[Bug 211897] horrible time skew under 10.3-R-p7 (seen once, not reproduced since)

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=211897 Mark Linimon changed: What|Removed |Added Assignee|b...@freebsd.org|lini...@freebsd.org Sta

[Bug 211897] horrible time skew under 10.3-R-p7 (seen once, not reproduced since)

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=211897 Martin S. Weber changed: What|Removed |Added Summary|horrible time skew under|horrible time skew under

[Bug 211897] horrible time skew under 10.3-R-p7

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=211897 --- Comment #8 from Martin S. Weber --- (In reply to Konstantin Belousov from comment #4) So, I can confirm that unpatched finds my CPU at 4GHz equals 4000 MHz. Sadly there seems to be a random element in -p7 finding my CPU at 4 GHz equal

[Bug 211897] horrible time skew under 10.3-R-p7

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=211897 --- Comment #7 from Martin S. Weber --- Here's the dmesg for 10.3-RELEASE (no patch) Table 'FACP' at 0xdb55adb8 Table 'APIC' at 0xdb55aec8 APIC: Found table at 0xdb55aec8 APIC: Using the MADT enumerator. MADT: Found CPU APIC ID 0 ACPI ID

[Bug 211897] horrible time skew under 10.3-R-p7

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=211897 --- Comment #6 from Martin S. Weber --- Here's the -p7 verbose dmesg. Interestingly, this time it did not see my CPU as 4400 Mhz, but as 4000 Mhz. Table 'FACP' at 0xdb55adb8 Table 'APIC' at 0xdb55aec8 APIC: Found table at 0xdb55aec8 APIC:

[Bug 211897] horrible time skew under 10.3-R-p7

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=211897 --- Comment #5 from Martin S. Weber --- per Konstantin's implicit request, here's the first of a few upcoming VERBOSE dmesgs. This one is for 10.3-R-p4 (k) / -p6 (u). Table 'FACP' at 0xdb55adb8 Table 'APIC' at 0xdb55aec8 APIC: Found table

[Bug 211897] horrible time skew under 10.3-R-p7

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=211897 --- Comment #4 from Konstantin Belousov --- Non-verbose dmesg is not useful for a diagnostic. >From the figure of the things I suspect that your issue might be failing 8254 piece of the chipset. Can you confirm or deny that booting non-pa

[Bug 211897] horrible time skew under 10.3-R-p7

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=211897 --- Comment #3 from Martin S. Weber --- And for easier legibility, here's a (-wu0) diff between the two dmesgs. I also notice that my CPU is recognized as 4.4Ghz under -p7, and as 4.0 Ghz under -p4, which also nicely aligns with my "10%" ti

[Bug 211897] horrible time skew under 10.3-R-p7

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=211897 --- Comment #2 from Martin S. Weber --- For completeness, here's the whole -p7 dmesg from my last boot: Copyright (c) 1992-2016 The FreeBSD Project. Copyright (c) 1979, 1980, 1983, 1986, 1988, 1989, 1991, 1992, 1993, 1994 The Regents of

[Bug 211897] horrible time skew under 10.3-R-p7

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=211897 --- Comment #1 from Martin S. Weber --- This is probably the culprit: from my -p7 dmesg: Aug 16 09:28:15 hephaistos kernel: Timecounter "TSC-low" frequency 1109872466 Hz quality 1000 vs. Timecounter "TSC-low" frequency 236900 Hz qu

[Bug 211897] horrible time skew under 10.3-R-p7

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=211897 Bug ID: 211897 Summary: horrible time skew under 10.3-R-p7 Product: Base System Version: 10.3-RELEASE Hardware: amd64 OS: Any Status: New Severity: