From e7104a2a96069975d489c60a30564372c6273a85 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Sat, 8 Nov 2014 20:14:20 -0500 Subject: [PATCH] xprtrdma: Cap req_cqinit Recent work made FRMR registration and invalidation completions unsignaled. This greatly reduces the adapter interrupt rate. Every so often, however, a posted send Work Request is allowed to signal. Otherwise, the provider's Work Queue will wrap and the workload will hang. The number of Work Requests that are allowed to remain unsignaled is determined by the value of req_cqinit. Currently, this is set to the size of the send Work Queue divided by two, minus 1. For FRMR, the send Work Queue is the maximum number of concurrent RPCs (currently 32) times the maximum number of Work Requests an RPC might use (currently 7, though some adapters may need more). For mlx4, this is 224 entries. This leaves completion signaling disabled for 111 send Work Requests. Some providers hold back dispatching Work Requests until a CQE is generated. If completions are disabled, then no CQEs are generated for quite some time, and that can stall the Work Queue. I've seen this occur running xfstests generic/113 over NFSv4, where eventually, posting a FAST_REG_MR Work Request fails with -ENOMEM because the Work Queue has overflowed. The connection is dropped and re-established. Cap the rep_cqinit setting so completions are not left turned off for too long. BugLink: https://bugzilla.linux-nfs.org/show_bug.cgi?id=269 Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/verbs.c | 4 +++- net/sunrpc/xprtrdma/xprt_rdma.h | 6 ++++++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 6ea29420f0ac..af45cf390126 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -733,7 +733,9 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, /* set trigger for requesting send completion */ ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 - 1; - if (ep->rep_cqinit <= 2) + if (ep->rep_cqinit > RPCRDMA_MAX_UNSIGNALED_SENDS) + ep->rep_cqinit = RPCRDMA_MAX_UNSIGNALED_SENDS; + else if (ep->rep_cqinit <= 2) ep->rep_cqinit = 0; INIT_CQCOUNT(ep); ep->rep_ia = ia; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index ac7fc9a31342..b799041b75bf 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -97,6 +97,12 @@ struct rpcrdma_ep { struct ib_wc rep_recv_wcs[RPCRDMA_POLLSIZE]; }; +/* + * Force a signaled SEND Work Request every so often, + * in case the provider needs to do some housekeeping. + */ +#define RPCRDMA_MAX_UNSIGNALED_SENDS (32) + #define INIT_CQCOUNT(ep) atomic_set(&(ep)->rep_cqcount, (ep)->rep_cqinit) #define DECR_CQCOUNT(ep) atomic_sub_return(1, &(ep)->rep_cqcount)