test suite reviews and discussions
 help / color / mirror / Atom feed
From: "Tu, Lijuan" <lijuan.tu@intel.com>
To: "Peng, Yuan" <yuan.peng@intel.com>, "dts@dpdk.org" <dts@dpdk.org>
Cc: "Peng, Yuan" <yuan.peng@intel.com>
Subject: Re: [dts] [PATCH]test_plans: add 3 cases to qos_sched_test_plan.rst
Date: Sat, 12 Oct 2019 05:56:23 +0000	[thread overview]
Message-ID: <8CE3E05A3F976642AAB0F4675D0AD20E0BB3EBDD@SHSMSX101.ccr.corp.intel.com> (raw)
In-Reply-To: <1569570925-140385-1-git-send-email-yuan.peng@intel.com>

Applied, thanks

> -----Original Message-----
> From: dts [mailto:dts-bounces@dpdk.org] On Behalf Of Peng Yuan
> Sent: Friday, September 27, 2019 3:55 PM
> To: dts@dpdk.org
> Cc: Peng, Yuan <yuan.peng@intel.com>
> Subject: [dts] [PATCH]test_plans: add 3 cases to qos_sched_test_plan.rst
> 
> Add 3 cases for Hqos new features to qos_sched_test_plan.rst
> 
> Signed-off-by: Peng Yuan <yuan.peng@intel.com>
> 
> diff --git a/test_plans/qos_sched_test_plan.rst
> b/test_plans/qos_sched_test_plan.rst
> index b8bc966..8675406 100644
> --- a/test_plans/qos_sched_test_plan.rst
> +++ b/test_plans/qos_sched_test_plan.rst
> @@ -588,3 +588,104 @@ for each of the RX, WT and TX thread are also
> supported,  providing flexibility to balance the work.
>  The EAL coremask/corelist is constrained to contain  the default mastercore
> 1 and the RX, WT and TX cores only.
> +
> +Test Case: Two Subports, different pipe profiles, different number of
> +pipes I
> +===============================================================
> ========
> +====== 1. Configure the profile.cfg file with two subports, two
> +different pipe
> +   profiles and different number of pipes::
> +
> +    [subport 0]
> +    number of pipes per subport = 2048
> +    pipe 0-2047 = 0       ; These pipes are configured with pipe profile 0
> +    [subport 1]
> +    number of pipes per subport = 512
> +    pipe 0-511 = 1        ; These pipes are configured with pipe profile 1
> +
> +    [pipe profile 0]
> +    tb rate = 305175               ; Bytes per second
> +    tb size = 1000000              ; Bytes
> +    tc 0 rate = 305175             ; Bytes per second
> +    tc 1 rate = 305175             ; Bytes per second
> +    ......
> +
> +    [pipe profile 1]
> +    tb rate = 1220700              ; Bytes per second
> +    tb size = 1000000              ; Bytes
> +
> +    tc 0 rate = 1220700            ; Bytes per second
> +    tc 1 rate = 1220700            ; Bytes per second
> +    ......
> +
> +2. This example uses a single packet flow configuration
> +   which creates one RX thread on lcore 5 reading from port 0
> +   and a worker thread on lcore 7 writing to port 1::
> +
> +    ./qos_sched -l 1,2,5,7 -n 4 -- -i --pfc "0,1,2,5,7" --cfg
> + ../profile.cfg
> +
> +3. The generator settings:
> +   Set IP dst address mode is random, and the mask is "255.255.255.0".
> +   Frame size=70bytes.
> +   Flow1: outer vlan id=0 inner vlan random mask 0XXXXXXXXXXX (2048 pipes)
> +   Flow2: outer vlan id=1 inner vlan random mask 000XXXXXXXXX (512 pipes)
> +   Each flow 50% max rate.
> +
> +4. Check the result:
> +   Only send flow1, the received packets by ixia port 1: 6.967mpps.
> +   Only send flow2, the received packets by ixia port 1: 6.967mpps.
> +   Send two flows at the same time, the received packets by ixia port 1:
> 13.888 mpps.
> +
> +Test Case: Two Subports, different pipe profiles, different number of
> +pipes II
> +===============================================================
> ========
> +======= 1. Configure the profile.cfg file the same with last case I.
> +
> +2. This example uses a single packet flow configuration
> +   which creates one RX thread on lcore 5 reading from port 0
> +   and a worker thread on lcore 7 writing to port 1::
> +
> +    ./qos_sched -l 1,2,5,7 -n 4 -- -i --pfc "0,1,2,5,7" --cfg
> + ../profile.cfg
> +
> +3. The generator settings:
> +   Set IP dst address mode is random, and the mask is "255.255.255.0".
> +   Frame size=70bytes.
> +   Flow1: outer vlan id=0 inner vlan random mask 0XXXXXXXXXXX (2048 pipes)
> +   Flow2: outer vlan id=1 inner vlan random mask 0000XXXXXXXX (256 pipes)
> +   Each flow 50% max rate.
> +
> +4. Check the result:
> +   Only send flow1, the received packets by ixia port 1: 6.967mpps.
> +   Only send flow2, the received packets by ixia port 1: 3.838mpps.
> +   Send two flows at the same time, the received packets by ixia port 1:
> 10.805mpps.
> +
> +Test Case: Redistribution of unused pipe BW to other pipes within the
> +same subport
> +===============================================================
> ========
> +===========
> +1. Use default profile_ov.cfg, Set::
> +
> +    CONFIG_RTE_SCHED_SUBPORT_TC_OV=y
> +
> +2. This example uses a single packet flow configuration
> +   which creates one RX thread on lcore 5 reading from port 0
> +   and a worker thread on lcore 7 writing to port 1::
> +
> +    ./qos_sched -l 1,2,5,7 -n 4 -- -i --pfc "0,1,2,5,7" --cfg
> + ../profile.cfg
> +
> +3. The generator settings:
> +   Configure 4 flows:
> +   Frame size=70bytes.
> +   Outer vlan ID = 0
> +   Flow 1: Inner vlan ID = 0
> +   Flow 2: Inner vlan ID = 1
> +   Flow 3: Inner vlan ID = 2
> +   Flow 4: Inner vlan ID = 3
> +   IP dst address = 100.0.0.12
> +   Each flow’s Max rate = 25%
> +   Send four flows at the same time, the TX rate by ixia port0 is 13.888mpps,
> +   the received packets by ixia port1: 0.092mpps.
> +
> +4. Disable the first flow, the TX rate by ixia port0 is 10.416mpps,
> +   the received packets by ixia port1 is still 0.092mpps.
> +
> +5. Configure only one flow with max rate = 100%
> +   Set inner vlan ID count mode "increment", repeat count=32, step=1.
> +   Send the flow, the receive rate is 0.092mpps.
> +   Then set inner vlan ID count mode "increment", repeat count=16, step=1.
> +   Send the flow, the receive rate is still 0.092mpps.
> --
> 2.7.4


      reply	other threads:[~2019-10-12  5:56 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-09-27  7:55 Peng Yuan
2019-10-12  5:56 ` Tu, Lijuan [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=8CE3E05A3F976642AAB0F4675D0AD20E0BB3EBDD@SHSMSX101.ccr.corp.intel.com \
    --to=lijuan.tu@intel.com \
    --cc=dts@dpdk.org \
    --cc=yuan.peng@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).