In balanced-alb mode you should see nearly equal TX size, but
something wrong with your statistics.
RX balanced by intercepting MAC address for ARP replays, so in theory
if you have enough clients you should have equally balanced RX.
I am also using balanced-alb with 60 gluster servers and nearly 1000
clients using them, my TX distribution is %50 between two links and RX
is %5-%95.
This means theory and practice differs way too much :)
On Tue, Feb 14, 2017 at 12:33 PM, Alessandro Briosi <ab1 at metalit.com>
wrote:> Hi all,
> I'd like to have a clarification on bonding with gluster.
>
> I have a gluster deployment which is using a bond with 4 eths.
>
> The bond is configured with balance-alb as 2 are connected to 1 switch
> and the other 2 to another switch.
> This is for traffic balance and redundancy.
>
> The switches are stacked with a 10Gbit cable. They are managed.
>
> The same connection is used for server and client (the servers are also
> client of themselfs).
>
> For what I understand balance-alb balances single connections, so one
> connection can get at max 1Gb speed.
>
> It though seems that only 1 ethernet is mainly used.
>
> This is the output for the interested ethernets (the same basically
> applyes to the other servers)
>
> bond2 Link encap:Ethernet HWaddr 00:0a:f7:a5:ec:5c
> inet addr:192.168.102.1 Bcast:192.168.102.255
Mask:255.255.255.0
> inet6 addr: fe80::20a:f7ff:fea5:ec5c/64 Scope:Link
> UP BROADCAST RUNNING MASTER MULTICAST MTU:9000 Metric:1
> RX packets:195041678 errors:0 dropped:4795 overruns:0 frame:0
> TX packets:244194369 errors:0 dropped:0 overruns:0 carrier:0
> collisions:0 txqueuelen:1000
> RX bytes:346742936782 (322.9 GiB) TX bytes:1202018794556 (1.0
> TiB)
>
> eth4 Link encap:Ethernet HWaddr 00:0a:f7:a5:ec:5c
> UP BROADCAST RUNNING SLAVE MULTICAST MTU:9000 Metric:1
> RX packets:194076526 errors:0 dropped:0 overruns:0 frame:0
> TX packets:239094839 errors:0 dropped:0 overruns:0 carrier:0
> collisions:0 txqueuelen:1000
> RX bytes:346669905046 (322.8 GiB) TX bytes:1185779765214 (1.0
> TiB)
> Interrupt:88
>
> eth5 Link encap:Ethernet HWaddr 00:0a:f7:a5:ec:5d
> UP BROADCAST RUNNING SLAVE MULTICAST MTU:9000 Metric:1
> RX packets:317620 errors:0 dropped:1597 overruns:0 frame:0
> TX packets:3969287 errors:0 dropped:0 overruns:0 carrier:0
> collisions:0 txqueuelen:1000
> RX bytes:21155944 (20.1 MiB) TX bytes:16107271750 (15.0 GiB)
> Interrupt:84
>
> eth6 Link encap:Ethernet HWaddr 00:0a:f7:a5:ec:5e
> UP BROADCAST RUNNING SLAVE MULTICAST MTU:9000 Metric:1
> RX packets:317620 errors:0 dropped:1596 overruns:0 frame:0
> TX packets:557634 errors:0 dropped:0 overruns:0 carrier:0
> collisions:0 txqueuelen:1000
> RX bytes:21155972 (20.1 MiB) TX bytes:35688576 (34.0 MiB)
> Interrupt:88
>
> eth7 Link encap:Ethernet HWaddr 00:0a:f7:a5:ec:5f
> UP BROADCAST RUNNING SLAVE MULTICAST MTU:9000 Metric:1
> RX packets:317618 errors:0 dropped:1596 overruns:0 frame:0
> TX packets:557633 errors:0 dropped:0 overruns:0 carrier:0
> collisions:0 txqueuelen:1000
> RX bytes:21155816 (20.1 MiB) TX bytes:35688512 (34.0 MiB)
> Interrupt:84
>
> #cat /proc/net/bonding/bond2
>
> Ethernet Channel Bonding Driver: v3.7.1 (April 27, 2011)
>
> Bonding Mode: adaptive load balancing
> Primary Slave: None
> Currently Active Slave: eth4
> MII Status: up
> MII Polling Interval (ms): 100
> Up Delay (ms): 0
> Down Delay (ms): 0
>
> Slave Interface: eth4
> MII Status: up
> Speed: 1000 Mbps
> Duplex: full
> Link Failure Count: 0
> Permanent HW addr: 00:0a:f7:a5:ec:5c
> Slave queue ID: 0
>
> Slave Interface: eth5
> MII Status: up
> Speed: 1000 Mbps
> Duplex: full
> Link Failure Count: 0
> Permanent HW addr: 00:0a:f7:a5:ec:5d
> Slave queue ID: 0
>
> Slave Interface: eth6
> MII Status: up
> Speed: 1000 Mbps
> Duplex: full
> Link Failure Count: 0
> Permanent HW addr: 00:0a:f7:a5:ec:5e
> Slave queue ID: 0
>
> Slave Interface: eth7
> MII Status: up
> Speed: 1000 Mbps
> Duplex: full
> Link Failure Count: 0
> Permanent HW addr: 00:0a:f7:a5:ec:5f
> Slave queue ID: 0
>
> Is this normal?
>
> I could use LACP though it would require me to use 2 bonds (1 for each
> switch), though I have no idea on how to configure a "failover".
>
> Any hint would be appreciated.
>
> Alessandro
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://lists.gluster.org/mailman/listinfo/gluster-users