Israel Fruchter

> @fruch I can move, but can you please edit the title and the original description 3 first lines to explain the issue exactly. update the description

happend few times again: ``` 2023-06-21T08:34:06+00:00 longevity-10gb-3h-master-db-node-7f3a461e-0-8 !INFO | scylla[6330]: Reactor stalled for 65 ms on shard 7. Backtrace: 0x419c8df 0x4194ff5 0x41945a7 0x4194628 0x3cb1f 0x13c140f 0x13c0fe7 0x155779e 0x240e290 0x26d8847 0x2375f97...

@roydahan I'm running into this again when trying to apply validation for perftune output , any distro version we have `systemd < 231`, `scylla_prepare` isn't getting executed. Or we drop...

> > seems very similar to: [#11528 (comment)](https://github.com/scylladb/scylladb/issues/11528#issuecomment-1365206311) > > we get a reactor stall and ssh get disconnected at the same time: > > ``` > > 2023-05-07T09:23:31+00:00 longevity-tls-50gb-3d-master-db-node-e54b587c-24...

> @fruch - are your nodes accessible to the world? I keep re-iterating, as can be here - [#14344 (comment)](https://github.com/scylladb/scylladb/issues/14344#issuecomment-1600890780) for example - you are being hit by scanners from...

> > Or we drop support of all those OSes, or we need to revert [cc90ff1](https://github.com/scylladb/scylladb/commit/cc90ff1646b196ca04ad7d889d83dc5b6a1451af) > > Is it only AL2? > If not, which other OS? As I...

> Not only trigger, remove the job pipeline, Argus, etc for now in master and enterprise. rasied https://github.com/scylladb/scylla-cluster-tests/issues/8946 if whom gonna do that need help, he can reach out to...

> Check the `dmesg` output for out-of-memory killer messages, it can happen that Linux just shuts down some ssh clients by seeing that it's the root of the process tree...

happens again during same nemesis, but during the decommission phase ``` 2023-06-30T08:59:39+00:00 longevity-large-partitions-8h-maste-db-node-c8d2e52f-9 !INFO | sshd[4636]: Bad packet length 2253167822. 2023-06-30T08:59:39+00:00 longevity-large-partitions-8h-maste-db-node-c8d2e52f-9 !INFO | sshd[4636]: ssh_dispatch_run_fatal: Connection from user scyllaadm...

> Why is this issue on Scylla? Are we going to decode and fix reactor stall (and only it), or is the main target here the sshd that loses its...