Re: [PATCH 4/7] fs: break the file_list_lock for sb->s_files

2007-01-28 Thread hui
On Sun, Jan 28, 2007 at 03:30:06PM +, Christoph Hellwig wrote: > On Sun, Jan 28, 2007 at 04:21:06PM +0100, Ingo Molnar wrote: > > > > sb->s_files is converted to a lock_list. furthermore to prevent the > > > > lock_list_head of getting too contended with concurrent add > > > > operations the

Re: [PATCH 4/7] fs: break the file_list_lock for sb->s_files

2007-01-28 Thread Ingo Molnar
* Christoph Hellwig <[EMAIL PROTECTED]> wrote: > > > NACK. Please don't start using lockdep internals in core code. > > > > what do you mean by that? > > struct lock_list is an lockdep implementation detail and should not > leak out and be used anywhere else. [...] no, it is not. It is a ne

Re: [PATCH 4/7] fs: break the file_list_lock for sb->s_files

2007-01-28 Thread Christoph Hellwig
On Sun, Jan 28, 2007 at 04:32:43PM +0100, Peter Zijlstra wrote: > please see patch 2/7, its unrelated to lockdep internals. I can't see any 2/7 on lkml yet.. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info

Re: [PATCH 4/7] fs: break the file_list_lock for sb->s_files

2007-01-28 Thread Peter Zijlstra
On Sun, 2007-01-28 at 15:30 +, Christoph Hellwig wrote: > On Sun, Jan 28, 2007 at 04:21:06PM +0100, Ingo Molnar wrote: > > > > sb->s_files is converted to a lock_list. furthermore to prevent the > > > > lock_list_head of getting too contended with concurrent add > > > > operations the add is

Re: [PATCH 4/7] fs: break the file_list_lock for sb->s_files

2007-01-28 Thread Christoph Hellwig
On Sun, Jan 28, 2007 at 04:21:06PM +0100, Ingo Molnar wrote: > > > sb->s_files is converted to a lock_list. furthermore to prevent the > > > lock_list_head of getting too contended with concurrent add > > > operations the add is buffered in per cpu filevecs. > > > > NACK. Please don't start usi

Re: [PATCH 4/7] fs: break the file_list_lock for sb->s_files

2007-01-28 Thread Ingo Molnar
* Christoph Hellwig <[EMAIL PROTECTED]> wrote: > On Sun, Jan 28, 2007 at 12:51:22PM +0100, Peter Zijlstra wrote: > > Break the protection of sb->s_files out from under the global > > file_list_lock. > > > > sb->s_files is converted to a lock_list. furthermore to prevent the > > lock_list_head

Re: [PATCH 4/7] fs: break the file_list_lock for sb->s_files

2007-01-28 Thread Christoph Hellwig
On Sun, Jan 28, 2007 at 12:51:22PM +0100, Peter Zijlstra wrote: > Break the protection of sb->s_files out from under the global file_list_lock. > > sb->s_files is converted to a lock_list. furthermore to prevent the > lock_list_head of getting too contended with concurrent add operations > the ad

[PATCH 4/7] fs: break the file_list_lock for sb->s_files

2007-01-28 Thread Peter Zijlstra
Break the protection of sb->s_files out from under the global file_list_lock. sb->s_files is converted to a lock_list. furthermore to prevent the lock_list_head of getting too contended with concurrent add operations the add is buffered in per cpu filevecs. This would ordinarily require a flush