nanosleep & sginap

New Message Reply Date view Thread view Subject view Author view

Ken Lindsay (kl++at++grossberg.arc.nasa.gov)
Mon, 29 Mar 1999 09:03:56 -0800 (PST)

i had done some fiddlin' a few weeks ago trying to get better resolution
than sginap provides, and so i tested nanosleep and usleep. my conclusion
was that their resolution (at least in the default setup in IRIX 6.5.1)
is 10 milliseconds, just like sginap. here is some sample data:

clock res RT: 0.010000000
clock res CYCLE: 0.000000021
clock res FAST: 0.000000021
CLK_TCK = 100 per sec ;

nanosleep CLOCK_SGI_CYCLE: 5 998102.163156189 delta: 0.009998625
nanosleep CLOCK_SGI_CYCLE: 6 998102.173152357 delta: 0.009996168
nanosleep CLOCK_SGI_CYCLE: 7 998102.183156946 delta: 0.010004589
nanosleep CLOCK_SGI_CYCLE: 8 998102.193156159 delta: 0.009999213
nanosleep CLOCK_SGI_CYCLE: 9 998102.203157892 delta: 0.010001733

usleep CLOCK_SGI_CYCLE: 4 998103.154809201 delta: 0.009997302
usleep CLOCK_SGI_CYCLE: 5 998103.164807448 delta: 0.009998247
usleep CLOCK_SGI_CYCLE: 6 998103.174807858 delta: 0.010000410
usleep CLOCK_SGI_CYCLE: 7 998103.184809843 delta: 0.010001985
usleep CLOCK_SGI_CYCLE: 8 998103.194807796 delta: 0.009997953

--> so how does one use these routines at their high resolution potential?

thanks

ken
-==-

ken "fire a few neurons" lindsay kl++at++ptolemy.arc.nasa.gov
NASA Ames Research Center Caelum Research Corp.
Mail Stop 269-1 (650) 604 3594 (fax)
Moffett Field, CA 94035-1000 (650) 604 3181 (vox)

REMEMBER: you don't have to be a civil servant to go "post office"

New Message Reply Date view Thread view Subject view Author view

This archive was generated by hypermail 2.0b2 on Mon Mar 29 1999 - 09:04:00 PST

This message has been cleansed for anti-spam protection. Replace '++at++' in any mail addresses with the '@' symbol.