> On Apr 12, 2016, at 10:15 AM, Christoph Hellwig <hch@xxxxxxxxxxxxx> wrote: > > On Mon, Apr 11, 2016 at 04:38:44PM -0400, Chuck Lever wrote: >> No, pre-4.2 Linux servers have a bug that can be fixed by >> applying the above commit, which shouldn't be difficult to >> backport. >> >> Clients have always been allowed to send NFS READ this way. > > But the clients might be out in a the wild. I think we'll need at > least a mount option to work around them. Huh? I'm talking about non-Linux clients. RFC 5666 allows this behavior, it always has. The Linux server before 9d11b51ce7c1 is broken, full stop. Our policy is that we do not work around broken NFS servers on our client. The exception is existing bugs in the Linux server, where we may work around them temporarily until an upstream fix is available. The client change is held off for one or two kernel releases after the server is fixed. I've made several changes like this already over the past two years, and I fail to see why this one is any different. In addition, there is always NFS/TCP on IPoIB to fall back on. Can you explain your concern more fully? -- Chuck Lever -- To unsubscribe from this list: send the line "unsubscribe linux-nfs" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
