Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 29 May 2015 09:38:05 +0000
From:      bugzilla-noreply@freebsd.org
To:        freebsd-bugs@FreeBSD.org
Subject:   [Bug 200493] Killing pid 11 (idle) wedges the disk IO
Message-ID:  <bug-200493-8-POMSOI3qrB@https.bugs.freebsd.org/bugzilla/>
In-Reply-To: <bug-200493-8@https.bugs.freebsd.org/bugzilla/>
References:  <bug-200493-8@https.bugs.freebsd.org/bugzilla/>

next in thread | previous in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=200493

--- Comment #4 from Edward Tomasz Napierala <trasz@FreeBSD.org> ---
The reason I didn't provide more information is that I believed it to be
trivially reproducible - and also because I can't tell much about it.  That is,
everything looks normal: the system is almost idle, vmstat/iostat/top etc don't
show anything weird...  It's just that "diskinfo -t" shows values orders of
magnitude worse than usual.

Actually, I've noticed something: idle threads priority.  Before:

# procstat -t 11
  PID    TID COMM             TDNAME           CPU  PRI STATE   WCHAN    
   11 100003 idle             idle: cpu0        -1  255 run     -         
   11 100004 idle             idle: cpu1         1  255 run     -  

# kill -KILL 11
[root@brick:/home/trasz]# procstat -t 11
  PID    TID COMM             TDNAME           CPU  PRI STATE   WCHAN    
   11 100003 idle             idle: cpu0         0  120 run     -         
   11 100004 idle             idle: cpu1        -1  255 run     -      

Bumping the idle thread's priority would explain what's happening.  But why
does it get bumped?

-- 
You are receiving this mail because:
You are the assignee for the bug.



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-200493-8-POMSOI3qrB>