On 13/8/2021 2:31 PM, Luca Boccassi wrote:
On Fri, 2021-08-13 at 11:42 +0000, Jiang, YuX wrote:
Hi Luca,
Testing with dpdk v20.11.3-rc1 from Intel looks good, no critical issue is
found.
Below issues have been fixed in 20.11.3-rc1:
1)ddp_gtp_qregion/fd_gtpu_ipv4_dstip: flow director does not work.
2)rxtx_offload/rxoffload_port: Pkt1 can't be distributed to the same queue.
Test Scope:
# Basic Intel(R) NIC testing
* Build: cover the build test combination with latest GCC/Clang/ICC version and
the popular OS revision such as Ubuntu20.04, CentOS8.3, Fedora34, RHEL8.3 and
so on. Listed but not all.
- All passed.
*PF(i40e, ixgbe): test scenarios including rte_flow/TSO/Jumboframe/checksum
offload/Tunnel, etc. Listed but not all.
- All test is done, no new issue is found.
Known issues as below:
1)https://bugs.dpdk.org/show_bug.cgi?id=790 unit_tests_power/power_cpufreq:
unit test failed: Clone from https://bugs.dpdk.org/show_bug.cgi?id=687 , this
issue is found in 21.05/LTS20.11.2, fixed in 21.08. But still failed in
LTS20.11.3-rc1.
*VF(i40e,ixgbe): test scenarios including vf-rte_flow/TSO/Jumboframe/checksum
offload/Tunnel, Listed but not all.
- All passed. No new issues are found.
*PF/VF(ice): test scenarios including switch features/Flow Director/Advanced
RSS/ACL/DCF/Flexible Descriptor and so on, Listed but not all.
- All test is done, no new issue is found.
Two known DPDK issues:
1)cvl_advanced_iavf_rss: change the SCTP port value, the hash value remains
unchanged. This issue is found in 20.11-rc3, fixed in 21.02, but it’s belong to
21.02 new feature, won’t backporting to LTS20.11.
2)Can't create 512 acl rules after creating a full mask switch rule. This issue
is also occurred in dpdk 20.11. Has fixed patch, but not merged.
Fixed patch link:
https://patchwork.dpdk.org/project/dpdk/patch/20210728022429.237010-1-simei...@intel.com/
* Intel NIC single core/NIC performance: test scenarios including PF/VF single
core performance test(AVX2+AVX512) test and so on. Listed but not all.
- All passed. No big performance data drop.
# Basic cryptodev and virtio testing
* Virtio: both function and performance test are covered. Such as
PVP/Virtio_loopback/virtio-user loopback/virtio-net VM2VM perf testing, etc..
Listed but not all.
- All test is done, no new issue is found.
One known issues as below:
1)The UDP fragmentation offload feature of Virtio-net device can’t be turned on
in the VM, long time kernel issue, bugzilla has been submited:
https://bugzilla.kernel.org/show_bug.cgi?id=207075 , not fixed yet.
* Cryptodev:
**Function test: test scenarios including Cryptodev API testing/CompressDev
ISA-L/QAT/ZLIB PMD Testing/FIPS, etc. Listed but not all.
- All passed.
**Performance test: test scenarios including Thoughput Performance
/Cryptodev Latency, etc. Listed but not all.
- No big performance data drop.
Best regards,
Yu Jiang
Thank you!
For https://bugs.dpdk.org/show_bug.cgi?id=790 if an appropriately
modified version of 29343b9030e38e8c3519ba01cb66724d45b13dc8 gets
backported I can merge it.
Hi Luca,
I've just submitted a patch that's a backported version of
29343b9030e38e8c3519ba01cb66724d45b13dc8, wouthout the dependency on the
CPCC driver patch set.
I was able to reproduce the issue without this patch, and the autotest
passes after this patch is applied.
Patchwork link here:
http://patches.dpdk.org/project/dpdk/patch/20210813141830.15397-1-david.h...@intel.com/
Checkpatch complains about the commit-id's as they're from the dpdk
repo, not dpdk-stable, I hope that's ok?
Rgds,
Dave.
