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

[Eryu Guan]

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 at 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.

> 
> > 
> > If I understand the code correctly, fi->direct_io = 1 is used to force
> > guest to use direct I/O even if guest opens file without O_DIRECT.
> 
> But in fact, direct I/O will be forced to buffer I/O even if with
> O_DIRECT. I will look into this problem by further testing, and very
> glad to share my test result.

Thanks!

Eryu