[dpdk-dev] [PATCH v2] net/ice: fix data path corrupt on secondary process

The rte_eth_devices array is not in share memory, it should not be referenced by ice_adapter which is shared by primary and secondary. Any process set ice_adapter->eth_dev will corrupt another process' context. The patch removed the field "eth_dev" from ice_adapter. Now, when the data paths try to

[dpdk-dev] [PATCH] net/ice: fix data path corrupt on secondary process

The rte_eth_devices array is not in share memory, it should not be referenced by ice_adapter which is shared by primary and secondary. Any process set ice_adapter->eth_dev will corrupt another process's context, this happens when a secondary vector path try to use below chain to get offload configu

[dpdk-dev] DTS Workgroup: MoM 05/19/2021

Attendees: Aaron Conole Honnappa Nagarahalli Thomas Monjalon Lijuan Tu Juraj Linkes Lincoln Lavoie The meeting announcements are sent to dev@dpdk.org. Minutes: Review action items from 5/12/2021 1) fm10K test cases can be removed. Intel DTS team will have a patch

[dpdk-dev] [PATCH] ixgbe: Add runtime tx/rx queue setup for X550

Hello, Zhang, qi, May I ask a question? I see this patch is delegate to you. It seems some cases are failed in this link, but are i40e cases, can we ignore them? Because seems not related with this patch. Thanks😊 http://patches.dpdk.org/project/dpdk/patch/20210524115329.40525-1-jianyue...@no

Re: [dpdk-dev] [dpdk-users] DPDK issue with Marvell NIC QLogic Corp. FastLinQ QL41000

Yes , I have configured it via grub. Grub: "default_hugepagesz=1G hugepagesz=1G hugepages=2" grub2-mkconfig -o /boot/grub2/grub.cfg Manual: mkdir /dev/hugepages1G mount -t hugetlbfs -o pagesize=1G none /dev/hugepages1G echo 2 > /sys/devices/system/node/node1/hugepages/hugepages-1048576kB/nr_hugep

Re: [dpdk-dev] [dpdk-users] DPDK issue with Marvell NIC QLogic Corp. FastLinQ QL41000

meminfo states: Hugepagesize:1048576 kB But in your initial mail you state Hugepage size is 1G. have you configured HugePage via grub ? Thanks. Regards, NV On Wed, May 26, 2021 at 12:21 AM Truring Team wrote: > Hi Nishant, > > cat /proc/meminfo > 11:59:29.200 §MemTotal: 231016

Re: [dpdk-dev] [dpdk-users] DPDK issue with Marvell NIC QLogic Corp. FastLinQ QL41000

Hi Nishant, cat /proc/meminfo 11:59:29.200 §MemTotal: 23101672 kB 11:59:29.200 §MemFree:15254764 kB 11:59:29.200 §MemAvailable: 19243184 kB 11:59:29.200 §Buffers:6792 kB 11:59:29.201 §Cached: 4084844 kB 11:59:29.201 §SwapCached:0 kB 11:59:29.201 §Ac

Re: [dpdk-dev] [dpdk-users] DPDK issue with Marvell NIC QLogic Corp. FastLinQ QL41000

Can you paste output of /proc/meminfo ? Regards, NV On Tue, May 25, 2021 at 9:52 PM Truring Team wrote: > Hi Team, > > I am trying to run the dpdk test-pmd application (DPDK 20.11 and DPDK > 21.05) with NIC QLogic Corp. FastLinQ QL41000 Series 10/25/40/50GbE > Controller but facing following

[dpdk-dev] [PATCH] net/ice: fix VXLAN flow rule creation error

From: Dapeng Yu In original implementation, error returned when creating VXLAN flow rule with SCTP or TCP as layer 4 protocol of inner segment. There are several root causes for the error: 1. ice_fdir_input_set_hdrs() set ICE_FLOW_SEG_HDR_UDP into protocol header flag of inner segment of VXLAN F

[dpdk-dev] [PATCH] net/vmxnet3: add interrupt support in MSI-X

Add support for MSI-x interrupt vectors to the vmxnet3 driver. This will allow more efficient deployments in cloud environments. By default it will try to allocate 1 vector (0) for link event and one MSI-x vector for each rx queue. To simplify things, it will only be enabled if the number of tx a

[dpdk-dev] DPDK issue with Marvell NIC QLogic Corp. FastLinQ QL41000

Hi Team, I am trying to run the dpdk test-pmd application (DPDK 20.11 and DPDK 21.05) with NIC QLogic Corp. FastLinQ QL41000 Series 10/25/40/50GbE Controller but facing following issues: If someone can look into the following logs and help me figure out the issue? 1. DPDK 20.11 ( Using 1 GB hu

[dpdk-dev] [PATCH] net/mlx5: allow copy from one tag to another

The modify field implementation in mlx5 driver has a check to prevent a copy from a field to the same field. But the level is not taken into account which prevents a copy from different tags. Check the level and allow a copy from one tag to another. Fixes: 641dbe4fb05 ("net/mlx5: support modify fi

Re: [dpdk-dev] [PATCH] app/testpmd: do not use a possibly NULL Pointer

Hi Thierry, > -Original Message- > From: dev On Behalf Of Thierry Herbelot > Sent: Monday, May 24, 2021 5:02 PM > To: dev@dpdk.org > Cc: Thierry Herbelot ; NBU-Contact- > Thomas Monjalon ; sta...@dpdk.org; Ori Kam > > Subject: [dpdk-dev] [PATCH] app/testpmd: do not use a possibly NULL >

Re: [dpdk-dev] [dpdk-ci] [PATCH] test: drop 'alarm_autotest' and 'cycles_autotest' from test suite

Thomas Monjalon writes: > 25/05/2021 02:16, Aaron Conole: >> The tests 'alarm_autotest' and 'cycles_autotest' rely on the underlying >> system having very accurate and precise timing. On systems where the timing >> isn't as rigid, or the load is particularly high, these tests are unreliable >> s

[dpdk-dev] [PATCH v1] doc: add deprecation notice for PIE active queue management changes

Add deprecation note for making changes related to implementation of PIE based active queue management support to DPDK scheduler library. These changes are aligned as suggested in the RFC[1]. https://mails.dpdk.org/archives/dev/2021-May/210067.html Signed-off-by: Liguzinski, WojciechX --- doc/g

[dpdk-dev] [PATCH] doc: add deprecation notice for PIE active queue management changes

Signed-off-by: Liguzinski, WojciechX --- doc/guides/rel_notes/deprecation.rst | 8 1 file changed, 8 insertions(+) diff --git a/doc/guides/rel_notes/deprecation.rst b/doc/guides/rel_notes/deprecation.rst index 9584d6bfd7..58f22a0276 100644 --- a/doc/guides/rel_notes/deprecation.rst +++

[dpdk-dev] Minutes of Technical Board Meeting, 2021-05-19

Minutes of Technical Board Meeting, 2021-05-19 == Members Attending - - Aaron - Bruce - Ferruh - Hemant - Honnappa - Jerin - Kevin - Konstantin - Maxime - Olivier (chair) - Thomas NOTE: The technical board meetings every second Wednesda

[dpdk-dev] [PATCH] fix Marvell maintainer email for atlantic

Fixing ex-Aquantia email - it is now part of Marvell. Removing Pavel Belous email - he is not in company now. Also adding Marvell company prefix to the driver names for both atlantic and qede, to eliminate any confusion. Qlogic is still actively used as a well known marketing name for the device

Re: [dpdk-dev] [RFC] Add selection between vector and scalar mode in ixgbe

On Tue, May 25, 2021 at 11:58:18AM +0500, Muhammad Ahmad wrote: > > The selection between scalar mode and vector mode was removed for > ixgbe driver in DPDK 20.02. The code base still has code > for scalar mode but it cannot be selected at compile time. The > vector mode is adequate for applicatio

Re: [dpdk-dev] rte_memcpy - fence and stream

On Mon, May 24, 2021 at 11:43:24PM +0530, Manish Sharma wrote: > I am looking at the source for rte_memcpy (this is a discussion only for > x86-64) > > For one of the cases, when aligned correctly, it uses > > /** > * Copy 64 bytes from one location to another, > * locations should not overlap.

Re: [dpdk-dev] [RFC PATCH 1/3] sched: add pie based congestion management

> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Liguzinski, > WojciechX > Sent: Monday, 24 May 2021 12.58 > > Implement pie based congestion management based on rfc8033 > > Signed-off-by: Liguzinski, WojciechX > --- > drivers/net/softnic/rte_eth_softnic_tm.c | 4 +- > lib/sched/meson.b

Re: [dpdk-dev] [21.08 PATCH v1 1/2] power: invert the monitor check

> -Original Message- > From: dev On Behalf Of Anatoly Burakov > Sent: Tuesday, May 11, 2021 11:32 PM > To: dev@dpdk.org; McDaniel, Timothy ; Xing, > Beilei ; Wu, Jingjing ; Yang, > Qiming ; Zhang, Qi Z ; > Wang, Haiyue ; Matan Azrad > ; Shahaf Shuler ; Viacheslav > Ovsiienko ; Richardso

Re: [dpdk-dev] [RFC PATCH 0/3] Add PIE support for HQoS library

> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Liguzinski, > WojciechX > Sent: Monday, 24 May 2021 12.58 > > DPDK sched library is equipped with mechanism that secures it from the > bufferbloat problem > which is a situation when excess buffers in the network cause high > latency and laten

[dpdk-dev] [PATCH v2] config/arm: add Qualcomm Centriq 2400 part number

0xc00 is for "SoC 2.0" Qualcom Centriq servers. 0x800 is for "SoC 1.1". Cc: Jerin Jacob Cc: Ruifeng Wang Cc: Honnappa Nagarahalli Cc: Juraj Linkeš Signed-off-by: Thierry Herbelot -- V2: add maintainers as Cc --- config/arm/meson.build | 1 + 1 file changed, 1 insertion(+) diff --git a/conf

Re: [dpdk-dev] [PATCH] config/arm: add Qualcomm Centriq 2400 part number

25/05/2021 10:16, Thierry Herbelot: > 0xc00 is for "SoC 2.0" Qualcom Centriq servers. > 0x800 is for "SoC 1.1". > > Signed-off-by: Thierry Herbelot Please Cc those who were involved in previous Qualcomm patch, and especially Arm maintainers.

[dpdk-dev] [PATCH] config/arm: add Qualcomm Centriq 2400 part number

0xc00 is for "SoC 2.0" Qualcom Centriq servers. 0x800 is for "SoC 1.1". Signed-off-by: Thierry Herbelot --- config/arm/meson.build | 1 + 1 file changed, 1 insertion(+) diff --git a/config/arm/meson.build b/config/arm/meson.build index e83a56e0d589..971a050efd93 100644 --- a/config/arm/meson.bu

Re: [dpdk-dev] [dpdk-ci] [PATCH] test: drop 'alarm_autotest' and 'cycles_autotest' from test suite

25/05/2021 02:16, Aaron Conole: > The tests 'alarm_autotest' and 'cycles_autotest' rely on the underlying > system having very accurate and precise timing. On systems where the timing > isn't as rigid, or the load is particularly high, these tests are unreliable > since the wake latency from the s

[dpdk-dev] [Bug 720] clang add -Db_sanitize=address compilation option compilation failed

https://bugs.dpdk.org/show_bug.cgi?id=720 Bug ID: 720 Summary: clang add -Db_sanitize=address compilation option compilation failed Product: DPDK Version: unspecified Hardware: x86 OS: Linux Stat