[icecast-dev] icecast-1.3.12 on SunOS

Thomas Vander Stichele thomas at urgent.rug.ac.be
Sun Sep 15 14:37:21 PDT 2002



> 
> Hello,
> 
> I sent the mail below a few days ago to the icecast user discussion and 
> support list.  Until now nobody could help me.  Maybe this list is a 
> better place for problems of this kind?

Apart from what probably is a bad assumption in the code, does it actually 
present a problem ? Meaning, even though it indicates 100% cpu usage, does 
it slow down your machine ? Maybe it's just spinning idly.  See what 
happens when other cpu eaters run.  If icecast plays nicely, it's probably 
not a big deal.

Thomas

 > Titus
> 
> 
> Anfang der weitergeleiteten E-Mail:
> >
> > Hello
> >
> > I compiled icecast-1.3.12 on a box with uname -a: SunOS star19 5.6 
> > Generic_105181-31 sun4u sparc SUNW,UltraSPARC-IIi-cEngine.  The result 
> > works properly.  The problem is that the icecast process generates 100% 
> > cpu load even if no sources and no clients are connected.
> >
> > If I trace the process using truss, I get the following:
> >
> > ...
> > open("/dev/zero", O_RDWR)                       = 1
> > mmap(0x00000000, 16384, PROT_READ|PROT_WRITE|PROT_EXEC, 
> > MAP_PRIVATE|MAP_NORESERV
> > E, 1, 0) = 0xEEBE0000
> > close(1)                                        = 0
> > mprotect(0xEEBE0000, 8192, PROT_NONE)           = 0
> > lwp_create(0xEF40FAF0, 0x00C0, 0xEEBE3E04)      = 6
> > lwp_continue(6)                                 = 0
> > lwp_create(0x00000001, 0x4000, 0xEF40FC8C)      = 0
> > lwp_schedctl(SC_STATE|SC_BLOCK, -1, 0xEEBE3D0C) = 0
> > time()                                          = 1031909555
> > time()                                          = 1031909555
> > time()                                          = 1031909555
> > time()                                          = 1031909555
> > time()                                          = 1031909555
> > time()                                          = 1031909555
> > time()                                          = 1031909555
> > ...
> > many times
> > ...
> > time()                                          = 1031909555
> > time()                                          = 1031909555
> > time()                                          = 1031909555
> > time()                                          = 1031909555
> > poll(0xEFFFD750, 1, 30)                         = 0
> > time()                                          = 1031909555
> > time()                                          = 1031909555
> > time()                                          = 1031909555
> > time()                                          = 1031909555
> > time()                                          = 1031909555
> > ...
> > time()                                          = 1031909556
> > poll(0xEF4ABA88, 0, 500)                        = 0
> > time()                                          = 1031909556
> > recvfrom(2, 0xEF4AFBA0, 8191, 0, 0x00063F38, 0xEF4ADB9C) Err#11 EAGAIN
> > time()                                          = 1031909556
> > lwp_sema_post(0xEF4B1E78)                       = 0
> > lwp_sema_wait(0xEF4B1E78)                       = 0
> > lwp_mutex_unlock(0xEF56B280)                    = 0
> > lwp_mutex_lock(0xEF56B280)                      = 0
> > time()                                          = 1031909556
> > time()                                          = 1031909556
> > time()                                          = 1031909556
> > time()                                          = 1031909556
> > lwp_sema_post(0xEF4B1E78)                       = 0
> > lwp_sema_wait(0xEF4B1E78)                       = 0
> > lwp_mutex_unlock(0xEF56B280)                    = 0
> > lwp_mutex_lock(0xEF56B280)                      = 0
> > time()                                          = 1031909556
> >
> >
> > ... and so on.  As you can see the time() is called many times per 
> > millisecond.
> >
> > Does anybody have an idea what the problem is and how it could be 
> > solved?
> >
> > Thanks,
> >  Titus
> >
> 
> --- >8 ----
> List archives:  http://www.xiph.org/archives/
> icecast project homepage: http://www.icecast.org/
> To unsubscribe from this list, send a message to 'icecast-dev-request at xiph.org'
> containing only the word 'unsubscribe' in the body.  No subject is needed.
> Unsubscribe messages sent to the list will be ignored/filtered.
> 


-- 

The Dave/Dina Project : future TV today ! - http://davedina.apestaart.org/
<-*-                      -*->
If lovin' you is wrong
then I don't wanna be right
<-*- thomas at apestaart.org -*->
URGent, the best radio on the Internet - 24/7 ! - http://urgent.rug.ac.be/

--- >8 ----
List archives:  http://www.xiph.org/archives/
icecast project homepage: http://www.icecast.org/
To unsubscribe from this list, send a message to 'icecast-dev-request at xiph.org'
containing only the word 'unsubscribe' in the body.  No subject is needed.
Unsubscribe messages sent to the list will be ignored/filtered.




More information about the Icecast-dev mailing list