[DPDK/vhost/virtio Bug 1671] [dpdk-25.03] loopback_virtio_user_server_mode: failed to launch dpdk-pdump

[bugzilla at dpdk.org]

https://bugs.dpdk.org/show_bug.cgi?id=1671

            Bug ID: 1671
           Summary: [dpdk-25.03] loopback_virtio_user_server_mode: failed
                    to launch dpdk-pdump
           Product: DPDK
           Version: 25.03
          Hardware: All
                OS: All
            Status: UNCONFIRMED
          Severity: normal
          Priority: Normal
         Component: vhost/virtio
          Assignee: dev at dpdk.org
          Reporter: yux.jiang at intel.com
  Target Milestone: ---

[Environment]

DPDK version: commit 5f37ee9c 25.03-rc2
OS: Ubuntu 24.04.1 LTS (Noble Numbat); 6.8.0-52-generic
Compiler: gcc version 13.3.0
Hardware platform: Intel(R) Xeon(R) Platinum 8280M CPU @ 2.70GHz

[Test Setup]
Steps to reproduce
List the steps to reproduce the issue.

1.Build dpdk
rm -rf x86_64-native-linuxapp-gcc
CC=gcc meson -Denable_kmods=True -Dlibdir=lib --default-library=static
x86_64-native-linuxapp-gcc
ninja -C x86_64-native-linuxapp-gcc

2.Launch vhost as client mode
x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 4-6 -n 4 --file-prefix=vhost
--no-pci   --vdev 'eth_vhost0,iface=vhost-net,client=1,queues=8' -- -i --rxq=8
--txq=8 --nb-cores=1 --txd=1024 --rxd=1024

3, Launch virtio-user as server mode
x86_64-native-linuxapp-gcc/app/dpdk-testpmd -l 1-3 -n 4  --file-prefix=virtio
--no-pci   --vdev
'net_virtio_user0,mac=00:01:02:03:04:05,path=vhost-net,server=1,queues=8,mrg_rxbuf=1,in_order=1'
-- -i --txd=1024 --rxd=1024 --nb-cores=1 --rxq=8 --txq=8

4, Launch dpdk-pdump
x86_64-native-linuxapp-gcc/app/dpdk-pdump  -v --file-prefix=virtio -- --pdump 
'device_id=net_virtio_user0,queue=0,rx-dev=/root/pdump-rx-q0.pcap,mbuf-size=8000'
--pdump 
'device_id=net_virtio_user0,queue=1,rx-dev=/root/pdump-rx-q1.pcap,mbuf-size=8000'

[Actual Result]
root at dut220:~/dpdk# x86_64-native-linuxapp-gcc/app/dpdk-pdump  -v
--file-prefix=virtio -- --pdump 
'device_id=net_virtio_user0,queue=0,rx-dev=/root/pdump-rx-q0.pcap,mbuf-size=8000'
--                             pdump 
'device_id=net_virtio_user0,queue=1,rx-dev=/root/pdump-rx-q1.pcap,mbuf-size=8000'
EAL: Detected CPU lcores: 112
EAL: Detected NUMA nodes: 2
EAL: RTE Version: 'DPDK 25.03.0-rc1'
EAL: Detected static linkage of DPDK
EAL: Multi-process socket /var/run/dpdk/virtio/mp_socket_371105_2b2d9d66c5630c
EAL: Selected IOVA mode 'VA'
EAL: VFIO support initialized
Port 1 MAC: 02 70 63 61 70 00
EAL: failed to send to (/var/run/dpdk/virtio/mp_socket) due to No such file or
directory
EAL: Fail to send request /var/run/dpdk/virtio/mp_socket:eal_dev_mp_request
EAL: Cannot send request to primary
EAL: Failed to send hotplug request to primary
EAL: failed to send to (/var/run/dpdk/virtio/mp_socket) due to No such file or
directory
EAL: Cannot send message to primary
EAL: Error - exiting with code: 1
vdev creation failed:create_mp_ring_vdev:764


[Expected Result]
Launch successfully

[Regression]
Is this issue a regression: (Y)
Bad commit id:
commit 2d87f8569934ddbb7ffa7f9d70b3d72196bdbdf7 (HEAD -> 2d87f85699)
Author: Huisong Li <lihuisong at huawei.com>
Date:   Tue Feb 18 19:31:56 2025 +0800

    app/testpmd: fix queue numbers after device attach

    Testpmd doesn't modify the Rx/Tx queue number of all ports after
    attaching a new device. The root cause is that
     "port config all rxq <value>" would check if all ports are stopped and
    the status of this port is still in 'RTE_PORT_HANDLING'. This status is
    later changed to 'RTE_PORT_STOPPED' in setup_attached_port()
    when starting the port.

    In addition, this new port needs to be initialized in advance because
    this information is depended by many commands. Otherwise other commands
    like "port config xxx" may also encounter similar issues.
    The initialization can't be done in new event callback.
    This patch moves setup_attached_port() to the time point 100ms
    after receiving the new event.

    Bugzilla ID: 1663
    Fixes: 994635edb2c0 ("app/testpmd: add port attach/detach for multiple
process")

    Signed-off-by: Huisong Li <lihuisong at huawei.com>

-- 
You are receiving this mail because:
You are the assignee for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mails.dpdk.org/archives/dev/attachments/20250307/11c406f2/attachment.htm>