On 2017/2/17 10:54, Jaegeuk Kim wrote:
> On 02/17, Hou Pengyang wrote:
>> On 2017/2/17 7:48, Jaegeuk Kim wrote:
>>> Hi Pengyang,
>>>
>>> Nice
>> Hi Jaegeuk,
>> catch!
>>>
>>> I think fggc_threshold needs to be revised, and we need to consider about
>>> general victim selection as well.
>>>
>>> Coul
On 02/17, Hou Pengyang wrote:
> On 2017/2/17 7:48, Jaegeuk Kim wrote:
> > Hi Pengyang,
> >
> > Nice
> Hi Jaegeuk,
> catch!
> >
> > I think fggc_threshold needs to be revised, and we need to consider about
> > general victim selection as well.
> >
> > Could you take a look at this?
> >
> > > Fro
On 2017/2/17 7:48, Jaegeuk Kim wrote:
> Hi Pengyang,
>
> Nice
Hi Jaegeuk,
catch!
>
> I think fggc_threshold needs to be revised, and we need to consider about
> general victim selection as well.
>
> Could you take a look at this?
>
>>From 23b265f5ca6405032d092e240c94a827f743e42b Mon Sep 17 00:00:00
Hi Daniel,
On 02/17, Daniel Black wrote:
> I was looking at Documentation/filesystems/f2fs.txt trying to work out
> how to do atomic writes.
>
> I did find https://www.spinics.net/lists/kernel/msg1839691.html which
> contains some elements.
>
> It seems F2FS_IOC_DB_OPEN might been replaced by
>
I was looking at Documentation/filesystems/f2fs.txt trying to work out
how to do atomic writes.
I did find https://www.spinics.net/lists/kernel/msg1839691.html which
contains some elements.
It seems F2FS_IOC_DB_OPEN might been replaced by
F2FS_IOC_START_ATOMIC_WRITE looking at fs/f2fs/f2fs.h
I'd
Hi Pengyang,
Nice catch!
I think fggc_threshold needs to be revised, and we need to consider about
general victim selection as well.
Could you take a look at this?
>From 23b265f5ca6405032d092e240c94a827f743e42b Mon Sep 17 00:00:00 2001
From: Hou Pengyang
Date: Thu, 16 Feb 2017 12:34:31 +
S
On 02/16, Chao Yu wrote:
> On 2017/2/16 9:16, Jaegeuk Kim wrote:
> > On 02/14, Jaegeuk Kim wrote:
> >> On 02/15, Chao Yu wrote:
> >>> On 2017/2/15 2:03, Jaegeuk Kim wrote:
> VFS uses f2fs_lookup() to decide f2fs_add_link() call during file
> creation.
> But, if there is a race condi
For foreground gc, greedy algorithm should be adapted, which makes
this formula work well:
(2 * (100 / config.overprovision + 1) + 6)
But currently, we fg_gc have a prior to select bg_gc victim segments to gc
first,
these victims are selected by cost-benefit algorithm, we can't guarantee