On Sat, 2014-09-20 at 20:36 -0700, Jaegeuk Kim wrote:
> On Sun, Sep 21, 2014 at 07:22:32AM +0800, Huang Ying wrote:
> > On Sat, 2014-09-20 at 09:23 -0700, Jaegeuk Kim wrote:
> > > On Thu, Sep 18, 2014 at 09:04:11PM +0800, huang ying wrote:
> > > > On Thu, Sep 18, 2014 at 1:51 PM, Jaegeuk Kim wrote
On Sun, Sep 21, 2014 at 07:22:32AM +0800, Huang Ying wrote:
> On Sat, 2014-09-20 at 09:23 -0700, Jaegeuk Kim wrote:
> > On Thu, Sep 18, 2014 at 09:04:11PM +0800, huang ying wrote:
> > > On Thu, Sep 18, 2014 at 1:51 PM, Jaegeuk Kim wrote:
> > >
> > > > We can summarize the roll forward recovery sc
On Sat, 2014-09-20 at 09:23 -0700, Jaegeuk Kim wrote:
> On Thu, Sep 18, 2014 at 09:04:11PM +0800, huang ying wrote:
> > On Thu, Sep 18, 2014 at 1:51 PM, Jaegeuk Kim wrote:
> >
> > > We can summarize the roll forward recovery scenarios as follows.
> > >
> > > [Term] F: fsync_mark, D: dentry_mark
>
On Thu, Sep 18, 2014 at 09:04:11PM +0800, huang ying wrote:
> On Thu, Sep 18, 2014 at 1:51 PM, Jaegeuk Kim wrote:
>
> > We can summarize the roll forward recovery scenarios as follows.
> >
> > [Term] F: fsync_mark, D: dentry_mark
> >
> > 1. inode(x) | CP | inode(x) | dnode(F)
> > -> Update the la
We can summarize the roll forward recovery scenarios as follows.
[Term] F: fsync_mark, D: dentry_mark
1. inode(x) | CP | inode(x) | dnode(F)
-> Update the latest inode(x).
2. inode(x) | CP | inode(F) | dnode(F)
-> No problem.
3. inode(x) | CP | dnode(F) | inode(x)
-> Recover to the latest dnode
