CN107870836A - A kind of automated testing method of Intel Omni Path performances - Google Patents
A kind of automated testing method of Intel Omni Path performances Download PDFInfo
- Publication number
- CN107870836A CN107870836A CN201711049680.6A CN201711049680A CN107870836A CN 107870836 A CN107870836 A CN 107870836A CN 201711049680 A CN201711049680 A CN 201711049680A CN 107870836 A CN107870836 A CN 107870836A
- Authority
- CN
- China
- Prior art keywords
- measured
- machine
- test
- script
- ssh
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2205—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using arrangements specific to the hardware being tested
- G06F11/221—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using arrangements specific to the hardware being tested to test buses, lines or interfaces, e.g. stuck-at or open line faults
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Tests Of Electronic Circuits (AREA)
Abstract
The present invention discloses a kind of automated testing method of Intel Omni Path performances, including:Prepare the machine to be measured of to be tested first and the second machine to be measured;First machine to be measured and the second machine to be measured are pre-processed;Copy test script to the first machine to be measured and the second machine to be measured;Test script includes parameter configuration script, ssh without cryptographic acess script and performs test script;First machine to be measured performs parameter configuration script, carries out environmental variance and sets and test parameter setting;Second machine to be measured performs parameter configuration script, carries out environmental variance and sets and test parameter setting;Second machine to be measured performs ssh without cryptographic acess script, configures the ssh of the first machine to be measured and the second machine to be measured without cryptographic acess, and whether the first machine to be measured of detection and the second machine to be measured can be with ssh without password login;Second machine to be measured performs test script, carries out performance test and delayed test, and output test result.The present invention reduces unnecessary interactive process, and the resources such as manpower, time, cost are saved for company.
Description
Technical field
The present invention relates to Intel Omni-Path performance tests field, and in particular to a kind of Intel Omni-Path performances
Automated testing method.
Background technology
Intel Omni-path frameworks (abbreviation OPA) be it is a kind of for HPC dispose and optimize tell interconnection technique
Framework, 100Gbps speed and extremely low delay can be provided.Omni-Path performance quality can have impact on HPC globality
Can, therefore Omni-Path performance test becomes to be even more important.OPA performance test at present is typically by manual operation, still
OPA performance test complex operation, manual operation error-prone.
The content of the invention
To solve the above problems, the present invention proposes a kind of method of automatic test Intel Omni-Path performances.
The technical scheme is that:A kind of automated testing method of Intel Omni-Path performances, including following step
Suddenly:
Prepare the machine to be measured of to be tested first and the second machine to be measured;First machine to be measured and the second machine to be measured are located in advance
Reason;
Copy test script to the first machine to be measured and the second machine to be measured;Test script include parameter configuration script, ssh without
Cryptographic acess script and execution test script;
First machine to be measured performs parameter configuration script, carries out environmental variance and sets and test parameter setting;
Second machine to be measured performs parameter configuration script, carries out environmental variance and sets and test parameter setting;
Second machine to be measured performs ssh without cryptographic acess script, configures the ssh of the first machine to be measured and the second machine to be measured without password
Access, and whether the first machine to be measured of detection and the second machine to be measured can be with ssh without password login;
Second machine to be measured performs test script, carries out performance test and delayed test, and output test result.
Further, pretreatment is carried out to the first machine to be measured and the second machine to be measured to specifically include:For the first machine to be measured and
Two machine installation operation systems to be measured, respective version OPA drivings are installed according to operating system.
Further, the described first machine to be measured performs parameter configuration script, carries out environmental variance setting and test parameter is set
Put and specifically include following steps:
The IP address of the OPA cards of first machine to be measured is set;
Modification system hostname is opa1;
Configuration/root/.mpd.conf and/etc/mpd.conf, is configured to performance testing tool parameter;
It is ssh without cryptographic acess configuration/etc/hosts;
Root/mpd.hosts is set;
Performance testing tool order is added to environmental variance.
Further, the described first machine to be measured performs parameter configuration script, carries out environmental variance setting and test parameter is set
Putting also includes step:
Closing influences the system service of test.
Further, the second machine to be measured performs parameter configuration script, carries out environmental variance and sets and test parameter setting tool
Body comprises the following steps:
The IP address of SUT2 PCIe card is set;
The hostname of modification system is opa2;
Configuration/root/.mpd.conf and/etc/mpd.conf, is configured to performance testing tool parameter;
It is ssh without cryptographic acess configuration/etc/hosts;
Root/mpd.hosts is set;
Performance testing tool order is added to environmental variance.
Further, the second machine to be measured performs parameter configuration script, carries out environmental variance and sets with test parameter setting also
Including step:
Closing influences the system service of test.
Further, the second machine to be measured performs ssh without cryptographic acess script, configures the first machine to be measured and the second machine to be measured
Ssh detects whether the first machine to be measured and the second machine to be measured can specifically include following step with ssh without password login without cryptographic acess
Suddenly:
The first machine to be measured and the second machine to be measured is waited to restart;
The dsa keys that first machine generation ssh to be measured is logged in;
The dsa keys of the first machine to be measured generation are copied to the second machine to be measured;
The dsa keys that second machine generation ssh to be measured is logged in;
The certification key that second machine generation to be measured logs in without key;
Tested without password login.
Further, the second machine to be measured performs test script, carries out performance test and delayed test, and export test
As a result test result is also saved in specified file after.
Further, the first machine to be measured and the second machine to be measured are server.
The automated testing method of Intel Omni-Path performances provided by the invention, carried out automatically according to test environment
Environmental variance is set, and test parameter is set, and Omni-path performance test is carried out using optimal test parameter, then will be surveyed
Test result formats and is processed and output to screen.In test process, reduce unnecessary interactive process, can be public affairs
Department saves the resources such as manpower, time, cost.
Embodiment
Below by specific embodiment, the present invention will be described in detail, and following examples are explanation of the invention, and
The invention is not limited in implementation below.
The present invention proposes that automated testing method replaces manual operation to complete the parameter configuration in performance test, environmental variance
Setting, the execution of test command and the processing of result, and test result is saved in execution file and achieved.This automation is surveyed
Method for testing is realized by test script, specifically includes following steps:
S1:Prepare the machine to be measured of to be tested first and the second machine to be measured;First machine to be measured and the second machine to be measured are carried out pre-
Processing;
It should be noted that the first machine to be measured and the second machine to be measured may each be server in the present embodiment.Tester
Two-server to be tested is assembled as needed.Above-mentioned pretreatment refers to:For the first machine to be measured and the second machine installation behaviour to be measured
Make system, respective version OPA drivings are installed according to operating system.
S2:Copy test script to the first machine to be measured and the second machine to be measured;Test script include parameter configuration script,
Ssh is without cryptographic acess script and performs test script.
S3:First machine to be measured performs parameter configuration script, carries out environmental variance and sets and test parameter setting.
S4:Second machine to be measured performs parameter configuration script, carries out environmental variance and sets and test parameter setting;
It should be noted that above-mentioned steps S3 and step S4 is mainly to carry out the PCIe card for Omni-Path frameworks
Performance carries out environmental variance and set and test parameter setting.
S5:Second machine to be measured performs ssh without cryptographic acess script, configure the ssh of the first machine to be measured and the second machine to be measured without
Cryptographic acess, and whether the first machine to be measured of detection and the second machine to be measured can be with ssh without password login.
S6:Second machine to be measured performs test script, carries out performance test and delayed test, and output test result;
It should be noted that this step can be carried out more to carry out Omni-path PCIe card bandwidth and delay performance test
Secondary test.Test result is output to specified file, convenient to contrast and consult in the future for achieving.
In the present embodiment, the first machines to be measured of above-mentioned steps S3 perform parameter configuration script, carry out environmental variance setting and survey
Examination parameter setting can specifically be realized by following methods step:
S3.1:The IP address of the OPA cards of first machine to be measured is set;
S3.2:Modification system hostname is opa1;
S3.3:Configuration/root/.mpd.conf and/etc/mpd.conf, is configured to performance testing tool parameter;
S3.4:It is ssh without cryptographic acess configuration/etc/hosts;
S3.5:Root/mpd.hosts is set;
S3.6:Performance testing tool order is added to environmental variance.
In addition, also settable step S3.7:Closing influences the system service of test.Tied to improve testing efficiency and test
The precision of fruit.
In the present embodiment, the second machines to be measured of above-mentioned steps S4 perform parameter configuration script, carry out environmental variance setting and survey
Examination parameter setting is specifically realized by following methods step:
S4.1:The IP address of SUT2 PCIe card is set;
S4.2:The hostname of modification system is opa2;
S4.3:Configuration/root/.mpd.conf and/etc/mpd.conf, is configured to performance testing tool parameter;
S4.4:It is ssh without cryptographic acess configuration/etc/hosts;
S4.5:Root/mpd.hosts is set;
S4.6:Performance testing tool order is added to environmental variance.
In addition, also settable step S4.7:Closing influences the system service of test.Tied to improve testing efficiency and test
The precision of fruit.
On the basis of above-described embodiment, the second machines to be measured of above-mentioned steps S5 perform ssh without cryptographic acess script, configuration first
The ssh of machine to be measured and the second machine to be measured is without cryptographic acess, and whether the first machine to be measured of detection and the second machine to be measured can be with ssh without close
Code logs in be realized especially by following methods step:
S5.1:The first machine to be measured and the second machine to be measured is waited to restart;
S5.2:The dsa keys that first machine generation ssh to be measured is logged in;
S5.3:The dsa keys of the first machine to be measured generation are copied to the second machine to be measured;
S5.4:The dsa keys that second machine generation ssh to be measured is logged in;
S5.5:The certification key that second machine generation to be measured logs in without key;
S5.6:Tested without password login.
The present embodiment is further illustrated with specific code below.
First, environmental variance and parameter setting are carried out, this part is mainly to carry out the PCIe card for Omni-Path frameworks
Performance carry out environmental variance set and test parameter set.
SUT1:
#!/bin/bash
# sets the IP address of SUT1 OPA cards
cat>/etc/sysconfig/network-scripts/ifcfg-ib0<<EOF
DEVICE=ib0
TYPE=InfiniBand
BOOTPROTO=static
IPADDR=10.10.10.1
NETMASK=255.255.255.0
ONBOOT=yes
EOF
The hostname of # modification systems is opa1
Sed-i's/HOSTNAME.*/HOSTNAME=opa1/'/etc/sysconfig/network
# configurations/root/.mpd.conf sets the parameter of performance testing tool
if[-f/root/.mpd.conf];then
{
rm-rf/root/.mpd.conf
}
fi
touch/root/.mpd.conf
chmod 600/root/.mpd.conf
Echo " MPD_SECRETWORD=mr45_j9z ">/root/.mpd.conf
# configurations/etc/mpd.conf sets the parameter of performance testing tool
if[-f/etc/mpd.conf];then
{
rm-rf/etc/mpd.conf
}
fi
touch/etc/mpd.conf
chmod 600/etc/mpd.conf
Echo " MPD_SECRETWORD=111111 ">/etc/mpd.conf
# be ssh without cryptographic acess configuration/etc/hosts,
echo"10.10.10.1opa1">>/etc/hosts
echo"10.10.10.2opa2">>/etc/hosts
# sets root/mpd.hosts
if[-f/root/.mpd.hosts];then
{
rm-rf/root/.mpd.hosts
}
fi
echo"opa1">>/root/.mpd.hosts
echo"opa2">>/root/.mpd.hosts
#path adds performance testing tool order to environmental variance
cat/root/.bashrc|grep PATH>bashtest.txt
if[-s bashtest.txt];then
sed-i'PATH/d'/root/.bashrc
fi
rm-rf bashtest.txt
cat path>>/root/.bashrc
#, which closes some, influences the system service of test
service iptables stop
service iptables save
service NetworkManager stop
chkconfigNetworkManager off
/etc/init.d/sshd restart
sleep 2
reboot
SUT2:
#!/bin/bash
# sets the IP address of SUT2 PCIe card
cat>/etc/sysconfig/network-scripts/ifcfg-ib0<<EOF
DEVICE=ib0
TYPE=InfiniBand
BOOTPROTO=static
IPADDR=10.10.10.2
NETMASK=255.255.255.0
ONBOOT=yes
EOF
The hostname of # modification systems is opa2
Sed-i's/HOSTNAME.*/HOSTNAME=opa2/'/etc/sysconfig/network
# configurations/root/.mpd.conf sets the parameter of performance testing tool
if[-f/root/.mpd.conf];then
{
rm-rf/root/.mpd.conf
}
fi
touch/root/.mpd.conf
chmod 600/root/.mpd.conf
Echo " MPD_SECRETWORD=mr45_j9z ">/root/.mpd.conf
# configurations/etc/mpd.conf sets the parameter of performance testing tool
if[-f/etc/mpd.conf];then
{
rm-rf/etc/mpd.conf
}
fi
touch/etc/mpd.conf
chmod 600/etc/mpd.conf
Echo " MPD_SECRETWORD=111111 ">/etc/mpd.conf
# be ssh without cryptographic acess configuration/etc/hosts,
echo"10.10.10.1opa1">>/etc/hosts
echo"10.10.10.2opa2">>/etc/hosts
# sets root/mpd.hosts
if[-f/root/.mpd.hosts];then
{
rm-rf/root/.mpd.hosts
}
fi
echo"opa1">>/root/.mpd.hosts
echo"opa2">>/root/.mpd.hosts
#path adds performance testing tool order to environmental variance
cat/root/.bashrc|grep PATH>bashtest.txt
if[-s bashtest.txt];then
sed-i'PATH/d'/root/.bashrc
fi
rm-rf bashtest.txt
cat path>>/root/.bashrc
#, which closes some, influences the system service of test
service iptables stop
service iptables save
service NetworkManager stop
chkconfigNetworkManager off
/etc/ini t.d/sshd restart
sleep 2
reboot
Two test machine realize ssh without code entry:
1. main program
#!/bin/bash
function get_ready()
{
# waits two-server to restart OK
ping 10.10.10.1>>/root/opa/ping.txt&
sleep 150
killall-9ping
cat/root/opa/ping.txt|grepttl|tail–n5>>/root/opa/ping1.txt
if[!-s/root/opa/ping1.txt];then
{
get_ready
}
fi
# is set without code entry
function ssh_keygen()
{
cd/root/opa
sh nopasswd.sh
}
#Main main programs
get_ready
ssh_keygen
2. subprogram 1:nopasswd.sh
#!/usr/bin/expect
set pasword 111111
set host1opa1
set host2opa2
set timeout-1
The dsa keys that #SUT1 generations ssh is logged in
spawn ssh-keygen-t dsa
expect"(/root/.ssh/id_dsa)"
send"\r"
expect{
"Overwrite(y/n)"
{
send"y\r"
expect"(empty for no passphrase):"
send"\r"
expect"again:"
send"\r\n"
exp_continue
}
"(empty for no passphrase):"
{
send"\r"
expect"again:"
send"\r\n"
exp_cont inue
}
eof
{
send_user"eof"
}
}
# copy generation key instruments to SUT2,
spawn scp keygen.sh root@opa2:/root
expect{
"continue connecting(yes/no)"
{
send"yes\r"
expect"password:"
send"$pasword\r"
exp_cont inue
}
"password:"
{
send"$pasword\r"
exp_continue
}
eof
{
send_user"eof"
}
}
#SUT2 generates dsa keys
spawn ssh-f root@opa2./keygen.sh
expect{
"password:"
{
send"$pasword\r"
exp_continue
}
eof
{
send_user"eof"
}
}
# generates the certification key without code entry
spawn scp/root/.ssh/id_dsa.pub$host2:/root/.ssh/authori zed_keys2;
expect{
"continue connecting(yes/no)"
{
send"yes\r"
expect"password:"
send"$pasword\r"
exp_continue
}
"password:"
{
send"$pasword\r"
exp_continue
}
eof
{
send_user"eof"
}
}
exec sleep 1
Spawn ssh-f-o StrictHostkeyChecking=no root@$ host2 ca t/root/.ssh/
id_dsa.pub>>/root/.ssh/authorized_keys2;
expect{
"password:"
{
send"$pasword\r"
exp_continue
}
eof
{
send_user"eof"
}
}
spawn scp root@opa2:/root/.ssh/authorized_keys2/root/.ssh/
expect{
"password:"
{
send"$pasword\r"
exp_continue
}
eof
}
exec sleep 1
# tests without code entry
Spawn ssh-f $ host2ssh-o StrictHostkeyChecking=no roo t@opa1
#result
spawn ssh$host2
expect{
"root@opa2"
{
send_user"successfully"
}
"password"
{
send_user"faild"}
}
send"exit\r"
expect eof
2. subprogram 2:keygen.sh
#!/usr/bin/expect
#ssh-keygen_auto automatically generates the machine dsa keys
set timeout-1
spawn ssh-keygen-t dsa
expect"(/root/.ssh/id_dsa):"
send"\r"
expect{
"Overwrite(y/n)"
{
send"y\r";
expect"(empty for no passphrase):"
send"\r"
expect"again:"
send"\r\n"
exp_cont inue
}
"(empty for no passphrase):"
{send"\r"
expect"again:"
send"\r\n"
exp_continue
}
eof
{
send_user"eof"
}
}
Then, Omni-path PCIe card bandwidth and delay performance test is carried out:
1. bandwidth test, testing 10 times, and output results to specified file:
#!/bin/bash
for i in{1..10}
do
mpirun-np 2-machinefilempd.hosts
/usr/mpi/gcc/mvapich-1.2.0/tests/osu_benchmarks-3.1.1/osu_bw|tee/
root/opa_bw.txt
done
2. delay test, testing 10 times, and output results to specified file:
#!/bin/bash
for i in{1..10}
do
mpirun-np 2-machinefilempd.hosts
/usr/mpi/gcc/mvapich-1.2.0/tests/osu_benchmarks-3.1.1/osu_lat|tee/
root/opa_lat.txt
Done
Above-mentioned SUT1 refers to the first machine to be measured, and SUT2 refers to the second machine to be measured.
By above-mentioned script, the parameter configuration in performance test, environmental variance setting, the execution of test command and knot are completed
The processing of fruit, and test result is saved in execution file and achieved.The substantial amounts of time can be saved using the script and is carried
The accuracy of height test.
Disclosed above is only the preferred embodiment of the present invention, but the present invention is not limited to this, any this area
What technical staff can think does not have creative change, and some improvement made without departing from the principles of the present invention and
Retouching, should all be within the scope of the present invention.
Claims (9)
1. a kind of automated testing method of Intel Omni-Path performances, it is characterised in that comprise the following steps:
Prepare the machine to be measured of to be tested first and the second machine to be measured;First machine to be measured and the second machine to be measured are pre-processed;
Copy test script to the first machine to be measured and the second machine to be measured;Test script includes parameter configuration script, ssh without password
Access script and perform test script;
First machine to be measured performs parameter configuration script, carries out environmental variance and sets and test parameter setting;
Second machine to be measured performs parameter configuration script, carries out environmental variance and sets and test parameter setting;
Second machine to be measured performs ssh without cryptographic acess script, and the ssh for configuring the first machine to be measured and the second machine to be measured visits without password
Ask, and whether the first machine to be measured of detection and the second machine to be measured can be with ssh without password login;
Second machine to be measured performs test script, carries out performance test and delayed test, and output test result.
2. the automated testing method of Intel Omni-Path performances according to claim 1, it is characterised in that to
One machine to be measured and the second machine to be measured carry out pretreatment and specifically included:For the first machine to be measured and the second machine installation operation system to be measured,
Respective version OPA drivings are installed according to operating system.
3. the automated testing method of Intel Omni-Path performances according to claim 2, it is characterised in that described
First machine to be measured performs parameter configuration script, carries out environmental variance setting and test parameter sets and specifically includes following steps:
The IP address of the OPA cards of first machine to be measured is set;
Modification system hostname is opa1;
Configuration/root/.mpd.conf and/etc/mpd.conf, is configured to performance testing tool parameter;
It is ssh without cryptographic acess configuration/etc/hosts;
Root/mpd.hosts is set;
Performance testing tool order is added to environmental variance.
4. the automated testing method of Intel Omni-Path performances according to claim 3, it is characterised in that described
First machine to be measured performs parameter configuration script, and carrying out environmental variance setting and test parameter setting also includes step:
Closing influences the system service of test.
5. the automated testing method of the Intel Omni-Path performances according to claim 3 or 4, it is characterised in that the
Two machines to be measured perform parameter configuration script, carry out environmental variance setting and test parameter sets and specifically includes following steps:
The IP address of SUT2 PCIe card is set;
The hostname of modification system is opa2;
Configuration/root/.mpd.conf and/etc/mpd.conf, is configured to performance testing tool parameter;
It is ssh without cryptographic acess configuration/etc/hosts;
Root/mpd.hosts is set;
Performance testing tool order is added to environmental variance.
6. the automated testing method of Intel Omni-Path performances according to claim 5, it is characterised in that second
Machine to be measured performs parameter configuration script, and carrying out environmental variance setting and test parameter setting also includes step:
Closing influences the system service of test.
7. the automated testing method of Intel Omni-Path performances according to claim 6, it is characterised in that second
Machine to be measured performs ssh without cryptographic acess script, configures the ssh of the first machine to be measured and the second machine to be measured without cryptographic acess, and detect
Whether the first machine to be measured and the second machine to be measured can specifically include following steps with ssh without password login:
The first machine to be measured and the second machine to be measured is waited to restart;
The dsa keys that first machine generation ssh to be measured is logged in;
The dsa keys of the first machine to be measured generation are copied to the second machine to be measured;
The dsa keys that second machine generation ssh to be measured is logged in;
The certification key that second machine generation to be measured logs in without key;
Tested without password login.
8. the automated testing method of the Intel Omni-Path performances according to any one of claim 1-4,6-7, it is special
Sign is that the second machine to be measured performs test script, carries out performance test and delayed test, and is gone back after outputing test result
Test result is saved in specified file.
9. the automated testing method of the Intel Omni-Path performances according to any one of claim 1-4,6-7, it is special
Sign is that the first machine to be measured and the second machine to be measured are server.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711049680.6A CN107870836A (en) | 2017-10-31 | 2017-10-31 | A kind of automated testing method of Intel Omni Path performances |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711049680.6A CN107870836A (en) | 2017-10-31 | 2017-10-31 | A kind of automated testing method of Intel Omni Path performances |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107870836A true CN107870836A (en) | 2018-04-03 |
Family
ID=61752845
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711049680.6A Pending CN107870836A (en) | 2017-10-31 | 2017-10-31 | A kind of automated testing method of Intel Omni Path performances |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107870836A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108829555A (en) * | 2018-06-25 | 2018-11-16 | 郑州云海信息技术有限公司 | Authentication test method and device in Citrix system |
CN109495339A (en) * | 2018-11-02 | 2019-03-19 | 郑州云海信息技术有限公司 | Method based on Intel-mpi tool test HCA card performance |
CN111737145A (en) * | 2020-07-21 | 2020-10-02 | 北京志翔科技股份有限公司 | Automatic testing method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140019808A1 (en) * | 2012-01-05 | 2014-01-16 | International Business Machines Corporation | Debugging of Adapters with Stateful Offload Connections |
CN104601410A (en) * | 2015-02-02 | 2015-05-06 | 浪潮电子信息产业股份有限公司 | Server automatic HCA card bandwidth testing method |
CN105760286A (en) * | 2016-02-17 | 2016-07-13 | 中国工商银行股份有限公司 | Application database dynamic property detection method and detection device |
CN107193730A (en) * | 2017-05-11 | 2017-09-22 | 丹露成都网络技术有限公司 | A kind of interface test method of automation |
-
2017
- 2017-10-31 CN CN201711049680.6A patent/CN107870836A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140019808A1 (en) * | 2012-01-05 | 2014-01-16 | International Business Machines Corporation | Debugging of Adapters with Stateful Offload Connections |
CN104601410A (en) * | 2015-02-02 | 2015-05-06 | 浪潮电子信息产业股份有限公司 | Server automatic HCA card bandwidth testing method |
CN105760286A (en) * | 2016-02-17 | 2016-07-13 | 中国工商银行股份有限公司 | Application database dynamic property detection method and detection device |
CN107193730A (en) * | 2017-05-11 | 2017-09-22 | 丹露成都网络技术有限公司 | A kind of interface test method of automation |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108829555A (en) * | 2018-06-25 | 2018-11-16 | 郑州云海信息技术有限公司 | Authentication test method and device in Citrix system |
CN109495339A (en) * | 2018-11-02 | 2019-03-19 | 郑州云海信息技术有限公司 | Method based on Intel-mpi tool test HCA card performance |
CN111737145A (en) * | 2020-07-21 | 2020-10-02 | 北京志翔科技股份有限公司 | Automatic testing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11936548B2 (en) | Active assurance for virtualized services | |
US10841336B2 (en) | Selectively providing mutual transport layer security using alternative server names | |
US10855694B2 (en) | Methods, systems, and computer readable media for monitoring encrypted packet flows within a virtual network environment | |
Wundsam et al. | {OFRewind}: Enabling Record and Replay Troubleshooting for Networks | |
US9614745B2 (en) | Systems and methods for cloud-based probing and diagnostics | |
US9509760B2 (en) | Virtual packet analyzer for a cloud computing environment | |
US20150278517A1 (en) | Method and system for comparing different versions of a cloud based application in a production environment using segregated backend systems | |
CN105022648A (en) | Test method of HCA card performance and pressure tests on basis of expect command | |
WO2017019684A1 (en) | Techniques for evaluating server system reliability, vulnerability and component compatibility using crowdsourced server and vulnerability data | |
WO2015187809A2 (en) | Techniques to isolating a portion of an online computing service | |
CN104579853A (en) | Method for network testing of server cluster system | |
CN103812726A (en) | Automated testing method and device for data communication equipment | |
CN107870836A (en) | A kind of automated testing method of Intel Omni Path performances | |
CN110913024B (en) | Cloud platform information synchronization method, system, control device and storage medium | |
CN107749807B (en) | Network function verification method and verification system for NFV | |
US11159416B1 (en) | Systems and methods of testing virtual private network communications using remote connectivity | |
US10033583B2 (en) | Accelerating device, connection and service discovery | |
AU2019213378A1 (en) | Playback of captured network transactions in a simulation environment | |
CN107181626B (en) | Method and system for monitoring network bandwidth of distributed storage cluster system | |
DeCusatis et al. | Modeling software defined networks using mininet | |
Sanaee et al. | Backdraft: a lossless virtual switch that prevents the slow receiver problem | |
US20210176155A1 (en) | Systems and methods for dynamic network traffic manipulation | |
US20230179985A1 (en) | Targeted pdu capture by a network device for roaming detection in wireless networks | |
Schottelius | High speed nat64 with p4 | |
Birkholz et al. | Enhancing security testing via automated replication of IT-asset topologies |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180403 |