[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <69df999a-1df2-595e-579d-a8c3fc700d7b@huawei.com>
Date: Thu, 9 Apr 2020 10:23:26 +0800
From: Chao Yu <yuchao0@...wei.com>
To: Jaegeuk Kim <jaegeuk@...nel.org>
CC: <linux-kernel@...r.kernel.org>,
<linux-f2fs-devel@...ts.sourceforge.net>, <kernel-team@...roid.com>
Subject: Re: [f2fs-dev] [PATCH] f2fs: introduce sysfs/data_io_flag to attach
REQ_META/FUA
On 2020/4/9 10:20, Jaegeuk Kim wrote:
> On 04/07, Chao Yu wrote:
>> On 2020/4/7 10:59, Jaegeuk Kim wrote:
>>> On 04/07, Chao Yu wrote:
>>>> On 2020/4/4 0:12, Jaegeuk Kim wrote:
>>>>> This patch introduces a way to attach REQ_META/FUA explicitly
>>>>> to all the data writes given temperature.
>>>>>
>>>>> -> attach REQ_FUA to Hot Data writes
>>>>>
>>>>> -> attach REQ_FUA to Hot|Warm Data writes
>>>>>
>>>>> -> attach REQ_FUA to Hot|Warm|Cold Data writes
>>>>>
>>>>> -> attach REQ_FUA to Hot|Warm|Cold Data writes as well as
>>>>> REQ_META to Hot Data writes
>>>>
>>>> Out of curiosity, what scenario it is used for?
>>>
>>> It's testing purpose to compare the bandwidths per different IO flags.
>>
>> Thanks for the hint. :)
>>
>> As nobarrier was set in Android, so REQ_PREFLUSH will not be considered in
>> this sysfs interface?
>
> I don't see any diff on performance, so not interesting. :)
I doubt it may has diff on non-ufs/emmc device? just guess.
Thanks,
>
>>
>> Thanks,
>>
>>>
>>>>
>>>> Thanks,
>>> .
>>>
> .
>
Powered by blists - more mailing lists