At Mon, 7 Jul 2025 20:02:09 +0200, Christof Meerwald <cmeerw%cmeerw.org@localhost> wrote: Subject: Re: NetBSD 10.1 VPS became unresponsive > > Just had the issue show up again on that machine (after 3 months) - I > have that VPS since around September last year, and it's been occuring > maybe every 1-3 months. > > The lighttpd error log shows: > > 2025-07-07 02:54:28: (server.c.469) warning: clock jumped 48611 secs > 2025-07-07 02:54:28: (server.c.482) clock jumped; attempting graceful > restart in < ~5 seconds, else hard restart > 2025-07-07 16:24:39: (server.c.1234) [note] graceful shutdown started Hmmm.... this sounds suspiciously like the Xen problems I and others have been having on some hardware. Do you have any other way of independently timestamping those logs? E.g. a serial console that can be monitored by conserver (or some other serial port logging software that can timestamp output)? If so then get these logs to also go to the console and this way you could see more clearly if the clock really did jump. You might be able to do something similar by forwarding syslog to another reliable server as well. Note that the Xen problems are all most likely related to how Xen emulates the RDTSC instruction to provide a "fake" constant-frequency (across hardware and domains) TSC. However maybe VirtFusion/KVM is doing something similar under the hood in the emulation of HPET. -- Greg A. Woods <gwoods%acm.org@localhost> Kelowna, BC +1 250 762-7675 RoboHack <woods%robohack.ca@localhost> Planix, Inc. <woods%planix.com@localhost> Avoncote Farms <woods%avoncote.ca@localhost>
Attachment:
pgpcQKyUkSlb9.pgp
Description: OpenPGP Digital Signature