[Bug 195234] New: unable to utilize bandwidth of all lacp lagg links using multiple clients and proper hashing algo
bugzilla-noreply at freebsd.org
bugzilla-noreply at freebsd.org
Thu Nov 20 23:35:45 UTC 2014
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=195234
Bug ID: 195234
Summary: unable to utilize bandwidth of all lacp lagg links
using multiple clients and proper hashing algo
Product: Base System
Version: 9.2-STABLE
Hardware: amd64
OS: Any
Status: Needs Triage
Severity: Affects Only Me
Priority: ---
Component: standards
Assignee: freebsd-standards at FreeBSD.org
Reporter: freebsd at safar.info
I'm using FreeNAS 9.2.1.8 distro for storage usacases. Storage wors great, the
lagg is giving me headache :) Issue is that I've 4 1G links connected between
lacp enabled switch ports and the FreeBSD. I've multiple other hosts connected
to the same switch and when opening the connection from all the hosts to the
FreeBSD target, all lacp links are used, but the total used
performance/capacity is equal to the capacity of single link. Meaning that even
though the traffic is splitted between all 4 links, the overall performance is
identical as if I'd be using one link only :) I've connected RHEL box to the
switch using the same 4 links with connected bonding in mode=4(lacp) and it
works as expected there. I've googled a lot to check what I'm doing wrong and
found one post describing my situation.
http://serverfault.com/questions/619574/freebsd-link-aggregation-no-faster-than-single-link
I've also tried to configure (undocumented) lagghash option to l4 only, but no
luck. I've tried to configure the switch part to active/passive mode, disabling
LAN HW offload, etc... My last network configuration (with disabled HW
offload)is here:
[root at vmstore] ~# ifconfig
re0: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500
options=8209b<RXCSUM,TXCSUM,VLAN_MTU,VLAN_HWTAGGING,VLAN_HWCSUM,WOL_MAGIC,LINKSTATE>
ether 00:24:1d:db:1b:16
inet 10.50.27.99 netmask 0xfffffe00 broadcast 10.50.27.255
nd6 options=9<PERFORMNUD,IFDISABLED>
media: Ethernet autoselect (1000baseT <full-duplex>)
status: active
em0: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 9000
options=2098<VLAN_MTU,VLAN_HWTAGGING,VLAN_HWCSUM,WOL_MAGIC>
ether 00:11:0a:5d:ec:48
nd6 options=9<PERFORMNUD,IFDISABLED>
media: Ethernet autoselect (1000baseT <full-duplex>)
status: active
em1: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 9000
options=2098<VLAN_MTU,VLAN_HWTAGGING,VLAN_HWCSUM,WOL_MAGIC>
ether 00:11:0a:5d:ec:48
nd6 options=9<PERFORMNUD,IFDISABLED>
media: Ethernet autoselect (1000baseT <full-duplex>)
status: active
em2: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 9000
options=98<VLAN_MTU,VLAN_HWTAGGING,VLAN_HWCSUM>
ether 00:11:0a:5d:ec:48
nd6 options=9<PERFORMNUD,IFDISABLED>
media: Ethernet autoselect (1000baseT <full-duplex>)
status: active
em3: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 9000
options=98<VLAN_MTU,VLAN_HWTAGGING,VLAN_HWCSUM>
ether 00:11:0a:5d:ec:48
nd6 options=9<PERFORMNUD,IFDISABLED>
media: Ethernet autoselect (1000baseT <full-duplex>)
status: active
ipfw0: flags=8801<UP,SIMPLEX,MULTICAST> metric 0 mtu 65536
nd6 options=9<PERFORMNUD,IFDISABLED>
lo0: flags=8049<UP,LOOPBACK,RUNNING,MULTICAST> metric 0 mtu 16384
options=600003<RXCSUM,TXCSUM,RXCSUM_IPV6,TXCSUM_IPV6>
inet6 ::1 prefixlen 128
inet6 fe80::1%lo0 prefixlen 64 scopeid 0xe
inet 127.0.0.1 netmask 0xff000000
nd6 options=21<PERFORMNUD,AUTO_LINKLOCAL>
lagg0: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 9000
options=98<VLAN_MTU,VLAN_HWTAGGING,VLAN_HWCSUM>
ether 00:11:0a:5d:ec:48
inet 172.16.0.100 netmask 0xffffff00 broadcast 172.16.0.255
nd6 options=9<PERFORMNUD,IFDISABLED>
media: Ethernet autoselect
status: active
laggproto lacp lagghash l2,l3,l4
laggport: em3 flags=1c<ACTIVE,COLLECTING,DISTRIBUTING>
laggport: em2 flags=1c<ACTIVE,COLLECTING,DISTRIBUTING>
laggport: em1 flags=1c<ACTIVE,COLLECTING,DISTRIBUTING>
laggport: em0 flags=1c<ACTIVE,COLLECTING,DISTRIBUTING>
--
You are receiving this mail because:
You are the assignee for the bug.
More information about the freebsd-standards
mailing list