Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1557375

Re: [f2fs-dev] [PATCH 04/10] f2fs: support IO alignment for DATA and NODE writes

From Chao Yu <yuchao0@huawei.com>
Newsgroups linux.kernel
Subject Re: [f2fs-dev] [PATCH 04/10] f2fs: support IO alignment for DATA and NODE writes
Date 2017-01-12 12:20 +0100
Message-ID <sYLAe-3jp-39@gated-at.bofh.it> (permalink)
References <sUazf-86o-3@gated-at.bofh.it> <sUazf-86o-1@gated-at.bofh.it> <sVP7j-27Q-1@gated-at.bofh.it> <sW3Dk-3ex-27@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw


On 2017/1/5 7:44, Jaegeuk Kim wrote:
> On 01/04, Chao Yu wrote:
>> Hi Jaegeuk,
>>
>> On 2016/12/31 2:51, Jaegeuk Kim wrote:
>>> This patch implements IO alignment by filling dummy blocks in DATA and NODE
>>> write bios. If we can guarantee, for example, 32KB or 64KB for such the IOs,
>>> we can eliminate underlying dummy page problem which FTL conducts in order to
>>> close MLC or TLC partial written pages.
>>>
>>> Note that,
>>>  - it requires "-o mode=lfs".
>>>  - IO size should be power of 2, not exceed BIO_MAX_PAGES, 256.
>>>  - read IO is still 4KB.
>>>  - do checkpoint at fsync, if dummy NODE page was written.
>>
>> Which scenario we can benefit from? Any numbers?
> 
> I described it in the patch. This is not targetting for performance improvement
> for now, but to address the dummy page write problem in FTL so that we can later
> implement very simple host-level FTL on top of open-channel SSD.

Alright, if we are doing this since FTL implementation is moved up, so I can
understand that.

Thanks,

> 
>> I doubt that there are some potential side-effect points:
>>  - write amplification will be more serious than before
>>  - free space will be more fragmented since dummy blocks is separated in whole
>> address space
>>  - there is less chance to merge small(unaligned) IOs in block layer
> 
> I agree, so I just added this as a mount option experimentally.
> One point would be that, if f2fs doesn't do this, FTL should do it. So I think,
> from the system point of view, f2fs is a better layer to do it.
> 
> Thanks,
> 
>>
>> Thoughts?
>>
>> Thanks,
> 
> .
> 

Back to linux.kernel | Previous | NextPrevious in thread | Find similar | Unroll thread


Thread

Re: [f2fs-dev] [PATCH 04/10] f2fs: support IO alignment for DATA and  NODE writes Chao Yu <yuchao0@huawei.com> - 2017-01-04 09:30 +0100
  Re: [f2fs-dev] [PATCH 04/10] f2fs: support IO alignment for DATA and  NODE writes Jaegeuk Kim <jaegeuk@kernel.org> - 2017-01-05 01:00 +0100
    Re: [f2fs-dev] [PATCH 04/10] f2fs: support IO alignment for DATA and  NODE writes Chao Yu <yuchao0@huawei.com> - 2017-01-12 12:20 +0100

csiph-web