DPDK patches and discussions
 help / color / mirror / Atom feed
From: "Jiang, YuX" <yux.jiang@intel.com>
To: Thomas Monjalon <thomas@monjalon.net>,
	"dev (dev@dpdk.org)" <dev@dpdk.org>
Cc: "Devlin, Michelle" <michelle.devlin@intel.com>,
	"Mcnamara, John" <john.mcnamara@intel.com>,
	"Yigit, Ferruh" <ferruh.yigit@intel.com>
Subject: Re: [dpdk-dev] [dpdk-announce] release candidate 21.11-rc1
Date: Mon, 1 Nov 2021 11:53:30 +0000	[thread overview]
Message-ID: <SJ0PR11MB5150A9E0193187DB766110F5FE8A9@SJ0PR11MB5150.namprd11.prod.outlook.com> (raw)
In-Reply-To: <SJ0PR11MB5150780AD8ACBEEDEC187D5FFE869@SJ0PR11MB5150.namprd11.prod.outlook.com>

> -----Original Message-----
> From: Jiang, YuX
> Sent: Thursday, October 28, 2021 3:11 PM
> To: Thomas Monjalon <thomas@monjalon.net>; dev (dev@dpdk.org)
> <dev@dpdk.org>
> Cc: Devlin, Michelle <michelle.devlin@intel.com>; Mcnamara, John
> <john.mcnamara@intel.com>; Yigit, Ferruh <ferruh.yigit@intel.com>
> Subject: RE: [dpdk-dev] [dpdk-announce] release candidate 21.11-rc1
>
> > -----Original Message-----
> > From: dev <dev-bounces@dpdk.org> On Behalf Of Thomas Monjalon
> > Sent: Tuesday, October 26, 2021 5:41 AM
> > To: announce@dpdk.org
> > Subject: [dpdk-dev] [dpdk-announce] release candidate 21.11-rc1
> >
> > A new DPDK release candidate is ready for testing:
> >     https://git.dpdk.org/dpdk/tag/?id=v21.11-rc1
> >
> > There are 1171 new patches in this snapshot, big as expected.
> >
> > Release notes:
> >     https://doc.dpdk.org/guides/rel_notes/release_21_11.html
> >
> > Highlights of 21.11-rc1:
> > * General
> >     - more than 512 MSI-X interrupts
> >     - hugetlbfs subdirectories
> >     - mempool flag for non-IO usages
> >     - device class for DMA accelerators
> >     - DMA drivers for Intel DSA and IOAT
> > * Networking
> >     - MTU handling rework
> >     - get all MAC addresses of a port
> >     - RSS based on L3/L4 checksum fields
> >     - flow match on L2TPv2 and PPP
> >     - flow flex parser for custom header
> >     - control delivery of HW Rx metadata
> >     - transfer flows API rework
> >     - shared Rx queue
> >     - Windows support of Intel e1000, ixgbe and iavf
> >     - testpmd multi-process
> >     - pcapng library and dumpcap tool
> > * API/ABI
> >     - API namespace improvements (mempool, mbuf, ethdev)
> >     - API internals hidden (intr, ethdev, security, cryptodev, eventdev,
> > cmdline)
> >     - flags check for future ABI compatibility (memzone, mbuf, mempool)
> >
> > Please test and report issues on bugs.dpdk.org.
> > DPDK 21.11-rc2 is expected in two weeks or less.
> >
> > Thank you everyone
> >
> Update the test status for Intel part. Till now dpdk21.11-rc1 test execution
> rate is 50%. No critical issue is found.
> But one little high issue https://bugs.dpdk.org/show_bug.cgi?id=843 impacts
> cryptodev function and performance test.
> Bad commit id is 8cb5d08db940a6b26f5c5ac03b49bac25e9a7022/Author:
> Harman Kalra <hkalra@marvell.com>. Please help to handle it.
> # Basic Intel(R) NIC testing
> * Build or compile:
>       *Build: cover the build test combination with latest GCC/Clang/ICC
> version and the popular OS revision such as Ubuntu20.04, Fedora34, RHEL8.4,
> etc.
>               - All test done.
>       *Compile: cover the CFLAGES(O0/O1/O2/O3) with popular OS such
> as Ubuntu20.04 and Fedora34.
>               - All test done.
>               - Find one bug: https://bugs.dpdk.org/show_bug.cgi?id=841
> Marvell Dev has provided patch and Intel validation team verify passed.
>                 Patch link:
> http://patchwork.dpdk.org/project/dpdk/patch/20211027131259.11775-1-
> ktejasree@marvell.com/
>       * PF(i40e, ixgbe): test scenarios including
> RTE_FLOW/TSO/Jumboframe/checksum offload/VLAN/VXLAN, etc.
>               - Execution rate is 60%. No new issue is found yet.
>       * VF(i40e, ixgbe): test scenarios including VF-
> RTE_FLOW/TSO/Jumboframe/checksum offload/VLAN/VXLAN, etc.
>
>               - Execution rate is 60%.
>               - One bug https://bugs.dpdk.org/show_bug.cgi?id=845
> about "vm_hotplug: vf testpmd core dumped after executing "device_del
> dev1" in qemu" is found.
>                       Bad commit id is commit
> c2bd9367e18f5b00c1a3c5eb281a512ef52c5dfd Author: Harman Kalra
> <hkalra@marvell.com>
>       * PF/VF(ice): test scenarios including Switch features/Package
> Management/Flow Director/Advanced Tx/Advanced RSS/ACL/DCF/Share
> code update/Flexible Descriptor, etc.
>               - Execution rate is 60%.
>               - One bug about kni_autotest failed on Suse15.3. Trying to
> find bad commit id. Known issues, Intel dev is under investigating.
>
>       * Intel NIC single core/NIC performance: test scenarios including
> PF/VF single core performance test, RFC2544 Zero packet loss performance
> test, etc.
>               - Execution rate is 60%.
>               - One bug about nic single core performance drop 2% is
> found. Bad commit id is commit:  efc6f9104c80d39ec168/Author: Olivier Matz
> <olivier.matz@6wind.com>
>       * Power and IPsec:
>               * Power: test scenarios including bi-
> direction/Telemetry/Empty Poll Lib/Priority Base Frequency, etc.
>                       - All passed.
>               * IPsec: test scenarios including ipsec/ipsec-gw/ipsec library
> basic test - QAT&SW/FIB library, etc.
>                       - Not Start.
> # 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/VMAWARE ESXI 7.0u3, etc.
>               - Execution rate is 80%.
>               - Two new bugs are found.
>                       - One about VMware ESXI 7.0U3: failed to start port.
> Intel Dev is under investigating.
>                       - One https://bugs.dpdk.org/show_bug.cgi?id=840
> about "dpdk-pdump capture the pcap file content are wrong" is found.
>                       Bad commit id: commit
> 10f726efe26c55805cf0bf6ca1b80e97b98eb724    //bad commit id Author:
> Stephen Hemminger <stephen@networkplumber.org>
>       * Cryptodev:
>               *Function test: test scenarios including Cryptodev API
> testing/CompressDev ISA-L/QAT/ZLIB PMD Testing/FIPS, etc.
>                       - Execution rate is 60%
>                       - Two new bugs are found.
>                               - One
> https://bugs.dpdk.org/show_bug.cgi?id=843 about crypto performance tests
> for QAT are failing. Bad commit id is
> 8cb5d08db940a6b26f5c5ac03b49bac25e9a7022/Author: Harman Kalra
> <hkalra@marvell.com>
>                               - One
> https://bugs.dpdk.org/show_bug.cgi?id=842 about FIP tests are failing. Bad
> commit id is commit f6849cdcc6ada2a8bc9b82e691eaab1aecf4952f Author:
> Akhil Goyal gakhil@marvell.com
>               *Performance test: test scenarios including Thoughput
> Performance /Cryptodev Latency, etc.
>                       - Execution rate is 10%. Most of performance test are
> blocked by Bug843.

Update the test status for Intel part. Till now dpdk21.11-rc1 test is almost finished. No critical issue is found.
One little high issue https://bugs.dpdk.org/show_bug.cgi?id=843 impacts cryptodev function and performance test.
It has patch https://git.dpdk.org/dpdk/commit/?id=eb89595d45ca268ebe6c0cb88f0ae17dba08d8f6 to fix and the patch has been merged into dpdk main.

# Basic Intel(R) NIC testing
* Build or compile:
        *Build: cover the build test combination with latest GCC/Clang/ICC version and the popular OS revision such as Ubuntu20.04, Fedora34, RHEL8.4, etc.
                - All test done. All passed.
        *Compile: cover the CFLAGES(O0/O1/O2/O3) with popular OS such as Ubuntu20.04 and RHEL8.4.
                - All test done.
                - Find one bug: https://bugs.dpdk.org/show_bug.cgi?id=841 Marvell Dev has provided patch and verify passed.
                  Patch link: http://patchwork.dpdk.org/project/dpdk/patch/20211027131259.11775-1-ktejasree@marvell.com/, patch has been applied into dpdk-next-net-mrvl/for-next-net.
        * PF(i40e, ixgbe): test scenarios including RTE_FLOW/TSO/Jumboframe/checksum offload/VLAN/VXLAN, etc.
                - All test done.
                - Find 5 new bugs.
                a, https://bugs.dpdk.org/show_bug.cgi?id=863 external_mempool_handler:execute mempool_autotest command failed on FreeBSD: verify patch passed.
                b, https://bugs.dpdk.org/show_bug.cgi?id=864 pmd_stacked_bonded/test_mode_backup_rx:after setup stacked bonded ports,start top level bond port.
                        - Has patch but verify failed.
                c, https://bugs.dpdk.org/show_bug.cgi?id=865 launch testpmd with "--vfio-intr=legacy" appears core dumped.
                        - Has patch from Redhat, Intel validation team will verify it later.
                d, when set rx_ offload rss_hash is set to off, port start will automatically load RSS_hash: Intel dev is investigating.
                e, checksum_offload/hardware_checksum_check_l4_tx: sctp checksum value incorrect: Intel dev is investigating.
        * VF(i40e, ixgbe): test scenarios including VF-RTE_FLOW/TSO/Jumboframe/checksum offload/VLAN/VXLAN, etc.
                - Execution rate is 60%.
                - Find 3 new bugs, Intel dev is investigating.
                a, https://bugs.dpdk.org/show_bug.cgi?id=845 about "vm_hotplug: vf testpmd core dumped after executing "device_del dev1" in qemu" is found.
                        - Bad commit id is commit c2bd9367e18f5b00c1a3c5eb281a512ef52c5dfd Author: Harman Kalra <hkalra@marvell.com>
                        - Marvell dev has no similar env, Intel validation team don't find avaiable app to reproduce this bug yet.
                b, send packet with vlan id(1~4095), vf port can received on i40e-2.17.1, this is not as expected: Intel dev is investigating.
                c, ixgbe_vf_get_extra_queue_information/ test_enable_dcb: executing "port config 0 dcb vt on 4 pfc off" failed under testpmd
        * PF/VF(ice): test scenarios including Switch features/Package Management/Flow Director/Advanced Tx/Advanced RSS/ACL/DCF/Share code update/Flexible Descriptor, etc.
                - All test done. No new issue is found during 21.11rc1. Some known issues are investigated by Intel Dev.
        * Intel NIC single core/NIC performance: test scenarios including PF/VF single core performance test, RFC2544 Zero packet loss performance test, etc.
                - All test done. No big performance drop.
        * Power and IPsec:
                * Power: test scenarios including bi-direction/Telemetry/Empty Poll Lib/Priority Base Frequency, etc.
                        - All passed.
                * IPsec: test scenarios including ipsec/ipsec-gw/ipsec library basic test - QAT&SW/FIB library, etc.
                        - All passed.
# 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/VMAWARE ESXI 7.0u3, etc.
                - All test done.
                - 3 new bugs are found.
                        - One about VMware ESXI 7.0U3: failed to start port. Intel Dev is under investigating.
                        - One https://bugs.dpdk.org/show_bug.cgi?id=840 about "dpdk-pdump capture the pcap file content are wrong" is found.
                                Bad commit id: commit 10f726efe26c55805cf0bf6ca1b80e97b98eb724    //bad commit id Author: Stephen Hemminger <stephen@networkplumber.org>
                        - vhost_event_idx_interrupt/wake_up_packed_ring_vhost_user_cores_by_multi_virtio_net_in_vms_with_event_idx_interrupt: start 2 packed ring vm, lcore can't waked up.
                                - Intel Dev is under investigating.
        * Cryptodev:
                *Function test: test scenarios including Cryptodev API testing/CompressDev ISA-L/QAT/ZLIB PMD Testing/FIPS, etc.
                        - All test done.
                        - 2 new bugs are found.
                                - One https://bugs.dpdk.org/show_bug.cgi?id=843 about crypto performance tests for QAT are failing. Patch has been merged into dpdk main branch.
                                - One https://bugs.dpdk.org/show_bug.cgi?id=842 about FIP tests are failing. Has patch to fix and verify passed.
                *Performance test: test scenarios including Thoughput Performance /Cryptodev Latency, etc.
                        - All test done. No big performance drop. Most of performance test are blocked by Bug843.

BRs
Yu Jiang

  reply	other threads:[~2021-11-01 11:53 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-10-25 21:40 Thomas Monjalon
2021-10-28  7:10 ` Jiang, YuX
2021-11-01 11:53   ` Jiang, YuX [this message]
2021-11-05 21:51 ` Thinh Tran
2021-11-08 10:50 ` Pei Zhang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=SJ0PR11MB5150A9E0193187DB766110F5FE8A9@SJ0PR11MB5150.namprd11.prod.outlook.com \
    --to=yux.jiang@intel.com \
    --cc=dev@dpdk.org \
    --cc=ferruh.yigit@intel.com \
    --cc=john.mcnamara@intel.com \
    --cc=michelle.devlin@intel.com \
    --cc=thomas@monjalon.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).