* Re: DPDK release candidate 25.11-rc1
2025-10-24 14:45 DPDK release candidate 25.11-rc1 Thomas Monjalon
@ 2025-11-06 23:09 ` Riley Fletcher
2025-11-07 9:29 ` Xu, HailinX
1 sibling, 0 replies; 3+ messages in thread
From: Riley Fletcher @ 2025-11-06 23:09 UTC (permalink / raw)
To: Thomas Monjalon, dev
IBM - Power Systems Testing
DPDK v25.11-rc1
* Build CI on Fedora 40, 41, 42 and 43 container images for ppc64le
* Basic PF on Mellanox: No issue found
* Performance: not tested.
* OS:- RHEL 10.0 kernel: 6.12.0-55.9.1.el10_0.ppc64le
with gcc version 14.2.1 20250110 (Red Hat 14.2.1-7)
Systems tested:
- LPARs on IBM Power10 CHRP IBM,9105-22A
NICs:
- Mellanox Technologies MT28800 Family [ConnectX-5 Ex]
- Firmware Version: 16.35.2000
- OFED 25.07-0.9.7
Regards,
Riley Fletcher
On Fri, 2025-10-24 at 16:45 +0200, Thomas Monjalon wrote:
> A new DPDK release candidate is ready for testing:
> https://git.dpdk.org/dpdk/tag/?id=v25.11-rc1
>
> There are 634 new patches in this snapshot.
>
> Release notes:
> https://doc.dpdk.org/guides/rel_notes/release_25_11.html
>
> Highlights of 25.11-rc1:
> - EAL option to remap lcore IDs
> - inter-domain DMA
> - mbuf optimizations
> - mbuf tracking for debug
> - cryptodev PQC ML algorithms
> - ethdev link connector info
> - Huawei SPx hinic3 ethernet driver
> - Nebulamatrix nbl ethernet driver
> - NXP ENETC4 ethernet driver
> - Wangxun Amber-Lite txgbe ethernet driver
>
> Please test and report issues on bugs.dpdk.org.
>
> This -rc1 was supposed to be released 18 days ago,
> so we are late in the schedule, sorry about that.
> We should try to close -rc2 during the first week of November.
> It means we have less than 2 weeks remaining
> for adding new features in the drivers.
> Adding features in libraries after -rc1 would be an exception,
> but it is possible.
>
> Thank you everyone
>
^ permalink raw reply [flat|nested] 3+ messages in thread* RE: DPDK release candidate 25.11-rc1
2025-10-24 14:45 DPDK release candidate 25.11-rc1 Thomas Monjalon
2025-11-06 23:09 ` Riley Fletcher
@ 2025-11-07 9:29 ` Xu, HailinX
1 sibling, 0 replies; 3+ messages in thread
From: Xu, HailinX @ 2025-11-07 9:29 UTC (permalink / raw)
To: Thomas Monjalon, dev; +Cc: Mcnamara, John, Richardson, Bruce, Ferruh Yigit
> -----Original Message-----
> From: Thomas Monjalon <thomas@monjalon.net>
> Sent: Friday, October 24, 2025 10:46 PM
> To: announce@dpdk.org
> Subject: DPDK release candidate 25.11-rc1
>
> A new DPDK release candidate is ready for testing:
> https://git.dpdk.org/dpdk/tag/?id=v25.11-rc1
>
> There are 634 new patches in this snapshot.
>
> Release notes:
> https://doc.dpdk.org/guides/rel_notes/release_25_11.html
>
> Highlights of 25.11-rc1:
> - EAL option to remap lcore IDs
> - inter-domain DMA
> - mbuf optimizations
> - mbuf tracking for debug
> - cryptodev PQC ML algorithms
> - ethdev link connector info
> - Huawei SPx hinic3 ethernet driver
> - Nebulamatrix nbl ethernet driver
> - NXP ENETC4 ethernet driver
> - Wangxun Amber-Lite txgbe ethernet driver
>
> Please test and report issues on bugs.dpdk.org.
>
> This -rc1 was supposed to be released 18 days ago, so we are late in the
> schedule, sorry about that.
> We should try to close -rc2 during the first week of November.
> It means we have less than 2 weeks remaining for adding new features in the
> drivers.
> Adding features in libraries after -rc1 would be an exception, but it is possible.
>
> Thank you everyone
>
Update the test status for Intel part. dpdk25.11-rc1 all validation test done. found 8 new issues.
New issues:
1. vxlan/vxlan_ipv6_checksum_offload: get incorrect checksum value for the inner L4 -> has fix patch
2. cpfl_vf_representor_rte_flow/port_representor_probe_scan: port attach failed -> has fix patch
3. [ice]kernelpf_iavf:test_iavf_dual_vlan_insert: received packet outer vlan is incorrect -> has fix patch
4. virtio_unit_cryptodev_func/test_cryptodev_virtio_autotest: test failed -> Intel dev is under investigating
5. [Crypto][QAT intree]crypto_perf_cryptodev_perf: dpdk-test-crypto-perf is unable to get max_nb_queue_pairs regardless of crypto_scheduler argument -> Intel dev is under investigating
6. setting DCB on the i40e nic causes testpmd to core dump -> Intel dev is under investigating
7. the nic is still sending pause frames when the traffic stops -> Intel dev is under investigating
8. Bug 1795 - checksum_offload/do_not_insert_checksum_on_the_transmit_packet: core dumped occurred when send packets -> Intel dev is under investigating
* Build & CFLAG compile: cover the build test with latest GCC/Clang version on the following OS(all passed)
- Ubuntu25.04/Ubuntu24.04.3
- RHEL9.6/RHEL10
- Fedora42
- FreeBSD14.3
- SUSE15.6
- OpenAnolis8.10
- OpenEuler24.04
- AzureLinux3.0
* Function tests: All test done and found 8 issues.
- ICE-(E810, E825, E830, E2100) PF/VF: test scenarios including basic/RTE_FLOW/TSO/Jumboframe/checksum offload/mac_filter/VLAN/VXLAN/RSS/Switch/Package Management/Flow Director/Advanced Tx/Advanced RSS/ACL/DCF/Flexible Descriptor, etc.
- i40E-(XXV710, X722) PF/VF: test scenarios including basic/RTE_FLOW/TSO/Jumboframe/checksum offload/mac_filter/VLAN/VXLAN/RSS, etc.
- IXGBE-(E610) PF/VF: test scenarios including basic/TSO/Jumboframe/checksum offload/mac_filter/VLAN/VXLAN/RSS, etc.
- IGC-(i226) PF: test scenarios including basic/RTE_FLOW/TSO/Jumboframe/checksum offload/mac_filter/VLAN/VXLAN/RSS, etc.
- IGB-(i350) PF: test scenarios including basic/RTE_FLOW/TSO/Jumboframe/checksum offload/mac_filter/VLAN/VXLAN/RSS, etc.
- IPsec: test scenarios including ipsec/ipsec-gw/ipsec library basic test - QAT&SW/FIB library, etc.
- Virtio: both function and performance test are covered. Such as PVP/Virtio_loopback/virtio-user loopback/virtio-net VM2VM perf testing/VMAWARE ESXI 9.0, etc.
- Cryptodev: test scenarios including Cryptodev API testing/CompressDev ISA-L/QAT/ZLIB PMD Testing/FIPS, etc.
- DLB: test scenarios including DLB2.0 and DLB2.5
- Other: test scenarios including AF_XDP, Power, CBDMA, DSA
* Performance test: All test done and passed
- Thoughput Performance
- Cryptodev Latency
- PF/VF NIC single core
- XXV710/E810/E2100 NIC Performance
Regards,
Xu, Hailin
^ permalink raw reply [flat|nested] 3+ messages in thread