Re: dtrace walltimestamp

From: Fabian Keil <freebsd-listen_at_fabiankeil.de>
Date: Sat, 20 Aug 2011 23:05:10 +0200
Ashley Williams <ashley.wil_at_gmail.com> wrote:

> walltimestamp and timestamp don't appear to be right in BETA-1:
> 
> 
> # dtrace -qn 'syscall::exec*:return { printf("%Y
> %s\n",walltimestamp,curpsinfo->pr_psargs); }'
> 1970 Jan  1 10:00:00 date
> 1970 Jan  1 10:00:00 ping
> 1970 Jan  1 10:00:00 ls

I can reproduce this on amd64 with a recent HEAD, walltimestamp
is always 0, which together with the dmesg warnings seems to indicate
that it's not supported (yet).

> # dtrace -qn 'syscall::exec*:return { printf("%Y
> %s\n",timestamp,curpsinfo->pr_psargs); }'
> 1970 Jan  6 12:02:27 ping
> 1970 Jan  6 12:02:29 ls
> 1970 Jan  6 12:02:31 dtrace

Note that the timestamp value is relative to the time
the system is booted (I think), and not to midnight,
January 1, 1970.

Assuming your system has been running for a few days
and the offsets are right as well, the output seems fine.

At least on my system, timestamp offsets can only can be relied
on with either kern.timecounter.hardware=TSC or with C3
states disabled, though.

Measuring the elapsed time (in ms) between events that happen
in roughly 1 second intervals with kern.timecounter.hardware=HPET
and dev.cpu.0.cx_lowest=C2:

  elapsed
           value  ------------- Distribution ------------- count
             990 |                                         0
            1000 |_at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at_  57
            1010 |                                         0
            1020 |                                         0
            1030 |_at_                                        1
            1040 |                                         0

  elapsed avg                                                    1007

And doing the same with dev.cpu.0.cx_lowest=C3:

  elapsed
           value  ------------- Distribution ------------- count
              40 |                                         0
              50 |_at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at__at_                      28
              60 |_at__at__at__at__at__at__at_                                  10
              70 |_at__at__at_                                      5
              80 |_at_                                        1
              90 |                                         0
             100 |_at_                                        2
             110 |_at_                                        2
             120 |_at_                                        2
             130 |                                         0
             140 |_at_                                        1
             150 |_at_                                        1
             160 |_at_                                        1
             170 |_at_                                        1
             180 |                                         0
             190 |                                         0
             200 |                                         0
             210 |                                         0
             220 |_at_                                        1
             230 |_at_                                        1
             240 |                                         0
             250 |                                         0
             260 |                                         0
             270 |                                         0
             280 |                                         0
             290 |_at_                                        1
             300 |_at_                                        1
             310 |                                         0
             320 |_at_                                        1
             330 |                                         0

  elapsed avg                                                      90

Fabian

Received on Sat Aug 20 2011 - 19:18:00 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:40:16 UTC