Date: Sat, 20 Jul 2019 20:31:08 +0000 From: bugzilla-noreply@freebsd.org To: ports-bugs@FreeBSD.org Subject: [Bug 239351] [panic] net/wireguard: spin lock held too long under heavy load Message-ID: <bug-239351-7788@https.bugs.freebsd.org/bugzilla/>
next in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D239351 Bug ID: 239351 Summary: [panic] net/wireguard: spin lock held too long under heavy load Product: Ports & Packages Version: Latest Hardware: amd64 OS: Any Status: New Severity: Affects Some People Priority: --- Component: Individual Port(s) Assignee: decke@FreeBSD.org Reporter: contact@evilham.com Assignee: decke@FreeBSD.org Flags: maintainer-feedback?(decke@FreeBSD.org) Created attachment 205949 --> https://bugs.freebsd.org/bugzilla/attachment.cgi?id=3D205949&action= =3Dedit coredump_spin_lock_held_too_long Hello, I had been debugging this for a while and was 95% sure my panic was being caused by a graphics thing, turns out I was wrong and it was caused by net/wireguard. The relevant packages and versions: wireguard-go-0.0.20190517 wireguard-0.0.20190702 It may also be relevant to mention that I use WireGuard to have IPv6-connectivity on the go, it only uses IPv6-addresses except for the IPv= 4 of the peer. I can reproduce the issue by starting 20 parallel downloads of big files (8= G), e.g.: for i in `seq 1 20`; do curl -6 ${BIG_FILE} > /dev/null &; done (The -6 param is because of the use I give to WireGuard as on-the-go IPv6) CPU usage rises (I think that's to be expected with WireGuard) and after so= me seconds the panic occurs (see core dump). It *may* also be relevant that this is running on a ThinkPad A485, which is affected by #231760. That means that ATM FreeBSD can only run with hw.pci.mcfg=3D0 in /boot/loader.conf. --=20 You are receiving this mail because: You are the assignee for the bug.=
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-239351-7788>