From: Lijuan Tu <lijuan.tu@intel.com>
To: dts@dpdk.org
Cc: Lijuan Tu <lijuan.tu@intel.com>
Subject: [dts] [v1, 3/5] vm_power_manager: remove perf test cases
Date: Wed, 4 Aug 2021 06:49:24 +0800 [thread overview]
Message-ID: <1628030966-187545-3-git-send-email-lijuan.tu@intel.com> (raw)
In-Reply-To: <1628030966-187545-1-git-send-email-lijuan.tu@intel.com>
the cases are no longer maintained.
Signed-off-by: Lijuan Tu <lijuan.tu@intel.com>
---
test_plans/vm_power_manager_test_plan.rst | 65 ------------------
tests/TestSuite_vm_power_manager.py | 106 ------------------------------
2 files changed, 171 deletions(-)
diff --git a/test_plans/vm_power_manager_test_plan.rst b/test_plans/vm_power_manager_test_plan.rst
index 992f315..7cac509 100644
--- a/test_plans/vm_power_manager_test_plan.rst
+++ b/test_plans/vm_power_manager_test_plan.rst
@@ -89,30 +89,6 @@ Prerequisites
- libvirtd (libvirt) 1.1.3.5
- Add virio-serial port
-4. IXIA Traffic Generator Configuration LPM table used for packet routing is:
-
- +---------+------------------------+----+
- | Entry # | LPM prefix (IP/length) | |
- +---------+------------------------+----+
- | 0 | 1.1.1.0/24 | P0 |
- +---------+------------------------+----+
- | 1 | 2.1.1.0/24 | P1 |
- +---------+------------------------+----+
-
-
- The flows should be configured and started by the traffic generator.
-
- +------+---------+------------+---------+------+-------+--------+
- | Flow | Traffic | IPv4 | IPv4 | Port | Port | L4 |
- | | Gen. | Src. | Dst. | Src. | Dest. | Proto. |
- | | Port | Address | Address | | | |
- +------+---------+------------+---------+------+-------+--------+
- | 1 | TG0 | 0.0.0.0 | 2.1.1.0 | any | any | UDP |
- +------+---------+------------+---------+------+-------+--------+
- | 2 | TG1 | 0.0.0.0 | 1.1.1.0 | any | any | UDP |
- +------+---------+------------+---------+------+-------+--------+
-
-
Test Case 1: VM Power Management Channel
========================================
@@ -282,44 +258,3 @@ Test Case 7: VM Power Management Multi VMs
8. Poweroff VM2 and remove VM2 from host vm_power_mgr::
vmpower> rm_vm <vm2_name>
-
-Test Case 8: VM l3fwd-power Latency
-===================================
-1. Connect two physical ports to IXIA
-2. Start VM and run l3fwd-power::
-
- l3fwd-power -c 6 -n 4 -- -p 0x3 --config '(P0,0,C{1.1.0}),(P1,0,C{1.2.0})'
-
-3. Configure packet flow in IxiaNetwork
-4. Start to send packets from IXIA and check the receiving packets and latency
-5. Record the latency of frame sizes 128
-6. Compare latency value with sample l3fwd
-
-Test Case 9: VM l3fwd-power Performance
-=======================================
-Start VM and run l3fwd-power::
-
- l3fwd-power -c 6 -n 4 -- -p 0x3 --config '(P0,0,C{1.1.0}),(P1,0,C{1.2.0})'
-
-Input traffic linerate varied from 0 to 100%, in order to see cpu frequency
-changes.
-
-The test report should provide the throughput rate measurements (in Mpps and %
-of the line rate for 2x NIC ports) and cpu frequency as listed in the table
-below:
-
- +---------------+---------------+-----------+
- | % Tx linerate | Rx % linerate | Cpu freq |
- +---------------+---------------+-----------+
- | 0 | | |
- +---------------+---------------+-----------+
- | 20 | | |
- +---------------+---------------+-----------+
- | 40 | | |
- +---------------+---------------+-----------+
- | 60 | | |
- +---------------+---------------+-----------+
- | 80 | | |
- +---------------+---------------+-----------+
- | 100 | | |
- +---------------+---------------+-----------+
diff --git a/tests/TestSuite_vm_power_manager.py b/tests/TestSuite_vm_power_manager.py
index 00910eb..fca122b 100644
--- a/tests/TestSuite_vm_power_manager.py
+++ b/tests/TestSuite_vm_power_manager.py
@@ -273,112 +273,6 @@ class TestVmPowerManager(TestCase, IxiaPacketGenerator):
vm2_dut.send_expect("quit", "# ")
vm2.stop()
- def test_perf_vmpower_latency(self):
- """
- Measure packet latency in VM
- """
- latency_header = ['Frame Size', 'Max latency', 'Min lantecy',
- 'Avg latency']
-
- self.result_table_create(latency_header)
-
- rx_port = self.dut_ports[0]
- tx_port = self.dut_ports[1]
-
- # build l3fwd-power
- out = self.vm_dut.send_expect("make -C examples/l3fwd-power", "# ")
- self.verify("Error" not in out, "compilation error 1")
- self.verify("No such file" not in out, "compilation error 2")
- # start l3fwd-power
- l3fwd_app = "./examples/l3fwd-power/build/l3fwd-power"
-
- cmd = l3fwd_app + " -c 6 -n 4 -- -p 0x3 --config " + \
- "'(0,0,1),(1,0,2)'"
-
- self.vm_dut.send_expect(cmd, "L3FWD_POWER: entering main loop")
-
- for frame_size in self.frame_sizes:
- # Prepare traffic flow
- payload_size = frame_size - HEADER_SIZE['udp'] - \
- HEADER_SIZE['ip'] - HEADER_SIZE['eth']
- dmac = self.dut.get_mac_address(self.dut_ports[0])
- flow = 'Ether(dst="%s")/IP(dst="2.1.1.0")/UDP()' % dmac + \
- '/Raw("X"*%d)' % payload_size
- self.tester.scapy_append('wrpcap("vmpower.pcap", [%s])' % flow)
- self.tester.scapy_execute()
-
- tgen_input = []
- tgen_input.append((self.tester.get_local_port(rx_port),
- self.tester.get_local_port(tx_port),
- "vmpower.pcap"))
- # run traffic generator
- [latency] = self.tester.traffic_generator_latency(tgen_input)
- print(latency)
- table_row = [frame_size, latency['max'], latency['min'],
- latency['average']]
- self.result_table_add(table_row)
-
- self.result_table_print()
-
- self.vm_dut.kill_all()
-
- def test_perf_vmpower_frequency(self):
- """
- Measure cpu frequency fluctuate with work load
- """
- latency_header = ['Tx linerate%', 'Rx linerate%', 'Cpu freq']
-
- self.result_table_create(latency_header)
-
- rx_port = self.dut_ports[0]
- tx_port = self.dut_ports[1]
-
- # build l3fwd-power
- out = self.vm_dut.send_expect("make -C examples/l3fwd-power", "# ")
- self.verify("Error" not in out, "compilation error 1")
- self.verify("No such file" not in out, "compilation error 2")
- # start l3fwd-power
- l3fwd_app = "./examples/l3fwd-power/build/l3fwd-power"
-
- cmd = l3fwd_app + " -c 6 -n 4 -- -p 0x3 --config " + \
- "'(0,0,1),(1,0,2)'"
-
- self.vm_dut.send_expect(cmd, "L3FWD_POWER: entering main loop")
-
- for rate in self.perf_rates:
- # Prepare traffic flow
- payload_size = self.def_framesize - HEADER_SIZE['udp'] - \
- HEADER_SIZE['ip'] - HEADER_SIZE['eth']
- dmac = self.dut.get_mac_address(self.dut_ports[0])
- flow = 'Ether(dst="%s")/IP(dst="2.1.1.0")/UDP()' % dmac + \
- '/Raw("X"*%d)' % payload_size
- self.tester.scapy_append('wrpcap("vmpower.pcap", [%s])' % flow)
- self.tester.scapy_execute()
-
- tgen_input = []
- tgen_input.append((self.tester.get_local_port(rx_port),
- self.tester.get_local_port(tx_port),
- "vmpower.pcap"))
-
- # register hook function for current cpu frequency
- self.hook_transmissoin_func = self.get_freq_in_transmission
- self.tester.extend_external_packet_generator(TestVmPowerManager,
- self)
- # run traffic generator, run 20 seconds for frequency stable
- _, pps = self.tester.traffic_generator_throughput(tgen_input,
- rate,
- delay=20)
- pps /= 1000000.0
- freq = self.cur_freq / 1000000.0
- wirespeed = self.wirespeed(self.nic, self.def_framesize, 1)
- pct = pps * 100 / wirespeed
- table_row = [rate, pct, freq]
- self.result_table_add(table_row)
-
- self.result_table_print()
-
- self.vm_dut.kill_all()
-
def get_freq_in_transmission(self):
self.cur_freq = self.get_cpu_frequency(self.vcpu_map[1])
print((utils.GREEN("Current cpu frequency %d" % self.cur_freq)))
--
1.8.3.1
next prev parent reply other threads:[~2021-08-03 14:59 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-03 22:49 [dts] [v1, 1/5] generic_filter: remove perf test case Lijuan Tu
2021-08-03 22:49 ` [dts] [v1, 2/5] nvgre: remove perf test cases Lijuan Tu
2021-08-03 22:49 ` Lijuan Tu [this message]
2021-08-03 22:49 ` [dts] [v1, 4/5] vxlan_sample: remove perf test case Lijuan Tu
2021-08-03 22:49 ` [dts] [v1, 5/5] remove cloud_filter as it is no longer maintained Lijuan Tu
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=1628030966-187545-3-git-send-email-lijuan.tu@intel.com \
--to=lijuan.tu@intel.com \
--cc=dts@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).