d/mutilate
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Indentation for command-line options.

Browse Source
This commit is contained in:
Jacob Leverich 2013-01-18 14:29:57 -08:00
parent 5a0fd63455
commit ac74a6ae40
1 changed files with 70 additions and 69 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

123
README.md
View File

@ -65,74 +65,75 @@ remote agents.
Command-line Options Command-line Options
==================== ====================
Usage: mutilate -s server[:port] [options]
"High-performance" memcached benchmarking tool Usage: mutilate -s server[:port] [options]
-h, --help Print help and exit "High-performance" memcached benchmarking tool
--version Print version and exit
-v, --verbose Verbosity. Repeat for more verbose.
--quiet Disable log messages.
Basic options: -h, --help Print help and exit
-s, --server=STRING Memcached server hostname[:port]. Repeat to specify --version Print version and exit
multiple servers. -v, --verbose Verbosity. Repeat for more verbose.
-q, --qps=INT Target aggregate QPS. 0 = peak QPS. (default=`0') --quiet Disable log messages.
-t, --time=INT Maximum time to run (seconds). (default=`5')
-K, --keysize=STRING Length of memcached keys (distribution).
(default=`30')
-V, --valuesize=STRING Length of memcached values (distribution).
(default=`200')
-r, --records=INT Number of memcached records to use. If multiple
memcached servers are given, this number is
divided by the number of servers.
(default=`10000')
-u, --update=FLOAT Ratio of set:get commands. (default=`0.0')
Advanced options: Basic options:
-T, --threads=INT Number of threads to spawn. (default=`1') -s, --server=STRING Memcached server hostname[:port]. Repeat to specify
-c, --connections=INT Connections to establish per server. (default=`1') multiple servers.
-d, --depth=INT Maximum depth to pipeline requests. (default=`1') -q, --qps=INT Target aggregate QPS. 0 = peak QPS. (default=`0')
-R, --roundrobin Assign threads to servers in round-robin fashion. -t, --time=INT Maximum time to run (seconds). (default=`5')
By default, each thread connects to every server. -K, --keysize=STRING Length of memcached keys (distribution).
-i, --iadist=STRING Inter-arrival distribution (distribution). Note: (default=`30')
The distribution will automatically be adjusted to -V, --valuesize=STRING Length of memcached values (distribution).
match the QPS given by --qps. (default=`200')
(default=`exponential') -r, --records=INT Number of memcached records to use. If multiple
--noload Skip database loading. memcached servers are given, this number is
--loadonly Load database and then exit. divided by the number of servers.
-B, --blocking Use blocking epoll(). May increase latency. (default=`10000')
-D, --no_nodelay Don't use TCP_NODELAY. -u, --update=FLOAT Ratio of set:get commands. (default=`0.0')
-w, --warmup=INT Warmup time before starting measurement.
-W, --wait=INT Time to wait after startup to start measurement.
-S, --search=N:X Search for the QPS where N-order statistic < Xus.
(i.e. --search 95:1000 means find the QPS where
95% of requests are faster than 1000us).
--scan=min:max:step Scan latency across QPS rates from min to max.
Agent-mode options: Advanced options:
-A, --agentmode Run client in agent mode. -T, --threads=INT Number of threads to spawn. (default=`1')
-a, --agent=host Enlist remote agent. -c, --connections=INT Connections to establish per server. (default=`1')
-l, --lambda_mul=INT Lambda multiplier. Increases share of QPS for this -d, --depth=INT Maximum depth to pipeline requests. (default=`1')
client. (default=`1') -R, --roundrobin Assign threads to servers in round-robin fashion.
By default, each thread connects to every server.
-i, --iadist=STRING Inter-arrival distribution (distribution). Note:
The distribution will automatically be adjusted to
match the QPS given by --qps.
(default=`exponential')
--noload Skip database loading.
--loadonly Load database and then exit.
-B, --blocking Use blocking epoll(). May increase latency.
-D, --no_nodelay Don't use TCP_NODELAY.
-w, --warmup=INT Warmup time before starting measurement.
-W, --wait=INT Time to wait after startup to start measurement.
-S, --search=N:X Search for the QPS where N-order statistic < Xus.
(i.e. --search 95:1000 means find the QPS where
95% of requests are faster than 1000us).
--scan=min:max:step Scan latency across QPS rates from min to max.
Some options take a 'distribution' as an argument. Agent-mode options:
Distributions are specified by <distribution>[:<param1>[,...]]. -A, --agentmode Run client in agent mode.
Parameters are not required. The following distributions are supported: -a, --agent=host Enlist remote agent.
-l, --lambda_mul=INT Lambda multiplier. Increases share of QPS for this
client. (default=`1')
[fixed:]<value> Always generates <value>. Some options take a 'distribution' as an argument.
uniform:<max> Uniform distribution between 0 and <max>. Distributions are specified by <distribution>[:<param1>[,...]].
normal:<mean>,<sd> Normal distribution. Parameters are not required. The following distributions are supported:
exponential:<lambda> Exponential distribution.
pareto:<loc>,<scale>,<shape> Generalized Pareto distribution.
gev:<loc>,<scale>,<shape> Generalized Extreme Value distribution.
To recreate the Facebook "ETC" request stream from [1], the [fixed:]<value> Always generates <value>.
following hard-coded distributions are also provided: uniform:<max> Uniform distribution between 0 and <max>.
normal:<mean>,<sd> Normal distribution.
exponential:<lambda> Exponential distribution.
pareto:<loc>,<scale>,<shape> Generalized Pareto distribution.
gev:<loc>,<scale>,<shape> Generalized Extreme Value distribution.
fb_value = a hard-coded discrete and GPareto PDF of value sizes To recreate the Facebook "ETC" request stream from [1], the
fb_key = "gev:30.7984,8.20449,0.078688", key-size distribution following hard-coded distributions are also provided:
fb_ia = "pareto:0.0,16.0292,0.154971", inter-arrival time dist.
[1] Berk Atikoglu et al., Workload Analysis of a Large-Scale Key-Value Store, fb_value = a hard-coded discrete and GPareto PDF of value sizes
SIGMETRICS 2012 fb_key = "gev:30.7984,8.20449,0.078688", key-size distribution
fb_ia = "pareto:0.0,16.0292,0.154971", inter-arrival time dist.
[1] Berk Atikoglu et al., Workload Analysis of a Large-Scale Key-Value Store,
SIGMETRICS 2012