Re: [PATCH v4 2/3] NFSD: add new NFSD_IO_DIRECT variants that may override stable_how

[Chuck Lever <chuck.lever@oracle.com>]

On 11/7/25 10:34 AM, Christoph Hellwig wrote:
> On Thu, Nov 06, 2025 at 05:56:32PM -0500, Mike Snitzer wrote:
>> OK, I'll take a closer look at NFS client controls for stable_how,
>> because NFSD clearly handles NFS_DATA_SYNC and NFS_FILE_SYNC so I just
>> assumed its because the client does actually send them.
> 
> Asking for NFS_DATA_SYNC / NFS_FILE_SYNC for O_ЅYNC/O_SYNC writes or
> even fdatasync/fsync calls that translate to a single on the write write
> request would be a valuable client additoon that should speed things up
> with most if not all servers.
> 
>>> And as I said above, "no plan to merge it for now," meaning it's still
>>> on the table for sometime down the road. I have some other ideas I'm
>>> cooking up, such as using BDI congestion to control NFS WRITE
>>> throttling.
>>
>> Hmm, I thought the BDI congestion infra got killed (by Jan Kara and
>> others).. which made me sad because when it was first introduced it
>> was amazing at solving some complex deadlocks (but we're talking 20
>> years ago now).  So I haven't kept my finger on the pulse of what is
>> still available to us relative to BDI congestion.
> 
> Yes, BDI congestion is gone, mostly because it didn't really work.
> I'm also not sure how it could have solved deadlocks.
> 
> I feel a little out of the loops, though - what are the NFS-level
> write throttling needs to start with?
> 

Let's not go down this path right now. I'd like to stay focused on
getting the direct WRITE work merged.


-- 
Chuck Lever