Since lookups in the classifier can be pretty expensive, we introduce this
(thread local) cache which simply compares the miniflows of the packets
Signed-off-by: Daniele Di Proietto
---
lib/dpif-netdev.c | 431 +-
1 file changed, 358 insertions
These function are used to stored the packet hash. 'netdev-dpdk' automatically
set this value to the RSS hash returned by the NIC. Other 'netdev's set it to 0
(which is an invalid hash value), so that callers can compute the hash on their
own.
If DPDK support is enabled, struct dpif_packet's membe
This series introduces in dpif-netdev an exact match cache for frequently
used flows. It uses the RSS hash (currently implemented only for netdev-dpdk)
to search the miniflow in an hash table.
While there might be still some tuning left to do, these patch provides
significant performance improveme
Thanks for the detailed and fast review.
I applied all your suggestions and I'll post a v4 soon
On 8/18/14, 11:06 PM, "Pravin Shelar" wrote:
>On Mon, Aug 18, 2014 at 1:29 PM, Daniele Di Proietto
> wrote:
>> Since lookups in the classifier can be pretty expensive, we introduce
>>this
>> (thread
On 8/18/14, 11:06 PM, "Pravin Shelar" wrote:
>On Mon, Aug 18, 2014 at 1:29 PM, Daniele Di Proietto
> wrote:
>> ofpbuf_rss() is introduced to get the RSS hash from the NIC. It works
>>only for
>> packets received by DPDK (otherwise it returns 0, which tells the
>>caller to
>> compute the hash in
This allows things like initiating a wait request on an interface
ofport being set.
When the optional field is empty and operation is != or excludes
then the result is true; otherwise it is false. If the field is
set then the field is compared normally for its type.
Signed-off-by: Terry Wilson
-
>On Tue, Aug 19, 2014 at 02:10:50AM +, Saurabh Shah wrote:
>> Hi Ben,
>>
>> >On Thu, Aug 14, 2014 at 08:35:36PM -0700, Nithin Raju wrote:
>> >> The datapath interface defined in odp-netlink.h needs some extensions
>> >> that are platform dependent. Some examples are the name of the
>> >>commu
On Tue, Aug 19, 2014 at 01:51:54PM -0700, Nithin Raju wrote:
> To verify if the netlink support in the kernel works, I updated
> the netlink-socket.c code to get the PID for a given device
> descriptor.
>
> In the existing code, userspace sets the PID, which will not be
> unique across different p
On Tue, Aug 19, 2014 at 01:51:52PM -0700, Nithin Raju wrote:
> In this change we create peer to OvsIoctl.[ch] that would interface
> with userspace using the netlink interface. The new files are called
> Datapath.[ch]. We are not deleting OvsIoctl.[ch] yet. Datapath.[ch]
> provides bare minimum fun
The datapath interface defined in odp-netlink.h needs some extensions
that are platform dependent. Some examples are the name of the communication
device on Windows and a set of commands that are specific to Windows.
In this change we define a datapath-windows/include/OvsDpInterfaceExt.h
to includ
In this change, we define netlink families and commands supported
by the Windows datapath. Only the control family and one command
is supported today to get the PID.
We also implement the 3 ioctls: read, write and transact. This is
bare minimum and can be used to implement the equivalent of a
recv
To verify if the netlink support in the kernel works, I updated
the netlink-socket.c code to get the PID for a given device
descriptor.
In the existing code, userspace sets the PID, which will not be
unique across different processes. So, it is better for the
kernel to generate the PID and give it
In this change we create peer to OvsIoctl.[ch] that would interface
with userspace using the netlink interface. The new files are called
Datapath.[ch]. We are not deleting OvsIoctl.[ch] yet. Datapath.[ch]
provides bare minimum functionality to register a pseudo device for
communication with userspa
The datapath interface defined in odp-netlink.h needs some extensions
that are platform dependent. Some examples are the name of the communication
device on Windows and a set of commands that are specific to Windows.
In this change we define a datapath-windows/include/OvsDpInterfaceExt.h
to includ
In this change we create peer to OvsIoctl.[ch] that would interface
with userspace using the netlink interface. The new files are called
Datapath.[ch]. We are not deleting OvsIoctl.[ch] yet. Datapath.[ch]
provides bare minimum functionality to register a pseudo device for
communication with userspa
In this change, we define netlink families and commands supported
by the Windows datapath. Only the control family and one command
is supported today to get the PID.
We also implement the 3 ioctls: read, write and transact. This is
bare minimum and can be used to implement the equivalent of a
recv
To verify if the netlink support in the kernel works, I updated
the netlink-socket.c code to get the PID for a given device
descriptor.
In the existing code, userspace sets the PID, which will not be
unique across different processes. So, it is better for the
kernel to generate the PID and give it
Thx, applied to master and branch-2.3
On Tue, Aug 19, 2014 at 11:52 AM, Ben Pfaff wrote:
> On Tue, Aug 19, 2014 at 11:06:04AM -0700, Alex Wang wrote:
> > This commit clarifies the documentation for 'bfd:enable'
> > when it is not specified.
> >
> > Signed-off-by: Alex Wang
>
> Acked-by: Ben Pf
On Tue, Aug 19, 2014 at 11:06:04AM -0700, Alex Wang wrote:
> This commit clarifies the documentation for 'bfd:enable'
> when it is not specified.
>
> Signed-off-by: Alex Wang
Acked-by: Ben Pfaff
___
dev mailing list
dev@openvswitch.org
http://openvswi
This commit clarifies the documentation for 'bfd:enable'
when it is not specified.
Signed-off-by: Alex Wang
---
vswitchd/vswitch.xml |3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/vswitchd/vswitch.xml b/vswitchd/vswitch.xml
index ab738da..6c49250 100644
--- a/vswitchd/v
On Tue, Aug 19, 2014 at 02:10:50AM +, Saurabh Shah wrote:
> Hi Ben,
>
> >On Thu, Aug 14, 2014 at 08:35:36PM -0700, Nithin Raju wrote:
> >> The datapath interface defined in odp-netlink.h needs some extensions
> >> that are platform dependent. Some examples are the name of the
> >>communication
Your message dated Tue, 19 Aug 2014 16:19:26 +
with message-id
and subject line Bug#740983: fixed in openvswitch 2.3.0+git20140819-1
has caused the Debian Bug report #740983,
regarding openvswitch-datapath-dkms: fails to build dkms module
to be marked as done.
This means that you claim that t
Accepted:
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA256
Format: 1.8
Date: Tue, 19 Aug 2014 08:19:21 -0700
Source: openvswitch
Binary: openvswitch-common openvswitch-switch openvswitch-ipsec openvswitch-pki
openvswitch-dbg python-openvswitch openvswitch-test openvswitch-vtep
Architecture: sou
To verify if the netlink support in the kernel works, I updated
the netlink-socket.c code to get the PID for a given device
descriptor.
In the existing code, userspace sets the PID, which will not be
unique across different processes. So, it is better for the
kernel to generate the PID and give it
openvswitch_2.3.0+git20140819-1_i386.changes uploaded successfully to localhost
along with the files:
openvswitch-common_2.3.0+git20140819-1_i386.deb
openvswitch-switch_2.3.0+git20140819-1_i386.deb
openvswitch-ipsec_2.3.0+git20140819-1_i386.deb
openvswitch-dbg_2.3.0+git20140819-1_i386.deb
> Is there any objection if we directly include OvsDpInterfaceExt.h in
> userspace (with the right #ifdefs, of course)? I don't understand why we
> would want to auto-generate a file just to include the kernel header file.
> This is what the auto-generated file is supposed to look like -
>
> /*
>
On Aug 18, 2014, at 5:08 PM, Alin Serdean
wrote:
> Hi Nithin,
>
> Just a few thoughts:
> Since get PID is a special case would it not be better to treat it as a
> DeviceIoControl;dwIoControlCode like OVS_IOCTL_TRANSACT (i.e.
> OVS_IOCTL_GET_PID)?
>
> We can drop the extra headers and the wh
On Tue, Aug 19, 2014 at 7:48 AM, Aditya Kamath wrote:
> Hi everyone,
>
> I am a student newly starting to work on a research project on OpenVSwitch. I
> have to add a data structure to the OVS kernel module to perform some
> statistics of the incoming packets. Also I want to be able to control t
Hi everyone,
I am a student newly starting to work on a research project on OpenVSwitch. I
have to add a data structure to the OVS kernel module to perform some
statistics of the incoming packets. Also I want to be able to control this data
structure from the controller, and make this data stru
On Mon, Aug 18, 2014 at 5:41 PM, Alin Serdean
wrote:
> Hi Guru,
>
> I tested the same thing with /FS
> (http://msdn.microsoft.com/en-us/library/dn502518.aspx ) earlier today but it
> was still hanging. I will retry on a fresh environment tomorrow.
Couple of things that you may want to keep in min
ovs/ovs-issues#15
All NET_BUFFERs of a NET_BUFFER_LIST must go through
the pipeline: extract, find flow, execute. Previously,
only the first NET_BUFFER of a NET_BUFFER_LIST was going
through this pipeline, which was erroneous.
OvsPartialCopyToMultipleNBLs is used to make each NET_BUFFER
have its
Hi Nithin,
He was working on the commands mapping and the arguments parsing, so no
duplicate effort at the moment just to clear it out.
He will look over the patches you sent out when he comes back from PTO and see
how he can best fit his effort.
Thanks,
Alin.
-Mesaj original-
De la:
32 matches
Mail list logo