Re: [Virtio-fs] [PATCH][RFC] viriofsd: do not fall back to buffer io when cache=auto

[piaojun <piaojun@huawei.com>]

On 2019/8/19 13:07, Eryu Guan wrote:
> On Mon, Aug 19, 2019 at 11:51:51AM +0800, piaojun wrote:
>>
>>
>> On 2019/8/19 11:15, Eryu Guan wrote:
>>> On Wed, Aug 14, 2019 at 05:46:42PM +0800, piaojun wrote:
>>>> Direct io flags will be tured off even if cache=auto, which seems a
>>>> little bit strange. It's better to keep the open flags set by user. If
>>>> I missed the discussion about this issue, please let me know, thanks.
>>>>
>>>> Signed-off-by: Jun Piao <piaojun@huawei.com>
>>>> ---
>>>>  contrib/virtiofsd/passthrough_ll.c | 4 ++++
>>>>  1 file changed, 4 insertions(+)
>>>>
>>>> diff --git a/contrib/virtiofsd/passthrough_ll.c b/contrib/virtiofsd/passthrough_ll.c
>>>> index 321bbb2..a080f0d 100644
>>>> --- a/contrib/virtiofsd/passthrough_ll.c
>>>> +++ b/contrib/virtiofsd/passthrough_ll.c
>>>> @@ -1687,6 +1687,8 @@ static void lo_create(fuse_req_t req, fuse_ino_t parent, const char *name,
>>>>  		fi->direct_io = 1;
>>>>  	else if (lo->cache == CACHE_ALWAYS)
>>>>  		fi->keep_cache = 1;
>>>> +	else
>>>> +		fi->direct_io = !!(fi->flags & O_DIRECT);
>>>>
>>>>  out:
>>>>  	lo_inode_put(lo, &parent_inode);
>>>> @@ -1899,6 +1901,8 @@ static void lo_open(fuse_req_t req, fuse_ino_t ino, struct fuse_file_info *fi)
>>>>  		fi->direct_io = 1;
>>>>  	else if (lo->cache == CACHE_ALWAYS)
>>>>  		fi->keep_cache = 1;
>>>> +	else
>>>> +		fi->direct_io = !!(fi->flags & O_DIRECT);
>>>>  	fuse_reply_open(req, fi);
>>>
>>> IMHO, this is necessary, it seems that in the case cache=auto/always,
> 
> Huge typo here, I meant "not necessary" here..
> 
>>> virtiofsd already follows what guest requests, i.e.  virtiofsd only does
>>> direct I/O when guest opens file with O_DIRECT.
>>
>> From my testing, virtiofsd won't do direct io even if guest opens file
>> with O_DIRECT when cache=auto/alway. It's weird to convert direct io to
>> buffer io at host side.
> 
> That doesn't match what's in my mind, I think FUSE_OPEN will pass guest
> open flags to virtiofsd and virtiofsd saves the fd (which is opened with
> O_DIRECT) in fd map, then subsequent FUSE_WRITE does direct write to
> that fd.

Yes, I agree with this. And my comment was a little confuing, so I have
to resend the patch later to make it more clear.

Jun