protocol] remote address: 127.0.0.1:54036 - std::__1::system_error...
@ivotron what’s the motivation for this change. To create a separate rpk release train ?