Hi Konstantin,
> Hi Dong,
>
>> -Original Message-
>> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of WangDong
>> Sent: Tuesday, May 05, 2015 4:38 PM
>> To: dev at dpdk.org
>> Subject: [dpdk-dev] [PATCH] librte_eal:Using compiler memory barrier for IA
>> processor's rte_wmb/rte_rmb
Hi all
I'm freshman of dpdk.
And , I want to use dpdk ovs. I compiled successfully.
like:
Bridge "br0"
Port "br0"
Interface "br0"
type: internal
Port "dpdk0"
On 5/7/15, 9:04 AM, "Bruce Richardson" wrote:
>On Thu, May 07, 2015 at 05:45:20PM +0200, Marc Sune wrote:
>>
>>
>> On 07/05/15 17:35, Bruce Richardson wrote:
>> >The "lib" directory is getting very crowded, with both general libs and
>> >poll mode drivers in it. This patch set proposes to mov
Control queue can't work for vhost-user mulitple queue mode,
so workaround to return a value directly in send_command function.
Signed-off-by: Changchun Ouyang
---
lib/librte_pmd_virtio/virtio_ethdev.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/lib/librte_pmd_virtio/virtio_ethdev.
Sample vhost leverage the VMDq+RSS in HW to receive packets and distribute them
into different queue in the pool according to their 5 tuples.
On the other hand, it enables multiple queues mode in vhost/virtio layer.
HW queue numbers in pool is required to be exactly same with the queue number
in
Sample vhost need know the queue number user want to enable for each virtio
device,
so add the new option '--rxq' into it.
Signed-off-by: Changchun Ouyang
---
examples/vhost/main.c | 46 ++
1 file changed, 42 insertions(+), 4 deletions(-)
diff --git
QEMU sends separate commands orderly to set the memory layout for each queue
in one virtio device, accordingly vhost need keep memory layout information
for each queue of the virtio device.
This also need adjust the interface a bit for function gpa_to_vva by
introducing the queue index to specify
Each virtio device could have multiple queues, say 2 or 4, at most 8.
Enabling this feature allows virtio device/port on guest has the ability to
use different vCPU to receive/transmit packets from/to each queue.
In multiple queues mode, virtio device readiness means all queues of
this virtio devi
In non-SRIOV environment, VMDq RSS could be enabled by MRQC register.
In theory, the queue number per pool could be 2 or 4, but only 2 queues are
available due to HW limitation, the same limit also exist in Linux ixgbe driver.
Signed-off-by: Changchun Ouyang
---
lib/librte_ether/rte_ethdev.c
This RFC patch set supports the multiple queues for each virtio device in vhost.
The vhost-user is used to enable the multiple queues feature, It's not ready
for vhost-cuse.
One prerequisite to enable this feature is that a QEMU patch plus a fix is
required to apply
on QEMU, pls refer to this li
On Tue, 5 May 2015 13:39:39 +0800
Cunming Liang wrote:
> + bytes_read = read(fd, &buf, bytes_read);
> + if (bytes_read < 0)
> + RTE_LOG(ERR, EAL, "Error reading from file "
> + "descriptor %d: %s\n", fd,
> + strerror(errno)
The read co
On Tue, 5 May 2015 13:39:38 +0800
Cunming Liang wrote:
> + else if (rc < 0) {
> + /* epoll_wait fail */
> + RTE_LOG(ERR, EAL, "epoll_wait returns with fail %s\n",
> + strerror(errno));
In real application there maybe other random signals.
Therefor
Add missing initialization of to pci_dev driver
The link from pci_dev back to the ethernet driver was not being set.
Signed-off-by: Stephen Hemminger
---
lib/librte_pmd_bond/rte_eth_bond_api.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/lib/librte_pmd_bond/rte_eth_bond_api.c
b/lib/librt
> > This series includes:
> >- Fix the "issue" introduced in 01fa1d6215fa7cd6b5303ac9296381b75b9226de:
> > files in librte_pmd_ixgbe/ixgbe/ are shared with FreeBSD and AFAIU
> > should not
> > be changed unless the change is pushed into the FreeBSD tree first.
> >- Remove unused
Hi DPDK users and developers,
Few weeks ago I came up with the idea to run openvswitch with dpdk backend
inside qemu-kvm virtual machine. I don't have enough supported NICs yet and
my plan was to start experimenting inside the virtualized environment,
achieve functional state of all the components
On 05/07/2015 06:49 PM, Wiles, Keith wrote:
>
> On 5/7/15, 8:33 AM, "Avi Kivity" wrote:
>
>> On 05/07/2015 06:27 PM, Wiles, Keith wrote:
>>> On 5/7/15, 7:02 AM, "Avi Kivity" wrote:
>>>
On Wed, Apr 22, 2015 at 6:11 PM, O'Driscoll, Tim
wrote:
> Does anybody have any input o
On 05/07/2015 06:27 PM, Wiles, Keith wrote:
>
> On 5/7/15, 7:02 AM, "Avi Kivity" wrote:
>
>> On Wed, Apr 22, 2015 at 6:11 PM, O'Driscoll, Tim
>>
>> wrote:
>>
>>> Does anybody have any input or comments on this?
>>>
>>>
-Original Message-
From: O'Driscoll, Tim
Sent: Thursday
On 05/07/2015 06:27 PM, Wiles, Keith wrote:
>
> On 5/7/15, 7:02 AM, "Avi Kivity" wrote:
>
>> On Wed, Apr 22, 2015 at 6:11 PM, O'Driscoll, Tim
>>
>> wrote:
>>
>>> Does anybody have any input or comments on this?
>>>
>>>
-Original Message-
From: O'Driscoll, Tim
Sent: Thursday
On Thu, May 7, 2015 at 9:22 AM, Oleg Strikov
wrote:
> Hi DPDK users and developers,
>
> Few weeks ago I came up with the idea to run openvswitch with dpdk backend
> inside qemu-kvm virtual machine. I don't have enough supported NICs yet and
> my plan was to start experimenting inside the virtuali
On 07/05/15 17:35, Bruce Richardson wrote:
> The "lib" directory is getting very crowded, with both general libs and
> poll mode drivers in it. This patch set proposes to move the PMDs out of the
> lib folder and to put them in a separate "pmds" folder. This should help
> with code browse-ability
On 7 May 2015 at 16:02, Avi Kivity wrote:
> One problem we've seen with dpdk is that it is a framework, not a library:
> it wants to create threads, manage memory, and generally take over. This
> is a problem for us, as we are writing a framework (seastar, [1]) and need
> to create threads, mana
On Thu, May 07, 2015 at 05:45:20PM +0200, Marc Sune wrote:
>
>
> On 07/05/15 17:35, Bruce Richardson wrote:
> >The "lib" directory is getting very crowded, with both general libs and
> >poll mode drivers in it. This patch set proposes to move the PMDs out of the
> >lib folder and to put them in a
On Wed, Apr 22, 2015 at 6:11 PM, O'Driscoll, Tim
wrote:
> Does anybody have any input or comments on this?
>
>
> > -Original Message-
> > From: O'Driscoll, Tim
> > Sent: Thursday, April 16, 2015 11:39 AM
> > To: dev at dpdk.org
> > Subject: Beyond DPDK 2.0
> >
> > Following the launch of
On Thu, May 07, 2015 at 04:35:49PM +0100, Bruce Richardson wrote:
> The "lib" directory is getting very crowded, with both general libs and
> poll mode drivers in it. This patch set proposes to move the PMDs out of the
> lib folder and to put them in a separate "pmds" folder. This should help
> wi
Hi all,
Recently, i've modified the vHost app - testpmd.
The modification includes the following steps:
1.obtain the payload of each packet
2.collect the information that i need. ex. 'url'
3.store the "url" into a disk file. ex. payload.txt
Th
In the Makefiles for the PMDs, the paths to the files are often
specified using the full path from $(RTE_SDK) variable. These paths can
be shortened, and make more flexible in case of a future path change by
specifying the paths using $(SRCDIR) instead.
Signed-off-by: Bruce Richardson
---
lib/li
The "lib" directory is getting very crowded, with both general libs and
poll mode drivers in it. This patch set proposes to move the PMDs out of the
lib folder and to put them in a separate "pmds" folder. This should help
with code browse-ability as the number of libs, and pmds increases.
Comment
Hi Avi,
On 05/07/2015 04:02 PM, Avi Kivity wrote:
> On Wed, Apr 22, 2015 at 6:11 PM, O'Driscoll, Tim
> wrote:
>
>> Does anybody have any input or comments on this?
>>
>>
>>> -Original Message-
>>> From: O'Driscoll, Tim
>>> Sent: Thursday, April 16, 2015 11:39 AM
>>> To: dev at dpdk.org
>>
Hi Dong,
> -Original Message-
> From: Wang Dong [mailto:dong.wang.pro at hotmail.com]
> Sent: Thursday, May 07, 2015 4:28 PM
> To: Ananyev, Konstantin; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] librte_eal:Using compiler memory barrier for
> IA processor's rte_wmb/rte_rmb.
>
> Hi
This is build infrastructure changes for bnx2x driver.
- enable BNX2X poll mode driver in default config.
- add it to mk
- put entry in MAINTAINERS
Note: I intentionally did not list myself as maintainer of this
driver. There is no official support for this driver.
Signed-off-by: Stephen Hemm
From: Sergey Kreys
Add driver for the Broadcom NetXtremeII 10 gigabit devices.
Signed-off-by: Stephen Hemminger
---
v3 - this is same as previous bcm driver just renamed
v4 - split into two pieces for review.
---
lib/librte_pmd_bnx2x/debug.c | 113 +
lib/librte_pmd_bnx2x/ecore_fw_d
From: Sergey Kreys
Add driver for the Broadcom NetXtremeII 10 gigabit devices.
Signed-off-by: Stephen Hemminger
---
v3 - this is same as previous bcm driver just renamed
v4 - split into two pieces for review.
---
lib/librte_pmd_bnx2x/Makefile |28 +
lib/librte_pmd_bnx2x/bnx2x.c
From: Stephen Hemminger
Some drivers need ability to access PCI config (for example for power
management). This adds an abstraction to do this; only implemented
on Linux, but should be possible on BSD.
Signed-off-by: Stephen Hemminger
---
lib/librte_eal/common/include/rte_pci.h | 28 ++
Update to previous sumbission.
- Split main source of driver from one monster patch into two large patches
- Add map files for shared library support
Stephen Hemminger (4):
pci: allow access to PCI config space
bnx2x: new poll mode driver (part1)
bnx2x: new poll mode driver (part2)
bnx2x
On Thu, May 7, 2015 at 10:57 AM, Xie, Huawei wrote:
> On 4/3/2015 1:02 AM, Pavel Boldin wrote:
> > Move ioctl `EVENTFD_COPY' handler code to an inline function.
> Pavel:
> There is no necessity to inline this function.
>
Xie, there is even no necessity to split this in a five piece patchseries.
I
On 5/7/15, 8:33 AM, "Avi Kivity" wrote:
>On 05/07/2015 06:27 PM, Wiles, Keith wrote:
>>
>> On 5/7/15, 7:02 AM, "Avi Kivity" wrote:
>>
>>> On Wed, Apr 22, 2015 at 6:11 PM, O'Driscoll, Tim
>>>
>>> wrote:
>>>
Does anybody have any input or comments on this?
> -Original Mes
On Thu, May 7, 2015 at 3:36 PM, Neil Horman wrote:
> > I tried to reuse modinfo, but the problem is that kmod implementation is
> > checking the filename extension against .ko and .ko.gz.
> >
> Well, you can alter modinfo so that it looks at .so files if you like, but
> thats
> not the only tool
On 5/7/15, 7:02 AM, "Avi Kivity" wrote:
>On Wed, Apr 22, 2015 at 6:11 PM, O'Driscoll, Tim
>
>wrote:
>
>> Does anybody have any input or comments on this?
>>
>>
>> > -Original Message-
>> > From: O'Driscoll, Tim
>> > Sent: Thursday, April 16, 2015 11:39 AM
>> > To: dev at dpdk.org
>> > S
This is needed to add / remove interfaces in multicast groups via the
ip tool.
The callback does nothing - the same as the kernel tun.c.
Signed-off-by: Simon Kagstrom
---
Marked RFC since I'm by no means an expert on this. We noticed this
when playing with KNI and IGMP handling.
lib/librte_eal
Hi,
I am trying to work with Intel Fortville (XL710) NICs in Passthrough mode from
a VM running dpdk app.
First I didn't have any TX traffic from the VM, I got dpdk patch for this issue
and it fixed it. (http://www.dpdk.org/dev/patchwork/patch/4588/)
But now I see that when trying to run mu
On 5/6/2015 2:38 AM, Stephen Hemminger wrote:
> On Tue, 5 May 2015 13:39:42 +0800
> Cunming Liang wrote:
>
>> diff --git a/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c
>> b/lib/librte_eal/linuxapp/eal/eal_pci_vfio.c
>> index aea1fb1..387f54c 100644
>> --- a/lib/librte_eal/linuxapp/eal/eal_pci_vf
On 5/6/2015 2:34 AM, Stephen Hemminger wrote:
> On Tue, 5 May 2015 13:39:39 +0800
> Cunming Liang wrote:
>
>> static void
>> +eal_intr_proc_rxtx_intr(int fd, struct rte_intr_handle *intr_handle)
>> +{
> Should be const intr_handle is not modified
[LCM] accept.
> Subject: [dpdk-dev] How to use dpdk ovs
[...]
> Who can tell me, thanks a lot.
>
you should post to discuss at openvswitch.org
Hi Andrey,
The main goal of this new functions is to calculate the hash which is equal
to the hash of the NIC.
According to XL710 datasheet table 7-5 for sctp input set consists of
IP4-S, IP4-D, SCTP-Verification-Tag. I don't see any NIC that uses QinQ or
single vlan tag, ip proto number, tunnel i
Hello Neil,
Reviving this old thread.
On Sat, Jan 31, 2015 at 7:35 PM, Neil Horman wrote:
> On Sat, Jan 31, 2015 at 05:55:07PM +0100, David Marchand wrote:
> > On Sat, Jan 31, 2015 at 5:32 PM, Neil Horman
> wrote:
> >
> > > On Sat, Jan 31, 2015 at 05:07:28PM +0100, David Marchand wrote:
> > >
On Thu, May 7, 2015 at 11:23 AM, Bruce Richardson <
bruce.richardson at intel.com> wrote:
> On Thu, May 07, 2015 at 09:19:09AM +0530, Sujith Sankar wrote:
> > This patch adds support for enic in the nic_uio driver so that enic
> could be used on FreeBSD.
> >
> > Signed-off-by: Sujith Sankar
>
> A
Hi Vladimir,
Yes, at the moment NICs support limited input sets for hash calculation, but
why limit SW for the same sets if it can be done in more general way and be
easily scalable for HW updates? Using limited input set for RSS is not a
feature of Toeplitz hash, but limitation of HW. I believ
On Wed, May 06, 2015 at 11:12:28AM +0300, Panu Matilainen wrote:
> Forcing a change of tools and workflows on everybody WILL create ill-will if
> nothing else.
>
> Also please realize that not everybody sees GitHub as the greatest thing
> since sliced bread. It has quite some "Hotel California" a
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Wednesday, May 06, 2015 5:11 PM
> To: De Lara Guarch, Pablo; dev at dpdk.org
> Subject: RE: [dpdk-dev] [PATCH v3 3/6] hash: update jhash function with the
> latest available
>
> Hi Pablo,
>
> > -Original Message-
> > From
On Thu, May 07, 2015 at 09:19:09AM +0530, Sujith Sankar wrote:
> This patch adds support for enic in the nic_uio driver so that enic could be
> used on FreeBSD.
>
> Signed-off-by: Sujith Sankar
Acked-by: Bruce Richardson
> ---
> lib/librte_eal/bsdapp/nic_uio/nic_uio.c | 1 +
> lib/l
It wouldn't check the configured maximum packet length, and then
the scattered receiving function wouldn't be selected at all even
if it wants to receive a jumbo frame. The fix is to select the
correct RX function according to the configurations.
Signed-off-by: Helin Zhang
---
lib/librte_pmd_i40
> -Original Message-
> From: Olivier MATZ [mailto:olivier.matz at 6wind.com]
> Sent: Thursday, May 07, 2015 8:32 AM
> To: Xu, HuilongX; Zoltan Kiss; Ananyev, Konstantin; dev at dpdk.org
> Cc: Cao, Waterman; Cao, Min; Zhang, Helin
> Subject: Re: [dpdk-dev] [PATCH v6 00/13] mbuf: enhancemen
On Thu, May 07, 2015 at 01:06:02PM +0200, David Marchand wrote:
> Hello Neil,
>
> Reviving this old thread.
>
> On Sat, Jan 31, 2015 at 7:35 PM, Neil Horman wrote:
>
> > On Sat, Jan 31, 2015 at 05:55:07PM +0100, David Marchand wrote:
> > > On Sat, Jan 31, 2015 at 5:32 PM, Neil Horman
> > wrote
Hi Huilong,
On 05/07/2015 03:57 AM, Xu, HuilongX wrote:
> Hi Olivier,
> Today I find a compile error, when I test ip fragment on dpdk.org. would you
> check this? thanks a lot.
> My dpdk.org commit: a6d71fa7146cc04320c2485d6dde44c1d888d652
> The compile error as below:
> CC main.o
> /root/dpdk/e
This patch adds support for enic in the nic_uio driver so that enic could be
used on FreeBSD.
Signed-off-by: Sujith Sankar
---
lib/librte_eal/bsdapp/nic_uio/nic_uio.c | 1 +
lib/librte_eal/common/include/rte_pci_dev_ids.h | 17 +
2 files changed, 18 insertions(+)
diff
Hi,
Below are the seps that I followed to get DPDK with OVS. Some of the
paths need to be changed to your env..
#12 Test Switching using OpenVSwitch with DPDK **
#--- Setup the ifaces as dpdk..
cd /home/vnspteam01/dpdk-1.7.1
cd /home/vnspteam01/dpdk-1.8.0
sudo modprobe uio
sudo modprob
On 4/3/2015 1:02 AM, Pavel Boldin wrote:
> Move ioctl `EVENTFD_COPY' handler code to an inline function.
Pavel:
There is no necessity to inline this function.
/huawei
On 4/16/2015 7:48 PM, Pavel Boldin wrote:
> Replace copy-pasted `fget_from_files' -> `filp_close' with
> a `sys_close' call.
>
> Signed-off-by: Pavel Boldin
> ---
> lib/librte_vhost/eventfd_link/eventfd_link.c | 49
> +++-
> 1 file changed, 12 insertions(+), 37 deletions(
On Wed, May 06, 2015 at 02:37:06PM -0700, Stephen Hemminger wrote:
> From: Stephen Hemminger
>
> Some drivers need ability to access PCI config (for example for power
> management). This adds an abstraction to do this; only implemented
> on Linux, but should be possible on BSD.
>
You didn't test
On 06/05/15 9:19 pm, "Bruce Richardson" wrote:
>On Wed, May 06, 2015 at 02:41:00PM +0530, Sujith Sankar wrote:
>> This patch adds the changes required to build enic for FreeBSD
>>
>
>Hi,
>
>I see no issues with this patch, but I suggest the description for it
>should
>be changed. There is no a
I did not finish a thought for some reason.
On 5/6/15, 4:49 PM, "Wiles, Keith" wrote:
>Hi Thomas, (sorry about the length)
>
>On 5/6/15, 2:37 PM, "Marc Sune" wrote:
>
>>
>>
>>On 06/05/15 23:09, Thomas Monjalon wrote:
>>> Hello everyone,
>>>
>>> I'm back from mini-holidays and it's good to see t
Hi Olivier,
Today I find a compile error, when I test ip fragment on dpdk.org. would you
check this? thanks a lot.
My dpdk.org commit: a6d71fa7146cc04320c2485d6dde44c1d888d652
The compile error as below:
CC main.o
/root/dpdk/examples/ip_fragmentation/main.c: In function 'init_mem':
/root/dpdk/exa
Tested-by: Min Cao
Patch name: [PATCH v2 00/33] i40e base driver update
Test Flag: Tested-by
Tester name:min.cao at intel.com
Result summary: total 66 cases, 54passed, 12 failed
Test Case 1:
Name: ipfrag
63 matches
Mail list logo
