Please pull NFS client RDMA changes for 3.16
Subsystems (2)
Hey Trond,
The following changes since commit fad01e866afdbe01a1f3ec06a39c3a8b9e197014:
Linux 3.15-rc8 (2014-06-01 19:12:24 -0700)
are available in the git repository at:
git://git.linux-nfs.org/projects/anna/nfs-rdma.git nfs-rdma
for you to fetch changes up to dc7e3277e118e5bfd4796dc7cb386c1162c7c647:
xprtrdma: Disconnect on registration failure (2014-06-02 14:09:00 -0400)
----------------------------------------------------------------
Allen Andrews (1):
nfs-rdma: Fix for FMR leaks
Chuck Lever (21):
xprtrdma: RPC/RDMA must invoke xprt_wake_pending_tasks() in process context
xprtrdma: Remove BOUNCEBUFFERS memory registration mode
xprtrdma: Remove MEMWINDOWS registration modes
xprtrdma: Remove REGISTER memory registration mode
xprtrdma: Fall back to MTHCAFMR when FRMR is not supported
xprtrdma: mount reports "Invalid mount option" if memreg mode not supported
xprtrdma: Simplify rpcrdma_deregister_external() synopsis
xprtrdma: Make rpcrdma_ep_destroy() return void
xprtrdma: Split the completion queue
xprtrmda: Reduce lock contention in completion handlers
xprtrmda: Reduce calls to ib_poll_cq() in completion handlers
xprtrdma: Limit work done by completion handler
xprtrdma: Reduce the number of hardway buffer allocations
xprtrdma: Ensure ia->ri_id->qp is not NULL when reconnecting
xprtrdma: Remove Tavor MTU setting
xprtrdma: Use macros for reconnection timeout constants
xprtrdma: Reset connection timeout after successful reconnect
SUNRPC: Move congestion window constants to header file
xprtrdma: Avoid deadlock when credit window is reset
xprtrdma: Remove BUG_ON() call sites
xprtrdma: Disconnect on registration failure
Shirley Ma (1):
xprtrdma: Allocate missing pagelist
Steve Wise (1):
xprtrdma: mind the device's max fast register page list depth
include/linux/sunrpc/xprt.h | 6 ++ net/sunrpc/xprt.c | 28 +++------ net/sunrpc/xprtrdma/rpc_rdma.c | 119 +++++++++++++++++--------------------- net/sunrpc/xprtrdma/transport.c | 90 ++++++++++------------------- net/sunrpc/xprtrdma/verbs.c | 753 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---------------------------------------------------------------------------------------------------------------------------------------------- net/sunrpc/xprtrdma/xprt_rdma.h | 17 ++++-- 6 files changed, 411 insertions(+), 602 deletions(-)
Quoted 6 lines · Anna Schumaker
Hey Trond,
The following changes since commit
fad01e866afdbe01a1f3ec06a39c3a8b9e197014:Linux 3.15-rc8 (2014-06-01 19:12:24 -0700)
Did you rebase these? All the commits appear to be labeled with today's date, and Chuck appears as the committer for all of them.
Signature · 5 lines
Trond Myklebust Linux NFS client maintainer, PrimaryData [email protected]
I pulled from Chuck's branch earlier today before sending this. He has all the date stamps set as June 2.
Quoted 12 lines · Trond Myklebust
Quoted 6 lines · Anna Schumaker
Hey Trond,
The following changes since commit
fad01e866afdbe01a1f3ec06a39c3a8b9e197014:Linux 3.15-rc8 (2014-06-01 19:12:24 -0700)
Did you rebase these? All the commits appear to be labeled with today's date, and Chuck appears as the committer for all of them.
Quoted 2 lines · Anna Schumaker
I pulled from Chuck's branch earlier today before sending this. He has all the date stamps set as June 2.
OK, this is broken and I'm not pulling. The point of asking you to maintain the tree was to ensure that the patches get reviewed by you, and that I have signed-off-bys etc showing that is the case.
Quoted 14 lines · Trond Myklebust
Quoted 12 lines
Quoted 6 lines · Anna Schumaker
Hey Trond,
The following changes since commit
fad01e866afdbe01a1f3ec06a39c3a8b9e197014:Linux 3.15-rc8 (2014-06-01 19:12:24 -0700)
Did you rebase these? All the commits appear to be labeled with today's date, and Chuck appears as the committer for all of them.
Signature · 5 lines
Trond Myklebust Linux NFS client maintainer, PrimaryData [email protected]
Quoted 8 lines · Trond Myklebust
Quoted 2 lines · Anna Schumaker
I pulled from Chuck's branch earlier today before sending this. He has all the date stamps set as June 2.
OK, this is broken and I'm not pulling. The point of asking you to maintain the tree was to ensure that the patches get reviewed by you, and that I have signed-off-bys etc showing that is the case.
Thanks Trond for checking. Where was broken? What we can help here?
Quoted 7 lines
Quoted 7 lines · Trond Myklebust
Quoted 6 lines
Quoted 4 lines · Anna Schumaker
Hey Trond,
The following changes since commit
fad01e866afdbe01a1f3ec06a39c3a8b9e197014:
Quoted 7 lines
Quoted 7 lines
Quoted 6 lines
Quoted 2 lines
Linux 3.15-rc8 (2014-06-01 19:12:24 -0700)
Did you rebase these? All the commits appear to be labeled with today's date, and Chuck appears as the committer for all of them.
Shirley
Quoted 5 lines · Shirley Ma
Quoted 2 lines · Trond Myklebust
On Tue, Jun 3, 2014 at 1:04 PM, Anna Schumaker
<[email protected]> wrote:
Quoted 8 lines
Quoted 6 lines
Quoted 2 lines
I pulled from Chuck's branch earlier today before sending this. He has all the date stamps set as June 2.
OK, this is broken and I'm not pulling. The point of asking you to maintain the tree was to ensure that the patches get reviewed by you, and that I have signed-off-bys etc showing that is the case.
Thanks Trond for checking. Where was broken? What we can help here?
Hi Shirley,
I meant that the process was broken, since I was losing the information about what Anna had reviewed and so the issue was how to fix that. I've now talked to Chuck and Anna and we've set up a model for how to work together in the future: the model I'd like to see is for Anna to publish a branch of patches that she has reviewed, with the signed-off-by line. That way I know that the contents are the exact same patches that were approved on the mailing lists.
Cheers
Trond
Quoted 17 lines
Quoted 7 lines
Quoted 7 lines · Trond Myklebust
Quoted 6 lines
Quoted 4 lines · Anna Schumaker
Hey Trond,
The following changes since commit
fad01e866afdbe01a1f3ec06a39c3a8b9e197014:Quoted 7 lines
Quoted 7 lines
Quoted 6 lines
Quoted 2 lines
Linux 3.15-rc8 (2014-06-01 19:12:24 -0700)
Did you rebase these? All the commits appear to be labeled with today's date, and Chuck appears as the committer for all of them.
Shirley
Signature · 5 lines
Trond Myklebust Linux NFS client maintainer, PrimaryData [email protected]
Quoted 10 lines · Trond Myklebust
Hi Shirley,
I meant that the process was broken, since I was losing the information about what Anna had reviewed and so the issue was how to fix that. I've now talked to Chuck and Anna and we've set up a model for how to work together in the future: the model I'd like to see is for Anna to publish a branch of patches that she has reviewed, with the signed-off-by line. That way I know that the contents are the exact same patches that were approved on the mailing lists.
Quoted 2 lines
Cheers
Trond
Nice, thanks!
Shirley