From: Chuck Lever <chuck.lever@oracle.com>
To: linux-nfs@vger.kernel.org, linux-rdma@vger.kernel.org
Subject: [PATCH V2 16/17] xprtrdma: Limit work done by completion handler
Date: Mon, 21 Apr 2014 18:03:08 -0400 [thread overview]
Message-ID: <20140421220308.12569.43779.stgit@manet.1015granger.net> (raw)
In-Reply-To: <20140421214442.12569.8950.stgit@manet.1015granger.net>
Sagi Grimberg <sagig@dev.mellanox.co.il> points out that a steady
stream of CQ events could starve other work because of the boundless
loop pooling in rpcrdma_{send,recv}_poll().
Instead of a (potentially infinite) while loop, return after
collecting a budgeted number of completions.
Note that the total number of WCs that can be handled during one
upcall is RPCRDMA_WC_BUDGET * 2, since the handler polls once before
and once after re-enabling completion notifications.
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
net/sunrpc/xprtrdma/verbs.c | 10 ++++++----
net/sunrpc/xprtrdma/xprt_rdma.h | 1 +
2 files changed, 7 insertions(+), 4 deletions(-)
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index abb8d8d..d46bdee 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -165,8 +165,9 @@ static int
rpcrdma_sendcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep)
{
struct ib_wc *wcs;
- int count, rc;
+ int budget, count, rc;
+ budget = RPCRDMA_WC_BUDGET / RPCRDMA_POLLSIZE;
do {
wcs = ep->rep_send_wcs;
@@ -177,7 +178,7 @@ rpcrdma_sendcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep)
count = rc;
while (count-- > 0)
rpcrdma_sendcq_process_wc(wcs++);
- } while (rc == RPCRDMA_POLLSIZE);
+ } while (rc == RPCRDMA_POLLSIZE && --budget);
return 0;
}
@@ -254,8 +255,9 @@ static int
rpcrdma_recvcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep)
{
struct ib_wc *wcs;
- int count, rc;
+ int budget, count, rc;
+ budget = RPCRDMA_WC_BUDGET / RPCRDMA_POLLSIZE;
do {
wcs = ep->rep_recv_wcs;
@@ -266,7 +268,7 @@ rpcrdma_recvcq_poll(struct ib_cq *cq, struct rpcrdma_ep *ep)
count = rc;
while (count-- > 0)
rpcrdma_recvcq_process_wc(wcs++);
- } while (rc == RPCRDMA_POLLSIZE);
+ } while (rc == RPCRDMA_POLLSIZE && --budget);
return 0;
}
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index cb4c882..0c3b88e 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -74,6 +74,7 @@ struct rpcrdma_ia {
* RDMA Endpoint -- one per transport instance
*/
+#define RPCRDMA_WC_BUDGET (128)
#define RPCRDMA_POLLSIZE (16)
struct rpcrdma_ep {
next prev parent reply other threads:[~2014-04-21 22:03 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-04-21 22:00 [PATCH V2 00/17] NFS/RDMA patches for review Chuck Lever
2014-04-21 22:00 ` [PATCH V2 01/17] xprtrdma: mind the device's max fast register page list depth Chuck Lever
2014-04-21 22:01 ` [PATCH V2 02/17] nfs-rdma: Fix for FMR leaks Chuck Lever
2014-04-21 22:01 ` [PATCH V2 03/17] xprtrdma: Enable RDMA pad optimization by default Chuck Lever
2014-04-22 15:05 ` Chuck Lever
2014-04-21 22:01 ` [PATCH V2 04/17] xprtrdma: RPC/RDMA must invoke xprt_wake_pending_tasks() in process context Chuck Lever
2014-04-21 22:01 ` [PATCH V2 05/17] xprtrdma: Remove BOUNCEBUFFERS memory registration mode Chuck Lever
2014-04-21 22:01 ` [PATCH V2 06/17] xprtrdma: Remove MEMWINDOWS registration modes Chuck Lever
2014-04-21 22:01 ` [PATCH V2 07/17] xprtrdma: Remove REGISTER memory registration mode Chuck Lever
2014-04-21 22:01 ` [PATCH V2 08/17] xprtrdma: Fall back to MTHCAFMR when FRMR is not supported Chuck Lever
2014-04-21 22:02 ` [PATCH V2 09/17] xprtrdma: mount reports "Invalid mount option" if memreg mode " Chuck Lever
2014-04-21 22:02 ` [PATCH V2 10/17] xprtrdma: Add CONFIG setting that can disable ALLPHYSICAL Chuck Lever
2014-04-22 6:23 ` Christoph Hellwig
2014-04-23 10:24 ` Sagi Grimberg
2014-04-21 22:02 ` [PATCH V2 11/17] xprtrdma: Simplify rpcrdma_deregister_external() synopsis Chuck Lever
2014-04-21 22:02 ` [PATCH V2 12/17] xprtrdma: Make rpcrdma_ep_destroy() return void Chuck Lever
2014-04-21 22:02 ` [PATCH V2 13/17] xprtrdma: Split the completion queue Chuck Lever
2014-04-21 22:02 ` [PATCH V2 14/17] xprtrmda: Reduce lock contention in completion handlers Chuck Lever
2014-04-21 22:02 ` [PATCH V2 15/17] xprtrmda: Reduce calls to ib_poll_cq() " Chuck Lever
2014-04-21 22:03 ` Chuck Lever [this message]
2014-04-23 10:15 ` [PATCH V2 16/17] xprtrdma: Limit work done by completion handler Sagi Grimberg
2014-04-21 22:03 ` [PATCH V2 17/17] xprtrdma: Reduce the number of hardway buffer allocations 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=20140421220308.12569.43779.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).