kris/httperf
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

convert README to markdown

Browse Source
This commit is contained in:
Mark Nottingham 2015-03-14 15:06:50 +11:00
parent 4ee16eb53b
commit 08b6b19782
1 changed files with 13 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
README
View File

@ -1,6 +1,5 @@
-*-Mode: outline-*-
* Building httperf ## Building httperf
This release of httperf is using the standard GNU configuration This release of httperf is using the standard GNU configuration
mechanism. The following steps can be used to build it: mechanism. The following steps can be used to build it:
@ -80,7 +79,7 @@ Solaris 8 (UltraSparc 64-bit)
It should be straight-forward to build httperf on other platforms, please report It should be straight-forward to build httperf on other platforms, please report
any build problems to the mailing list along with the platform specifications. any build problems to the mailing list along with the platform specifications.
* Mailing list ## Mailing list
A mailing list has been set up to encourage discussions among the A mailing list has been set up to encourage discussions among the
httperf user community. This list is managed by majordomo. To httperf user community. This list is managed by majordomo. To
@ -91,7 +90,7 @@ subscribe to the list, send a mail containing the body:
to majordomo@linux.hpl.hp.com. To post an article to the list, send to majordomo@linux.hpl.hp.com. To post an article to the list, send
it directly to httperf@linux.hpl.hp.com. it directly to httperf@linux.hpl.hp.com.
* Running httperf ## Running httperf
IMPORTANT: It is crucial to run just one copy of httperf per client IMPORTANT: It is crucial to run just one copy of httperf per client
machine. httperf sucks up all available CPU time on a machine. It is machine. httperf sucks up all available CPU time on a machine. It is
@ -101,11 +100,11 @@ ensure that it can generate the desired workload with good accuracy,
so do not try to change this without fully understanding what the so do not try to change this without fully understanding what the
issues are. issues are.
** Examples ### Examples
The simplest way to invoke httperf is with a command line of the form: The simplest way to invoke httperf is with a command line of the form:
httperf --server wailua --port 6800 > httperf --server wailua --port 6800
This command results in httperf attempting to make one request for URL This command results in httperf attempting to make one request for URL
http://wailua:6800/. After the reply is received, performance http://wailua:6800/. After the reply is received, performance
@ -124,7 +123,7 @@ value using the --timeout option. In the example below, a timeout of
one second is specified (the ramification of this option will be one second is specified (the ramification of this option will be
explained later): explained later):
httperf --server wailua --port 6800 --num-conns 100 --rate 10 --timeout 1 > httperf --server wailua --port 6800 --num-conns 100 --rate 10 --timeout 1
The performance statistics printed by httperf at the end of the test The performance statistics printed by httperf at the end of the test
might look like this: might look like this:
@ -157,7 +156,7 @@ received from the server ("Reply"), miscellaneous results relating to
the CPU time and network bandwidth used, and, finally, a summary of the CPU time and network bandwidth used, and, finally, a summary of
errors encountered ("Errors"). Let's discuss each in turn: errors encountered ("Errors"). Let's discuss each in turn:
** "Total" Results ## "Total" Results
The "Total" line summarizes how many TCP connections were initiated by The "Total" line summarizes how many TCP connections were initiated by
the client, how many requests it sent, how many replies it received, the client, how many requests it sent, how many replies it received,
@ -169,7 +168,7 @@ replies were received. It also shows that total test-duration was
Total: connections 100 requests 100 replies 100 test-duration 9.905 s Total: connections 100 requests 100 replies 100 test-duration 9.905 s
** "Connection" Results ## "Connection" Results
These results convey information related to the TCP connections that These results convey information related to the TCP connections that
are used to communicate with the web server. are used to communicate with the web server.
@ -221,7 +220,7 @@ responses.
Connection length [replies/conn]: 1.000 Connection length [replies/conn]: 1.000
** "Request" Results ## "Request" Results
The first line in the "Request"-related results give the rate at which The first line in the "Request"-related results give the rate at which
HTTP requests were issued and the period-length that the rate HTTP requests were issued and the period-length that the rate
@ -243,7 +242,7 @@ the line show below, the average request size was 57 bytes.
Request size [B]: 57.0 Request size [B]: 57.0
** "Reply" Results ## "Reply" Results
For simple measurements, the section with the "Reply" results is For simple measurements, the section with the "Reply" results is
probably the most interesting one. The first line gives statistics on probably the most interesting one. The first line gives statistics on
@ -292,7 +291,7 @@ were "successful" replies as they contained a status code of 200
Reply status: 1xx=0 2xx=100 3xx=0 4xx=0 5xx=0 Reply status: 1xx=0 2xx=100 3xx=0 4xx=0 5xx=0
** Miscellaneous Results ## Miscellaneous Results
This section starts with a summary of the CPU time the client This section starts with a summary of the CPU time the client
consumed. The line below shows that 2.71 seconds were spent executing consumed. The line below shows that 2.71 seconds were spent executing
@ -322,7 +321,7 @@ network payload only (i.e., it doesn't account for protocol headers)
and does not take into account retransmissions that may occur at the and does not take into account retransmissions that may occur at the
TCP level. TCP level.
** "Errors" ## "Errors"
The final section contains statistics on the errors that occurred The final section contains statistics on the errors that occurred
during the test. The "total" figure shows the total number of errors during the test. The "total" figure shows the total number of errors
@ -379,7 +378,7 @@ The meaning of each error is described below:
debug support and specifying option --debug 1. debug support and specifying option --debug 1.
** Selecting appropriate timeout values ## Selecting appropriate timeout values
Since the client machine has only a limited set of resource available, Since the client machine has only a limited set of resource available,
it cannot sustain arbitrarily high HTTP request rates. One limit is it cannot sustain arbitrarily high HTTP request rates. One limit is