projects
/
fio.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
Add clue for ENOMEM hugepage allocation
[fio.git]
/
HOWTO
diff --git
a/HOWTO
b/HOWTO
index 99cbaea37eb760dca27875eab9bcb8bd9def2292..3af491325d3324b69117cc946728d7cd23ab8060 100644
(file)
--- a/
HOWTO
+++ b/
HOWTO
@@
-343,6
+343,9
@@
ioengine=str Defines how the job issues io to the file. The following
or receive, if the latter only the port
argument is used.
or receive, if the latter only the port
argument is used.
+ netsplice Like net, but uses splice/vmsplice to
+ map data and send/receive.
+
cpu Doesn't transfer any data, but burns CPU
cycles according to the cpuload= and
cpucycle= options. Setting cpuload=85
cpu Doesn't transfer any data, but burns CPU
cycles according to the cpuload= and
cpucycle= options. Setting cpuload=85
@@
-466,10
+469,16
@@
ratecycle=int Average bandwidth for 'rate' and 'ratemin' over this number
of milliseconds.
cpumask=int Set the CPU affinity of this job. The parameter given is a
of milliseconds.
cpumask=int Set the CPU affinity of this job. The parameter given is a
- bitmask of allowed CPU's the job may run on. See man
+ bitmask of allowed CPU's the job may run on. So if you want
+ the allowed CPUs to be 1 and 5, you would pass the decimal
+ value of (1 << 1 | 1 << 5), or 34. See man
sched_setaffinity(2). This may not work on all supported
operating systems or kernel versions.
sched_setaffinity(2). This may not work on all supported
operating systems or kernel versions.
+cpus_allowed=str Controls the same options as cpumask, but it allows a text
+ setting of the permitted CPUs instead. So to use CPUs 1 and
+ 5, you would specify cpus_allowed=1,5.
+
startdelay=int Start this job the specified number of seconds after fio
has started. Only useful if the job file contains several
jobs, and you want to delay starting some jobs to a certain
startdelay=int Start this job the specified number of seconds after fio
has started. Only useful if the job file contains several
jobs, and you want to delay starting some jobs to a certain
@@
-717,7
+726,10
@@
runt= The runtime of that thread
slat= Submission latency (avg being the average, stdev being the
standard deviation). This is the time it took to submit
the io. For sync io, the slat is really the completion
slat= Submission latency (avg being the average, stdev being the
standard deviation). This is the time it took to submit
the io. For sync io, the slat is really the completion
- latency, since queue/complete is one operation there.
+ latency, since queue/complete is one operation there. This
+ value can be in miliseconds or microseconds, fio will choose
+ the most appropriate base and print that. In the example
+ above, miliseconds is the best scale.
clat= Completion latency. Same names as slat, this denotes the
time from submission to completion of the io pieces. For
sync io, clat will usually be equal (or very close) to 0,
clat= Completion latency. Same names as slat, this denotes the
time from submission to completion of the io pieces. For
sync io, clat will usually be equal (or very close) to 0,