device list argument to -D|--devices separated by semicolon not colon
Fixes: 512566d40074 ("BTT: Added user guide")
incoming requests either go through Q2G+G2I or Q2M,
rather than Q2G+Q2I or Q2M,
otherwise Q2G would be counted twice for the sum of Q2G+Q2I==Q2G+(Q2G+G2I)
typo: ov => of
typo: Aerage => Average
file_mbps_fp.dat provides data for mebibytes not millibits per second
consistent upper case usage for Q2d, D2c
--iostat|-I producing results "from" iostat sounded as if we would really
run the iostat tool in parallel, but we only emulate the same output from
just our own blktrace data "as if" we would have been running iostat in
parallel
--per-io-dump|-p records are separated by blank lines, not blank spaces
describe freq argument to --periodic-latencies|-L as in man page
--dev-maps|-M seems no longer under construction so describe what the code
supports since commit 63eba14776db ("[PATCH] Add Alan's btt tool")
typographical double quotes in regular text (as opposed to verbatim)
typo: performend => performed
--time-start/-t and --time-end/T: for easier readability use same
consistent phrasing with the case of unspecified option in parentheses
typo: exentsion => extension
copy&paste: short option -Z is long option -do-active, not --q2d-latencies
Fixes: 2e37a10ee8b4 ("btt: Added in I/O activity per device and system-wide")
man page: --per-io-dump|-p seems to also show get request traces ('G')
according to code and corresponding example in btt.tex
Signed-off-by: Steffen Maier <maier@xxxxxxxxxxxxx>
---
btt/doc/btt.tex | 43 ++++++++++++++++++++++++++++---------------
doc/btt.1 | 2 +-
2 files changed, 29 insertions(+), 16 deletions(-)
diff --git a/btt/doc/btt.tex b/btt/doc/btt.tex
index dbd1fde612d4..92507f3071ac 100644
--- a/btt/doc/btt.tex
+++ b/btt/doc/btt.tex
@@ -196,7 +196,7 @@ Q2C 0.000207665 0.125405263 1.830917198 2262311
IO\footnote{It should be noted that incoming requests either go through:
\begin{enumerate}
- \item Q2G + Q2I
+ \item Q2G + G2I
or
@@ -354,8 +354,8 @@ IO\footnote{It should be noted that incoming requests either go through:
\begin{description}
\item[\# Live] Number of periods of ``liveness.''
- \item[Avg. Act] Average length of each period ov ``liveness.''
- \item[Avg. !Act] Aerage length of each non-active period.
+ \item[Avg. Act] Average length of each period of ``liveness.''
+ \item[Avg. !Act] Average length of each non-active period.
\item[\% Live] Percent of total time spent with the driver/device active.
\end{description}
@@ -475,7 +475,7 @@ pdflush 0.000000790 0.000006752 0.247231307 179791
see section~\ref{sec:dhist}.
\item[\emph{file}\_mbps\_fp.dat] Provides a set of data for
- mb-per-second values each second
+ MiB-per-second values each second
- for more information see section~\ref{sec:rstat}.
\item[\emph{file}\_iops\_fp.dat] Provides a set of data for
@@ -502,7 +502,7 @@ pdflush 0.000000790 0.000006752 0.247231307 179791
than grepping through a blkparse output file for example). The
details on this file is included in section~\ref{sec:per-io}.
- \item[iostat] Latency information -- both Q2d, D2c and Q2C --
+ \item[iostat] Latency information -- both Q2D, D2C and Q2C --
on a per-IO basis can be generated. These are described in
section~\ref{sec:lat}.
@@ -681,7 +681,7 @@ figure~\ref{fig:rstats}).
\newpage\section{iostat Data File}
\label{sec:iostat}
- \texttt{btt} attempts to produce the results from running an
+ \texttt{btt} attempts to produce the results as if running an
\texttt{iostat -x} command in parallel with the system as it is being
traced. The fields (columns) generated by the \texttt{--iostat} or
\texttt{-I} option can be seen from the following output snippet --
@@ -720,7 +720,7 @@ Device: rrqm/s wrqm/s r/s w/s rsec/s wsec/s
The \emph{--per-io-dump} or \emph{-p} option triggers this behavior,
and will produce a file containing streams of IOs (separated by blank
- spaces). As an example, here is a snippet of 4 IOs that were merged
+ lines). As an example, here is a snippet of 4 IOs that were merged
together, you will note there are 3 merged IOs, and 1 inserted in the
stream. The issue and completion traces are replicated per IO.
@@ -975,8 +975,8 @@ Usage: btt 2.09
the traces parsed. With this option, one can reduce the analysis to
one or more devices provided in the string passed to this option. The
device identifiers are the major and minor number of each device, and
- each device identifier is separated by a colon (:). A valid specifier
- for devices 8,0 and 8,8 would then be: \texttt{"8,0:8,8"}.
+ each device identifier is separated by a semicolon (;). A valid specifier
+ for devices 8,0 and 8,8 would then be: \texttt{"8,0;8,8"}.
\subsection{\texttt{--exes}/\texttt{-e}}
\label{sec:o-e}
@@ -1019,6 +1019,8 @@ Usage: btt 2.09
When given a value greater than 0, this option will create two data
files (q2c \& d2c) per device containing a periodic timestamp \&
average latency over that period.
+ The frequency argument value is a floating point value expressing seconds
+ for the period length.
\subsection{\texttt{--seeks-per-second}\texttt{-m}}
\label{sec:o-m}
@@ -1036,7 +1038,18 @@ Usage: btt 2.09
\subsection{\texttt{--dev-maps}/\texttt{-M}}
\label{sec:o-M}
- Internal option, still under construction.
+ Takes a previously created text file with one device mapping per line.
+ Each line contains a word string representing the device name,
+ a space character as field separator, and in the second field the major and
+ minor device number in comma separated format.
+ Lines which contain the substring ``Device'' are ignored.
+ E.g.\
+\begin{verbatim}
+Devices mapping names from major,minor device IDs
+/dev/sda 8,0
+/dev/sdb 8,16
+\end{verbatim}
+ This allows for better output of device names.
\subsection{\texttt{--output-file}/\texttt{-o}}
\label{sec:o-o}
@@ -1055,7 +1068,7 @@ Usage: btt 2.09
\label{sec:o-P}
The \texttt{-P} option will generate a file that contains a list of all IO
-"sequences" - showing only the Q, D \& C operation times. The D \& C
+``sequences'' - showing only the Q, D \& C operation times. The D \& C
time values are separated from the Q time values with a vertical bar.
\subsection{\texttt{--q2c-latencies}/\texttt{-q}}
@@ -1070,7 +1083,7 @@ time values are separated from the Q time values with a vertical bar.
This option tells \texttt{btt} to generate a data file (using the given
name as a base) which contains: A time stamp in the first column,
and then the number of \emph{active} requests issued to the device
- driver. (The value is incremented when an \emph{issue} is performend,
+ driver. (The value is incremented when an \emph{issue} is performed,
and decremented when a \emph{complete} is performed.
\subsection{\texttt{--no-remaps}/\texttt{-r}}
@@ -1105,7 +1118,7 @@ time values are separated from the Q time values with a vertical bar.
These options allow one to dictate to \texttt{btt} when to start and stop
parsing of trace data in terms of seconds since the start of the run. The
trace chosen will be between the start time (or 0.0 if not
- specified) and end time (or the end of the run) specified.
+ specified) and end time (or the end of the run if not specified).
\subsection{\texttt{--unplug-hist}/\texttt{-u}}
\label{sec:o-u}
@@ -1168,7 +1181,7 @@ Sending stats data to bttX.avg
\emph{Some} of the data produced by default can also be shipped
simultaneously to another file in an easy to parse form. When
the \texttt{-o} option is selected (thus producing a file with a
- \texttt{.avg} exentsion), \emph{and} the \texttt{-X} flag is present,
+ \texttt{.avg} extension), \emph{and} the \texttt{-X} flag is present,
then \texttt{btt} will generate this file.
The format is space-delimited values starting with a 3-character
@@ -1231,7 +1244,7 @@ ARQ 8,16 12.938165321
This option instructs \texttt{btt} to generate the Q2D latency file
discussed in section~\ref{sec:lat-q2d}.
-\subsection{\texttt{--q2d-latencies}/\texttt{-Z}}
+\subsection{\texttt{--do-active}/\texttt{-Z}}
\label{sec:o-Z}
This option generates per-device (and total system) data files. Each
diff --git a/doc/btt.1 b/doc/btt.1
index 28cf912d2ebb..97296b95c73b 100644
--- a/doc/btt.1
+++ b/doc/btt.1
@@ -234,7 +234,7 @@ Specifies the output file name.
.B \-\-per\-io\-dump=<\fIoutput name\fR>
.RS 4
The \-p option will generate a file that contains a list of all IO
-"sequences" \- showing the parts of each IO (Q, A, I/M, D, & C).
+"sequences" \- showing the parts of each IO (Q, A, G, I/M, D, & C).
.RE
.B \-P <\fIoutput name\fR>
--
2.14.2
--
To unsubscribe from this list: send the line "unsubscribe linux-btrace" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
