ich777/linux_media
1
0
Fork 0
mirror of https://github.com/tbsdtv/linux_media.git synced 2025-07-23 04:33:26 +02:00
Code Issues Packages Projects Releases Wiki Activity

SUNRPC: Move xpt_mutex into socket xpo_sendto methods

Browse Source 
It appears that the RPC/RDMA transport does not need serialization
of calls to its xpo_sendto method. Move the mutex into the socket
methods that still need that serialization.

Tail latencies are unambiguously better with this patch applied.
fio randrw 8KB 70/30 on NFSv3, smaller numbers are better:

    clat percentiles (usec):

With xpt_mutex:
r    | 99.99th=[ 8848]
w    | 99.99th=[ 9634]

Without xpt_mutex:
r    | 99.99th=[ 8586]
w    | 99.99th=[ 8979]

Serializing the construction of RPC/RDMA transport headers is not
really necessary at this point, because the Linux NFS server
implementation never changes its credit grant on a connection. If
that should change, then svc_rdma_sendto will need to serialize
access to the transport's credit grant fields.

Reported-by: kbuild test robot <lkp@intel.com>
[ cel: fix uninitialized variable warning ]
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
This commit is contained in:
Chuck Lever
2020-05-02 10:37:44 -04:00
parent b9bbe6ed63
commit ca4faf543a
6 changed files with 64 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
net/sunrpc/svc_xprt.c
View File

@@ -914,16 +914,10 @@ int svc_send(struct svc_rqst *rqstp)
xb->page_len +
xb->tail[0].iov_len;
trace_svc_sendto(xb);
/* Grab mutex to serialize outgoing data. */
mutex_lock(&xprt->xpt_mutex);
trace_svc_stats_latency(rqstp);
if (test_bit(XPT_DEAD, &xprt->xpt_flags)
|| test_bit(XPT_CLOSE, &xprt->xpt_flags))
len = -ENOTCONN;
else
len = xprt->xpt_ops->xpo_sendto(rqstp);
mutex_unlock(&xprt->xpt_mutex);
len = xprt->xpt_ops->xpo_sendto(rqstp);
trace_svc_send(rqstp, len);
svc_xprt_release(rqstp);