when we test performance of bulk product create api request using Apache 2 Benchmark, it takes to much time for return response of request.
I tested bulk api requests with 200 total number of requests & 25 concurrency level
Live Server Data
This is Apache Benchmark Result
$ ab -n 200 -c 25 -s 800 <api_url>
This is ApacheBench, Version 2.3 <$Revision: 1901567 $>
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Licensed to The Apache Software Foundation, http://www.apache.org/
Benchmarking <api_url> (be patient)
Completed 100 requests
Completed 200 requests
Finished 200 requests
Server Software: Apache
Server Hostname: <api_url>
Concurrency Level: 25
Time taken for tests: 1825.329 seconds
Complete requests: 200
Failed requests: 0
Requests per second: 0.11 [#/sec] (mean)
Time per request: 228166.105 [ms] (mean)
Time per request: 9126.644 [ms] (mean, across all concurrent requests)
Transfer rate: 313.50 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 4 259 760.3 87 3458
Processing: 11530 224407 17776.1 227501 242597
Waiting: 11501 223702 17661.3 226799 241997
Total: 11536 224666 17877.9 227903 242602
Percentage of the requests served within a certain time (ms)
50% 227903
66% 229995
75% 231201
80% 232007
90% 235161
95% 236600
98% 239193
99% 241998
100% 242602 (longest request)
Live Server Apache & Php.ini Configuration
Intel(R) Xeon(R) CPU E5-2697 v3 @ 2.60GHz
core 56
Total Memory = 193068 MiB
Maximum Spare Servers = 10
Server Limit = 256
Max Request Workers = 150
Max Connections per child = 10000
Keep-Alive = On
Keep-Alive Timeout = 5
Max Keep-Alive Requests = 100
Timeout = 300
max_execution_time = 30
memory_limit = 2G (*Magento's Min. recommended)
opcache.enable = On
gzip compression = enabled
Local Development System Data
This is Apache Benchmark Result
$ ab -n 200 -c 25 -s 800 <api_url>
This is ApacheBench, Version 2.3 <$Revision: 1879490 $>
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Licensed to The Apache Software Foundation, http://www.apache.org/
Benchmarking <api_url> (be patient)
Completed 100 requests
Completed 200 requests
Finished 200 requests
Server Software: Apache/2.4.52
Server Hostname: <api_url>
Concurrency Level: 25
Time taken for tests: 13.566 seconds
Complete requests: 200
Failed requests: 0
Requests per second: 14.74 [#/sec] (mean)
Time per request: 1695.800 [ms] (mean)
Time per request: 67.832 [ms] (mean, across all concurrent requests)
Transfer rate: 271.61 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 0 0.1 0 0
Processing: 243 1628 472.0 1657 2864
Waiting: 238 1618 468.9 1641 2832
Total: 243 1628 472.0 1657 2864
Percentage of the requests served within a certain time (ms)
50% 1657
66% 1799
75% 1891
80% 1944
90% 2142
95% 2512
98% 2631
99% 2846
100% 2864 (longest request)
Local Server & Php.ini Configuration
Intel(R) Core(TM) i3-9100 CPU @ 3.60GHz
core 4
Total Memory = 11862.5 MiB
Max Requests :- Per Child: 0 - Keep Alive: on - Max Per Connection: 100
Timeouts :- Connection: 300 - Keep-Alive: 5
memory_limit = 756M
opcache.enable = On
gzip compression = enabled
Apache Benchmark Result of Live Server with concurrency 10
$ ab -n 200 -c 10 -s 800 <api_url>
This is ApacheBench, Version 2.3 <$Revision: 1901567 $>
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Licensed to The Apache Software Foundation, http://www.apache.org/
Benchmarking <api_url> (be patient)
Completed 100 requests
Completed 200 requests
Finished 200 requests
Server Software: Apache
Server Hostname: <api_url>
Concurrency Level: 10
Time taken for tests: 1332.961 seconds
Complete requests: 200
Failed requests: 0
Requests per second: 0.15 [#/sec] (mean)
Time per request: 66648.037 [ms] (mean)
Time per request: 6664.804 [ms] (mean, across all concurrent requests)
Transfer rate: 429.30 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 3 21 32.2 5 91
Processing: 17982 65490 4646.0 65398 75602
Waiting: 17886 65226 4614.8 65095 75300
Total: 17986 65511 4649.5 65402 75607
Percentage of the requests served within a certain time (ms)
50% 65402
66% 66109
75% 66587
80% 66991
90% 70792
95% 72711
98% 74708
99% 75212
100% 75607 (longest request)
Apache Benchmark Result of Local Server with concurrency 10
$ ab -n 200 -c 10 -s 800 <api_url>
This is ApacheBench, Version 2.3 <$Revision: 1879490 $>
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Licensed to The Apache Software Foundation, http://www.apache.org/
Benchmarking <api_url> (be patient)
Completed 100 requests
Completed 200 requests
Finished 200 requests
Server Software: Apache/2.4.52
Server Hostname: <api_url>
Concurrency Level: 10
Time taken for tests: 13.210 seconds
Complete requests: 200
Failed requests: 0
Requests per second: 15.14 [#/sec] (mean)
Time per request: 660.524 [ms] (mean)
Time per request: 66.052 [ms] (mean, across all concurrent requests)
Transfer rate: 278.93 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 0 0.0 0 0
Processing: 237 644 126.4 666 933
Waiting: 229 641 125.6 666 922
Total: 237 644 126.4 666 933
Percentage of the requests served within a certain time (ms)
50% 666
66% 707
75% 724
80% 734
90% 791
95% 845
98% 908
99% 932
100% 933 (longest request)
Apache Benchmark Result of Live Server with concurrency 3
$ ab -n 200 -c 3 -s 800 <api_url>
This is ApacheBench, Version 2.3 <$Revision: 1901567 $>
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Licensed to The Apache Software Foundation, http://www.apache.org/
Benchmarking <api_url> (be patient)
Completed 100 requests
Completed 200 requests
Finished 200 requests
Server Software: Apache
Server Hostname: <api_url>
Concurrency Level: 3
Time taken for tests: 1275.103 seconds
Complete requests: 200
Failed requests: 0
Requests per second: 0.16 [#/sec] (mean)
Time per request: 19126.552 [ms] (mean)
Time per request: 6375.517 [ms] (mean, across all concurrent requests)
Transfer rate: 448.78 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 3 5 5.0 4 38
Processing: 13393 18910 1324.7 18391 21411
Waiting: 13344 18825 1321.8 18305 21360
Total: 13399 18914 1324.4 18395 21416
Percentage of the requests served within a certain time (ms)
50% 18395
66% 19192
75% 20377
80% 20592
90% 20842
95% 20964
98% 21174
99% 21297
100% 21416 (longest request)
Updated :-
Server MPM : prefork
Server API : CGI/FastCGI
**Issue :- ** when we send multiple requests at the same time, than why magento 2 takes to much time to respond to us.
what want wrong for me? please help me.
please guide me to improve performance of Magento 2.
