Process accounting/timing has broken recently

[Julian Elischer]

On 12/5/10 10:24 PM, Garrett Cooper wrote:
> On Sun, Dec 5, 2010 at 10:22 PM, Julian Elischer<julian at freebsd.org>  wrote:
>> On 12/5/10 10:19 PM, Garrett Cooper wrote:
>>> On Sun, Dec 5, 2010 at 10:12 PM, Steve Kargl
>>> <sgk at troutmask.apl.washington.edu>    wrote:
>>>> On Sun, Dec 05, 2010 at 04:00:32PM -0800, Julian Elischer wrote:
>>>>> On 12/5/10 3:18 PM, Steve Kargl wrote:
>>>>>> Sometime in the last 7-10 days, some one made a
>>>>>> change that has broken process accounting/timing.
>>>>>>
>>>>>> laptop:kargl[42] foreach i ( 0 1 2 3 4 5 6 7 8 9 )
>>>>>> foreach? time ./testf
>>>>>> foreach? end
>>>>>> Max ULP: 0.501607 for x in [-18.000000:88.709999] with dx =
>>>>>> 1.067100e-04
>>>>>>         69.55 real        38.39 user        30.94 sys
>>>>>> Max ULP: 0.501607 for x in [-18.000000:88.709999] with dx =
>>>>>> 1.067100e-04
>>>>>>         68.82 real        40.95 user        27.60 sys
>>>>>> Max ULP: 0.501607 for x in [-18.000000:88.709999] with dx =
>>>>>> 1.067100e-04
>>>>>>         69.14 real        38.90 user        30.02 sys
>>>>>> Max ULP: 0.501607 for x in [-18.000000:88.709999] with dx =
>>>>>> 1.067100e-04
>>>>>>         68.79 real        40.59 user        27.99 sys
>>>>>> Max ULP: 0.501607 for x in [-18.000000:88.709999] with dx =
>>>>>> 1.067100e-04
>>>>>>         68.93 real        39.76 user        28.96 sys
>>>>>> Max ULP: 0.501607 for x in [-18.000000:88.709999] with dx =
>>>>>> 1.067100e-04
>>>>>>         68.71 real        41.21 user        27.29 sys
>>>>>> Max ULP: 0.501607 for x in [-18.000000:88.709999] with dx =
>>>>>> 1.067100e-04
>>>>>>         69.05 real        39.68 user        29.15 sys
>>>>>> Max ULP: 0.501607 for x in [-18.000000:88.709999] with dx =
>>>>>> 1.067100e-04
>>>>>>         68.99 real        39.98 user        28.80 sys
>>>>>> Max ULP: 0.501607 for x in [-18.000000:88.709999] with dx =
>>>>>> 1.067100e-04
>>>>>>         69.02 real        39.64 user        29.16 sys
>>>>>> Max ULP: 0.501607 for x in [-18.000000:88.709999] with dx =
>>>>>> 1.067100e-04
>>>>>>         69.38 real        37.49 user        31.67 sys
>>>>>>
>>>>>> testf is a numerically intensive program that tests the
>>>>>> accuracy of expf() in a tight loop.  User time varies
>>>>>> by ~3 seconds on my lightly loaded 2 GHz core2 duo processor.
>>>>>> I'm fairly certain that the code does not suddenly grow/loose
>>>>>> 6 GFLOP of operations.
>>>>>>
>>>>> I know it's a lot to ask but it may be something that you can help
>>>>> with if you
>>>>> had the time to triangulate in on the change that did it..
>>>>> I presume that since you are an "old hand" you can check out sources
>>>>> at different revisions..
>>>> I was hoping that someone (possibly the person responsible) would
>>>> recognize the symptoms and recommend a revision or two to revert.
>>>> Otherwise, doing a binary search will take some time in that it
>>>> takes 4+ hours for a buildworld/kernel cycle on my laptop.
>>>      If you can provide the source for the application you're running
>>> above and instructions on how to compile it, I can at least give you a
>>> bit of a head start :).
>>> Thanks,
>>> -Garrett
>>>
>> plus which probably just
>> `cd /sys/amd64/conf config GENERIC;cd ../compile/GENERIC; make kernel`
>>   would be enough...
>      But couldn't it be libthr changes? There have been a handful of
> those that have been committed recently by davidxu.

Unlikely as there was no mention of there being any thread involvement.
probably just replacing the kernel would be enough..
It'd be easy to find out.. see if one 2 weeks old fixes the problem :-)

> HTH,
> -Garrett
>