docs: move rate_cycle description

[fio.git] / HOWTO.rst

diff --git a/HOWTO.rst b/HOWTO.rst
index bbd9496eefb37f952e3dea1f76adbd2df54a2e76..8d4c6e1cca48324cb7a566ae795cfe0351181027 100644 (file)
--- a/HOWTO.rst
+++ b/HOWTO.rst
@@ -1232,13 +1232,12 @@ I/O type
 
 .. option:: randrepeat=bool
 
 
 .. option:: randrepeat=bool
 

-       Seed the random number generator used for random I/O patterns in a
-       predictable way so the pattern is repeatable across runs. Default: true.
+        Seed all random number generators in a predictable way so the pattern
+        is repeatable across runs. Default: true.

 
 .. option:: allrandrepeat=bool
 
 
 .. option:: allrandrepeat=bool
 

-       Seed all random number generators in a predictable way so results are
-       repeatable across runs.  Default: false.
+       Alias for :option:`randrepeat`. Default: true.

 
 .. option:: randseed=int
 
 
 .. option:: randseed=int
 


@@ -1308,6 +1307,11 @@ I/O type
                **random**
                        Advise using **FADV_RANDOM**.
 
                **random**
                        Advise using **FADV_RANDOM**.
 

+               **noreuse**
+                       Advise using **FADV_NOREUSE**. This may be a no-op on older Linux
+                       kernels. Since Linux 6.3, it provides a hint to the LRU algorithm.
+                       See the :manpage:`posix_fadvise(2)` man page.
+

 .. option:: write_hint=str
 
        Use :manpage:`fcntl(2)` to advise the kernel what life time to expect
 .. option:: write_hint=str
 
        Use :manpage:`fcntl(2)` to advise the kernel what life time to expect


@@ -3199,6 +3203,11 @@ I/O rate
        fio will ignore the thinktime and continue doing IO at the specified
        rate, instead of entering a catch-up mode after thinktime is done.
 
        fio will ignore the thinktime and continue doing IO at the specified
        rate, instead of entering a catch-up mode after thinktime is done.
 

+.. option:: rate_cycle=int
+
+       Average bandwidth for :option:`rate` and :option:`rate_min` over this number
+       of milliseconds. Defaults to 1000.
+

 
 I/O latency
 ~~~~~~~~~~~
 
 I/O latency
 ~~~~~~~~~~~


@@ -3237,11 +3246,6 @@ I/O latency
        microseconds. Comma-separated values may be specified for reads, writes,
        and trims as described in :option:`blocksize`.
 
        microseconds. Comma-separated values may be specified for reads, writes,
        and trims as described in :option:`blocksize`.
 

-.. option:: rate_cycle=int
-
-       Average bandwidth for :option:`rate` and :option:`rate_min` over this number
-       of milliseconds. Defaults to 1000.
-

 
 I/O replay
 ~~~~~~~~~~
 
 I/O replay
 ~~~~~~~~~~


@@ -3821,10 +3825,11 @@ Steady state
 
 .. option:: steadystate_duration=time, ss_dur=time
 
 
 .. option:: steadystate_duration=time, ss_dur=time
 

-       A rolling window of this duration will be used to judge whether steady state
-       has been reached. Data will be collected once per second. The default is 0
-       which disables steady state detection.  When the unit is omitted, the
-       value is interpreted in seconds.
+        A rolling window of this duration will be used to judge whether steady
+        state has been reached. Data will be collected every
+        :option:`ss_interval`.  The default is 0 which disables steady state
+        detection.  When the unit is omitted, the value is interpreted in
+        seconds.

 
 .. option:: steadystate_ramp_time=time, ss_ramp=time
 
 
 .. option:: steadystate_ramp_time=time, ss_ramp=time
 


@@ -3832,6 +3837,14 @@ Steady state
        collection for checking the steady state job termination criterion. The
        default is 0.  When the unit is omitted, the value is interpreted in seconds.
 
        collection for checking the steady state job termination criterion. The
        default is 0.  When the unit is omitted, the value is interpreted in seconds.
 

+.. option:: steadystate_check_interval=time, ss_interval=time
+
+        The values during the rolling window will be collected with a period of
+        this value. If :option:`ss_interval` is 30s and :option:`ss_dur` is
+        300s, 10 measurements will be taken. Default is 1s but that might not
+        converge, especially for slower devices, so set this accordingly. When
+        the unit is omitted, the value is interpreted in seconds.
+

 
 Measurements and reporting
 ~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 Measurements and reporting
 ~~~~~~~~~~~~~~~~~~~~~~~~~~


@@ -4404,15 +4417,23 @@ writes in the example above).  In the order listed, they denote:
                 It is the sum of submission and completion latency.
 
 **bw**
                 It is the sum of submission and completion latency.
 
 **bw**

-               Bandwidth statistics based on samples. Same names as the xlat stats,
-               but also includes the number of samples taken (**samples**) and an
-               approximate percentage of total aggregate bandwidth this thread
-               received in its group (**per**). This last value is only really
-               useful if the threads in this group are on the same disk, since they
-               are then competing for disk access.
+               Bandwidth statistics based on measurements from discrete
+               intervals. Fio continuously monitors bytes transferred and I/O
+               operations completed. By default fio calculates bandwidth in
+               each half-second interval (see :option:`bwavgtime`) and reports
+               descriptive statistics for the measurements here. Same names as
+               the xlat stats, but also includes the number of samples taken
+               (**samples**) and an approximate percentage of total aggregate
+               bandwidth this thread received in its group (**per**). This
+               last value is only really useful if the threads in this group
+               are on the same disk, since they are then competing for disk
+               access.

 
 **iops**
 
 **iops**

-               IOPS statistics based on samples. Same names as bw.
+               IOPS statistics based on measurements from discrete intervals.
+               For details see the description for bw above. See
+               :option:`iopsavgtime` to control the duration of the intervals.
+               Same values reported here as for bw except for percentage.

 
 **lat (nsec/usec/msec)**
                The distribution of I/O completion latencies. This is the time from when
 
 **lat (nsec/usec/msec)**
                The distribution of I/O completion latencies. This is the time from when