Re: [PATCH 2/2] fs/ext4/namei.c: reducing contention on s_orphan_lock mmutex

2013-10-03 Thread Thavatchai Makphaibulchoke
On 10/03/2013 06:41 PM, Andreas Dilger wrote: >> +struct inode *next_inode; > > Stack space in the kernel is not so abundant that all (or any?) of these > should get their own local variable. > >> >> -if (!EXT4_SB(sb)->s_journal) > > Same here. > > > Cheers, Andreas Thanks Andreas

Re: [PATCH 2/2] fs/ext4/namei.c: reducing contention on s_orphan_lock mmutex

2013-10-03 Thread Andreas Dilger
On 2013-10-02, at 9:36 AM, T Makphaibulchoke wrote: > Instead of using a single per super block mutex, s_orphan_lock, to serialize > all orphan list updates, a separate mutex and spinlock are used to > protect the on disk and in memory orphan lists respecvitely. > > At the same time, a per

Re: [PATCH 2/2] fs/ext4/namei.c: reducing contention on s_orphan_lock mmutex

2013-10-03 Thread Thavatchai Makphaibulchoke
On 10/02/2013 08:05 PM, Zheng Liu wrote: > Hello, > >> -if (!EXT4_SB(sb)->s_journal) >> +if (ext4_sb->s_journal) > > typo: !ext4_sb->s_journal > I am not sure whether or not this will impact the result because when > journal is enabled the inode will not be added

Re: [PATCH 2/2] fs/ext4/namei.c: reducing contention on s_orphan_lock mmutex

2013-10-03 Thread Thavatchai Makphaibulchoke
On 10/02/2013 08:05 PM, Zheng Liu wrote: Hello, -if (!EXT4_SB(sb)-s_journal) +if (ext4_sb-s_journal) typo: !ext4_sb-s_journal I am not sure whether or not this will impact the result because when journal is enabled the inode will not be added into orphan

Re: [PATCH 2/2] fs/ext4/namei.c: reducing contention on s_orphan_lock mmutex

2013-10-03 Thread Andreas Dilger
On 2013-10-02, at 9:36 AM, T Makphaibulchoke wrote: Instead of using a single per super block mutex, s_orphan_lock, to serialize all orphan list updates, a separate mutex and spinlock are used to protect the on disk and in memory orphan lists respecvitely. At the same time, a per inode

Re: [PATCH 2/2] fs/ext4/namei.c: reducing contention on s_orphan_lock mmutex

2013-10-03 Thread Thavatchai Makphaibulchoke
On 10/03/2013 06:41 PM, Andreas Dilger wrote: +struct inode *next_inode; Stack space in the kernel is not so abundant that all (or any?) of these should get their own local variable. -if (!EXT4_SB(sb)-s_journal) Same here. Cheers, Andreas Thanks Andreas for the comments.

Re: [PATCH 2/2] fs/ext4/namei.c: reducing contention on s_orphan_lock mmutex

2013-10-02 Thread Zheng Liu
Hello, On Wed, Oct 02, 2013 at 09:36:59AM -0600, T Makphaibulchoke wrote: > Instead of using a single per super block mutex, s_orphan_lock, to serialize > all orphan list updates, a separate mutex and spinlock are used to > protect the on disk and in memory orphan lists respecvitely. > > At the

[PATCH 2/2] fs/ext4/namei.c: reducing contention on s_orphan_lock mmutex

2013-10-02 Thread T Makphaibulchoke
Instead of using a single per super block mutex, s_orphan_lock, to serialize all orphan list updates, a separate mutex and spinlock are used to protect the on disk and in memory orphan lists respecvitely. At the same time, a per inode mutex is used to serialize orphan list updates of a single

[PATCH 2/2] fs/ext4/namei.c: reducing contention on s_orphan_lock mmutex

2013-10-02 Thread T Makphaibulchoke
Instead of using a single per super block mutex, s_orphan_lock, to serialize all orphan list updates, a separate mutex and spinlock are used to protect the on disk and in memory orphan lists respecvitely. At the same time, a per inode mutex is used to serialize orphan list updates of a single

Re: [PATCH 2/2] fs/ext4/namei.c: reducing contention on s_orphan_lock mmutex

2013-10-02 Thread Zheng Liu
Hello, On Wed, Oct 02, 2013 at 09:36:59AM -0600, T Makphaibulchoke wrote: Instead of using a single per super block mutex, s_orphan_lock, to serialize all orphan list updates, a separate mutex and spinlock are used to protect the on disk and in memory orphan lists respecvitely. At the same