Re: Failed to open profile device: Device or resource busy

[Maynard J. <may...@us...>]

On 07/30/2012 03:55 AM, Avi Gozlan wrote:
> Hello again,
> 
> I did not get any response for the below issue. I would be thankful if any OProfile expert could take a look.
Avi,
It seems that somehow oprofile has gotten into a weird state on your system.  I suggest doing the following:
	1. Reboot the system
	2. rm /root/.oprofile/daemonrc
	3. rm -rf /var/lib/oprofile
	4. Setup and run oprofile again.

If these steps don't help, it may be best to ask for help on IRC at #oprofile (see http://oprofile.sourceforge.net/irc/).  Sometimes it's easier to debug things like this "live" versus via email.

-Maynard

> 
> Thanks,
> 
> Avi
> 
> -----Original Message-----
> From: Avi Gozlan 
> Sent: Thursday, July 19, 2012 3:22 PM
> To: opr...@li...
> Cc: Avi Gozlan
> Subject: Failed to open profile device: Device or resource busy
> 
> Hi,
> 
> I'm using OProfile 0.9.7 on a Nhealem machine (8-core, cpu family = 6, model=26) booting as x86_64.
> 
> The first run of 'opcontrol --start' and then 'opcontrol --shutdown' succeeds. However, if trying then to sample again using 'opcontrol --start' I get a failure with the following message:
> 
> Using 2.6+ OProfile kernel interface.
> Reading module info.
> Failed to open profile device: Device or resource busy Couldn't start oprofiled.
> Check the log file "/var/lib/oprofile/samples/oprofiled.log" and kernel syslog
> 
> Following is the content of /var/lib/oprofile/samples/oprofiled.log:
> 
> oprofiled started Thu Jul 19 15:02:33 2012 kernel pointer size: 8
> 
> dmesg Oprofile related output:
> 
> oprofile: using NMI interrupt
> 
> Various utilities used to unload the kernel module (opcontrol --deinit, rmmod oprofile) fail. For 'opcontrol --deinit' I get:
> 
> umount: /dev/oprofile: device is busy
> umount: /dev/oprofile: device is busy
> Unloading oprofile module
> ERROR: Module oprofile is in use
> 
> After about 5 minutes apparently the driver becomes free again as 'opcontrol --start' succeeds. During the long time beforehand this operation fails.
> 
> The machine has only 2G RAM. Can this explain the problem? How?
> 
> Output of 'strace opcontrol --start':
> 
> ...
> open("/dev/oprofile/1/unit_mask", O_WRONLY|O_CREAT|O_TRUNC|O_LARGEFILE, 0666) =
> 3
> fcntl64(1, F_GETFD)                     = 0
> fcntl64(1, F_DUPFD, 10)                 = 10
> fcntl64(1, F_GETFD)                     = 0
> fcntl64(10, F_SETFD, FD_CLOEXEC)        = 0
> dup2(3, 1)                              = 1
> close(3)                                = 0
> write(1, "15\n", 3)                     = 3
> dup2(10, 1)                             = 1
> fcntl64(10, F_GETFD)                    = 0x1 (flags FD_CLOEXEC)
> close(10)                               = 0
> pipe([3, 4])                            = 0
> rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 rt_sigprocmask(SIG_BLOCK, [INT CHLD], [], 8) = 0 clone(child_stack=0, flags=CLONE_CHILD_CLEARTID|CLONE_CHILD_SETTID|SIGCHLD, chil
> d_tidptr=0xf7e2a988) = 23966
> rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 rt_sigaction(SIGCHLD, {0x807a420, [], 0}, {0x807a420, [], 0}, 8) = 0
> close(4)                                = 0
> read(3, "0\n", 128)                     = 2
> read(3, "", 128)                        = 0
> close(3)                                = 0
> rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 rt_sigaction(SIGINT, {0x807afe0, [], 0}, {SIG_DFL}, 8) = 0 waitpid(-1, [{WIFEXITED(s) && WEXITSTATUS(s) == 0}], 0) = 23966 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0
> --- SIGCHLD (Child exited) @ 0 (0) ---
> waitpid(-1, 0xffb0ef78, WNOHANG)        = -1 ECHILD (No child processes)
> sigreturn()                             = ? (mask now [])
> rt_sigaction(SIGINT, {SIG_DFL}, {0x807afe0, [], 0}, 8) = 0 rt_sigprocmask(SIG_BLOCK, NULL, [], 8)  = 0 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 rt_sigprocmask(SIG_BLOCK, NULL, [], 8)  = 0 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 rt_sigprocmask(SIG_BLOCK, NULL, [], 8)  = 0 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 rt_sigprocmask(SIG_BLOCK, NULL, [], 8)  = 0 ...
> rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 rt_sigprocmask(SIG_BLOCK, NULL, [], 8)  = 0 rt_sigprocmask(SIG_BLOCK, NULL, [], 8)  = 0 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 rt_sigprocmask(SIG_BLOCK, [INT CHLD], [], 8) = 0 rt_sigprocmask(SIG_BLOCK, [CHLD], [INT CHLD], 8) = 0 rt_sigprocmask(SIG_SETMASK, [INT CHLD], NULL, 8) = 0 clone(child_stack=0, flags=CLONE_CHILD_CLEARTID|CLONE_CHILD_SETTID|SIGCHLD, chil
> d_tidptr=0xf7e2a988) = 23969
> rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 rt_sigprocmask(SIG_SETMASK, [], NULL, 8) = 0 rt_sigprocmask(SIG_BLOCK, [CHLD], [], 8) = 0 rt_sigaction(SIGINT, {0x807afe0, [], 0}, {SIG_DFL}, 8) = 0 waitpid(-1, Failed to open profile device: Device or resource busy Using 2.6+ OProfile kernel interface.
> Reading module info.
> [{WIFEXITED(s) && WEXITSTATUS(s) == 1}], 0) = 23969 ...
> 
> I would be thankful if you can shel some light on this issue or suggest a workaround.
> 
> Thanks,
> 
> Avi
> 
> 
> 
> ------------------------------------------------------------------------------
> Live Security Virtual Conference
> Exclusive live event will cover all the ways today's security and 
> threat landscape has changed and how IT managers can respond. Discussions 
> will include endpoint security, mobile security and the latest in malware 
> threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
> _______________________________________________
> oprofile-list mailing list
> opr...@li...
> https://lists.sourceforge.net/lists/listinfo/oprofile-list
>