From: Lokesh Chakka <lvenkatakumarchakka@gmail.com>
To: Stephen Hemminger <stephen@networkplumber.org>
Cc: users <users@dpdk.org>
Subject: Re: No free hugepages reported
Date: Tue, 2 Apr 2024 12:44:59 +0530 [thread overview]
Message-ID: <CACh--si9b_0HLVkZLzXgfLb+AXsBSdrkzmYn86yjNkEKT=2qxw@mail.gmail.com> (raw)
In-Reply-To: <CACh--siHC_zuqt7hVo=L3tT-G7GJOkgHH1UqcREJaGE4_n5AVQ@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 4858 bytes --]
hi,
To add more information, the server I'm using has two CPU sockets and two
NUMA nodes. One is numbered as Node 2 and other one as Node 6
one more observation is the following command is getting executed
successfully.
$ sudo dpdk-hugepages.py -p 1G --setup 2G -n 2
also the following one
$ sudo dpdk-hugepages.py -p 1G --setup 2G -n 6
After executing the first command, 1G huge pages are getting created. After
executing the second command, huge pages under node 2 are getting deleted.
Following is the output of dpdk-testpmd command
****************************************************************************************************
EAL: Detected CPU lcores: 128
EAL: Detected NUMA nodes: 8
EAL: Detected shared linkage of DPDK
EAL: Multi-process socket /var/run/dpdk/rte/mp_socket
EAL: Selected IOVA mode 'VA'
EAL: No free 1048576 kB hugepages reported on node 0
EAL: No free 1048576 kB hugepages reported on node 1
EAL: No free 1048576 kB hugepages reported on node 3
EAL: No free 1048576 kB hugepages reported on node 4
EAL: No free 1048576 kB hugepages reported on node 5
EAL: No free 1048576 kB hugepages reported on node 6
EAL: No free 1048576 kB hugepages reported on node 7
EAL: VFIO support initialized
set_mempolicy: Invalid argument
set_mempolicy: Invalid argument
set_mempolicy: Invalid argument
set_mempolicy: Invalid argument
EAL: Using IOMMU type 1 (Type 1)
set_mempolicy: Invalid argument
set_mempolicy: Invalid argument
EAL: Probe PCI driver: net_ice (8086:1592) device: 0000:63:00.0 (socket 3)
set_mempolicy: Invalid argument
PANIC in eth_dev_shared_data_prepare():
Cannot allocate ethdev shared data
0: /lib/x86_64-linux-gnu/librte_eal.so.23 (rte_dump_stack+0x41)
[7dbb0fe000b1]
1: /lib/x86_64-linux-gnu/librte_eal.so.23 (__rte_panic+0xc1) [7dbb0fde11c7]
2: /lib/x86_64-linux-gnu/librte_ethdev.so.23 (7dbb0fedb000+0x8b16)
[7dbb0fee3b16]
3: /lib/x86_64-linux-gnu/librte_ethdev.so.23 (rte_eth_dev_allocate+0x31)
[7dbb0feef971]
4: /usr/lib/x86_64-linux-gnu/dpdk/pmds-23.0/librte_net_ice.so.23
(7dbb0f70e000+0x67465) [7dbb0f775465]
5: /usr/lib/x86_64-linux-gnu/dpdk/pmds-23.0/librte_bus_pci.so.23
(7dbb0fc64000+0x4c76) [7dbb0fc68c76]
6: /usr/lib/x86_64-linux-gnu/dpdk/pmds-23.0/librte_bus_pci.so.23
(7dbb0fc64000+0x8af4) [7dbb0fc6caf4]
7: /lib/x86_64-linux-gnu/librte_eal.so.23 (rte_bus_probe+0x23)
[7dbb0fdeeab3]
8: /lib/x86_64-linux-gnu/librte_eal.so.23 (7dbb0fdd4000+0x123bf)
[7dbb0fde63bf]
9: dpdk-testpmd (5813e0022000+0x45150) [5813e0067150]
10: /lib/x86_64-linux-gnu/libc.so.6 (7dbb0ec00000+0x28150) [7dbb0ec28150]
11: /lib/x86_64-linux-gnu/libc.so.6 (__libc_start_main+0x89) [7dbb0ec28209]
12: dpdk-testpmd (5813e0022000+0x48e55) [5813e006ae55]
Aborted
****************************************************************************************************
Thanks & Regards
--
Lokesh Chakka.
On Mon, Apr 1, 2024 at 2:50 AM Lokesh Chakka <lvenkatakumarchakka@gmail.com>
wrote:
> hi Stephen,
>
> Thanks for the reply. Following is the observation...
>
> *************************************************************
> $ dpdk-hugepages.py -s
> Node Pages Size Total
> 2 512 2Mb 1Gb
> 6 512 2Mb 1Gb
>
> Hugepages mounted on /dev/hugepages /mnt/huge
>
> $ sudo dpdk-hugepages.py -p 1G --setup 2G
> Unable to set pages (0 instead of 2 in
> /sys/devices/system/node/node4/hugepages/hugepages-1048576kB/nr_hugepages).
> *************************************************************
>
>
> Regards
> --
> Lokesh Chakka.
>
>
> On Mon, Apr 1, 2024 at 12:36 AM Stephen Hemminger <
> stephen@networkplumber.org> wrote:
>
>> On Sun, 31 Mar 2024 16:28:19 +0530
>> Lokesh Chakka <lvenkatakumarchakka@gmail.com> wrote:
>>
>> > Hello,
>> >
>> > I've installed dpdk in Ubuntu 23.10 with the command "sudo apt -y
>> install
>> > dpdk*"
>> >
>> > added "nodev /mnt/huge hugetlbfs pagesize=1GB 0 0" in /etc/fstab
>> > added "vm.nr_hugepages=1024" in /etc/sysctl.conf
>> >
>> > rebooted the machine and then did devbind using the following command:
>> >
>> > sudo modprobe vfio-pci && sudo dpdk-devbind.py --bind=vfio-pci 63:00.0
>> > 63:00.1
>> >
>> > Huge page info is as follows :
>> >
>> > *************************************************
>> > $ cat /proc/meminfo | grep Huge
>> > AnonHugePages: 6144 kB
>> > ShmemHugePages: 0 kB
>> > FileHugePages: 0 kB
>> > HugePages_Total: 1024
>> > HugePages_Free: 1023
>> > HugePages_Rsvd: 0
>> > HugePages_Surp: 0
>> > Hugepagesize: 2048 kB
>> > Hugetlb: 2097152 kB
>> > *************************************************
>>
>> Your hugepages are not setup correctly. The mount is for 1G pages
>> and the sysctl entry makes 2M pages.
>>
>> Did you try using the dpdk-hugepages script?
>>
>
[-- Attachment #2: Type: text/html, Size: 7023 bytes --]
prev parent reply other threads:[~2024-04-02 7:15 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-31 10:58 Lokesh Chakka
2024-03-31 19:06 ` Stephen Hemminger
2024-03-31 21:20 ` Lokesh Chakka
2024-04-02 7:14 ` Lokesh Chakka [this message]
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='CACh--si9b_0HLVkZLzXgfLb+AXsBSdrkzmYn86yjNkEKT=2qxw@mail.gmail.com' \
--to=lvenkatakumarchakka@gmail.com \
--cc=stephen@networkplumber.org \
--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).