[ovs-discuss] QoS (ingress_policing limitation ) is not working under VLAN+Bridge combination

ashish yadav ashishyadav78 at gmail.com
Mon Jul 22 06:19:49 UTC 2013


Hi ,

Sorry ...The Fig is distorted in above mail thread (after posting) ...
The ethernet link* 10Gbps* |  is between HOST1 & HOST2 using eth0 both side.

Thanks & Regards
      Ashish


On Mon, Jul 22, 2013 at 11:42 AM, ashish yadav <ashishyadav78 at gmail.com>wrote:

> Hi Ben,
>
> I try to make small Fig for your's understanding here :
>
>                                                         HOST2
>
> ovsbro.4093------ovsbr0------eth0-----------|
>                                         vlan
> tag=                                          |
>                                           4093
>                                               |
>
> 192.168.102.198                                  |
>
> |
>
> |
>
> |    10Gbps
>
> |
>
> |
>
> |
>                   VM1                                  HOST1
>                           |
>              eth0.4093--eth0--vnet0--ovsbr0.4093--0vsbr0--eth0-----------|
>               vlan tag=                      vlan tag=
>                  4093                            4093
>             192.168.102.5                   192.168.102.199
>
> Now ingress policing is set for interface vnet0:
>
>   ovs-vsctl set interface vnet0 ingress_policing_rate=10000
>   ovs-vsctl set Interface vnet0 ingress_policing_burst=100
>
> Now running netperif or Iperf (client ) at VM1 show no affect of  ingress
> policing setting .
> If I am doing something wrong here ?
> Why Ingress Policing not work with tagged VLAN + OVSBridge ?
>
> Thanks & Regards
>        Ashish
>
>
>
> On Fri, Jul 19, 2013 at 12:50 PM, ashish yadav <ashishyadav78 at gmail.com>wrote:
>
>> Hi,
>>
>> Case is different than previously reported by Qiu Yu.
>>
>> In my case , I am taping the Vlan first & then applying ingress policing
>> later.
>>
>> The system look like this:
>> [root at ash]# ovs-vsctl show
>> 54c73046-ccbd-4f8c-8226-2c724fd34a23
>>     Bridge "ovsbr0"
>>         Port "ovsbr0"
>>             Interface "ovsbr0"
>>                 type: internal
>>         Port "vnet0"
>>             Interface "vnet0"
>>         Port "eth0"
>>             Interface "eth0"
>>         Port "ovsbr0.4093"
>>             tag: 4093
>>             Interface "ovsbr0.4093"
>>                 type: internal
>>     Bridge "virbr0"
>>         Port "virbr0-nic"
>>             Interface "virbr0-nic"
>>         Port "virbr0"
>>             Interface "virbr0"
>>                 type: internal
>>     ovs_version: "1.4.3"
>>
>>
>> After that apply ingress policing:
>> [root at ash]# ovs-vsctl set interface vnet0 ingress_policing_rate=10000
>> [root at ash]# ovs-vsctl set Interface vnet0 ingress_policing_burst=100
>>
>> It set ingress policing as seen:
>> [root at ash]# ovs-vsctl list Interface vnet0
>> _uuid               : 62e37f45-debe-4082-892c-cc6a46ccd289
>> admin_state         : up
>> cfm_fault           : []
>> cfm_mpid            : []
>> cfm_remote_mpids    : []
>> duplex              : full
>> external_ids        : {}
>> ingress_policing_burst: 10000
>> ingress_policing_rate: 1000000
>> lacp_current        : []
>> link_resets         : 1
>> link_speed          : 10000000
>> link_state          : up
>> mac                 : []
>> mtu                 : 9000
>> name                : "vnet0"
>> ofport              : 3
>> options             : {}
>> other_config        : {}
>> statistics          : {collisions=0, rx_bytes=468, rx_crc_err=0,
>> rx_dropped=0, rx_errors=0, rx_frame_err=0, rx_over_err=0, rx_packets=6,
>> tx_bytes=8336, tx_dropped=0, tx_errors=0, tx_packets=161}
>> status              : {driver_name=tun, driver_version="1.6",
>> firmware_version="N/A"}
>> type                : ""
>>
>>
>>
>> [root at ash]# tc qdisc show dev vnet0
>> qdisc pfifo_fast 0: root refcnt 2 bands 3 priomap  1 2 2 2 1 2 0 0 1 1 1
>> 1 1 1 1 1
>> qdisc ingress ffff: parent ffff:fff1 ----------------
>>
>>
>> [root at ash]# tc filter show dev vnet0 parent ffff:fff1
>> filter parent ffff: protocol ip pref 50 u32
>> filter parent ffff: protocol ip pref 50 u32 fh 800: ht divisor 1
>> filter parent ffff: protocol ip pref 50 u32 fh 800::800 order 2048 key ht
>> 800 bkt 0 flowid :1
>>   match 00000000/00000000 at 12
>>  police 0xe rate 10000Kbit burst 100Kb mtu 64Kb action drop overhead 0b
>> ref 1 bind 1
>>
>>
>> Now in Virtual Machine(VM) VM1,  vlan is set using vconfig:
>> root at VM1:~# vconfig add eth0 4093
>> Added VLAN with VID == 4093 to IF -:eth0:-
>> root at VM1:~# ifconfig eth0 0.0.0.0
>> root at VM1:~# ifconfig eth0.4093 192.168.102.5
>>
>> Now do netperf from Vlan Virtual Machine VM1 (in host1) to Host2 (Vlan):
>>
>> root at VM1:~# ping 192.168.102.198 ........................  IP of Host2
>> Vlan Inferface
>> PING 192.168.102.198 (192.168.102.198) 56(84) bytes of data.
>> 64 bytes from 192.168.102.198: icmp_seq=1 ttl=64 time=1.55 ms
>> 64 bytes from 192.168.102.198: icmp_seq=2 ttl=64 time=0.365 ms
>>
>> --- 192.168.102.198 ping statistics ---
>> 2 packets transmitted, 2 received, 0% packet loss, time 1001ms
>> rtt min/avg/max/mdev = 0.365/0.960/1.555/0.595 ms
>> root at VM1:~# netperf -4 -H 192.168.102.198
>> MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to
>> 192.168.102.198 () port 0 AF_INET
>> Recv   Send    Send
>> Socket Socket  Message  Elapsed
>> Size   Size    Size     Time     Throughput
>> bytes  bytes   bytes    secs.    10^6bits/sec
>>
>>  87380  16384  16384    10.01     935.15 ................................
>> The value exceeds the limitation
>> root at VM1:~# netperf -4 -H 192.168.102.198
>> MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to
>> 192.168.102.198 () port 0 AF_INET
>> Recv   Send    Send
>> Socket Socket  Message  Elapsed
>> Size   Size    Size     Time     Throughput
>> bytes  bytes   bytes    secs.    10^6bits/sec
>>
>>  87380  16384  16384    10.02     937.70
>> root at VM1:~# netperf -4 -t UDP_STREAM -H 192.168.102.198
>> MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to
>> 192.168.102.198 () port 0 AF_INET
>> Socket  Message  Elapsed      Messages
>> Size    Size     Time         Okay Errors   Throughput
>> bytes   bytes    secs            #      #   10^6bits/sec
>>
>> 129024   65507   10.00       84373      0    4421.43
>> 229376           10.00         112              5.87
>>
>> root at VM1:~# netperf -4 -t UDP_STREAM -H 192.168.102.198 -- -m 8712
>> MIGRATED UDP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to
>> 192.168.102.198 () port 0 AF_INET
>> Socket  Message  Elapsed      Messages
>> Size    Size     Time         Okay Errors   Throughput
>> bytes   bytes    secs            #      #   10^6bits/sec
>>
>> 129024    8712   10.00      382668      0    2666.93
>> 229376           10.00       91198            635.59
>>
>>
>>
>> So any clue that why ingress Policing not work with Vlan+OVS-Bridge
>> Combination ?
>>
>>
>> Thanks & Regards
>>       Ashish
>>
>>
>>
>> On Thu, Jul 18, 2013 at 7:44 PM, Ben Pfaff <blp at nicira.com> wrote:
>>
>>> This week.
>>> On Jul 18, 2013 7:07 AM, "ashish yadav" <ashishyadav78 at gmail.com> wrote:
>>>
>>>> Hi Ben,
>>>>
>>>> Could you please point out which month/year archive mailing list this
>>>> problem discuss ?
>>>>
>>>> Thanks & Regards
>>>>      Ashish
>>>>
>>>>
>>>> On Thu, Jul 18, 2013 at 7:25 PM, Ben Pfaff <blp at nicira.com> wrote:
>>>>
>>>>> You're the second person to ask about this combination this week.
>>>>> Please look in the list archive.
>>>>> On Jul 18, 2013 2:45 AM, "ashish yadav" <ashishyadav78 at gmail.com>
>>>>> wrote:
>>>>>
>>>>>> Hi,
>>>>>>
>>>>>> I am trying to test QoS (ingress_policing limitation ) with  VLAN+OVS
>>>>>> Bridge combination, but its not working.
>>>>>>
>>>>>> # Connection environment is:
>>>>>>   ovsbr0.4093 --ovsbr0--eth0--<10G>--eth0-ovsbr0--ovsbr0.4093
>>>>>>
>>>>>>   Where ovsbr0.4093 is Vlan ( with Virtual Machine )  and eth0 is
>>>>>> physical port on Host.
>>>>>>    eth0 is connected as port in openvswitch bridge(ovsbr0).
>>>>>> Two Host are used for above environment.
>>>>>>
>>>>>> I am using ovs_version 1.4.3 .
>>>>>>
>>>>>> If any one able to test ingress_policing limitation with  VLAN+OVS
>>>>>> Bridge combination ?
>>>>>>
>>>>>>
>>>>>> Thanks & Regards
>>>>>>       Ashish
>>>>>>
>>>>>> _______________________________________________
>>>>>> discuss mailing list
>>>>>> discuss at openvswitch.org
>>>>>> http://openvswitch.org/mailman/listinfo/discuss
>>>>>>
>>>>>>
>>>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://openvswitch.org/pipermail/ovs-discuss/attachments/20130722/a21969fb/attachment.html>


More information about the discuss mailing list