diff options
| author | Eric Dumazet <eric.dumazet@gmail.com> | 2011-09-19 05:52:27 +0000 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2011-09-28 13:29:50 -0400 |
| commit | 16e5726269611b71c930054ffe9b858c1cea88eb (patch) | |
| tree | 50d25ec97d639b418964bad2f45774d657468c74 /net/netlink | |
| parent | a9e9fd7182332d0cf5f3e601df3e71dd431b70d7 (diff) | |
| download | op-kernel-dev-16e5726269611b71c930054ffe9b858c1cea88eb.zip op-kernel-dev-16e5726269611b71c930054ffe9b858c1cea88eb.tar.gz | |
af_unix: dont send SCM_CREDENTIALS by default
Since commit 7361c36c5224 (af_unix: Allow credentials to work across
user and pid namespaces) af_unix performance dropped a lot.
This is because we now take a reference on pid and cred in each write(),
and release them in read(), usually done from another process,
eventually from another cpu. This triggers false sharing.
# Events: 154K cycles
#
# Overhead Command Shared Object Symbol
# ........ ....... .................. .........................
#
10.40% hackbench [kernel.kallsyms] [k] put_pid
8.60% hackbench [kernel.kallsyms] [k] unix_stream_recvmsg
7.87% hackbench [kernel.kallsyms] [k] unix_stream_sendmsg
6.11% hackbench [kernel.kallsyms] [k] do_raw_spin_lock
4.95% hackbench [kernel.kallsyms] [k] unix_scm_to_skb
4.87% hackbench [kernel.kallsyms] [k] pid_nr_ns
4.34% hackbench [kernel.kallsyms] [k] cred_to_ucred
2.39% hackbench [kernel.kallsyms] [k] unix_destruct_scm
2.24% hackbench [kernel.kallsyms] [k] sub_preempt_count
1.75% hackbench [kernel.kallsyms] [k] fget_light
1.51% hackbench [kernel.kallsyms] [k]
__mutex_lock_interruptible_slowpath
1.42% hackbench [kernel.kallsyms] [k] sock_alloc_send_pskb
This patch includes SCM_CREDENTIALS information in a af_unix message/skb
only if requested by the sender, [man 7 unix for details how to include
ancillary data using sendmsg() system call]
Note: This might break buggy applications that expected SCM_CREDENTIAL
from an unaware write() system call, and receiver not using SO_PASSCRED
socket option.
If SOCK_PASSCRED is set on source or destination socket, we still
include credentials for mere write() syscalls.
Performance boost in hackbench : more than 50% gain on a 16 thread
machine (2 quad-core cpus, 2 threads per core)
hackbench 20 thread 2000
4.228 sec instead of 9.102 sec
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/netlink')
| -rw-r--r-- | net/netlink/af_netlink.c | 5 |
1 files changed, 2 insertions, 3 deletions
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4330db9..1201b6d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1324,10 +1324,9 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, if (msg->msg_flags&MSG_OOB) return -EOPNOTSUPP; - if (NULL == siocb->scm) { + if (NULL == siocb->scm) siocb->scm = &scm; - memset(&scm, 0, sizeof(scm)); - } + err = scm_send(sock, msg, siocb->scm); if (err < 0) return err; |
