[Gluster-users] write performance with NIC bonding

[Дмитрий Глушенок]

Hi,

It is because your switch is not performing round-robin distribution while sending data to server (probably it can't). Usually it is enough to configure ip-port LACP hashing to evenly distribute traffic by all ports in aggregation. But any single tcp connections will still be using only one interface.

--
Dmitry Glushenok
Jet Infosystems

> 21 сент. 2016 г., в 23:42, James Ching <jching at bbn.com> написал(а):
> 
> Hi,
> 
> I'm using gluster 3.7.5 and I'm trying to get port bonding working properly with the gluster protocol.  I've bonded the NICs using round robin because I also bond it at the switch level with link aggregation.  I've used this type of bonding without a problem with my other applications but for some reason gluster does not want to utilize all 3 NICs for writes but it does for reads... any of you come across this or know why?  Here's the output of the traffic on the NICs you can see that RX is unbalanced but TX is completely balanced across the 3 NICs.  I've tried both mounting via glusterfs or nfs, both result in the same imbalance. Am I missing some configuration?
> 
> 
> root at e-gluster-01:~# ifconfig
> bond0     Link encap:Ethernet
>          inet addr:xxxxxxxxxxxx  Bcast:128.33.23.255 Mask:255.255.248.0
>          inet6 addr: fe80::46a8:42ff:fe43:8817/64 Scope:Link
>          UP BROADCAST RUNNING MASTER MULTICAST  MTU:1500 Metric:1
>          RX packets:160972852 errors:0 dropped:0 overruns:0 frame:0
>          TX packets:122295229 errors:0 dropped:0 overruns:0 carrier:0
>          collisions:0 txqueuelen:0
>          RX bytes:152800624950 (142.3 GiB)  TX bytes:138720356365 (129.1 GiB)
> 
> em1       Link encap:Ethernet
>          UP BROADCAST RUNNING SLAVE MULTICAST  MTU:1500  Metric:1
>          RX packets:160793725 errors:0 dropped:0 overruns:0 frame:0
>          TX packets:40763142 errors:0 dropped:0 overruns:0 carrier:0
>          collisions:0 txqueuelen:1000
>          RX bytes:152688146880 (142.2 GiB)  TX bytes:46239971255 (43.0 GiB)
>          Interrupt:41
> 
> em2       Link encap:Ethernet
>          UP BROADCAST RUNNING SLAVE MULTICAST  MTU:1500  Metric:1
>          RX packets:92451 errors:0 dropped:0 overruns:0 frame:0
>          TX packets:40750031 errors:0 dropped:0 overruns:0 carrier:0
>          collisions:0 txqueuelen:1000
>          RX bytes:9001370 (8.5 MiB)  TX bytes:46216513162 (43.0 GiB)
>          Interrupt:45
> 
> em3       Link encap:Ethernet
>          UP BROADCAST RUNNING SLAVE MULTICAST  MTU:1500  Metric:1
>          RX packets:86676 errors:0 dropped:0 overruns:0 frame:0
>          TX packets:40782056 errors:0 dropped:0 overruns:0 carrier:0
>          collisions:0 txqueuelen:1000
>          RX bytes:103476700 (98.6 MiB)  TX bytes:46263871948 (43.0 GiB)
>          Interrupt:40
> 
> 
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://www.gluster.org/mailman/listinfo/gluster-users

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.gluster.org/pipermail/gluster-users/attachments/20160922/a339136d/attachment.html>