Red Hat Bugzilla – Bug 170545
kernel_lock() problem through NFS mount
Last modified: 2007-11-30 17:07:21 EST
From Bugzilla Helper:
User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.7.8) Gecko/20050512 Red Hat/1.0.4-1.4.1 Firefox/1.0.4
Description of problem:
We have discovered a problem where the kernel lock is still being held by a process
when it returns to user mode. This results in other processes that are in the kernel
and want the kernel lock spinning inside of lock_kernel() and reacquire_kernel_lock()
even though the real lock holder is no longer in the kernel.
Version-Release number of selected component (if applicable):
Steps to Reproduce:
2.mount a nfs filesystem
3.unlock a nfs mounted file
Actual Results: all sorts of weird behavior happens with kernel lock held and going to user space.. espeically on SMP systems, you can notice the slowness of the system since it renders other cpus useless during swapping to user space.
Expected Results: On smp kernel, there shouldn't be any slowness when a cpu goes into user space.
*** Bug 170546 has been marked as a duplicate of this bug. ***
Created attachment 119871 [details]
Backport of the entire NFS locking changes from 2.6.11
I think we should include the entire NFS locking code from 2.6.11. This fixes
several known problems including exiting the kernel with the kernel_lock still
*** This bug has been marked as a duplicate of 167192 ***