From: Ali Alnubani <alialnu@nvidia.com>
To: Bruce Richardson <bruce.richardson@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>,
NBU-Contact-Thomas Monjalon <thomas@monjalon.net>,
Asaf Penso <asafp@nvidia.com>
Subject: [dpdk-dev] performance degradation with fpic
Date: Thu, 15 Oct 2020 16:00:44 +0000 [thread overview]
Message-ID: <DM6PR12MB4618640B2ABCFA4D3B33C445DA020@DM6PR12MB4618.namprd12.prod.outlook.com> (raw)
Hi Bruce,
We have been seeing in some cases that the DPDK forwarding performance is up to 9% lower when DPDK is built as static with meson compared to a build with makefiles.
The same degradation can be reproduced with makefiles on older DPDK releases when building with EXTAR_CFLAGS set to "-fPIC", it can also be resolved in meson when passing "pic: false" to meson's static_library call (more tweaking needs to be done to prevent building shared libraries because this change breaks them).
I can reproduce this drop with the following cases:
* Baremetal / NIC: ConnectX-4 Lx / OS: RHEL7.4 / CPU: Intel(R) Xeon(R) Gold 6154. Testpmd command:
testpmd -c 0x7ffc0000 -n 4 -w d8:00.1 -w d8:00.0 --socket-mem=2048,2048 -- --port-numa-config=0,1,1,1 --socket-num=1 --burst=64 --txd=512 --rxd=512 --mbcache=512 --rxq=2 --txq=2 --nb-cores=1 --no-lsc-interrupt -i -a --rss-udp
* KVM guest with SR-IOV passthrough / OS: RHEL7.4 / NIC: ConnectX-5 / Host's CPU: Intel(R) Xeon(R) Gold 6154. Testpmd command:
testpmd --master-lcore=0 -c 0x1ffff -n 4 -w 00:05.0,mprq_en=1,mprq_log_stride_num=6 --socket-mem=2048,0 -- --port-numa-config=0,0 --socket-num=0 --burst=64 --txd=1024 --rxd=1024 --mbcache=512 --rxq=16 --txq=16 --nb-cores=8 --port-topology=chained --forward-mode=macswap --no-lsc-interrupt -i -a --rss-udp
* Baremetal / OS: Ubuntu 18.04 / NIC: ConnectX-5 / CPU: Intel(R) Xeon(R) CPU E5-2697A v4. Testpmd command:
testpmd -n 4 -w 0000:82:00.0,rxqs_min_mprq=8,mprq_en=1 -w 0000:82:00.1,rxqs_min_mprq=8,mprq_en=1 -c 0xff80 -- --burst=64 --mbcache=512 -i --nb-cores=8 --rxq=8 --txq=8 --txd=1024 --rxd=1024 --rss-udp --auto-start
The packets being received and forwarded by testpmd are of IPv4/UDP type and 64B size.
Should we disable PIC in static builds?
Regards,
Ali
next reply other threads:[~2020-10-15 16:00 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-15 16:00 Ali Alnubani [this message]
2020-10-15 17:08 ` Bruce Richardson
2020-10-15 17:14 ` Thomas Monjalon
2020-10-15 17:28 ` [dpdk-dev] [EXT] " Jerin Jacob Kollanukkaran
2020-10-16 8:29 ` Bruce Richardson
2020-10-16 8:39 ` Jerin Jacob
2020-10-15 21:44 ` [dpdk-dev] " Stephen Hemminger
2020-10-16 8:35 ` Bruce Richardson
2020-10-16 9:59 ` Bruce Richardson
2020-10-19 11:47 ` Ali Alnubani
2020-10-19 13:01 ` Bruce Richardson
2020-10-22 13:17 ` Ali Alnubani
2020-10-22 13:57 ` Bruce Richardson
2020-10-22 14:16 ` Ali Alnubani
2020-11-02 10:40 ` Ali Alnubani
2020-11-02 11:01 ` Luca Boccassi
2020-11-02 15:00 ` Bruce Richardson
2020-11-03 10:18 ` Thomas Monjalon
2020-11-03 10:45 ` Luca Boccassi
2020-11-03 11:23 ` Bruce Richardson
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=DM6PR12MB4618640B2ABCFA4D3B33C445DA020@DM6PR12MB4618.namprd12.prod.outlook.com \
--to=alialnu@nvidia.com \
--cc=asafp@nvidia.com \
--cc=bruce.richardson@intel.com \
--cc=dev@dpdk.org \
--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).