1
linux/net
Eric Dumazet ebc0ffae5d fib: RCU conversion of fib_lookup()
fib_lookup() converted to be called in RCU protected context, no
reference taken and released on a contended cache line (fib_clntref)

fib_table_lookup() and fib_semantic_match() get an additional parameter.

struct fib_info gets an rcu_head field, and is freed after an rcu grace
period.

Stress test :
(Sending 160.000.000 UDP frames on same neighbour,
IP route cache disabled, dual E5540 @2.53GHz,
32bit kernel, FIB_HASH) (about same results for FIB_TRIE)

Before patch :

real	1m31.199s
user	0m13.761s
sys	23m24.780s

After patch:

real	1m5.375s
user	0m14.997s
sys	15m50.115s

Before patch Profile :

13044.00 15.4% __ip_route_output_key vmlinux
 8438.00 10.0% dst_destroy           vmlinux
 5983.00  7.1% fib_semantic_match    vmlinux
 5410.00  6.4% fib_rules_lookup      vmlinux
 4803.00  5.7% neigh_lookup          vmlinux
 4420.00  5.2% _raw_spin_lock        vmlinux
 3883.00  4.6% rt_set_nexthop        vmlinux
 3261.00  3.9% _raw_read_lock        vmlinux
 2794.00  3.3% fib_table_lookup      vmlinux
 2374.00  2.8% neigh_resolve_output  vmlinux
 2153.00  2.5% dst_alloc             vmlinux
 1502.00  1.8% _raw_read_lock_bh     vmlinux
 1484.00  1.8% kmem_cache_alloc      vmlinux
 1407.00  1.7% eth_header            vmlinux
 1406.00  1.7% ipv4_dst_destroy      vmlinux
 1298.00  1.5% __copy_from_user_ll   vmlinux
 1174.00  1.4% dev_queue_xmit        vmlinux
 1000.00  1.2% ip_output             vmlinux

After patch Profile :

13712.00 15.8% dst_destroy             vmlinux
 8548.00  9.9% __ip_route_output_key   vmlinux
 7017.00  8.1% neigh_lookup            vmlinux
 4554.00  5.3% fib_semantic_match      vmlinux
 4067.00  4.7% _raw_read_lock          vmlinux
 3491.00  4.0% dst_alloc               vmlinux
 3186.00  3.7% neigh_resolve_output    vmlinux
 3103.00  3.6% fib_table_lookup        vmlinux
 2098.00  2.4% _raw_read_lock_bh       vmlinux
 2081.00  2.4% kmem_cache_alloc        vmlinux
 2013.00  2.3% _raw_spin_lock          vmlinux
 1763.00  2.0% __copy_from_user_ll     vmlinux
 1763.00  2.0% ip_output               vmlinux
 1761.00  2.0% ipv4_dst_destroy        vmlinux
 1631.00  1.9% eth_header              vmlinux
 1440.00  1.7% _raw_read_unlock_bh     vmlinux

Reference results, if IP route cache is enabled :

real	0m29.718s
user	0m10.845s
sys	7m37.341s

25213.00 29.5% __ip_route_output_key   vmlinux
 9011.00 10.5% dst_release             vmlinux
 4817.00  5.6% ip_push_pending_frames  vmlinux
 4232.00  5.0% ip_finish_output        vmlinux
 3940.00  4.6% udp_sendmsg             vmlinux
 3730.00  4.4% __copy_from_user_ll     vmlinux
 3716.00  4.4% ip_route_output_flow    vmlinux
 2451.00  2.9% __xfrm_lookup           vmlinux
 2221.00  2.6% ip_append_data          vmlinux
 1718.00  2.0% _raw_spin_lock_bh       vmlinux
 1655.00  1.9% __alloc_skb             vmlinux
 1572.00  1.8% sock_wfree              vmlinux
 1345.00  1.6% kfree                   vmlinux

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-05 20:39:38 -07:00
..
9p Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 2010-10-04 11:56:38 -07:00
802 net: return operator cleanup 2010-09-23 14:33:39 -07:00
8021q net: add a core netdev->rx_dropped counter 2010-10-05 14:47:55 -07:00
appletalk
atm net neigh: RCU conversion of neigh hash table 2010-10-05 14:54:36 -07:00
ax25 Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 2010-09-09 22:27:33 -07:00
bluetooth net: return operator cleanup 2010-09-23 14:33:39 -07:00
bridge bridge : Sanitize skb before it enters the IP stack 2010-09-19 12:42:34 -07:00
caif caif: remove duplicated include 2010-10-05 00:47:37 -07:00
can net: simplify flags for tx timestamping 2010-08-19 00:08:30 -07:00
core fib: RCU conversion of fib_lookup() 2010-10-05 20:39:38 -07:00
dcb
dccp net: return operator cleanup 2010-09-23 14:33:39 -07:00
decnet net neigh: RCU conversion of neigh hash table 2010-10-05 14:54:36 -07:00
dns_resolver DNS: If the DNS server returns an error, allow that to be cached [ver #2] 2010-08-11 17:11:28 +00:00
dsa phylib: available for any speed ethernet 2010-08-11 23:03:50 -07:00
econet net: return operator cleanup 2010-09-23 14:33:39 -07:00
ethernet net: return operator cleanup 2010-09-23 14:33:39 -07:00
ieee802154
ipv4 fib: RCU conversion of fib_lookup() 2010-10-05 20:39:38 -07:00
ipv6 net neigh: RCU conversion of neigh hash table 2010-10-05 14:54:36 -07:00
ipx
irda net: return operator cleanup 2010-09-23 14:33:39 -07:00
iucv
key net: return operator cleanup 2010-09-23 14:33:39 -07:00
l2tp net: constify some ppp/pptp structs 2010-09-21 18:04:47 -07:00
lapb
llc net/llc: storing negative error codes in unsigned short 2010-09-16 22:38:23 -07:00
mac80211 Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6 into for-davem 2010-10-01 11:12:36 -04:00
netfilter ipvs: Use frag walker helper in SCTP proto support. 2010-10-05 00:27:05 -07:00
netlabel
netlink netlink: Make NETLINK_USERSOCK work again. 2010-08-31 09:51:37 -07:00
netrom
packet net: simplify flags for tx timestamping 2010-08-19 00:08:30 -07:00
phonet Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 2010-10-04 11:56:38 -07:00
rds Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 2010-09-27 01:03:03 -07:00
rfkill net: return operator cleanup 2010-09-23 14:33:39 -07:00
rose Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 2010-09-27 01:03:03 -07:00
rxrpc Add a dummy printk function for the maintenance of unused printks 2010-08-12 09:51:35 -07:00
sched net: dynamic ingress_queue allocation 2010-10-05 00:23:44 -07:00
sctp Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 2010-10-04 11:56:38 -07:00
sunrpc Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 2010-09-27 01:03:03 -07:00
tipc net: return operator cleanup 2010-09-23 14:33:39 -07:00
unix AF_UNIX: Implement SO_TIMESTAMP and SO_TIMETAMPNS on Unix sockets 2010-10-05 14:54:36 -07:00
wanrouter
wimax
wireless Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6 into for-davem 2010-10-01 11:12:36 -04:00
x25 X.25 remove bkl in poll 2010-09-22 13:35:51 -07:00
xfrm xfrm: Allow different selector family in temporary state 2010-09-20 11:11:38 -07:00
compat.c
Kconfig net: RPS needs to depend upon USE_GENERIC_SMP_HELPERS 2010-09-14 21:42:22 -07:00
Makefile
nonet.c
socket.c net: remove address space warnings in net/socket.c 2010-09-08 13:46:13 -07:00
sysctl_net.c
TUNABLE