diff options
| author | Chuck Lever | 2015-08-03 19:03:39 +0200 |
|---|---|---|
| committer | Anna Schumaker | 2015-08-05 22:21:27 +0200 |
| commit | b3221d6a53c44cd572a3a400abdd1e2a24bea587 (patch) | |
| tree | 52a48a8a88cd0b9c1a5b92f5797421f1aa5e642c /net/sunrpc/xprtrdma/xprt_rdma.h | |
| parent | xprtrdma: Clean up rpcrdma_ia_open() (diff) | |
| download | kernel-qcow2-linux-b3221d6a53c44cd572a3a400abdd1e2a24bea587.tar.gz kernel-qcow2-linux-b3221d6a53c44cd572a3a400abdd1e2a24bea587.tar.xz kernel-qcow2-linux-b3221d6a53c44cd572a3a400abdd1e2a24bea587.zip | |
xprtrdma: Remove logic that constructs RDMA_MSGP type calls
RDMA_MSGP type calls insert a zero pad in the middle of the RPC
message to align the RPC request's data payload to the server's
alignment preferences. A server can then "page flip" the payload
into place to avoid a data copy in certain circumstances. However:
1. The client has to have a priori knowledge of the server's
preferred alignment
2. Requests eligible for RDMA_MSGP are requests that are small
enough to have been sent inline, and convey a data payload
at the _end_ of the RPC message
Today 1. is done with a sysctl, and is a global setting that is
copied during mount. Linux does not support CCP to query the
server's preferences (RFC 5666, Section 6).
A small-ish NFSv3 WRITE might use RDMA_MSGP, but no NFSv4
compound fits bullet 2.
Thus the Linux client currently leaves RDMA_MSGP disabled. The
Linux server handles RDMA_MSGP, but does not use any special
page flipping, so it confers no benefit.
Clean up the marshaling code by removing the logic that constructs
RDMA_MSGP type calls. This also reduces the maximum send iovec size
from four to just two elements.
/proc/sys/sunrpc/rdma_inline_write_padding is a kernel API, and
thus is left in place.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Tested-by: Devesh Sharma <devesh.sharma@avagotech.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Diffstat (limited to 'net/sunrpc/xprtrdma/xprt_rdma.h')
| -rw-r--r-- | net/sunrpc/xprtrdma/xprt_rdma.h | 19 |
1 files changed, 10 insertions, 9 deletions
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 82190118b8d9..8422c09043b0 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -88,7 +88,6 @@ struct rpcrdma_ep { int rep_connected; struct ib_qp_init_attr rep_attr; wait_queue_head_t rep_connect_wait; - struct rpcrdma_regbuf *rep_padbuf; struct rdma_conn_param rep_remote_cma; struct sockaddr_storage rep_remote_addr; struct delayed_work rep_connect_worker; @@ -255,16 +254,18 @@ struct rpcrdma_mr_seg { /* chunk descriptors */ char *mr_offset; /* kva if no page, else offset */ }; +#define RPCRDMA_MAX_IOVS (2) + struct rpcrdma_req { - unsigned int rl_niovs; /* 0, 2 or 4 */ - unsigned int rl_nchunks; /* non-zero if chunks */ - unsigned int rl_connect_cookie; /* retry detection */ - struct rpcrdma_buffer *rl_buffer; /* home base for this structure */ + unsigned int rl_niovs; + unsigned int rl_nchunks; + unsigned int rl_connect_cookie; + struct rpcrdma_buffer *rl_buffer; struct rpcrdma_rep *rl_reply;/* holder for reply buffer */ - struct ib_sge rl_send_iov[4]; /* for active requests */ - struct rpcrdma_regbuf *rl_rdmabuf; - struct rpcrdma_regbuf *rl_sendbuf; - struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS]; + struct ib_sge rl_send_iov[RPCRDMA_MAX_IOVS]; + struct rpcrdma_regbuf *rl_rdmabuf; + struct rpcrdma_regbuf *rl_sendbuf; + struct rpcrdma_mr_seg rl_segments[RPCRDMA_MAX_SEGS]; }; static inline struct rpcrdma_req * |