K 10
svn:author
V 4
oleg
K 8
svn:date
V 27
2008-04-25T10:29:26.000000Z
K 7
svn:log
V 1464
MFC:
src/sys/netinet/ip_dummynet.h	1.41
src/sys/netinet/ip_dummynet.c	1.111-1.114
src/sys/netinet/ip_fw_pfil.c	1.26
src/sys/net/if_bridge.c		1.107
src/sys/net/if_ethersubr.c	1.240
src/sbin/ipfw/ipfw.8		1.206

- style(9) cleanup.
- dummynet_io() declaration has changed.
- Alter packet flow inside dummynet and introduce 'fast' mode of dummynet
  operation: allow certain packets to bypass dummynet scheduler. Benefits are:
  -- lower latency: if packet flow does not exceed pipe bandwidth, packets
     will not be (up to tick) delayed (due to dummynet's scheduler granularity).
  -- lower overhead: if packet avoids dummynet scheduler it shouldn't reenter
     ip stack later. Such packets can be fastforwarded.
  -- recursion (which can lead to kernel stack exhaution) eliminated. This fix
     long existed panic, which can be triggered this way:
	kldload dummynet
	sysctl net.inet.ip.fw.one_pass=0
	ipfw pipe 1 config bw 0
	for i in `jot 30`; do ipfw add 1 pipe 1 icmp from any to any; done
	ping -c 1 localhost
- New sysctl nodes:
  net.inet.ip.dummynet.io_fast -	enables 'fast' dummynet io
  net.inet.ip.dummynet.io_pkt -		packets passed to dummynet
  net.inet.ip.dummynet.io_pkt_fast -	packets avoided dummynet scheduler
  net.inet.ip.dummynet.io_pkt_drop -	packets dropped by dummynet
- Workaround p->numbytes overflow, which can result in infinite loop inside
  dummynet module (prerequisite is using queues with "fat" pipe).

PR:	kern/113548 kern/121955

END