svcrdma: Release write chunk resources without re-queuing

Each RDMA Send completion triggers a cascade of work items on the
svcrdma_wq unbound workqueue:

  ib_cq_poll_work (on ib_comp_wq, per-CPU)
    -> svc_rdma_send_ctxt_put -> queue_work    [work item 1]
      -> svc_rdma_write_info_free -> queue_work [work item 2]

Every transition through queue_work contends on the unbound
pool's spinlock. Profiling an 8KB NFSv3 read/write workload
over RDMA shows about 4% of total CPU cycles spent on this
lock, with the cascading re-queue of write_info release
contributing roughly 1%.

The initial queue_work in svc_rdma_send_ctxt_put is needed to
move release work off the CQ completion context (which runs on
a per-CPU bound workqueue). However, once executing on
svcrdma_wq, there is no need to re-queue for each write_info
structure. svc_rdma_reply_chunk_release already calls
svc_rdma_cc_release inline from the same svcrdma_wq context,
and svc_rdma_recv_ctxt_put does the same from nfsd thread
context.

Release write chunk resources inline in
svc_rdma_write_info_free, removing the intermediate
svc_rdma_write_info_free_async work item and the wi_work
field from struct svc_rdma_write_info.

Reviewed-by: Mike Snitzer <snitzer@kernel.org>
Tested-by: Jonathan Flynn <jonathan.flynn@hammerspace.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index df6e08aaad57093b7c06989075b41fa3880d704c..14eb9d52742ef6d17f7b540c7f349ff45367add2 100644 (file)
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -230,7 +230,6 @@ struct svc_rdma_write_info {
        unsigned int            wi_next_off;
 
        struct svc_rdma_chunk_ctxt      wi_cc;
-       struct work_struct      wi_work;
 };
 
 struct svc_rdma_send_ctxt {

diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index 402e2ceca4ff75e1788b4068117739b6779ad694..cca8ec973de4b98598585cf900837b29d19c14f3 100644 (file)
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -236,21 +236,12 @@ svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma,
        return info;
 }
 
-static void svc_rdma_write_info_free_async(struct work_struct *work)
+static void svc_rdma_write_info_free(struct svc_rdma_write_info *info)
 {
-       struct svc_rdma_write_info *info;
-
-       info = container_of(work, struct svc_rdma_write_info, wi_work);
        svc_rdma_cc_release(info->wi_rdma, &info->wi_cc, DMA_TO_DEVICE);
        kfree(info);
 }
 
-static void svc_rdma_write_info_free(struct svc_rdma_write_info *info)
-{
-       INIT_WORK(&info->wi_work, svc_rdma_write_info_free_async);
-       queue_work(svcrdma_wq, &info->wi_work);
-}
-
 /**
  * svc_rdma_write_chunk_release - Release Write chunk I/O resources
  * @rdma: controlling transport