From: "Liu, Yong" <yong.liu@intel.com>
To: "Tu, LijuanX A" <lijuanx.a.tu@intel.com>, "dts@dpdk.org" <dts@dpdk.org>
Subject: Re: [dts] [PATCH V3 1/3] Add multiple pthread test plan
Date: Thu, 10 Sep 2015 05:08:53 +0000 [thread overview]
Message-ID: <86228AFD5BCD8E4EBFD2B90117B5E81E10EE4E4D@SHSMSX103.ccr.corp.intel.com> (raw)
In-Reply-To: <1441856756-21478-1-git-send-email-lijuanx.a.tu@intel.com>
Thanks lijuan, some comments about test plan.
> -----Original Message-----
> From: dts [mailto:dts-bounces@dpdk.org] On Behalf Of Lijuan Tu
> Sent: Thursday, September 10, 2015 11:46 AM
> To: dts@dpdk.org
> Subject: [dts] [PATCH V3 1/3] Add multiple pthread test plan
>
> Signed-off-by: Lijuan Tu <lijuanx.a.tu@intel.com>
> ---
> test_plans/multiple_pthread_test_plan.rst | 116
> ++++++++++++++++++++++++++++++
> 1 file changed, 116 insertions(+)
> create mode 100644 test_plans/multiple_pthread_test_plan.rst
>
> diff --git a/test_plans/multiple_pthread_test_plan.rst
> b/test_plans/multiple_pthread_test_plan.rst
> new file mode 100644
> index 0000000..b7b29d4
> --- /dev/null
> +++ b/test_plans/multiple_pthread_test_plan.rst
> @@ -0,0 +1,116 @@
> +..f
> + <COPYRIGHT_TAG>
> +
> +===============================
> +Multiple Pthread Test Instructions
> +===============================
> +
> +Cgroup Function Test
> +--------------------------
> +
> +Description
> +-----------
> +
> +This test is a basic multiple pthread test which demonstrates the basics
> of control group. Cgroup is a Linux kernel feature that limits, accounts
> for and isolates the resource usage, like CPU, memory, disk I/O, network,
> etc of a collection of processes. Now, it's focus on the CPU usage.
> +
> +Prerequisites
> +-------------
> +Support igb_uio driver, kernel is 3.11+. Use "modeprobe uio" "modprobe
> igb_uio" and then use "./tools/dpdk_nic_bind.py --bind=igb_uio
> device_bus_id" to bind the ports.
> +
> +Assuming that an Intel� DPDK build has been set up and the testpmd
> +applications have been built.
> +
I think this suite require multicores, so please add prerequisite on cpu module.
> +Os required: Linux and FreeBSD
> +
> +Test Case 1: Basic operation
> +--------------------------
> +
> +To run the application, start the testpmd with the lcoress all running
> with threads and also the unique core assigned, command as follows::
> +
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='0@8,(4-
> 5)@9' -n 4 -- -i --portmask=0xc
> + EAL: Master lcore 0 is ready (tid=ffd4900;cpuset=[8])
> + EAL: lcore 4 is ready (tid=873e7700;cpuset=[9])
> + EAL: lcore 5 is ready (tid=873e7700;cpuset=[9])
> +To check the output, we shall make sure the lcore are init on the correct
> cpu. e.g. Duing INIT log we can found below:
> +
> +The process should start successfully and display a command prompt as
> follows::
> +
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='0@8,(4-
> 5)@9' -n 4 -- -i --portmask=0xc
> + Checking link statuses...
> + Port 0 Link Up - speed 10000 Mbps - full-duplex
> + Port 1 Link Up - speed 10000 Mbps - full-duplex
> + Done
> +
> +Start the packet forwarding as follows
> +
> + testpmd>set fwd mac
> +
> +Before running the test, make sure the core is a unique one otherwise,
> the throughput will be floating on different cores, another thing is to
> make sure all the logic cores are running, command as follows:
> +
> + testpmd>set corelist 4,5
> +
> +pay attention that set corelist need to be configured before start,
> otherwise, it will not work
> +
> + testpmd>start
> +
> + testpmd>show config fwd
> +
> +Using the command to find the threads that's running, as follows:
> +
> + ps -C testpmd -L -opid,tid,%cpu,psr,args
> +
> +Result as follows:
> +
> + PID TID %CPU PSR COMMAND
> + 179459 179459 0.2 8 ./x86_64-native-linuxapp-gcc/app/testpmd --
> lcores=0@8,(4-5)@9 -n 4 -- -i --portmask=0xc
> + 179459 179460 0.0 21 ./x86_64-native-linuxapp-gcc/app/testpmd --
> lcores=0@8,(4-5)@9 -n 4 -- -i --portmask=0xc
> + 179461 0.0 21 ./x86_64-native-linuxapp-gcc/app/testpmd --
> lcores=0@8,(4-5)@9 -n 4 -- -i --portmask=0xc
> + 179459 179462 80.4 9 ./x86_64-native-linuxapp-gcc/app/testpmd --
> lcores=0@8,(4-5)@9 -n 4 -- -i --portmask=0xc
> + 179459 179463 0.0 9 ./x86_64-native-linuxapp-gcc/app/testpmd --
> lcores=0@8,(4-5)@9 -n 4 -- -i --portmask=0xc
> +
> +You will see that there are two threads running on core 9. The last 2
> threads are running threads, their TID will be assigned to the tasks in
> the folder thread0.
> +
> + cd /sys/fs/cgroup/cpu/dpdk/thread0
> + echo 179462 > tasks
> + echo 179463 > tasks
> +
> +Assgined the percentage of cpu these two threads occupy as follows:
> +
> + echo 10000 > cpu.cfs_quota_us
> +
> +This means the two threads will totally occupy 10% of the CPU and each 5%.
> +
> +
How to measure that each cpu only can occupy 5%, should we start performance and measure cpu usage?
> +Boundary Test
> +-------------------------
> +
> +Test Case 2: Positive Test
> +---------------------------------------------
> +
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='0@8,(4-
> 5)@(8-11)' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --
> txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='1,2@(0-
> 4,6),(3-4,6)@5,(7,8)' -n 4 -- -i --txfreet=32 --rxfreet=32 --
> txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --
> lcores='(0,CONFIG_RTE_MAX_LCORE-1)@(4,5)' -n 4 -- -i --txfreet=32 --
> rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='(0,64-
> 66)@(4,5)' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --
> txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='2-5,6,7-9'
> -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='2, (3-5)@
> 3' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='(0,7-
> 4)@(4,5)' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> +
> +Test Case 3: Negative Test
> +---------------------------------------------------
> +
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='(0-,4-
> 7)@(4,5)' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='(-1,4-
> 7)@(4,5)' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='(0,4-7-
> 9)@(4,5)' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --
> lcores='(0,abcd)@(4,5)' -n 4 -- -i --txfreet=32 --rxfreet=32 --
> txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='(0,4-7)@(1-
> ,5)' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='(0,4-7)@(-
> 1,5)' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='(0,4-
> 7)@(4,5-8-9)' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --
> txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='(0,4-
> 7)@(abc,5)' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --
> txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='(0,4-
> 7)@(4,xyz)' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --
> txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='(0,4-
> 7)=(8,9)' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='2,3@4,(0-
> 1,,4))' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='[0-,4-
> 7]@(4,5)' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='(0-,4-
> 7)@[4,5]' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='3-4@3,2@5-
> 6' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='2,,3''2--3'
> -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> + ./x86_64-native-linuxapp-gcc/app/testpmd --lcores='2,,,3''2--
> 3' -n 4 -- -i --txfreet=32 --rxfreet=32 --txqflags=0xf01 --txrst=32
> --
> 1.8.3.1
next prev parent reply other threads:[~2015-09-10 5:08 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-10 3:45 Lijuan Tu
2015-09-10 3:45 ` [dts] [PATCH V3 2/3] Add multiple pthread test suite, Lijuan Tu
2015-09-10 3:45 ` [dts] [PATCH V3 3/3] Add multiple pthread test suite in execution file Lijuan Tu
2015-09-10 5:08 ` Liu, Yong [this message]
2015-09-16 6:40 ` [dts] [PATCH V3 1/3] Add multiple pthread test plan Wan, Qun
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=86228AFD5BCD8E4EBFD2B90117B5E81E10EE4E4D@SHSMSX103.ccr.corp.intel.com \
--to=yong.liu@intel.com \
--cc=dts@dpdk.org \
--cc=lijuanx.a.tu@intel.com \
/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).