Chuck Lever 2d6491a56c svcrdma: Don't account for Receive queue "starvation" ... >From what I can tell, calling ->recvfrom when there is no work to do is a normal part of operation. This is the only way svc_recv can tell when there is no more data ready to receive on the transport. Neither the TCP nor the UDP transport implementations have a "starve" metric. The cost of receive starvation accounting is bumping an atomic, which results in extra (IMO unnecessary) bus traffic between CPU sockets, while holding a spin lock. Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Signed-off-by: J. Bruce Fields <bfields@redhat.com>		2017-06-28 14:21:44 -04:00
..
backchannel.c	xprtrdma: Delete an error message for a failed memory allocation in xprt_rdma_bc_setup()	2017-05-24 07:53:37 -04:00
fmr_ops.c	xprtrdma: Refactor management of mw_list field	2017-02-10 14:02:37 -05:00
frwr_ops.c	xprtrdma: Refactor management of mw_list field	2017-02-10 14:02:37 -05:00
Makefile	svcrdma: Remove svc_rdma_marshal.c	2017-06-28 14:21:43 -04:00
module.c	rpcrdma: Merge svcrdma and xprtrdma modules into one	2015-06-04 16:56:02 -04:00
rpc_rdma.c	xprtrdma: Squelch ENOBUFS warnings	2017-04-25 16:12:33 -04:00
svc_rdma.c	svcrdma: Reduce size of sge array in struct svc_rdma_op_ctxt	2017-04-25 17:25:55 -04:00
svc_rdma_backchannel.c	svcrdma: Clean up RPC-over-RDMA backchannel reply processing	2017-04-25 17:25:55 -04:00
svc_rdma_recvfrom.c	svcrdma: Don't account for Receive queue "starvation"	2017-06-28 14:21:44 -04:00
svc_rdma_rw.c	svcrdma: Avoid Send Queue overflow	2017-06-28 14:21:43 -04:00
svc_rdma_sendto.c	svcrdma: Avoid Send Queue overflow	2017-06-28 14:21:43 -04:00
svc_rdma_transport.c	svcrdma: Remove the req_map cache	2017-04-25 17:25:55 -04:00
transport.c	xprtrdma: Support unplugging an HCA from under an NFS mount	2017-04-25 16:12:24 -04:00
verbs.c	xprtrdma: Annotate receive workqueue	2017-04-25 16:12:31 -04:00
xprt_rdma.h	xprtrdma: Remove rpcrdma_buffer::rb_pool	2017-04-25 16:12:35 -04:00