As we know, hot plug is an importance feature whenever it use for the
datacenter device's
fail-safe and consumption management , or use for the dynamic deployment and
SRIOV
Live Migration in SDN/NFV, it could be bring the higher flexibility and
continuality of the
networking services in multipl
Hi Yongseok
From: Yongseok Koh
> On Wed, May 23, 2018 at 04:45:33AM -0700, Matan Azrad wrote:
> >
> > Hi Yongseok
> > + Steven
> >
> > From: Yongseok Koh
> > > On Tue, May 22, 2018 at 10:36:43PM -0700, Matan Azrad wrote:
> > > > Hi Yongseok
> > > >
> > > > From: Yongseok Koh
> > > > > +#ifdef H
If the NIC has a queue number larger than 128, then we need to change
the ``MAX_QUEUES`` to a larger number to make sure we allocate a big
enough memory pool for device setup.
Signed-off-by: Xiao Wang
---
doc/guides/sample_app_ug/vhost.rst | 10 ++
1 file changed, 10 insertions(+)
diff
> On May 23, 2018, at 10:28 PM, Shahaf Shuler wrote:
>
> On some distros, the inbox rdma-core tree can contain the Software
> Parser enum while the remaining structs still missing.
>
> Fixes: 5f8ba81c4228 ("net/mlx5: support generic tunnel offloading")
> Cc: xuemi...@mellanox.com
>
> Signed-of
Wednesday, May 23, 2018 2:27 PM, Yongseok Koh:
> Cc: dev@dpdk.org; Yongseok Koh
> Subject: [PATCH] net/mlx5: fix SW parser offset
>
> Fixes: 8589e944d075 ("net/mlx5: fix setting offsets for SW parser")
>
> Signed-off-by: Yongseok Koh
> ---
> drivers/net/mlx5/mlx5_rxtx.h | 5 ++---
> 1 file cha
https://dpdk.org/tracker/show_bug.cgi?id=51
Bug ID: 51
Summary: make coverage aborts with core dump
Product: DPDK
Version: 18.02
Hardware: x86
OS: Linux
Status: CONFIRMED
Severity: normal
Priorit
For virtio-user server mode, One use case comes across segmentation fault.
step 1: Launch vhost side as client firstly.
step 2: launch virtio-user side as server.
The cause is: after registering virtio_interrupt_handler into
eal-intr-thread, two threads (main thread and eal-intr-thread) have
sync
On some distros, the inbox rdma-core tree can contain the Software
Parser enum while the remaining structs still missing.
Fixes: 5f8ba81c4228 ("net/mlx5: support generic tunnel offloading")
Cc: xuemi...@mellanox.com
Signed-off-by: Shahaf Shuler
---
On v2:
- Check only for struct mlx5dv_sw_pars
*** gcc cross compile dpdk, including a fix and a doc ***
Gavin Hu (2):
mk: fix cross build errors
doc: add a guide doc for cross compiling from x86
buildtools/pmdinfogen/Makefile | 2 +-
doc/cross_compiling_sdk.txt | 58
mk/toolchain/
Signed-off-by: Gavin Hu
Reviewed-by: Steve Capper
Reviewed-by: Honnappa Nagarahalli
---
doc/cross_compiling_sdk.txt | 58 +
1 file changed, 58 insertions(+)
create mode 100644 doc/cross_compiling_sdk.txt
diff --git a/doc/cross_compiling_sdk.txt b/do
The "-Wimplicit-fallthrough=2" option was introduced into gcc 7.0, it was
enabled when the cross compiler gcc is greater than 7.0, but for the host
side buildtools/pmdinfogen, if the native is older than 7.0, it should not
be enabled.
The fix is to differentiate the host gcc Werror options from th
Thanks for the review.
I added a comment to explain why lldp is disabled in the code, and sent the v2
patch.
Thanks,
Zijie
-- Original --
From: "Zhang, Qi Z";
Date: Tue, May 22, 2018 09:00 PM
To: "Zijie Pan"; "dev@dpdk.org";
Cc: "Xing, Beilei"; "Laurent
H
Add a new API rte_pmd_i40e_set_lldp_cmd to control LLDP agent for i40e.
It supports the following i40e debug lldp commands:
- start/stop of the LLDP agent.
- get local/remote of the LLDP MIB (Management Information Base).
Signed-off-by: Laurent Hardy
Signed-off-by: Zijie Pan
Acked-by: Qi
Hi Koh,
> -Original Message-
> From: Yongseok Koh
> Sent: Thursday, May 24, 2018 2:34 AM
> To: Matan Azrad
> Cc: Shahaf Shuler ; Adrien Mazarguil
> ; Nélio
> Laranjeiro ; dev@dpdk.org; sta...@dpdk.org;
> Xueming(Steven) Li
>
> Subject: Re: [dpdk-dev] [PATCH] net/mlx5: fix GRE flow rule
On Wed, May 23, 2018 at 02:59:37PM +0300, Shahaf Shuler wrote:
> On some distros, the inbox rdma-core tree can contain the Software
> Parser enum while the remaining structs still missing.
>
> Fixes: 5f8ba81c4228 ("net/mlx5: support generic tunnel offloading")
> Cc: xuemi...@mellanox.com
>
> Sign
Hi Thomas,
This patchset depends on https://dpdk.org/dev/patchwork/patch/40361/
Thanks!
-Rasesh
> From: Mody, Rasesh
> Sent: Wednesday, May 23, 2018 1:57 PM
>
> Signed-off-by: Rasesh Mody
> ---
> drivers/net/qede/LICENSE.qede_pmd |2 +-
> drivers/net/qede/Makefile
Signed-off-by: Rasesh Mody
---
drivers/net/bnx2x/LICENSE.bnx2x_pmd |2 +-
drivers/net/bnx2x/Makefile |4 ++--
drivers/net/bnx2x/bnx2x.c |4 ++--
drivers/net/bnx2x/bnx2x.h |4 ++--
drivers/net/bnx2x/bnx2x_ethdev.c|4 ++--
drivers/net/bnx2x/bnx2x
Signed-off-by: Rasesh Mody
---
drivers/net/qede/LICENSE.qede_pmd |2 +-
drivers/net/qede/Makefile |4 ++--
drivers/net/qede/base/bcm_osal.c |4 ++--
drivers/net/qede/base/bcm_osal.h |4 ++--
drivers/net/qede/base/common_hsi
Hi all,
Are there any caveats with the usage of RTE_ETH_FOREACH_DEV? I have 4
interfaces bound to the igb_uio driver, but the macro seems to never
enumerate over any of them.
On another note, trying to manually specify a whitelist of devices to use
as a command line option always yields a message
Hi,
I followed the hyper-v support thread on this board, but
I haven't seen any release notes for hyper-v yet.
Questions:
Was hyper-v support released as planned ?
If so, in what release ?
If not, what release of DPDK will support it ?
and last,
What kernel version is required ?
Thank you so much
From: Shahed Shaikh
In 100G mode, we poll firmware slow path completion for every 1 second,
which is not enough and may result in completion timeout if
driver misses that window.
Patch "eal: set affinity for control threads" exposed this issue since
alarm callback runs in control thread context.
Create compression PMD for Intel QuickAssist devices
Currently only the C62x device is supported.
The qat comp PMD supports
- stateless compression and
decompression using the deflate algorithm.
- checksum generation: Adler32, CRC32 and combined.
The compression service is hosted on a QuickA
On Wed, May 23, 2018 at 04:45:33AM -0700, Matan Azrad wrote:
>
> Hi Yongseok
> + Steven
>
> From: Yongseok Koh
> > On Tue, May 22, 2018 at 10:36:43PM -0700, Matan Azrad wrote:
> > > Hi Yongseok
> > >
> > > From: Yongseok Koh
> > > > Creating a flow having pattern from the middle of a packet i
Report current configured link auto-negotiation. Also initialize
rte_eth_link.
Coverity issue: 280648
Fixes: f5b3c7b29357 ("net/cxgbevf: fix inter-VM traffic when physical link
down")
Signed-off-by: Rahul Lakkireddy
---
drivers/net/cxgbe/cxgbe_ethdev.c | 3 ++-
1 file changed, 2 insertions(+),
Remove reference to deprecated ethdev offload parameter from liquidio
documentation.
Fixes: dd6aab16711c ("net/liquidio: move to new offload API")
Signed-off-by: Shijith Thotton
---
doc/guides/nics/liquidio.rst | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/doc/guides/ni
Hi Ferruh,
> From: Ferruh Yigit [mailto:ferruh.yi...@intel.com]
> Sent: Wednesday, May 23, 2018 8:48 AM
>
> On 5/23/2018 12:16 AM, Rasesh Mody wrote:
> > This patch fixes VF MTU update to work without having to restart the
> > vport and there by not requiring port re-configuration. It adds a VF
>
On Wed, May 23, 2018 at 4:57 PM, Ferruh Yigit
wrote:
> On 5/23/2018 1:28 PM, Alejandro Lucero wrote:
> > DPDK apps can be executed as non-root users but current NFP lock
> > file for avoiding concurrent accesses to CPP interface is precluding
> > this option or requires to modify system file perm
On 5/23/2018 1:28 PM, Alejandro Lucero wrote:
> DPDK apps can be executed as non-root users but current NFP lock
> file for avoiding concurrent accesses to CPP interface is precluding
> this option or requires to modify system file permissions.
>
> When the NFP device is bound to VFIO, this driver
This expands the ISA-L documentation to give more a detailed explanation
of the mapping between the compressdev API levels and PMD levels.
Signed-off-by: Lee Daly
---
doc/guides/compressdevs/isal.rst | 63 +++-
1 file changed, 55 insertions(+), 8 deletions(-)
On 5/23/2018 11:14 AM, Alejandro Lucero wrote:
> This was missed in a previous patch for using new offload API.
>
> It turns out the line can be removed because that internal PMD
> crc_len data is not being used.
>
> Fixes: a922c6a789ff ("net/nfp: support new HW offloads API")
>
> Signed-off-by:
On 5/23/2018 8:46 AM, Beilei Xing wrote:
> Cppcheck reports following error,
> (error) Shifting 32-bit value by 36 bits is undefined behaviour
>
> According to datasheet, there's PHY type and PHY type extension
> in setting PHY config command, should exclude PHY type extension
> when setting PHY t
On 5/23/2018 12:16 AM, Rasesh Mody wrote:
> This patch fixes VF MTU update to work without having to restart the
> vport and there by not requiring port re-configuration. It adds a
> VF MTU Update TLV to achieve the same. Firmware can handle VF MTU update
> by just pausing the vport.
>
> Fixes: dd
> Added known issue of rte_abort taking a long time on FreeBSD due to recent
> memory subsystem rework.
>
> Signed-off-by: Reshma Pattan
> Acked-by: Anatoly Burakov
> ---
> v2: reworded.
> ---
> doc/guides/rel_notes/release_18_05.rst | 15 +++
> 1 file changed, 15 insertions(+)
>
<
DPDK apps can be executed as non-root users but current NFP lock
file for avoiding concurrent accesses to CPP interface is precluding
this option or requires to modify system file permissions.
When the NFP device is bound to VFIO, this driver does not allow this
concurrent access, so the lock file
On some distros, the inbox rdma-core tree can contain the Software
Parser enum while the remaining structs still missing.
Fixes: 5f8ba81c4228 ("net/mlx5: support generic tunnel offloading")
Cc: xuemi...@mellanox.com
Signed-off-by: Shahaf Shuler
---
drivers/net/mlx5/Makefile | 7 ++-
drivers
23/05/2018 13:37, Yang, Zhiyong:
> From: Yang, Zhiyong
> >
> > Hi Thomas,
> >
> > From: Thomas Monjalon [mailto:tho...@monjalon.net]
> > > 22/05/2018 20:38, Ferruh Yigit:
> > > > On 5/22/2018 2:12 PM, Thomas Monjalon wrote:
> > > > > Any update to improve this workaround?
> > > > >
> > > > > 21/0
Signed-off-by: Raslan Darawsheh
---
doc/guides/rel_notes/release_18_05.rst | 151 +
1 file changed, 151 insertions(+)
diff --git a/doc/guides/rel_notes/release_18_05.rst
b/doc/guides/rel_notes/release_18_05.rst
index cc4b77f..2f5bab4 100644
--- a/doc/guides/rel_n
Hi Yongseok
+ Steven
From: Yongseok Koh
> On Tue, May 22, 2018 at 10:36:43PM -0700, Matan Azrad wrote:
> > Hi Yongseok
> >
> > From: Yongseok Koh
> > > Creating a flow having pattern from the middle of a packet is
> > > allowed. For example,
> > >
> > > testpmd> flow create 0 ingress patter
Makefiles are updated with new test case lists.
Test cases are classified as -
P1 - Main test cases,
P2 - Cryptodev/driver test cases,
P3 - Perf test cases which takes longer than 10s,
P4 - Logging/Dump test cases.
Makefile is updated with different targets
for the above classified groups.
Test ca
Update test command line with no additional arguments,
as FreeBSD doesn't support socket-mem, file-prefix options
Signed-off-by: Jananee Parthasarathy
Reviewed-by: Reshma Pattan
Reviewed-by: Anatoly Burakov
---
test/test/autotest_runner.py | 8 +++-
1 file changed, 7 insertions(+), 1 delet
Fixed in autotest_test_funcs.py to handle test cases
which returns "Skipped" as result.
The issue was skipped test cases got timed out,
causing delay in autotests execution.
Signed-off-by: Jananee Parthasarathy
Reviewed-by: Reshma Pattan
Reviewed-by: Anatoly Burakov
---
test/test/autotest_test
Autotest config is enhanced with additional test cases
being added to autotest_data.py
Signed-off-by: Jananee Parthasarathy
Reviewed-by: Reshma Pattan
Reviewed-by: Anatoly Burakov
---
test/test/autotest_data.py | 471 -
1 file changed, 462 insertions
1/4: new test cases are added to autotest config
2/4: skipped test case result is updated appropriately
3/4: test cmdline is updated to support freebsd
4/4: added make targets for group of testcases
---
v4: classify testcases based on priority and run with different targets
---
Jananee Parthasara
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Yang, Zhiyong
> Sent: Wednesday, May 23, 2018 9:52 AM
> To: Thomas Monjalon ; Yigit, Ferruh
>
> Cc: dev@dpdk.org; Matan Azrad ; Iremonger, Bernard
> ; Yao, Lei A ;
> maxime.coque...@redhat.com; Bie, Tiwei ;
> sta
Fixes: 8589e944d075 ("net/mlx5: fix setting offsets for SW parser")
Signed-off-by: Yongseok Koh
---
drivers/net/mlx5/mlx5_rxtx.h | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/net/mlx5/mlx5_rxtx.h b/drivers/net/mlx5/mlx5_rxtx.h
index d65cd1be8..f53bb43c3 100644
DPDK apps can be executed as non-root users but current NFP lock
file for avoiding concurrent accesses to CPP interface is precluding
this option or requires to modify system file permissions.
When the NFP device is bound to VFIO, this driver does not allow this
concurrent access, so the lock file
This was missed in a previous patch for using new offload API.
It turns out the line can be removed because that internal PMD
crc_len data is not being used.
Fixes: a922c6a789ff ("net/nfp: support new HW offloads API")
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_net.c | 2 --
1 fil
23/05/2018 12:09, Ferruh Yigit:
> On 5/11/2018 12:58 AM, Thomas Monjalon wrote:
> > A new hook function is added and called inside the PMDs at the end
> > of the device probing:
> > - in primary process, after allocating, init and config
> > - in secondary process, after attaching and local
On 5/11/2018 12:58 AM, Thomas Monjalon wrote:
> A new hook function is added and called inside the PMDs at the end
> of the device probing:
> - in primary process, after allocating, init and config
> - in secondary process, after attaching and local init
>
> This new function is almost
ETH APIs dev_attach and dev_dettach can be exercised from primary
process only. Secondary process only maps the resource and does
not have access to internal device list. Hence updating documentation
to reflect the same.
Signed-off-by: Vipin Varghese
---
lib/librte_ethdev/rte_ethdev.h | 6 ++
On Tue, May 22, 2018 at 10:36:43PM -0700, Matan Azrad wrote:
> Hi Yongseok
>
> From: Yongseok Koh
> > Creating a flow having pattern from the middle of a packet is allowed. For
> > example,
> >
> > testpmd> flow create 0 ingress pattern vxlan vni is 20 / end actions ...
> >
> > Device can par
Currently when resetting bond mac address, we are getting the
persisted mac address from slave info considering primary port
as index. But we need to compare the port id from slave info
with the primary port to get the primary slave index and get
the persisted mac address. Without this fix, persist
On 5/23/2018 1:16 AM, Yao chuhong wrote:
> hi, Ferruh & Shijith
>
> Sorry, I can't reply the email in time, because it was late at night.
Hi Chuhong,
I was aware it is late for you so I updated the commit log for you.
> I read your email, Will use commit log suggested by Shijith and the patch
>
Add tested Intel platforms with Intel NICs to the release note.
Signed-off-by: Yulong Pei
---
doc/guides/rel_notes/release_18_05.rst | 74 ++
1 file changed, 74 insertions(+)
diff --git a/doc/guides/rel_notes/release_18_05.rst
b/doc/guides/rel_notes/release_18_0
On 22-May-18 9:38 PM, Thomas Monjalon wrote:
22/05/2018 18:35, Anatoly Burakov:
When using --no-shconf option, the expectation is that no multiprocess
will be supported as no shared files are created. However, fbarray
still creates some shared files that prevent multiple processes with
the same
Hi Ferruh,
I have checked the patch done. I am ok with the same.
Thanks
Vipin Varghese
> -Original Message-
> From: Yigit, Ferruh
> Sent: Wednesday, May 23, 2018 1:41 PM
> To: Wiles, Keith ; Varghese, Vipin
>
> Cc: DPDK ; ophi...@mellanox.com; tho...@monjalon.net;
> ol...@mellanox.com
>
On 5/23/2018 5:48 AM, Wiles, Keith wrote:
>
>
>> On May 22, 2018, at 11:44 PM, Varghese, Vipin
>> wrote:
>>
>> The TX function is shared between TAP and TUN PMD. Checking TUN-TAP
>> type field will ensure the TAP PMD will always have protocol field
>> as 0.
>>
>> Signed-off-by: Vipin Varghese
Cppcheck reports following error,
(error) Shifting 32-bit value by 36 bits is undefined behaviour
According to datasheet, there's PHY type and PHY type extension
in setting PHY config command, should exclude PHY type extension
when setting PHY type.
Fixes: 1bb8f661168d ("net/i40e: fix link down a
Le 23/05/2018 à 07:52, Wang, Qihua (NSB - CN/Hangzhou) a écrit :
Hi DPDK expert,
I am Nokia engineer. We are upgrading 6wind from 6wind 4.13->4.17, with DPDK
upgrading from 16.04->17.05. We use AVP PMD driver.
From the performance test result, the CPU load of RX core increase from 72% to
94% u
59 matches
Mail list logo
