Hi, I need help and send you an mail.
I recently found that there was an OVS using eBPF.
(http://openvswitch.org/support/ovscon2016/7/1120-tu.pdf)
However, I can not find any information on how to install it.
If you are using eBPF + OVS, please let me know if you have any insights
about it.
Tha
Hi,
I want to measure the performance of OVS in multi core.
I have a server on two Xeon 2630 v2 (NUMA) with 4 dual port 10GbE NIC. the
server with 12 cores and 8 physical ports run OVS. 4ports are for receiving
40Gbps traffic and the other 4 ports are for sending 40Gbps traffic.
I use DPDK pktge
cores. It
is very weird.
If you have some experience running multi core on OVS, please let me know
about how to set or some insights.
2017-08-30 11:50 GMT+09:00 Blue Lang :
> Do you have 40+gbs of bandwidth on the bus available?
>
> On Tue, Aug 29, 2017 at 10:03 PM, Heung Sik Cho
Hi,
I want to measure the performance of OVS in multi core.
I have a server on two Xeon 2630 v2 (NUMA) with 8 dual port 10GbE NIC. the
server run OVS. Also there are other two server, which are that one is DPDK
pktgen TX, the other is DPDK pktgen RX. Pktgen TX send to OVS server on 40G
line(4* 10
Hi,
I've used dpdk-ovs and studied it. Recently I came to know that DPDK
applications can be run as primary or secondary process.
So, I'm wondering if there is secondary process when ovs-dpdk is run.
Especially, is ovs-vswitchd run as secondary process?
Please let me know if you have any insigh
Hi,
I have used OVS for L3 forwarding from A to C through B(OVS).
I have wanted to achieve higher performance of OVS and found that OVS
attempts to receive batch of packets from 'rx'.
However I couldn't find 'TX batch of packet'.
doesn't OVS support TX batch?
Please let me know if you have an
Hi,
I want to check the performance of DPDK OVS in aspect of forwarding as
below URL.
https://drive.google.com/a/os.korea.ac.kr/file/d/
0BxEx0xE0gw2ETjhkaUpzN3YxSVU/view?usp=sharing
There is a similar experiment at 'Intel® Open Network Platform Release 2.1
Performance Test Report'. Also, the
gt;
> On Fri, Jun 09, 2017 at 01:47:14PM +0900, Heung Sik Choi wrote:
> > Thanks to reply.
> >
> > Regarding your second question, which flow rules are you asking about?
> >
> > I just want to know that when ovs had only an in-kernel microflow cache,
> > How many i
> kernel-to-user-to-kernel transition and (if the megaflow cache is
> effective) the additional OpenFlow translations.
>
> Regarding your second question, which flow rules are you asking about?
>
> On Fri, Jun 09, 2017 at 12:22:09PM +0900, Heung Sik Choi wrote:
> > What d
If there are the big difference, can you
tell me the difference in numbers?
2017-06-09 0:43 GMT+09:00 Ben Pfaff :
> On Thu, Jun 08, 2017 at 04:33:54PM +0900, Heung Sik Choi wrote:
> > 1. If only microflow cache works and there are many short lived
> > connections, does it make many t
Hi,
I have studied OVS in performance aspect. And, I found out that flow
masking and looking up table have quite overhead.
I read a paper ' “The Design and Implementation of Open vSwitch.” USENIX
NSDI 2015', and discovered that there is why use masking process in the
paper.
the paper said
Hi,
I have studied OVS in performance aspect. And, I found out that flow
masking and looking up table have quite overhead.
I read a paper ' “The Design and Implementation of Open vSwitch.” USENIX
NSDI 2015', and discovered that there is why use masking process in the
paper.
the paper said "*Whil
Hi,
I insert many flows entries in ovs flowtable. the command I used is below:
ovs-ofctl add-flow ovs-br1
ip,nw_dst=100.0."$i"."$j",actions=mod_dl_dst:90:e2:ba:5b:88:2c,in_port
the other host machine(DPDK-pktgen) which is connected OVS machine send
packets with 100.0."$i"."$j".
I use RSS mode,
ny insights.
2017-05-24 1:50 GMT+09:00 Greg Rose :
> On Tue, 2017-05-23 at 16:42 +0900, Heung Sik Choi wrote:
> > Hi,
> >
> >
> > In many articles about ovs, there are some mention that hashing
> > function cause quite significant overhead. Also, I did 'per
Hi,
In many articles about ovs, there are some mention that hashing function
cause quite significant overhead. Also, I did 'perf record' performing OVS
L3 forwarding, and found that.
So, an idea comes up, which is that implement RSS hash algorithm(Toeplitz
hash algorithm) in kernel datapath modul
Hello,
I currently study openvswitch's flow table for better packet processing.
I looked into datapath.c and flow_table.c, but I can't find how to insert a
flow in flow table. Also, I understand that ovs' flow processing way
include 'Megaflow' and 'Exact Match Cache', but I can't find that in the
Hello
I have some question about ovs' flow table implementation after visiting
this url
https://software.intel.com/en-us/articles/ovs-dpdk-datapath-classifier-part-2
Are there some difference in flow table implementation between original ovs
and dpdk ovs?
Also, are there any differences in hash
17 matches
Mail list logo