From: Chuck Lever <chuck.lever@oracle.com>
To: linux-rdma@vger.kernel.org, linux-nfs@vger.kernel.org
Subject: [PATCH v1 02/22] xprtrdma: Create more MRs at a time
Date: Mon, 10 Sep 2018 11:09:06 -0400 [thread overview]
Message-ID: <20180910150906.10564.92061.stgit@manet.1015granger.net> (raw)
In-Reply-To: <20180910150040.10564.97487.stgit@manet.1015granger.net>
Some devices require more than 3 MRs to build a single 1MB I/O.
Ensure that rpcrdma_mrs_create() will add enough MRs to build that
I/O. Otherwise it's possible for ->send_request to loop acquiring
some MRs, not getting enough, getting called again, recycling the
previous MRs, then not getting enough, lather rinse repeat.
I'm "reusing" ia->ri_max_segs. All of its accessors seem to want the
maximum number of data segments plus two, so I'm going to bake that
into the initial calculation.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
net/sunrpc/xprtrdma/fmr_ops.c | 1 +
net/sunrpc/xprtrdma/frwr_ops.c | 1 +
net/sunrpc/xprtrdma/rpc_rdma.c | 2 --
net/sunrpc/xprtrdma/verbs.c | 2 +-
4 files changed, 3 insertions(+), 3 deletions(-)
diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
index 0f7c465..db589a2 100644
--- a/net/sunrpc/xprtrdma/fmr_ops.c
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -187,6 +187,7 @@ enum {
ia->ri_max_segs = max_t(unsigned int, 1, RPCRDMA_MAX_DATA_SEGS /
RPCRDMA_MAX_FMR_SGES);
+ ia->ri_max_segs += 2; /* segments for head and tail buffers */
return 0;
}
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 1bb00dd..1cc4db5 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -276,6 +276,7 @@
ia->ri_max_segs = max_t(unsigned int, 1, RPCRDMA_MAX_DATA_SEGS /
ia->ri_max_frwr_depth);
+ ia->ri_max_segs += 2; /* segments for head and tail buffers */
return 0;
}
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index c8ae983..33da912 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -71,7 +71,6 @@ static unsigned int rpcrdma_max_call_header_size(unsigned int maxsegs)
size = RPCRDMA_HDRLEN_MIN;
/* Maximum Read list size */
- maxsegs += 2; /* segment for head and tail buffers */
size = maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32);
/* Minimal Read chunk size */
@@ -97,7 +96,6 @@ static unsigned int rpcrdma_max_reply_header_size(unsigned int maxsegs)
size = RPCRDMA_HDRLEN_MIN;
/* Maximum Write list size */
- maxsegs += 2; /* segment for head and tail buffers */
size = sizeof(__be32); /* segment count */
size += maxsegs * rpcrdma_segment_maxsz * sizeof(__be32);
size += sizeof(__be32); /* list discriminator */
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 956a5ea..5625a50 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1019,7 +1019,7 @@ struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_buffer *buf)
LIST_HEAD(free);
LIST_HEAD(all);
- for (count = 0; count < 3; count++) {
+ for (count = 0; count < ia->ri_max_segs; count++) {
struct rpcrdma_mr *mr;
int rc;
next prev parent reply other threads:[~2018-09-10 20:03 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-09-10 15:08 [PATCH v1 00/22] NFS/RDMA client patches for v4.20 Chuck Lever
2018-09-10 15:09 ` [PATCH v1 01/22] xprtrdma: Reset credit grant properly after a disconnect Chuck Lever
2018-09-10 15:09 ` Chuck Lever [this message]
2018-09-10 15:09 ` [PATCH v1 03/22] xprtrdma: Explicitly resetting MRs is no longer necessary Chuck Lever
2018-09-10 15:09 ` [PATCH v1 04/22] xprtrdma: Name MR trace events consistently Chuck Lever
2018-09-10 15:09 ` [PATCH v1 05/22] xprtrdma: Refactor chunk encoding Chuck Lever
2018-09-10 15:09 ` [PATCH v1 06/22] xprtrdma: Refactor chunktype handling Chuck Lever
2018-09-10 15:09 ` [PATCH v1 07/22] xprtrdma: Support Write+Reply Replies Chuck Lever
2018-09-10 15:09 ` [PATCH v1 08/22] sunrpc: Fix connect metrics Chuck Lever
2018-09-12 18:41 ` Anna Schumaker
2018-09-10 15:09 ` [PATCH v1 09/22] sunrpc: Report connect_time in seconds Chuck Lever
2018-09-10 15:09 ` [PATCH v1 10/22] xprtrdma: Rename rpcrdma_conn_upcall Chuck Lever
2018-09-10 15:09 ` [PATCH v1 11/22] xprtrdma: Conventional variable names in rpcrdma_conn_upcall Chuck Lever
2018-09-10 15:09 ` [PATCH v1 12/22] xprtrdma: Eliminate "connstate" variable from rpcrdma_conn_upcall() Chuck Lever
2018-09-10 15:10 ` [PATCH v1 13/22] xprtrdma: Re-organize the switch() in rpcrdma_conn_upcall Chuck Lever
2018-09-10 15:10 ` [PATCH v1 14/22] xprtrdma: Simplify RPC wake-ups on connect Chuck Lever
2018-09-10 15:10 ` [PATCH v1 15/22] xprtrdma: Rename rpcrdma_qp_async_error_upcall Chuck Lever
2018-09-10 15:10 ` [PATCH v1 16/22] xprtrdma: Remove memory address of "ep" from an error message Chuck Lever
2018-09-10 15:10 ` [PATCH v1 17/22] svcrdma: Don't disable BH's in backchannel Chuck Lever
2018-09-10 15:10 ` [PATCH v1 18/22] xprtrdma: Move rb_flags initialization Chuck Lever
2018-09-10 15:10 ` [PATCH v1 19/22] xprtrdma: Report when there were zero posted Receives Chuck Lever
2018-09-10 15:10 ` [PATCH v1 20/22] xprtrdma: Add documenting comments Chuck Lever
2018-09-10 15:10 ` [PATCH v1 21/22] xprtrdma: Clean up xprt_rdma_disconnect_inject Chuck Lever
2018-09-10 15:10 ` [PATCH v1 22/22] xprtrdma: Squelch a sparse warning Chuck Lever
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180910150906.10564.92061.stgit@manet.1015granger.net \
--to=chuck.lever@oracle.com \
--cc=linux-nfs@vger.kernel.org \
--cc=linux-rdma@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).