select/poll/usleep precision on FreeBSD vs Linux vs OSX

[Luigi Rizzo]

On Thu, Mar 01, 2012 at 02:23:15AM +0100, Luigi Rizzo wrote:
> On Thu, Mar 01, 2012 at 11:33:46AM +1100, Bruce Evans wrote:
> > On Wed, 29 Feb 2012, Luigi Rizzo wrote:
> > 
> > >I have always been annoyed by the fact that FreeBSD rounds timeouts
> > >in select/usleep/poll in very conservative ways, so i decided to
> > >try how other systems behave in this respect. Attached is a simple
> > >program that you should be able to compile and run on various OS
> > >and see what happens.
> > 
> > Many are broken, indeed.
> > 
> > The simple program isn't attached.
> ...
> 
> > >
> > >	        |    Actual timeout
> > >               |      select            | poll  | usleep|
> > >	timeout | FBSD  | Linux | OSX    | FBSD  | FBSD  |
> > >	usec    | 9.0   | Vbox  | 10.6   |  9.0  |  9.0  |
> > >	--------+-------+-------+--------+-------+-------+
> > >	    1      2000      99       6     0      2000
> > >	   10      2000     109      15     0      2000
> > >	   50      2000     149      66     0      2000
> > >	  100      2000     196     133     0      2000
> > >	  500      2000     597     617     0      2000
> > >	 1000      2000    1103    1136    2000    2000
> > >	 1001      3000    1103    1136    2000    3000 <---
> > >	 1500      3000    1608    1631    2000    3000 <---
> > >      2000	   3000    2096    2127    3000    3000
> > >	 2001	   4000                    3000    4000 <---
> > >	 3001	   5000                    4000    5000 <---
> > >
> > >Note how the rounding (poll has the timeout in milliseconds) affects
> > 
> > You must have synced with timer interrupts to get the above.  Timeouts
> 
> yes i have -- the test code does almost nothing after returning from
> a select, on a system that does some amount of work times could be
> up to 1000us shorter. Still a huge error on short timeouts.
> 
> I should also comment that these are average values on an otherwise
> idle system -- i will try to post a histogram of the actual values,

Below are the statistics of select() delays on my MacBook for
timeouts of 1-10-50-100-500-1000-1001 us

Interesting that some of the delays are actually up to 25us shorter
than they should, and the average is higher than the requested
value (tends to settle to 100-150us for large delays).

    > ministat -n ~/d1 ~/d10 ~/d50 ~/d100 ~/d500 ~/d1000 ~/d1001
    x /home/luigi/d1
    + /home/luigi/d10
    * /home/luigi/d50
    % /home/luigi/d100
    # /home/luigi/d500
    @ /home/luigi/d1000
    O /home/luigi/d1001
	N           Min           Max        Median           Avg        Stddev
    x 305202             0           943             7      6.553037         2.134
    + 130798             0           862            15     15.290815     2.6807354
    * 30265            18          1002            66     66.083562     10.170399
    % 14480            75          1072           137     138.12894     29.507796
    # 3146           474          1098           656     635.87603     48.670018
    @ 1750           987          1924          1158     1143.2394     48.220706
    O 1748           986          2337          1159     1144.4102     53.547987

cheers
luigi