> Is the layer2+3 option simply undocumented via modinfo or is it not
> present in the CentOS bonding module?
It's docuemnted in the kernel docs rpm,
/usr/share/doc/kernel-doc-2.6.18/Documentation/networking/bonding.txt.
---
This
On Tue, 11 Jan 2011, James Pearson wrote:
> You could use xmit_hash_policy=layer2+3 - which just uses MAC and IP
> addresses (which you do have more control over) - and see if you can
> pick a mix of IP/MAC addresses that would result in all four
> interfaces being used (theoretically) - and se
On 1/11/2011 10:18 AM, lheck...@users.sourceforge.net wrote:
>
>> Hashing 4 values to 4 targets seems like collisions would be likely no
>> matter how you do it. The TX packet/byte values from ifconfig on the
>> NICs should show how much went out each interface.
>
> Yes, we checked that in addit
lheck...@users.sourceforge.net wrote:
>>I guess you need to look at the bonding src code - looks like it is in
>>drivers/net/bonding/bond_main.c - for CentOS 5 it is:
>
>
> C xor is bitwise.
>
> I did a bit of scripting and found that the algorithm seems much more
> sensitive to port number
> Hashing 4 values to 4 targets seems like collisions would be likely no
> matter how you do it. The TX packet/byte values from ifconfig on the
> NICs should show how much went out each interface.
Yes, we checked that in addition to iperf's output. One interface was
essentially idle.
---
On 1/11/2011 10:05 AM, lheck...@users.sourceforge.net wrote:
>
>> I guess you need to look at the bonding src code - looks like it is in
>> drivers/net/bonding/bond_main.c - for CentOS 5 it is:
>
> C xor is bitwise.
>
> I did a bit of scripting and found that the algorithm seems much more
> s
> I guess you need to look at the bonding src code - looks like it is in
> drivers/net/bonding/bond_main.c - for CentOS 5 it is:
C xor is bitwise.
I did a bit of scripting and found that the algorithm seems much more
sensitive to port numbers than IP addresses. Not that iperf gives much
co
lheck...@users.sourceforge.net wrote:
>>According to the Linux bonding docs, xmit_hash_policy=layer3+4 uses:
>>
>> ((source port XOR dest port) XOR
>> ((source IP XOR dest IP) AND 0x)
>> modulo slave count
>>
>>So I guess you could plug in in the above IP addresses an
> According to the Linux bonding docs, xmit_hash_policy=layer3+4 uses:
>
>((source port XOR dest port) XOR
> ((source IP XOR dest IP) AND 0x)
> modulo slave count
>
> So I guess you could plug in in the above IP addresses and port numbers
> and see if you get
lheck...@users.sourceforge.net wrote:
> I have a Dell server with four bonded, gigabit interfaces. Bonding mode is
> 802.3ad, xmit_hash_policy=layer3+4. When testing this setup with iperf,
> I never get more than a total of about 3Gbps throughput. Is there anything
> to tweak to get better thro
10 matches
Mail list logo
