diff options
| author | Chuck Lever <chuck.lever@oracle.com> | 2018-05-04 15:35:20 -0400 |
|---|---|---|
| committer | Anna Schumaker <Anna.Schumaker@Netapp.com> | 2018-05-07 09:20:04 -0400 |
| commit | 7c8d9e7c8863905951d4eaa7a8d277150f3a37f7 (patch) | |
| tree | 16017a18ac2150272b7b5dd4be6fe1cd5d230aeb /net/sunrpc/xprtrdma/xprt_rdma.h | |
| parent | 0e0b854cfb3302b1907e9d3a927469b95710238f (diff) | |
| download | linux-7c8d9e7c8863905951d4eaa7a8d277150f3a37f7.tar.gz linux-7c8d9e7c8863905951d4eaa7a8d277150f3a37f7.tar.bz2 linux-7c8d9e7c8863905951d4eaa7a8d277150f3a37f7.zip | |
xprtrdma: Move Receive posting to Receive handler
Receive completion and Reply handling are done by a BOUND
workqueue, meaning they run on only one CPU.
Posting receives is currently done in the send_request path, which
on large systems is typically done on a different CPU than the one
handling Receive completions. This results in movement of
Receive-related cachelines between the sending and receiving CPUs.
More importantly, it means that currently Receives are posted while
the transport's write lock is held, which is unnecessary and costly.
Finally, allocation of Receive buffers is performed on-demand in
the Receive completion handler. This helps guarantee that they are
allocated on the same NUMA node as the CPU that handles Receive
completions.
Signed-off-by: Chuck Lever <chuck.lever@oracle.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 | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 1d7bb6e5db18..4915a6dd58c9 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -197,6 +197,7 @@ struct rpcrdma_rep { __be32 rr_proc; int rr_wc_flags; u32 rr_inv_rkey; + bool rr_temp; struct rpcrdma_regbuf *rr_rdmabuf; struct rpcrdma_xprt *rr_rxprt; struct work_struct rr_work; @@ -397,11 +398,11 @@ struct rpcrdma_buffer { struct rpcrdma_sendctx **rb_sc_ctxs; spinlock_t rb_lock; /* protect buf lists */ - int rb_send_count, rb_recv_count; struct list_head rb_send_bufs; struct list_head rb_recv_bufs; u32 rb_max_requests; u32 rb_credits; /* most recent credit grant */ + int rb_posted_receives; u32 rb_bc_srv_max_requests; spinlock_t rb_reqslock; /* protect rb_allreqs */ @@ -558,13 +559,13 @@ void rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *); int rpcrdma_ep_post(struct rpcrdma_ia *, struct rpcrdma_ep *, struct rpcrdma_req *); int rpcrdma_ep_post_recv(struct rpcrdma_ia *, struct rpcrdma_rep *); +void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp); /* * Buffer calls - xprtrdma/verbs.c */ struct rpcrdma_req *rpcrdma_create_req(struct rpcrdma_xprt *); void rpcrdma_destroy_req(struct rpcrdma_req *); -int rpcrdma_create_rep(struct rpcrdma_xprt *r_xprt); int rpcrdma_buffer_create(struct rpcrdma_xprt *); void rpcrdma_buffer_destroy(struct rpcrdma_buffer *); struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_buffer *buf); @@ -577,7 +578,6 @@ void rpcrdma_mr_defer_recovery(struct rpcrdma_mr *mr); struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *); void rpcrdma_buffer_put(struct rpcrdma_req *); -void rpcrdma_recv_buffer_get(struct rpcrdma_req *); void rpcrdma_recv_buffer_put(struct rpcrdma_rep *); struct rpcrdma_regbuf *rpcrdma_alloc_regbuf(size_t, enum dma_data_direction, |