DPDK usage discussions
 help / color / mirror / Atom feed
From: pckcn <409816927@qq.com>
To: users <users@dpdk.org>
Subject: [dpdk-users] a issue about DPDK l3fwd-power in multi-core mode
Date: Sat, 29 Sep 2018 21:22:42 +0800	[thread overview]
Message-ID: <tencent_53BD8FB5C114FC5F5DD222F4718DF8B2A50A@qq.com> (raw)

hello,
May i ask a issue about l3fwd-power example program, I cannot run it on my board for multi-queue mode.
I plan to use a single queue for each core to handle port 0, but after trial, I can run it with a single-core single-queue command. Each thread in the multi-core is blocked on epoll_wait, no response, the example is built-in, is there a solution to this problem?


Environment:
Linux ubuntu 4.4.0 x64 
Ubuntu 16.04.5 LTS
dpdk18.08
Network card Intel I211 4 port 2 queue 4 core


Run in multi core(blocked in epoll_wait):
./l3fwd-power -l 0-3 -n 4 -- -p 3 --config "(0,0,0),(0,1,1)"


Run in single core:
./l3fwd-power -l 0-3 -n 4 -- -p 3 --config "(0,0,0)"


Output:

root@ubuntu:~/dpdk-18.08/examples/l3fwd-power/build# ./l3fwd-power -l 0-1 -n 4 -- -p 3 --config "(0,0,0),(0,1,1)"
EAL: Detected 4 lcore(s)
EAL: Detected 1 NUMA nodes
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Probing VFIO support...
EAL: no supported IOMMU extensions found!
EAL: VFIO support could not be initialized
EAL: PCI device 0000:01:00.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 8086:1539 net_e1000_igb
EAL: PCI device 0000:02:00.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 8086:1539 net_e1000_igb
EAL: PCI device 0000:03:00.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 8086:1539 net_e1000_igb
EAL: PCI device 0000:06:00.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 8086:1539 net_e1000_igb
EAL: PCI device 0000:07:00.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 8086:1539 net_e1000_igb
EAL: PCI device 0000:08:00.0 on NUMA socket -1
EAL: Invalid NUMA socket, default to 0
EAL: probe driver: 8086:1539 net_e1000_igb
POWER: Attempting to initialise ACPI cpufreq power management...
POWER: Power management governor of lcore 0 has been set to user space successfully
POWER: File not openned
POWER: Cannot get available frequencies of lcore 0
POWER: Attempting to initialise VM power management...
GUEST_CHANNEL: Opening channel '/dev/virtio-ports/virtio.serial.port.poweragent.0' for lcore 0
GUEST_CHANNEL: Unable to to connect to '/dev/virtio-ports/virtio.serial.port.poweragent.0' with error No such file or directory
POWER: Unable to set Power Management Environment for lcore 0
POWER: Library initialization failed on core 0
POWER: Attempting to initialise ACPI cpufreq power management...
POWER: Power management governor of lcore 1 has been set to user space successfully
POWER: File not openned
POWER: Cannot get available frequencies of lcore 1
POWER: Attempting to initialise VM power management...
GUEST_CHANNEL: Opening channel '/dev/virtio-ports/virtio.serial.port.poweragent.1' for lcore 1
GUEST_CHANNEL: Unable to to connect to '/dev/virtio-ports/virtio.serial.port.poweragent.1' with error No such file or directory
POWER: Unable to set Power Management Environment for lcore 1
POWER: Library initialization failed on core 1

Initializing port 0 ... Creating queues: nb_rxq=2 nb_txq=2... Address:00:02:B6:85:1E:C2, Allocated mbuf pool on socket 0
LPM: Adding route 0x01010100 / 24 (0)
LPM: Adding route 0x02010100 / 24 (1)
LPM: Adding route 0x03010100 / 24 (2)
LPM: Adding route 0x04010100 / 24 (3)
LPM: Adding route 0x05010100 / 24 (4)
LPM: Adding route 0x06010100 / 24 (5)
LPM: Adding route 0x07010100 / 24 (6)
LPM: Adding route 0x08010100 / 24 (7)
txq=0,0,0 txq=1,1,0
Initializing port 1 ... Creating queues: nb_rxq=0 nb_txq=2... Address:00:02:B6:85:1E:C3, txq=0,0,0 txq=1,1,0

Skipping disabled port 2

Skipping disabled port 3

Initializing rx queues on lcore 0 ... rxq=0,0,0
Initializing rx queues on lcore 1 ... rxq=0,1,0

Checking link status.........................................done
Port 0 Link Up - speed 100 Mbps - full-duplex
Port 1 Link Up - speed 1000 Mbps - full-duplex
L3FWD_POWER: entering main loop on lcore 1
L3FWD_POWER: -- lcoreid=1 portid=0 rxqueueid=1
L3FWD_POWER: entering main loop on lcore 0
L3FWD_POWER: -- lcoreid=0 portid=0 rxqueueid=0
EAL: Event already been added.
L3FWD_POWER: lcore 1 sleeps until interrupt triggers
L3FWD_POWER: lcore 0 sleeps until interrupt triggers
L3FWD_POWER: lcore 1 is waked up from rx interrupt on port 0 queue 1
L3FWD_POWER: lcore 1 sleeps until interrupt triggers







Intel power management technology is not turned on, but i think it should not be affected by the code.

Thank you

                 reply	other threads:[~2018-09-29 13:22 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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=tencent_53BD8FB5C114FC5F5DD222F4718DF8B2A50A@qq.com \
    --to=409816927@qq.com \
    --cc=users@dpdk.org \
    /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).