[ovs-discuss] Cache memory with ovs-dpdk

[Sara Gittlin]

Hi
Maybe this is a stupid question. but do we use HW cache for e.g flow-table
with ovs-dpdk ?
Thank you
-Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

[ovs-discuss] ovs configuration for my setup

[Sara Gittlin]

Hello
i have 3 physical interfaces eth0, eth1,eth2 in my server A
eth0 is the interface to reach the default GW and it is also the
communication interface - i.e. I  can reach A only through eth0.
eth1 and eth2 are connected back to back to another server B.
**My requirement**  is to send packets  from A to a (destination)  public
IP in the cloud (aws machine) via eth1 or eth2 - then these pkts will be
forwarded by B to the default GW.
Ususally (without OvS) of course these packets go out through eth0 to the
default GW.
what is the OVS setup in server A required for this behavior? , I tried
many setups in which I've  lost communication to server A.

i thought to put all eth0 and eth1 eth2 in br0 , assign the eth0 IP to br0
, and manipulate the traffic by setting up flows in ofctl , but cannot
manage because i'm  loosing connection to A whenever I  add eth0 to the
br0, although I assign its IP to br0.
Please help .
Thanks -Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] Connection loss when adding comm interface to ovs

[Sara Gittlin]

Ok - found the answer for the 1st question in
http://docs.openvswitch.org/en/latest/faq/issues/
you have to assign the ip-address to the br0.
what about my 2nd question : how to delete the persistent ovs configuration
file before running ovs ?
-Sara

On Wed, Dec 19, 2018 at 1:31 PM Sara Gittlin  wrote:

> Hello
> I have  a very simple setup in server A :  br0 and then I add my
> communication interface [interface to outside network]  to br0.
> after that i cannot ssh  server A . why ?
> also after reboot when i run ovs - the DB is persistent - and i loose
> communication again.  how to delete the DB file before running ovs ?
> Thank you
> -Sara
>
>
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

[ovs-discuss] Connection loss when adding comm interface to ovs

[Sara Gittlin]

Hello
I have  a very simple setup in server A :  br0 and then I add my
communication interface [interface to outside network]  to br0.
after that i cannot ssh  server A . why ?
also after reboot when i run ovs - the DB is persistent - and i loose
communication again.  how to delete the DB file before running ovs ?
Thank you
-Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] add-flow based on dest-ip and dest-port

[Sara Gittlin]

Thank you Mark
-Sara

On Tue, Dec 18, 2018 at 8:55 PM Mark Michelson  wrote:

> On 12/18/18 8:33 AM, Sara Gittlin wrote:
> > Hello
> > can you give the correct syntax to use "ovs-ofctl add-flow" for packet
> > destined to ip=x and dest-port=y, the action should be output to port z
> > Thank you
> > -Sara
>
> In order to add such a flow, you will need to have a switch to add the
> flow to. In addition, when you say "dest-port" you'll need to be sure to
> specify tcp or udp.
>
> Assuming that the switch you want to add the flow to is "br0" and that
> you want to match on both TCP and UDP traffic, then you could add the
> following two flows:
>
> ovs-ofctl add-flow br0 ip,nw_dst=x,tcp,tp_dest=y,actions=output:z
> ovs-ofctl add-flow br0 ip,nw_dst=x,udp,tp_dest=y,actions=output:z
>
> These commands will add the flows to table 0, with a priority of 0. If
> you want to add the flows to specific tables and with specific
> priorities, you can add "table=" and "priority=" to the flow
> as well.
>
> I suggest you read the following manpages to learn more:
>
> ovs-fields(7): Tells all of the fields that can be used in an openflow
> match.
>
> ovs-ofctl(8): Tells the syntax and lots of extra information for the
> "ovs-ofctl add-flow" command. Also tells all the actions that can be
> used in an openflow flow.
>
>
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

[ovs-discuss] add-flow based on dest-ip and dest-port

[Sara Gittlin]

Hello
can you give the correct syntax to use "ovs-ofctl add-flow" for packet
destined to ip=x and dest-port=y, the action should be output to port z
Thank you
-Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] Adding new c file to ovs

[Sara Gittlin]

I know that i have to add it to the automake.mk , is it enough ?

On Thu, Aug 30, 2018 at 4:07 PM Sara Gittlin  wrote:

> Hello
> can someone refer me to  the steps required to add c or h file to OVS.
> Thank you
> -Sara
>
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

[ovs-discuss] Adding new c file to ovs

[Sara Gittlin]

Hello
can someone refer me to  the steps required to add c or h file to OVS.
Thank you
-Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] Mega-flow generation

[Sara Gittlin]

Thank you Billy.

On Thu, Aug 30, 2018 at 12:24 PM O Mahony, Billy 
wrote:

> Hi Sara,
>
>
>
> A colleague of mine had a lot of difficulty using dpctl/add-flow to add
> flow directly to the datapath. And the man-page is a little lukewarm on
> it’s usage too albeit you are just debugging (ovs-vswitchd (8)-  DATAPATH
> FLOW TABLE DEBUGGING COMMANDS) . Also you will find that whatever rules you
> can insert will be very shortly deleted again by the revalidator thread as
> they will not correspond to any existing ofproto rule.
>
>
>
> You should set up flows using ofctl then generate packets to match those
> flows and you should be able to monitor the netlink messages exchanged
> between vswitchd and the vswitch .ko as the megaflow is installed to the
> kernel module. I don’t know how you might monitor the netlink messages -
> ip-monitor (8) is a possibility. Turning on vswitchd debug in the relevant
> module is another possibility.
>
>
>
> Hope some of that helps,
>
>
>
> Billy.
>
>
>
>
>
>
>
> *From:* Sara Gittlin [mailto:sara.gitt...@gmail.com]
> *Sent:* Thursday, August 30, 2018 9:44 AM
> *To:* O Mahony, Billy 
> *Cc:* Ben Pfaff ; ovs-discuss@openvswitch.org
> *Subject:* Re: [ovs-discuss] Mega-flow generation
>
>
>
> i think i can 'ride on'  the callback "dpctl_put_flow"  - which is invoked
> whenever the cli  'ovs-dpctl add-flow' is executed.correct ?
>
>
>
> On Thu, Aug 30, 2018 at 10:32 AM Sara Gittlin 
> wrote:
>
> Billy,
>
> Can you please refer me to the code where we start the megaflow creation
> to the kernel upon an upcall,  and where we send it to the kernel via the
> netlink socket ?
>
> what i want to do is - to generate megaflows, based on openflow tables,
> not neccesararily upon an upcall, that is not reactive mode and to send to
> the kernel.
>
> Another question is,  who is responsible to  associate a specific
> megaflow  to the appropriate table in the cache ?  is it the kernel
> module or vswitchd ?
>
> Thank you
>
> -Sara
>
>
>
>
>
> On Tue, Aug 28, 2018 at 1:12 PM Sara Gittlin 
> wrote:
>
> Thank you Ben and Billy
>
> -Sara
>
>
>
> On Tue, Aug 28, 2018 at 11:27 AM O Mahony, Billy 
> wrote:
>
> Hi Sara,
>
> This article
> https://software.intel.com/en-us/articles/ovs-dpdk-datapath-classifier
> gives practical overview of how megaflows, aka wildcarded or datapath
> flows, work at least in the ovs-dpdk (userspace datapath) context.
>
> Regards,
> Billy
>
> > -Original Message-
> > From: ovs-discuss-boun...@openvswitch.org [mailto:ovs-discuss-
> > boun...@openvswitch.org] On Behalf Of Ben Pfaff
> > Sent: Monday, August 27, 2018 5:10 PM
> > To: Sara Gittlin 
> > Cc: ovs-discuss@openvswitch.org
> > Subject: Re: [ovs-discuss] Mega-flow generation
> >
> > On Mon, Aug 27, 2018 at 02:46:19PM +0300, Sara Gittlin wrote:
> > > Can someone refer me to the code of the megaflow generation process ?
> > > Is this process  invoked by an upcall from the kernel module ? like in
> > > microflow ?
> >
> > Did you read the OVS paper?  It's all about megaflows.
> > http://www.openvswitch.org/support/papers/nsdi2015.pdf
> > ___
> > discuss mailing list
> > disc...@openvswitch.org
> > https://mail.openvswitch.org/mailman/listinfo/ovs-discuss
>
>
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] Mega-flow generation

[Sara Gittlin]

i think i can 'ride on'  the callback "dpctl_put_flow"  - which is invoked
whenever the cli  'ovs-dpctl add-flow' is executed.correct ?

On Thu, Aug 30, 2018 at 10:32 AM Sara Gittlin 
wrote:

> Billy,
> Can you please refer me to the code where we start the megaflow creation
> to the kernel upon an upcall,  and where we send it to the kernel via the
> netlink socket ?
> what i want to do is - to generate megaflows, based on openflow tables,
> not neccesararily upon an upcall, that is not reactive mode and to send to
> the kernel.
> Another question is,  who is responsible to  associate a specific
> megaflow  to the appropriate table in the cache ?  is it the kernel
> module or vswitchd ?
> Thank you
> -Sara
>
>
> On Tue, Aug 28, 2018 at 1:12 PM Sara Gittlin 
> wrote:
>
>> Thank you Ben and Billy
>> -Sara
>>
>> On Tue, Aug 28, 2018 at 11:27 AM O Mahony, Billy <
>> billy.o.mah...@intel.com> wrote:
>>
>>> Hi Sara,
>>>
>>> This article
>>> https://software.intel.com/en-us/articles/ovs-dpdk-datapath-classifier
>>> gives practical overview of how megaflows, aka wildcarded or datapath
>>> flows, work at least in the ovs-dpdk (userspace datapath) context.
>>>
>>> Regards,
>>> Billy
>>>
>>> > -----Original Message-
>>> > From: ovs-discuss-boun...@openvswitch.org [mailto:ovs-discuss-
>>> > boun...@openvswitch.org] On Behalf Of Ben Pfaff
>>> > Sent: Monday, August 27, 2018 5:10 PM
>>> > To: Sara Gittlin 
>>> > Cc: ovs-discuss@openvswitch.org
>>> > Subject: Re: [ovs-discuss] Mega-flow generation
>>> >
>>> > On Mon, Aug 27, 2018 at 02:46:19PM +0300, Sara Gittlin wrote:
>>> > > Can someone refer me to the code of the megaflow generation process ?
>>> > > Is this process  invoked by an upcall from the kernel module ? like
>>> in
>>> > > microflow ?
>>> >
>>> > Did you read the OVS paper?  It's all about megaflows.
>>> > http://www.openvswitch.org/support/papers/nsdi2015.pdf
>>> > ___
>>> > discuss mailing list
>>> > disc...@openvswitch.org
>>> > https://mail.openvswitch.org/mailman/listinfo/ovs-discuss
>>>
>>
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] Mega-flow generation

[Sara Gittlin]

Billy,
Can you please refer me to the code where we start the megaflow creation to
the kernel upon an upcall,  and where we send it to the kernel via the
netlink socket ?
what i want to do is - to generate megaflows, based on openflow tables,
not neccesararily upon an upcall, that is not reactive mode and to send to
the kernel.
Another question is,  who is responsible to  associate a specific  megaflow
to the appropriate table in the cache ?  is it the kernel module or
vswitchd ?
Thank you
-Sara


On Tue, Aug 28, 2018 at 1:12 PM Sara Gittlin  wrote:

> Thank you Ben and Billy
> -Sara
>
> On Tue, Aug 28, 2018 at 11:27 AM O Mahony, Billy 
> wrote:
>
>> Hi Sara,
>>
>> This article
>> https://software.intel.com/en-us/articles/ovs-dpdk-datapath-classifier
>> gives practical overview of how megaflows, aka wildcarded or datapath
>> flows, work at least in the ovs-dpdk (userspace datapath) context.
>>
>> Regards,
>> Billy
>>
>> > -Original Message-
>> > From: ovs-discuss-boun...@openvswitch.org [mailto:ovs-discuss-
>> > boun...@openvswitch.org] On Behalf Of Ben Pfaff
>> > Sent: Monday, August 27, 2018 5:10 PM
>> > To: Sara Gittlin 
>> > Cc: ovs-discuss@openvswitch.org
>> > Subject: Re: [ovs-discuss] Mega-flow generation
>> >
>> > On Mon, Aug 27, 2018 at 02:46:19PM +0300, Sara Gittlin wrote:
>> > > Can someone refer me to the code of the megaflow generation process ?
>> > > Is this process  invoked by an upcall from the kernel module ? like in
>> > > microflow ?
>> >
>> > Did you read the OVS paper?  It's all about megaflows.
>> > http://www.openvswitch.org/support/papers/nsdi2015.pdf
>> > ___
>> > discuss mailing list
>> > disc...@openvswitch.org
>> > https://mail.openvswitch.org/mailman/listinfo/ovs-discuss
>>
>
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] Mega-flow generation

[Sara Gittlin]

Thank you Ben and Billy
-Sara

On Tue, Aug 28, 2018 at 11:27 AM O Mahony, Billy 
wrote:

> Hi Sara,
>
> This article
> https://software.intel.com/en-us/articles/ovs-dpdk-datapath-classifier
> gives practical overview of how megaflows, aka wildcarded or datapath
> flows, work at least in the ovs-dpdk (userspace datapath) context.
>
> Regards,
> Billy
>
> > -Original Message-
> > From: ovs-discuss-boun...@openvswitch.org [mailto:ovs-discuss-
> > boun...@openvswitch.org] On Behalf Of Ben Pfaff
> > Sent: Monday, August 27, 2018 5:10 PM
> > To: Sara Gittlin 
> > Cc: ovs-discuss@openvswitch.org
> > Subject: Re: [ovs-discuss] Mega-flow generation
> >
> > On Mon, Aug 27, 2018 at 02:46:19PM +0300, Sara Gittlin wrote:
> > > Can someone refer me to the code of the megaflow generation process ?
> > > Is this process  invoked by an upcall from the kernel module ? like in
> > > microflow ?
> >
> > Did you read the OVS paper?  It's all about megaflows.
> > http://www.openvswitch.org/support/papers/nsdi2015.pdf
> > ___
> > discuss mailing list
> > disc...@openvswitch.org
> > https://mail.openvswitch.org/mailman/listinfo/ovs-discuss
>
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

[ovs-discuss] Mega-flow generation

[Sara Gittlin]

Hello all
Can someone refer me to the code of the megaflow generation process ?
Is this process  invoked by an upcall from the kernel module ? like in
microflow ?
Thank you in advance
-Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

[ovs-discuss] Cannot find definition of rule_collection_add

[Sara Gittlin]

Hello  all,
I cannot find the definition of the function rule_collection_add - used in
ofproto.c
is it a dynamic library function ?

Thank you
-Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] What is a l2 pkt microflow

[Sara Gittlin]

Thank you Ben
Is this L2 flow is an entry in one of the kernel megaflow tables ?
otherwise if it an entry in the kernel microflow table - then there
should be  multiple microflow tables,  because L2 flow keys consist
only of L2 header, while  for other flow the keys are l2+l3 headers. i
thought that there is only a single microflow table so  classification
takes  O(1).
--Sara


On Mon, Nov 20, 2017 at 7:38 PM, Ben Pfaff <b...@ovn.org> wrote:
> On Thu, Nov 16, 2017 at 07:46:05PM +0200, Sara Gittlin wrote:
>> I understand that microflow kernel cache entries consist of full set of
>> header keys.
>> What about a l2 pkt e.g cfm pkt. What are the hash keys for cfm pkt in the
>> single microflow table?
>
> Just the Ethernet header.
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

[ovs-discuss] What is a l2 pkt microflow

[Sara Gittlin]

Hello
I understand that microflow kernel cache entries consist of full set of
header keys.
What about a l2 pkt e.g cfm pkt. What are the hash keys for cfm pkt in the
single microflow table?
Thank you in advance
Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

[ovs-discuss] OVS Flow insert

[Sara Gittlin]

Hello
Can someone refer to the code where a  new flow is inserted to
openflow tables in the OVS, as a consequence action of a received
message from a controller?
Thanks in advance
--Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

[ovs-discuss] an API to retrieve OpenFlow entries

[Sara Gittlin]

Hello,

1. Is there an  API (other than cli) to retrieve all OpenFlow
entries from ofproto tables ?   get first , get next  etc ..

2. When an openflow entry/flow  is retrieved - how can i
identify/understand  the **form** of the entry i.e. what are the
fields/keys  to match on ? e.g. ETH + VLAN ,   ETH+IP ,   ETH_IP+ TCP
port  etc..

Thank in advance,
-Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] Hashing to megaflow entry

[Sara Gittlin]

Thank you Justin,
i understand from the article, that generating megaflows and
installing in the kernel cache is already implemented in userspace -
ovs.
Before reading this article, i thought that megaflows were implemented
only for L2 normal mode.
Sara

On Tue, Aug 22, 2017 at 1:09 AM, Justin Pettit <jpet...@ovn.org> wrote:
>
>> On Aug 21, 2017, at 8:19 AM, Sara Gittlin <sara.gitt...@gmail.com> wrote:
>>
>> One more - I did not see in the article that if a match is found in
>> megaflow cache - then a microflow is generated to be installed in the
>> microflow cache to improve performance for subsequnce packets
>
> An exact-match cache (microflow cache) is an implementation of the datapath.  
> The userspace and out-of-tree OVS Linux kernel module that ships as part of 
> OVS contain an exact-match cache that's managed by the datapath.  The 
> upstream OVS kernel module that ships with the Linux kernel was rejected by 
> the Linux upstream community, so it does not contain one.
>
> --Justin
>
>
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] Hashing to megaflow entry

[Sara Gittlin]

One more - I did not see in the article that if a match is found in
megaflow cache - then a microflow is generated to be installed in the
microflow cache to improve performance for subsequnce packets

Sara


On Mon, Aug 21, 2017 at 2:21 PM, Sara Gittlin <sara.gitt...@gmail.com> wrote:
> Thank you Justin,
> Indeed this article is very helpful.
> i understand from the article, that generating megaflows and
> installing in the kernel cache is already implemented in userspace -
> ovs.
> Before reading this article, i thought that megaflows were implemented
> only for L2 normal mode.
> Sara
>
>
>
> On Thu, Aug 17, 2017 at 9:59 AM, Justin Pettit <jpet...@ovn.org> wrote:
>>
>>> On Aug 16, 2017, at 11:56 PM, Sara Gittlin <sara.gitt...@gmail.com> wrote:
>>>
>>> Hi,
>>> Suppose we support megaflows, How the hashing is performed in the
>>> kernel module ?
>>> when packet arrives how do we know 'beforehand' to mask key fields in
>>> order to hit the megaflow entry ?
>>
>> If you haven't done so already, I'd highly recommend looking at our NSDI 
>> paper that answers many of your questions:
>>
>> 
>> https://www.usenix.org/system/files/conference/nsdi15/nsdi15-paper-pfaff.pdf
>>
>> I hope you find it helpful.
>>
>> --Justin
>>
>>
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] Hashing to megaflow entry

[Sara Gittlin]

Thank you Justin,
Indeed this article is very helpful.
i understand from the article, that generating megaflows and
installing in the kernel cache is already implemented in userspace -
ovs.
Before reading this article, i thought that megaflows were implemented
only for L2 normal mode.
Sara



On Thu, Aug 17, 2017 at 9:59 AM, Justin Pettit <jpet...@ovn.org> wrote:
>
>> On Aug 16, 2017, at 11:56 PM, Sara Gittlin <sara.gitt...@gmail.com> wrote:
>>
>> Hi,
>> Suppose we support megaflows, How the hashing is performed in the
>> kernel module ?
>> when packet arrives how do we know 'beforehand' to mask key fields in
>> order to hit the megaflow entry ?
>
> If you haven't done so already, I'd highly recommend looking at our NSDI 
> paper that answers many of your questions:
>
> 
> https://www.usenix.org/system/files/conference/nsdi15/nsdi15-paper-pfaff.pdf
>
> I hope you find it helpful.
>
> --Justin
>
>
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

[ovs-discuss] Hashing to megaflow entry

[Sara Gittlin]

Hi,
Suppose we support megaflows, How the hashing is performed in the
kernel module ?
when packet arrives how do we know 'beforehand' to mask key fields in
order to hit the megaflow entry ?

Thank in advance
Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] OVS megaflows

[Sara Gittlin]

I took a look  at the datapath code -  saw only single table, which
its entries are microflows and megaflows
the megaflows are indicated by non-zero mask fields
Sara


On Wed, Aug 16, 2017 at 9:59 AM, Sara Gittlin <sara.gitt...@gmail.com> wrote:
> Thank you Joe
> Few questions:
> 1. Are there 2 separate flow tables in the kernel data-path ? for
> microflows and megaflows ?
>
> 2. If the answer is yes :
>- When pkt arrives,  is it first checked against the microflows
> table and if there is no  match, then it checked against the megaflows
> table ?
>
>- Then if the pkt matches a megaflow - a new microflow will be
> generated by the kernel for this pkt ?  this make sense to improve
> performance.
>
>
> Sara
>
>
> On Tue, Aug 15, 2017 at 7:16 PM, Joe Stringer <j...@ovn.org> wrote:
>> On the first point - it's a little more subtle than that. A traffic
>> flow (eg, a connection) must arrive at OVS, the first packet is sent
>> through userspace, which causes userspace to install a megaflow into
>> the datapath. Subsequently, if any traffic which matches that megaflow
>> arrives, it will directly 'hit' the megaflow entry and execute the
>> associated actions without going to userspace. Typically we use
>> "microflow" to refer to a packet headers description which
>> exact-matches all known fields, while "megaflow" allows a mask to be
>> applied in addition to this, which allows the traffic which would
>> otherwise be handled by multiple microflows to instead be handled by a
>> single megaflow. There is no dependency between megaflows and
>> microflows.
>>
>> Cheers,
>> Joe
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] OVS megaflows

[Sara Gittlin]

Thank you Joe
Few questions:
1. Are there 2 separate flow tables in the kernel data-path ? for
microflows and megaflows ?

2. If the answer is yes :
   - When pkt arrives,  is it first checked against the microflows
table and if there is no  match, then it checked against the megaflows
table ?

   - Then if the pkt matches a megaflow - a new microflow will be
generated by the kernel for this pkt ?  this make sense to improve
performance.


Sara


On Tue, Aug 15, 2017 at 7:16 PM, Joe Stringer  wrote:
> On the first point - it's a little more subtle than that. A traffic
> flow (eg, a connection) must arrive at OVS, the first packet is sent
> through userspace, which causes userspace to install a megaflow into
> the datapath. Subsequently, if any traffic which matches that megaflow
> arrives, it will directly 'hit' the megaflow entry and execute the
> associated actions without going to userspace. Typically we use
> "microflow" to refer to a packet headers description which
> exact-matches all known fields, while "megaflow" allows a mask to be
> applied in addition to this, which allows the traffic which would
> otherwise be handled by multiple microflows to instead be handled by a
> single megaflow. There is no dependency between megaflows and
> microflows.
>
> Cheers,
> Joe
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] OVS megaflows

[Sara Gittlin]

Can i summarize:
1. Once N microflows are installed in the kernel cache:
we can install a megaflow/s in kernel datapath,  if it possible to
generate a megaflow/s for them
2. These megaflow/s remain in the kernel megaflow cache as long as the
associated flows are in userspace openflow tables, regardless of
 microflows eviction from kernel cache.
Thanks in advance
Sara


On Mon, Aug 14, 2017 at 8:47 PM, Joe Stringer <j...@ovn.org> wrote:
> The FAQ is referring to megaflows as well, the reasons are the same.
> Neither microflows nor megaflows can be pre-populated.
>
> On 14 August 2017 at 00:35, Sara Gittlin <sara.gitt...@gmail.com> wrote:
>> I  understand that this citation refers to the kernel microflows  tables.
>> the kernel megaflows table *can be* pre-populated. Correct ?
>> Sara
>>
>> On Mon, Aug 14, 2017 at 9:31 AM, Sara Gittlin <sara.gitt...@gmail.com> wrote:
>>> Thanks you Joe
>>> the following citation is in a contradiction to the idea of
>>> pre-populating megaflows in kernel datapath .
>>> this is from  http://docs.openvswitch.org/en/latest/faq/design/
>>>
>>> "Q: Can OVS populate the kernel flow table in advance instead of in
>>> reaction to packets?
>>>
>>> A: No. There are several reasons:
>>>
>>> Kernel flows are not as sophisticated as OpenFlow flows, which means
>>> that some OpenFlow policies could require a large number of kernel
>>> flows. The “conjunctive match” feature is an extreme example: the
>>> number of kernel flows it requires is the product of the number of
>>> flows in each dimension.
>>> With multiple OpenFlow flow tables and simple sets of actions, the
>>> number of kernel flows required can be as large as the product of the
>>> number of flows in each dimension. With more sophisticated actions,
>>> the number of kernel flows could be even larger.
>>> Open vSwitch is designed so that any version of OVS userspace
>>> interoperates with any version of the OVS kernel module. This forward
>>> and backward compatibility requires that userspace observe how the
>>> kernel module parses received packets. This is only possible in a
>>> straightforward way when userspace adds kernel flows in reaction to
>>> received packets."
>>>
>>> Thanks in advance - Sara
>>>
>>> On Mon, Jul 24, 2017 at 10:58 PM, Joe Stringer <j...@ovn.org> wrote:
>>>> On 23 July 2017 at 06:37, Sara Gittlin <sara.gitt...@gmail.com> wrote:
>>>>> Hello,
>>>>> I understand that there is a support for megaflows in the kernel and 
>>>>> netlink.
>>>>> I also understand that there is no megaflow implementation in ofproto.
>>>>> i.e. there is no implementation of compressing (if possible) all flows
>>>>> in ofproto table to megaflows and installing it in the datapath. is
>>>>> that correct ?
>>>>
>>>> That's right - rather than pre-populating a representation of the
>>>> entire OpenFlow state, the ofproto-dpif implementation uses an
>>>> "upcall" model where the datapath acts as a cache for forwarding
>>>> behaviour, and the cache is populated on-demand as traffic arrives.
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] OVS megaflows

[Sara Gittlin]

I  understand that this citation refers to the kernel microflows  tables.
the kernel megaflows table *can be* pre-populated. Correct ?
Sara

On Mon, Aug 14, 2017 at 9:31 AM, Sara Gittlin <sara.gitt...@gmail.com> wrote:
> Thanks you Joe
> the following citation is in a contradiction to the idea of
> pre-populating megaflows in kernel datapath .
> this is from  http://docs.openvswitch.org/en/latest/faq/design/
>
> "Q: Can OVS populate the kernel flow table in advance instead of in
> reaction to packets?
>
> A: No. There are several reasons:
>
> Kernel flows are not as sophisticated as OpenFlow flows, which means
> that some OpenFlow policies could require a large number of kernel
> flows. The “conjunctive match” feature is an extreme example: the
> number of kernel flows it requires is the product of the number of
> flows in each dimension.
> With multiple OpenFlow flow tables and simple sets of actions, the
> number of kernel flows required can be as large as the product of the
> number of flows in each dimension. With more sophisticated actions,
> the number of kernel flows could be even larger.
> Open vSwitch is designed so that any version of OVS userspace
> interoperates with any version of the OVS kernel module. This forward
> and backward compatibility requires that userspace observe how the
> kernel module parses received packets. This is only possible in a
> straightforward way when userspace adds kernel flows in reaction to
> received packets."
>
> Thanks in advance - Sara
>
> On Mon, Jul 24, 2017 at 10:58 PM, Joe Stringer <j...@ovn.org> wrote:
>> On 23 July 2017 at 06:37, Sara Gittlin <sara.gitt...@gmail.com> wrote:
>>> Hello,
>>> I understand that there is a support for megaflows in the kernel and 
>>> netlink.
>>> I also understand that there is no megaflow implementation in ofproto.
>>> i.e. there is no implementation of compressing (if possible) all flows
>>> in ofproto table to megaflows and installing it in the datapath. is
>>> that correct ?
>>
>> That's right - rather than pre-populating a representation of the
>> entire OpenFlow state, the ofproto-dpif implementation uses an
>> "upcall" model where the datapath acts as a cache for forwarding
>> behaviour, and the cache is populated on-demand as traffic arrives.
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

[ovs-discuss] OVS megaflows

[Sara Gittlin]

Hello,
I understand that there is a support for megaflows in the kernel and netlink.
I also understand that there is no megaflow implementation in ofproto.
i.e. there is no implementation of compressing (if possible) all flows
in ofproto table to megaflows and installing it in the datapath. is
that correct ?
Thanks in advance - Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] A tool to feel-up flow-tables in ofproto

[Sara Gittlin]

Many thanks Blue
Now im able to generate huge amount of entries in ofproto tables. These are
simple flows because i run the controller w simple-switch-l3 .how to run it
to generate more complex flows.
Sara.

בתאריך 19 ביולי 2017 20:05,‏ "Blue Lang" <b...@veracity.io> כתב:

> Sara,
>
> Follow the mininet tutorials for creating large topologies with nox or
> pox, then run dump-flows accordingly.
>
> https://inside-openflow.com/2016/06/29/custom-mininet-
> topologies-and-introducing-atom/
>
>
> Thanks,
>
> On Wed, Jul 19, 2017 at 7:12 AM, Sara Gittlin <sara.gitt...@gmail.com>
> wrote:
>
>> On Mon, Jul 17, 2017 at 8:21 PM, Ben Pfaff <b...@ovn.org> wrote:
>> > On Mon, Jul 17, 2017 at 10:47:12AM +0300, Sara Gittlin wrote:
>> >> On Sun, Jul 16, 2017 at 09:37:05AM +0300, Sara Gittlin wrote:
>> >> > On Wed, Jul 12, 2017 at 11:40:41AM +0300, Sara Gittlin wrote:
>> >> > > Thank you Ben
>> >> > >
>> >> > > >> I need a tool to feel up the flow tables in ofproto.
>> >> > > >> do you know what tool/other should i use ?
>> >> > >
>> >> > > >What does it mean "to feel up" a flow table?
>> >> > >
>> >> > > i want to be able to read ofctl tables and to get a big output ~
>> 1
>> >> > > - 5 flows.
>> >> > > i need it to order to run some algo. on these flows (e.g. try to
>> >> > > generate megaflows .. )
>> >> > > i know that i can do it with sdn controller -  is there other
>> tools ?
>> >> >
>> >> > >Do you just want to run "ovs-ofctl dump-flows"?
>> >> > >
>> >> >>  Thanks Ben
>> >> >>  this can be an option, unless there is a better way to retrieve all
>> >> > > flows in ofproto
>> >>
>> >> > So far, you've said that you don't want to use a controller and you
>> want
>> >> > something "better" than ovs-ofctl.  What would be better?  It's
>> >> > difficult to help when you don't give us much information on what you
>> >> > want.
>> >>
>> >> Ben,  i think i understand now.
>> >> I should use SDN controller , but how to create a big topology so lot
>> >> of flows can be created ?
>> >> mininet ? openstack ? other ?
>> >
>> > I'll have to leave that question to others, because it's not my area of
>> > expertise.  I do hear a lot of good things about mininet.
>> Alternatively - where  can i find a real dataset of the output  of
>> ovs-dpct dump-flows   or ovs-ofctl dump-flows br
>> this should be a big dump  file  of the output of one of these commands
>> above
>> Thanks - Sara
>> ___
>> discuss mailing list
>> disc...@openvswitch.org
>> https://mail.openvswitch.org/mailman/listinfo/ovs-discuss
>>
>
>
>
> --
> Blue Lang
> PM *| *Veracity
>
> 3423 Piedmont Rd NE
>
> Suite 350
>
> Atlanta, GA  30305
> Cell:  (770) 265-1381 <+17702651381>
> https://www.linkedin.com/in/bluelang/
> b...@veracity.io
> www.veracity.io
>
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] A tool to feel-up flow-tables in ofproto

[Sara Gittlin]

On Mon, Jul 17, 2017 at 8:21 PM, Ben Pfaff <b...@ovn.org> wrote:
> On Mon, Jul 17, 2017 at 10:47:12AM +0300, Sara Gittlin wrote:
>> On Sun, Jul 16, 2017 at 09:37:05AM +0300, Sara Gittlin wrote:
>> > On Wed, Jul 12, 2017 at 11:40:41AM +0300, Sara Gittlin wrote:
>> > > Thank you Ben
>> > >
>> > > >> I need a tool to feel up the flow tables in ofproto.
>> > > >> do you know what tool/other should i use ?
>> > >
>> > > >What does it mean "to feel up" a flow table?
>> > >
>> > > i want to be able to read ofctl tables and to get a big output ~ 1
>> > > - 5 flows.
>> > > i need it to order to run some algo. on these flows (e.g. try to
>> > > generate megaflows .. )
>> > > i know that i can do it with sdn controller -  is there other tools ?
>> >
>> > >Do you just want to run "ovs-ofctl dump-flows"?
>> > >
>> >>  Thanks Ben
>> >>  this can be an option, unless there is a better way to retrieve all
>> > > flows in ofproto
>>
>> > So far, you've said that you don't want to use a controller and you want
>> > something "better" than ovs-ofctl.  What would be better?  It's
>> > difficult to help when you don't give us much information on what you
>> > want.
>>
>> Ben,  i think i understand now.
>> I should use SDN controller , but how to create a big topology so lot
>> of flows can be created ?
>> mininet ? openstack ? other ?
>
> I'll have to leave that question to others, because it's not my area of
> expertise.  I do hear a lot of good things about mininet.
Alternatively - where  can i find a real dataset of the output  of
ovs-dpct dump-flows   or ovs-ofctl dump-flows br
this should be a big dump  file  of the output of one of these commands above
Thanks - Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] A tool to feel-up flow-tables in ofproto

[Sara Gittlin]

On Sun, Jul 16, 2017 at 09:37:05AM +0300, Sara Gittlin wrote:
> On Wed, Jul 12, 2017 at 11:40:41AM +0300, Sara Gittlin wrote:
> > Thank you Ben
> >
> > >> I need a tool to feel up the flow tables in ofproto.
> > >> do you know what tool/other should i use ?
> >
> > >What does it mean "to feel up" a flow table?
> >
> > i want to be able to read ofctl tables and to get a big output ~ 1
> > - 5 flows.
> > i need it to order to run some algo. on these flows (e.g. try to
> > generate megaflows .. )
> > i know that i can do it with sdn controller -  is there other tools ?
>
> >Do you just want to run "ovs-ofctl dump-flows"?
> >
>>  Thanks Ben
>>  this can be an option, unless there is a better way to retrieve all
> > flows in ofproto

> So far, you've said that you don't want to use a controller and you want
> something "better" than ovs-ofctl.  What would be better?  It's
> difficult to help when you don't give us much information on what you
> want.

Ben,  i think i understand now.
I should use SDN controller , but how to create a big topology so lot
of flows can be created ?
mininet ? openstack ? other ?
Thank you. Sara

On Sun, Jul 16, 2017 at 8:46 PM, Ben Pfaff <b...@ovn.org> wrote:
> On Sun, Jul 16, 2017 at 09:37:05AM +0300, Sara Gittlin wrote:
>> On Wed, Jul 12, 2017 at 11:40:41AM +0300, Sara Gittlin wrote:
>> > Thank you Ben
>> >
>> > >> I need a tool to feel up the flow tables in ofproto.
>> > >> do you know what tool/other should i use ?
>> >
>> > >What does it mean "to feel up" a flow table?
>> >
>> > i want to be able to read ofctl tables and to get a big output ~ 1
>> > - 5 flows.
>> > i need it to order to run some algo. on these flows (e.g. try to
>> > generate megaflows .. )
>> > i know that i can do it with sdn controller -  is there other tools ?
>>
>> Do you just want to run "ovs-ofctl dump-flows"?
>>
>> Thanks Ben
>> this can be an option, unless there is a better way to retrieve all
>> flows in ofproto
>
> So far, you've said that you don't want to use a controller and you want
> something "better" than ovs-ofctl.  What would be better?  It's
> difficult to help when you don't give us much information on what you
> want.
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] A tool to feel-up flow-tables in ofproto

[Sara Gittlin]

On Wed, Jul 12, 2017 at 11:40:41AM +0300, Sara Gittlin wrote:
> Thank you Ben
>
> >> I need a tool to feel up the flow tables in ofproto.
> >> do you know what tool/other should i use ?
>
> >What does it mean "to feel up" a flow table?
>
> i want to be able to read ofctl tables and to get a big output ~ 1
> - 5 flows.
> i need it to order to run some algo. on these flows (e.g. try to
> generate megaflows .. )
> i know that i can do it with sdn controller -  is there other tools ?

Do you just want to run "ovs-ofctl dump-flows"?

Thanks Ben
this can be an option, unless there is a better way to retrieve all
flows in ofproto
Sara


On Wed, Jul 12, 2017 at 6:15 PM, Ben Pfaff <b...@ovn.org> wrote:
> On Wed, Jul 12, 2017 at 11:40:41AM +0300, Sara Gittlin wrote:
>> Thank you Ben
>>
>> >> I need a tool to feel up the flow tables in ofproto.
>> >> do you know what tool/other should i use ?
>>
>> >What does it mean "to feel up" a flow table?
>>
>> i want to be able to read ofctl tables and to get a big output ~ 1
>> - 5 flows.
>> i need it to order to run some algo. on these flows (e.g. try to
>> generate megaflows .. )
>> i know that i can do it with sdn controller -  is there other tools ?
>
> Do you just want to run "ovs-ofctl dump-flows"?
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

Re: [ovs-discuss] A tool to feel-up flow-tables in ofproto

[Sara Gittlin]

Thank you Ben

>> I need a tool to feel up the flow tables in ofproto.
>> do you know what tool/other should i use ?

>What does it mean "to feel up" a flow table?

i want to be able to read ofctl tables and to get a big output ~ 1
- 5 flows.
i need it to order to run some algo. on these flows (e.g. try to
generate megaflows .. )
i know that i can do it with sdn controller -  is there other tools ?
Thanks you in advance - Sara

On Tue, Jul 11, 2017 at 6:38 PM, Ben Pfaff <b...@ovn.org> wrote:
> On Tue, Jul 11, 2017 at 10:58:39AM +0300, Sara Gittlin wrote:
>> I need a tool to feel up the flow tables in ofproto.
>> do you know what tool/other should i use ?
>
> What does it mean "to feel up" a flow table?
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss

[ovs-discuss] A tool to feel-up flow-tables in ofproto

[Sara Gittlin]

Hello,
I need a tool to feel up the flow tables in ofproto.
do you know what tool/other should i use ?
Thank you in advance - Sara
___
discuss mailing list
disc...@openvswitch.org
https://mail.openvswitch.org/mailman/listinfo/ovs-discuss