On Tue, Jun 05, 2018 at 09:36:32PM +, Yongseok Koh wrote:
> > On Jun 4, 2018, at 11:52 PM, Nélio Laranjeiro
> > wrote:
> >
> > On Mon, Jun 04, 2018 at 10:37:31AM -0700, Yongseok Koh wrote:
> >> rte_errno should be saved only if error has occurred because rte_errno
> >> could have garbage val
Now that the 18.05 release is complete, we need to update the roadmap for
18.08. The features that we plan to contribute are below. We'll submit a patch
to update the roadmap page with this info.
Power Management: Turbo Core Thread Pinning - An API will be created to
distinguish between regula
> -Original Message-
> From: Yigit, Ferruh
> Sent: Tuesday, June 5, 2018 2:44 PM
> To: Mcnamara, John ; Kovacevic, Marko
>
> Cc: dev@dpdk.org; Yigit, Ferruh ; Thomas Monjalon
> ; Shreyansh Jain
> Subject: [PATCH v2] doc: add suggested new feature order to release notes
>
> Signed-off-
New API added, rte_power_get_capabilities(), that allows the
application to query the power and performance capabilities
of the CPU cores.
Signed-off-by: Radu Nicolau
---
lib/librte_power/power_acpi_cpufreq.c | 21 +
lib/librte_power/power_acpi_cpufreq.h | 17 ++
li
Added high/regular performance core pinning configuration options
that can be used in place of the existing 'config' option.
'--high-perf-cores CORELIST' option allow the user to specify a high performance
cores list; if this option is not used and the 'perf-config' option is used, the
application
On 06/06/2018 12:03 AM, Rasesh Mody wrote:
> Fix fast path array index which is used for passing L2 handles to RSS
> indirection table, properly distribute rxq handles for indirection table.
> Currently, it is using the local copy of indirection table. When the RX
> queue configuration changes the
Hi Ferruh,
2018-06-05 18:42 GMT+02:00 Ferruh Yigit :
>
> On 6/4/2018 1:09 PM, Michal Krawczyk wrote:
> > The ENA driver was updated with the new features and few fixes and minor
> > changes are introduced.
> > First of all, the communication layer which is delivered by vendor was
> > updated - the
Hi Chas.
Thank you for the review.
>This is fine but you are missing one bit. If a slave is added after you can
>configured the MAC
>addresses, you will need to replay the configured MAC addresses into that
>slave.
Yeah, I've missed that part about adding a slave when a bond is already workin
For ESP transport and BYPASS mode the app might generate output
packets with invalid IPv4 header checksum.
At least such behavior was observed on few Intel NICs.
The reason is that the app didn't set ipv4 header checksum to zero
before passing it to the HW.
Fixes: 906257e965b7 ("examples/ipsec-sec
On Tue, May 29, 2018 at 6:48 PM, Ophir Munk wrote:
> Hi Sameeh,
>
> RSS ebpf source code compilation is planned for dpdk next releases.
>
>
>
> In order to compile the current tap_bpf_program.c code you will need
> definitions found in iproute2:
>
>
>
> https://git.kernel.org/pub/scm/network/ipro
From: "Charles (Chas) Williams"
When the bond PMD is stopped, the active slave count is reset.
For 802.3ad mode this potentially leaks memory and clears state since
a second sequential activate_slave() will occur when the bond PMD is
restarted and the LSC callback is triggered while the active sl
Having Rx mergeable buffers feature enabled should not be
a reason to not use Tx simple path.
Signed-off-by: Maxime Coquelin
---
drivers/net/virtio/virtio_ethdev.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/virtio/virtio_ethdev.c
b/drivers/net/virtio/virtio_ethdev.c
index bd
This series addresses a problem seen when running benchmars,
where we see a big difference in Tx performance depending on
whether Rx mergeable is enabled or not.
With patch 1, Tx simple path is selected even when Rx-mrg is
negotiated.
Digging a bit further, I found that Tx simple path could be
sel
Simple Tx path is not compliant with the Virtio specification,
as it assumes the device will use the descriptors in order.
VIRTIO_F_IN_ORDER feature has been introduced recently, but the
simple Tx path is not compliant with it as VIRTIO_F_IN_ORDER
requires that chained descriptors are used sequent
Instead of checking the multiple Virtio features bits for
every packet, let's do the check once at configure time and
store it in virtio_hw struct.
Signed-off-by: Maxime Coquelin
---
drivers/net/virtio/virtio_ethdev.c | 19 +++
drivers/net/virtio/virtio_pci.h| 3 +++
drivers
This patch improves the Tx path selection depending on
whether the application request for offloads, and on whether
offload features have been negotiated.
When the application doesn't request for Tx offload features,
the corresponding features bits aren't negotiated.
When Tx offload virtio featur
Signed-off-by: Maxime Coquelin
---
drivers/net/virtio/virtio_ethdev.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/net/virtio/virtio_ethdev.c
b/drivers/net/virtio/virtio_ethdev.c
index b023ec02e..357968fdd 100644
--- a/drivers/net/virtio/virtio_ethdev.c
+++ b/dr
+Tech-board as I think that this should have more input at the design stage
ahead of any code patches being pushed.
On Mon, Jun 04, 2018 at 09:56:10AM +0800, Guo, Jia wrote:
> hi,bruce
>
>
> On 5/29/2018 7:20 PM, Bruce Richardson wrote:
> > On Thu, May 24, 2018 at 07:55:43AM +0100, Guo, Jia wrot
> -Original Message-
> From: Richardson, Bruce
> Sent: Wednesday, June 6, 2018 1:55 PM
> To: Guo, Jia ; techbo...@dpdk.org
> Cc: dev@dpdk.org; Ananyev, Konstantin ;
> step...@networkplumber.org; Yigit, Ferruh
> ; gaetan.ri...@6wind.com; Wu, Jingjing
> ; tho...@monjalon.net;
> mo...@mell
On 6/6/2018 7:19 AM, Shreyansh Jain wrote:
> On 6/5/2018 6:58 PM, Ferruh Yigit wrote:
>> On 6/5/2018 1:36 PM, Shreyansh Jain wrote:
>>> Hello Ferruh,
>>>
-Original Message-
From: Ferruh Yigit [mailto:ferruh.yi...@intel.com]
Sent: Tuesday, June 5, 2018 2:34 PM
To: Thomas
On 6/6/2018 1:04 PM, Konstantin Ananyev wrote:
For ESP transport and BYPASS mode the app might generate output
packets with invalid IPv4 header checksum.
At least such behavior was observed on few Intel NICs.
The reason is that the app didn't set ipv4 header checksum to zero
before passing it t
Some Makefiles are using CONFIG_RTE_EXEC_ENV and others
are using CONFIG_RTE_EXEC_ENV_LINUXAPP.
Use the latter one for consistency.
We could remove CONFIG_RTE_EXEC_ENV later if considered useless.
Signed-off-by: Thomas Monjalon
---
examples/ethtool/Makefile | 2 +
Hi Chas
From: Chas Williams
> From: "Charles (Chas) Williams"
>
> When the bond PMD is stopped, the active slave count is reset.
> For 802.3ad mode this potentially leaks memory and clears state since a second
> sequential activate_slave() will occur when the bond PMD is restarted and the
> LSC
06/06/2018 08:56, Thomas Monjalon:
> Patchwork will stop working during approximately one hour
> or hopefully less, today June 6th.
> It will be upgraded to patchwork 2.
>
> Sorry for the inconvenience.
The upgrade to patchwork 2.0.2 is now done:
https://dpdk.org/dev/patchwork/about
Ther
On Wed, Jun 6, 2018 at 9:57 AM, Matan Azrad wrote:
> Hi Chas
>
> From: Chas Williams
> > From: "Charles (Chas) Williams"
> >
> > When the bond PMD is stopped, the active slave count is reset.
> > For 802.3ad mode this potentially leaks memory and clears state since a
> second
> > sequential acti
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Thomas Monjalon
> Sent: Wednesday, June 6, 2018 3:03 PM
> To: dev@dpdk.org
> Cc: c...@dpdk.org; dpdk...@iol.unh.edu; Patrick MacArthur
> ; alia...@mellanox.com
> Subject: Re: [dpdk-dev] [dpdk-ci] maintenance on DPDK
On Wed, Jun 6, 2018 at 7:52 AM, Alex Kiselev wrote:
> Hi Chas.
>
> Thank you for the review.
>
> >This is fine but you are missing one bit. If a slave is added after you
> can configured the MAC
> >addresses, you will need to replay the configured MAC addresses into that
> slave.
>
> Yeah, I've
> -Original Message-
> From: ci [mailto:ci-boun...@dpdk.org]
> Sent: Wednesday, June 6, 2018 4:22 PM
> To: Thomas Monjalon ; dev@dpdk.org
> Cc: c...@dpdk.org; dpdk...@iol.unh.edu; Patrick MacArthur
> ; alia...@mellanox.com
> Subject: Re: [dpdk-ci] [dpdk-dev] maintenance on DPDK patchwork to
On Wed, Jun 06, 2018 at 08:55:01AM +0200, Nélio Laranjeiro wrote:
> On Tue, Jun 05, 2018 at 09:36:32PM +, Yongseok Koh wrote:
> > > On Jun 4, 2018, at 11:52 PM, Nélio Laranjeiro
> > > wrote:
> > >
> > > On Mon, Jun 04, 2018 at 10:37:31AM -0700, Yongseok Koh wrote:
> > >> rte_errno should be
On 6/6/2018 12:03 AM, Rasesh Mody wrote:
> Fix fast path array index which is used for passing L2 handles to RSS
> indirection table, properly distribute rxq handles for indirection table.
> Currently, it is using the local copy of indirection table. When the RX
> queue configuration changes the lo
On 6/6/2018 12:46 PM, Michał Krawczyk wrote:
> Hi Ferruh,
>
> 2018-06-05 18:42 GMT+02:00 Ferruh Yigit :
>>
>> On 6/4/2018 1:09 PM, Michal Krawczyk wrote:
>>> The ENA driver was updated with the new features and few fixes and minor
>>> changes are introduced.
>>> First of all, the communication lay
Add small amount of additional code, use consistent variable names
across code blocks, change the image to represent queues and
CPU cores intuitively. These help improve the eventdev library
documentation.
Signed-off-by: Honnappa Nagarahalli
Reviewed-by: Gavin Hu
Acked-by: Jerin Jacob
Acked-by:
At this point valid data is already set by rte_eth_get_device_info.
device field becomes zero and consumer is not able to retrieve pci data.
Signed-off-by: Damjan Marion
---
drivers/net/i40e/i40e_ethdev_vf.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/i40e/i40e_ethdev_vf.c
b/
The problem is if a dpdk app uses the same iface(s) both as rx_iface and
tx_iface then it will receive back the packets it sends.
If my app sends a packet to portid=X with rte_eth_tx_burst() then I wouldn't
expect to receive it back by rte_eth_rx_burst() for that same portid=X
(assuming of cour
Support rx of in direction packets only
Useful for apps that also tx to eth_pcap ports in order not to see them
echoed back in as rx when out direction is also captured
Signed-off-by: ido goshen
---
v2: clean checkpatch warning
drivers/net/pcap/rte_eth_pcap.c | 36 ++
The CFP for DPDK Summit Userspace (September 5th & 6th in Dublin) is available
now at: https://goo.gl/forms/Jh70MIA7QJE2nSBb2.
The deadline for submissions is Friday July 27th. Submissions should focus on
the key technical challenges facing the project. Suggested topics include:
* New APIs, libr
Call for speakers Open for:
1. June 30th, Bangalore: Packet Processing, Cloud and Edge Next Gen SDN/NFV
Networks - Out of the Box Network Developers meet up
(https://www.meetup.com/Out-of-the-Box-Network-Developers-Bangalore/events/251225679/)
2. June 28th, Taipei: Packet Processing an
For i40evf, internal rx interrupt and adminq interrupt share the same
source, that cause a lot cpu cycles be wasted on interrupt handler
on rx path. This is complained by customers which require low latency
(when set I40E_ITR_INTERVAL to small value), but have to be sufferred by
tremendous interrup
On 6/6/2018 8:54 PM, Bruce Richardson wrote:
+Tech-board as I think that this should have more input at the design stage
ahead of any code patches being pushed.
On Mon, Jun 04, 2018 at 09:56:10AM +0800, Guo, Jia wrote:
hi,bruce
On 5/29/2018 7:20 PM, Bruce Richardson wrote:
On Thu, May 24,
Currently no matter if there's global change, the global
configuration will be always logged. But there's no value
to log the info if the configuration is not changed.
This patch prints only real global changes.
Also, change log level from DEBUG to WARNING.
Signed-off-by: Beilei Xing
---
drivers
The summarized global register change info will be logged
no matter if there's real global register change. Since
only real changes are logged now, there's no need to
summarize global register change info, otherwise will
cause misunderstanding.
Signed-off-by: Beilei Xing
---
drivers/net/i40e/i40
Only real changes should be logged, so only the first
detected change will be logged. Log should be like:
i40e device xx:xx.x changed global register [xxx] original: xxx, new: xxx
Beilei Xing (2):
net/i40e: print real global changes
net/i40e: remove summarized global register change info
dri
On Wed, Jun 06, 2018 at 02:31:28PM +0200, Maxime Coquelin wrote:
> Instead of checking the multiple Virtio features bits for
> every packet, let's do the check once at configure time and
> store it in virtio_hw struct.
>
> Signed-off-by: Maxime Coquelin
> ---
[...]
> @@ -270,8 +261,7 @@ virtqueue
On Wed, Jun 06, 2018 at 02:31:27PM +0200, Maxime Coquelin wrote:
> Signed-off-by: Maxime Coquelin
Reviewed-by: Tiwei Bie
> ---
> drivers/net/virtio/virtio_ethdev.c | 4 +++-
> 1 file changed, 3 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/net/virtio/virtio_ethdev.c
> b/drivers/net/v
On Wed, Jun 06, 2018 at 02:31:26PM +0200, Maxime Coquelin wrote:
[...]
> @@ -1886,6 +1888,15 @@ virtio_dev_configure(struct rte_eth_dev *dev)
> (1ULL << VIRTIO_NET_F_GUEST_TSO4) |
> (1ULL << VIRTIO_NET_F_GUEST_TSO6);
>
> + if (tx_offloads & (DEV_TX_
On Wed, Jun 06, 2018 at 02:31:25PM +0200, Maxime Coquelin wrote:
> Having Rx mergeable buffers feature enabled should not be
> a reason to not use Tx simple path.
>
> Signed-off-by: Maxime Coquelin
> ---
> drivers/net/virtio/virtio_ethdev.c | 1 -
> 1 file changed, 1 deletion(-)
>
> diff --git
The xstats api expects that the driver fills both values and ids for each
filled entries.
Fixes: bfb9c2260be2 ("net/bnxt: support xstats get/reset")
Signed-off-by: David Marchand
---
drivers/net/bnxt/bnxt_stats.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/bnxt/bnxt_stats
On Wed, Jun 06, 2018 at 02:31:24PM +0200, Maxime Coquelin wrote:
[...]
> +
> +static int
> +virtio_dev_args(struct rte_eth_dev *dev)
> +{
> + struct rte_kvargs *kvlist;
> + struct rte_devargs *devargs;
> + const char *valid_args[] = {
> + VIRTIO_SIMPLE_TX_SUPPORT,
> +
> -Original Message-
> From: Li, Xiaoyun
> Sent: Wednesday, June 6, 2018 2:17 PM
> To: Xing, Beilei ; Zhang, Qi Z
> Cc: dev@dpdk.org; Li, Xiaoyun
> Subject: [PATCH] net/i40e: firmware status check
>
> Check the firmware status at init time. If the status is abnormal, alert the
> user
49 matches
Mail list logo
