14:05:38 jbk I think your ioctl() is handled in cmlb but should be handled by actual disk driver... 14:06:09 after a bit of dtrace I figured out the problem... 14:06:51 a) it has to be the rdsk (character device) node, and b) the device itself doesn't have a flushable write cache 14:07:04 (the latter was a bit of a surprise) 15:01:48 I just filed bug #17776. Why do I expect this to increment directly to 20000? :) 15:23:36 missed the chance to say you thought it oct to do that :P 15:26:19 heh 16:05:45 jbk: FWIW, most NVMe ssds that have a supercap don't advertise a volatile write cache that I've seen. 16:48:23 Do we compile bhyve with smatch on? 16:49:21 Looks like we do. 16:49:28 Much better. 19:13:32 has anyone tried https://github.com/slackhq/nebula on illumos/smartos? 19:29:13 I use tailscale. It uses wireguard-go a userland implementation of wg. It also uses the tun driver. Tailscale works, but the tun driver not the fastest implementation. 19:49:50 szilard - there is already a *bsd versions of the nebula client. There is a "managed" version from defined.net, that offers an API for automatic joining the network (https://docs.defined.net/guides/automating-host-creation/) for dynamically created hosts... 19:50:58 I have tried tailscale, too. But I don't like the idea to use tailscales relays. 19:54:48 i've not looked at it in a while, but when I did, the things that stood out to me were the lack of algorithm agility (which I know was explicit, but I think that was a mistake/overreaction to the complexity of IKE(v2)) and how it seemed to require static IPs in a lot of cases that traditionally don't get them (but maybe in an IPv6 world it's less of an issue?) 20:02:09 You can use headscale instead of the tailscale relays. It is open source 21:02:09 tailscale is miraculous, and if you want to use the open coordination clones they exist 21:02:25 I would _imagine_ that breaks some of the nat-traversal trickery they do 21:03:22 nahum would be the expert