Merged.
Thank you,
2013-09-05 (목), 12:45 +0800, Jin Xu:
> From: Jin Xu
>
> This patch improves the gc efficiency by optimizing the victim
> selection policy. With this optimization, the random re-write
> performance could increase up to 20%.
>
> For f2fs, when disk is in shortage of free spaces
From: Jin Xu
This patch improves the gc efficiency by optimizing the victim
selection policy. With this optimization, the random re-write
performance could increase up to 20%.
For f2fs, when disk is in shortage of free spaces, gc will selects
dirty segments and moves valid blocks around for maki
Yes, I will submit the patch later.
On 05/09/2013 07:50, Jaegeuk Kim wrote:
> Hi Jin,
>
> 2013-09-04 (수), 21:17 +0800, Jin Xu:
>> Hi Jaegeuk,
>>
>> On 04/09/2013 17:40, Jaegeuk Kim wrote:
>>> Hi Jin,
>>>
>>> 2013-09-04 (수), 07:59 +0800, Jin Xu:
Hi Jaegeuk,
On 03/09/2013 08:45, Jaege
Hi Jin,
2013-09-04 (수), 21:17 +0800, Jin Xu:
> Hi Jaegeuk,
>
> On 04/09/2013 17:40, Jaegeuk Kim wrote:
> > Hi Jin,
> >
> > 2013-09-04 (수), 07:59 +0800, Jin Xu:
> >> Hi Jaegeuk,
> >>
> >> On 03/09/2013 08:45, Jaegeuk Kim wrote:
> >>> Hi Jin,
> >>>
> [...]
> >
> > It seems that we can
Hi Jaegeuk,
On 04/09/2013 17:40, Jaegeuk Kim wrote:
> Hi Jin,
>
> 2013-09-04 (수), 07:59 +0800, Jin Xu:
>> Hi Jaegeuk,
>>
>> On 03/09/2013 08:45, Jaegeuk Kim wrote:
>>> Hi Jin,
>>>
[...]
>
> It seems that we can obtain the performance gain just by setting the
> MAX_VICTIM_SEARCH to
Hi Jin,
2013-09-04 (수), 07:59 +0800, Jin Xu:
> Hi Jaegeuk,
>
> On 03/09/2013 08:45, Jaegeuk Kim wrote:
> > Hi Jin,
> >
> >> [...]
> >>>
> >>> It seems that we can obtain the performance gain just by setting the
> >>> MAX_VICTIM_SEARCH to 4096, for example.
> >>> So, how about just adding an endin
Hi Jaegeuk,
On 03/09/2013 08:45, Jaegeuk Kim wrote:
> Hi Jin,
>
>> [...]
>>>
>>> It seems that we can obtain the performance gain just by setting the
>>> MAX_VICTIM_SEARCH to 4096, for example.
>>> So, how about just adding an ending criteria like below?
>>>
>>
>> I agree that we could get the per
Hi Jin,
> [...]
> >
> > It seems that we can obtain the performance gain just by setting the
> > MAX_VICTIM_SEARCH to 4096, for example.
> > So, how about just adding an ending criteria like below?
> >
>
> I agree that we could get the performance improvement by simply
> enlarging the MAX_VICTIM_
Hi Jaegeuk,
On 08/29/2013 07:56 PM, Jaegeuk Kim wrote:
> Hi,
>
> 2013-08-29 (목), 08:48 +0800, Jin Xu:
>> From: Jin Xu
>>
>> This patch improves the foreground gc efficiency by optimizing the
>> victim selection policy. With this optimization, the random re-write
>> performance could increase up t
Hi Jaegeuk,
On Thu, Aug 29, 2013 at 7:56 PM, Jaegeuk Kim
wrote:
>
> Hi,
>
> 2013-08-29 (목), 08:48 +0800, Jin Xu:
> > From: Jin Xu
> >
> > This patch improves the foreground gc efficiency by optimizing the
> > victim selection policy. With this optimization, the random re-write
> > performance co
Hi Jaegeuk,
On Thu, Aug 29, 2013 at 7:56 PM, Jaegeuk Kim wrote:
> Hi,
>
> 2013-08-29 (목), 08:48 +0800, Jin Xu:
> > From: Jin Xu
> >
> > This patch improves the foreground gc efficiency by optimizing the
> > victim selection policy. With this optimization, the random re-write
> > performance coul
Hi,
2013-08-29 (목), 08:48 +0800, Jin Xu:
> From: Jin Xu
>
> This patch improves the foreground gc efficiency by optimizing the
> victim selection policy. With this optimization, the random re-write
> performance could increase up to 20%.
>
> For f2fs, foreground gc happens when disk is lack of
Correct the wrongly placed gc statistics in the test result part:
without the patch
created 52023 files of size 32768 bytes in 341 seconds
finished 10 loops in 4204 seconds
(internally, 1255 gc were done, 181101 garbage blocks were reclaimed)
with the patch
created 52023 files
From: Jin Xu
This patch improves the foreground gc efficiency by optimizing the
victim selection policy. With this optimization, the random re-write
performance could increase up to 20%.
For f2fs, foreground gc happens when disk is lack of free spaces,
it selects dirty segments and moves valid b
14 matches
Mail list logo
