linux/net/ipv4
Jarek Poplawski 345aa03120 ipv4: Fix fib_trie rebalancing, part 4 (root thresholds)
Pawel Staszewski wrote:
<blockquote>
Some time ago i report this:
http://bugzilla.kernel.org/show_bug.cgi?id=6648

and now with 2.6.29 / 2.6.29.1 / 2.6.29.3 and 2.6.30 it back
dmesg output:
oprofile: using NMI interrupt.
Fix inflate_threshold_root. Now=15 size=11 bits
...
Fix inflate_threshold_root. Now=15 size=11 bits

cat /proc/net/fib_triestat
Basic info: size of leaf: 40 bytes, size of tnode: 56 bytes.
Main:
        Aver depth:     2.28
        Max depth:      6
        Leaves:         276539
        Prefixes:       289922
        Internal nodes: 66762
          1: 35046  2: 13824  3: 9508  4: 4897  5: 2331  6: 1149  7: 5
9: 1  18: 1
        Pointers: 691228
Null ptrs: 347928
Total size: 35709  kB
</blockquote>

It seems, the current threshold for root resizing is too aggressive,
and it causes misleading warnings during big updates, but it might be
also responsible for memory problems, especially with non-preempt
configs, when RCU freeing is delayed long after call_rcu.

It should be also mentioned that because of non-atomic changes during
resizing/rebalancing the current lookup algorithm can miss valid leaves
so it's additional argument to shorten these activities even at a cost
of a minimally longer searching.

This patch restores values before the patch "[IPV4]: fib_trie root
node settings", commit: 965ffea43d from
v2.6.22.

Pawel's report:
<blockquote>
I dont see any big change of (cpu load or faster/slower
routing/propagating routes from bgpd or something else) - in avg there
is from 2% to 3% more of CPU load i dont know why but it is - i change
from "preempt" to "no preempt" 3 times and check this my "mpstat -P ALL
1 30"
always avg cpu load was from 2 to 3% more compared to "no preempt"
[...]
cat /proc/net/fib_triestat
Basic info: size of leaf: 20 bytes, size of tnode: 36 bytes.
Main:
        Aver depth:     2.44
        Max depth:      6
        Leaves:         277814
        Prefixes:       291306
        Internal nodes: 66420
          1: 32737  2: 14850  3: 10332  4: 4871  5: 2313  6: 942  7: 371  8: 3  17: 1
        Pointers: 599098
Null ptrs: 254865
Total size: 18067  kB
</blockquote>

According to this and other similar reports average depth is slightly
increased (~0.2), and root nodes are shorter (log 17 vs. 18), but
there is no visible performance decrease. So, until memory handling is
improved or added parameters for changing this individually, this
patch resets to safer defaults.

Reported-by: Pawel Staszewski <pstaszewski@itcare.pl>
Reported-by: Jorge Boncompte [DTI2] <jorge@dti2.net>
Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
Tested-by: Pawel Staszewski <pstaszewski@itcare.pl>
Signed-off-by: David S. Miller <davem@davemloft.net>
2009-07-08 10:46:45 -07:00
..
netfilter netfilter: tcp conntrack: fix unacknowledged data detection with NAT 2009-06-29 14:07:56 +02:00
af_inet.c ipv4: remove ip_mc_drop_socket() declaration from af_inet.c. 2009-06-03 21:43:26 -07:00
ah4.c netns xfrm: AH/ESP in netns! 2008-11-25 17:59:27 -08:00
arp.c Revert "ipv4: arp announce, arp_proxy and windows ip conflict verification" 2009-06-30 19:47:08 -07:00
cipso_ipv4.c netlabel: Label incoming TCP connections correctly in SELinux 2009-03-28 15:01:36 +11:00
datagram.c mib: add net to IP_INC_STATS_BH 2008-07-16 20:20:11 -07:00
devinet.c net: Fix devinet_sysctl_forward 2009-05-18 22:15:58 -07:00
esp4.c netns xfrm: AH/ESP in netns! 2008-11-25 17:59:27 -08:00
fib_frontend.c ipv4: cleanup: remove unnecessary include. 2009-05-18 15:16:38 -07:00
fib_hash.c ipv4: cleanup - remove two unused parameters from fib_semantic_match(). 2009-05-18 15:16:37 -07:00
fib_lookup.h ipv4: cleanup - remove two unused parameters from fib_semantic_match(). 2009-05-18 15:16:37 -07:00
fib_rules.c net: Remove unused parameter from fill method in fib_rules_ops. 2009-05-20 17:26:23 -07:00
fib_semantics.c ipv4: cleanup - remove two unused parameters from fib_semantic_match(). 2009-05-18 15:16:37 -07:00
fib_trie.c ipv4: Fix fib_trie rebalancing, part 4 (root thresholds) 2009-07-08 10:46:45 -07:00
icmp.c net: skb->dst accessors 2009-06-03 02:51:04 -07:00
igmp.c net: skb->dst accessors 2009-06-03 02:51:04 -07:00
inet_connection_sock.c net: move bsockets outside of read only beginning of struct inet_hashinfo 2009-02-01 12:31:33 -08:00
inet_diag.c net: correct off-by-one write allocations reports 2009-06-18 00:29:12 -07:00
inet_fragment.c inet fragments: fix sparse warning: context imbalance 2009-02-26 23:13:35 -08:00
inet_hashtables.c net: move bsockets outside of read only beginning of struct inet_hashinfo 2009-02-01 12:31:33 -08:00
inet_lro.c include/net net/ - csum_partial - remove unnecessary casts 2008-11-19 15:44:53 -08:00
inet_timewait_sock.c Merge branch 'for-linus2' of git://git.kernel.org/pub/scm/linux/kernel/git/vegard/kmemcheck 2009-06-16 13:09:51 -07:00
inetpeer.c net: clean up net/ipv4/ah4.c esp4.c fib_semantics.c inet_connection_sock.c inetpeer.c ip_output.c 2008-11-03 00:23:42 -08:00
ip_forward.c net: skb->dst accessors 2009-06-03 02:51:04 -07:00
ip_fragment.c ipv4: Use frag list abstraction interfaces. 2009-06-09 00:19:37 -07:00
ip_gre.c net: skb->dst accessors 2009-06-03 02:51:04 -07:00
ip_input.c inet: Call skb_orphan before tproxy activates 2009-06-26 19:22:37 -07:00
ip_options.c net: skb->dst accessors 2009-06-03 02:51:04 -07:00
ip_output.c net: No more expensive sock_hold()/sock_put() on each tx 2009-06-11 02:55:43 -07:00
ip_sockglue.c net: skb->rtable accessor 2009-06-03 02:51:02 -07:00
ipcomp.c netns xfrm: state lookup in netns 2008-11-25 17:30:50 -08:00
ipconfig.c ipv4: teach ipconfig about the MTU option in DHCP 2009-05-19 15:36:17 -07:00
ipip.c net: skb->dst accessors 2009-06-03 02:51:04 -07:00
ipmr.c PIM-SM: namespace changes 2009-06-14 03:16:13 -07:00
Kconfig ipv4: update ARPD help text 2009-06-13 23:36:32 -07:00
Makefile IPVS: Move IPVS to net/netfilter/ipvs 2008-10-07 08:38:24 +11:00
netfilter.c net: skb->dst accessors 2009-06-03 02:51:04 -07:00
proc.c snmp: add missing counters for RFC 4293 2009-04-27 02:45:02 -07:00
protocol.c net: remove CVS keywords 2008-06-11 21:00:38 -07:00
raw.c net: correct off-by-one write allocations reports 2009-06-18 00:29:12 -07:00
route.c ipv4 routing: Ensure that route cache entries are usable and reclaimable with caching is off 2009-06-23 16:36:26 -07:00
syncookies.c syncookies: remove last_synq_overflow from struct tcp_sock 2009-04-20 02:25:26 -07:00
sysctl_net_ipv4.c net: '&' redux 2008-11-03 18:21:05 -08:00
tcp_bic.c tcp: add helper for AI algorithm 2009-03-02 03:00:15 -08:00
tcp_cong.c tcp: add helper for AI algorithm 2009-03-02 03:00:15 -08:00
tcp_cubic.c tcp: add helper for AI algorithm 2009-03-02 03:00:15 -08:00
tcp_diag.c net: inet_diag_handler structs can be const 2008-11-19 15:43:27 -08:00
tcp_highspeed.c [TCP]: Cong.ctrl modules: remove unused good_ack from cong_avoid 2008-01-28 14:55:41 -08:00
tcp_htcp.c htcp: merge icsk_ca_state compare 2009-03-02 03:00:14 -08:00
tcp_hybla.c tcp: Fix tcp_hybla zero congestion window growth with small rho and large cwnd. 2008-10-07 15:58:17 -07:00
tcp_illinois.c [TCP]: Cong.ctrl modules: remove unused good_ack from cong_avoid 2008-01-28 14:55:41 -08:00
tcp_input.c tcp: fix loop in ofo handling code and reduce its complexity 2009-05-29 15:02:29 -07:00
tcp_ipv4.c net: skb->dst accessors 2009-06-03 02:51:04 -07:00
tcp_lp.c [TCP]: Cong.ctrl modules: remove unused good_ack from cong_avoid 2008-01-28 14:55:41 -08:00
tcp_minisocks.c tcp: missing check ACK flag of received segment in FIN-WAIT-2 state 2009-06-25 20:03:15 -07:00
tcp_output.c tcp: Stop non-TSO packets morphing into TSO 2009-06-29 19:41:39 -07:00
tcp_probe.c tcp: '< 0' test on unsigned 2009-03-13 16:05:14 -07:00
tcp_scalable.c tcp: add helper for AI algorithm 2009-03-02 03:00:15 -08:00
tcp_timer.c tcp: cleanup ca_state mess in tcp_timer 2009-03-02 03:00:13 -08:00
tcp_vegas.c tcp: tcp_vegas ssthresh bugfix 2009-05-25 22:44:59 -07:00
tcp_vegas.h [TCP]: congestion control API pass RTT in microseconds 2007-07-31 02:27:57 -07:00
tcp_veno.c tcp: add helper for AI algorithm 2009-03-02 03:00:15 -08:00
tcp_westwood.c [TCP]: congestion control API pass RTT in microseconds 2007-07-31 02:27:57 -07:00
tcp_yeah.c tcp: add helper for AI algorithm 2009-03-02 03:00:15 -08:00
tcp.c tcp: Do not tack on TSO data to non-TSO packet 2009-06-29 19:41:43 -07:00
tunnel4.c [IPV4] TUNNEL4: Fix incoming packet length check for inter-protocol tunnel. 2008-06-05 04:02:33 +09:00
udp_impl.h udp: introduce struct udp_table and multiple spinlocks 2008-10-29 01:41:45 -07:00
udp.c net: correct off-by-one write allocations reports 2009-06-18 00:29:12 -07:00
udplite.c udp: RCU handling for Unicast packets. 2008-10-29 02:11:14 -07:00
xfrm4_input.c net: skb->dst accessors 2009-06-03 02:51:04 -07:00
xfrm4_mode_beet.c ipsec: Interfamily IPSec BEET 2008-08-06 02:39:30 -07:00
xfrm4_mode_transport.c [IPSEC]: Use IPv6 calling convention as the convention for x->mode->output 2007-10-10 16:55:54 -07:00
xfrm4_mode_tunnel.c net: skb->dst accessors 2009-06-03 02:51:04 -07:00
xfrm4_output.c net: skb->dst accessors 2009-06-03 02:51:04 -07:00
xfrm4_policy.c xfrm4: fix the ports decode of sctp protocol 2009-07-03 19:10:06 -07:00
xfrm4_state.c xfrm: remove useless forward declarations 2008-11-25 01:05:54 -08:00
xfrm4_tunnel.c [IPCOMP]: Fix reception of incompressible packets 2008-01-31 19:27:24 -08:00