Lines Matching refs:IO
32 \texttt{btt} is a post-processing tool for the block layer IO tracing
36 is a block layer IO tracing mechanism which provides detailed
41 form of multiple individual traces per IO executed during the traced
43 IO rates and the like. \texttt{btt} goes further and produces a variety
108 \item[average component times across all IOs] The time line of each IO
112 \item Time needed to insert or merge an incoming IO onto the request
113 queue. This is the average time from when the IO enters the block
114 IO layer (queue trace) until it is inserted (insert trace).
136 the IO is inserted or merged onto the request queue, until it is
145 actual IO was issued to the driver until is completed (completion
146 trace) back to the block IO layer.
156 being handed to the block IO layer.
163 are combined via merges into a single IO issued and completed. We
190 as to where IO spend most of the time on average. The following output
192 IO\footnote{It should be noted that incoming requests either go through:
214 hardware) is to understand the block IO layer ends up merging incoming
228 we see that (on average) the block IO layer is combining upwards of
229 125 incoming requests into a single request down the IO stack. The
230 resultant average IO size is 124 blocks.
244 providing a set of indicators showing how close incoming IO requests
246 providing a set of indicators showing how close the IO requests are
259 the block IO layer in adjacent sectors. (Obviously, the higher this
265 such times the IO request queue elements are not able to be processed
321 An important consideration when analyzing block IO schedulers is to
324 being held by the IO scheduler when an incoming IO request was being
361 to do with the originating IO. For example, if an application is
362 doing buffered IO, then the actual submitted IOs will most likely
366 the IO in the first place.
405 IO enters the block IO layer for a given
437 incoming IO requests, for more information see section~\ref{sec:qhist}.
440 of IO requests submitted to lower layer drivers, for more information
458 \item[per IO detail] Each and every IO traced can be output in a form
459 that shows each of the IO components on consecutive lines (rather
461 details on this file is included in section~\ref{sec:per-io}.
464 on a per-IO basis can be generated. These are described in
467 \item[seek details] A set of data files containing all IO-to-IO
555 outgoing IO sizes (in blocks). For simplicity, the histogram buckets
556 are one-for-one for sizes up to 1,024 blocks in the IO, and then a
564 The first column (X values) is the various IO sizes, and the second
574 red point (representing 8 blocks per IO), whereas the other two had
588 and blue dots are somewhat similar below about 192 blocks per IO going
619 \newpage\section{\label{sec:per-io}Per-IO Data File}
622 IO processed. The time line data contains rudimentary information for
635 The \emph{--per-io-dump} or \emph{-p} option triggers this behavior,
639 stream. The issue and completion traces are replicated per IO.
679 provide per-IO latency information, one for queue time (Q2D), one
680 for total IO time (Q2C) and one for latencies induced by lower layer
689 \texttt{btt} can also produce two data files containing all IO-to-IO sector
722 sectors from the previous IO in column 2 (Y values). Here is a snippet
754 \emph{closest} distance between the previous IO and this IO. The
756 \emph{end} of the previous IO and the beginning of the next, or the
757 end of this IO and the start of the next.
761 between the end of the previous IO and the start of this IO.
817 [ -p <output name> | --per-io-dump=<output name> ]
818 [ -P <output name> | --per-io-trees=<output name> ]
836 seek distances based solely upon the ending block address of one IO,
838 of the closeness to either the beginning or end of the previous IO. See
943 \subsection{\label{sec:o-p}\texttt{--per-io-dump}/\texttt{-p}}
945 This option tells \texttt{btt} to generate the per IO dump file as
946 discussed in section~\ref{sec:per-io}.
948 \subsection{\label{sec:o-P}\texttt{--per-io-tress}/\texttt{-P}}
950 The \texttt{-P} option will generate a file that contains a list of all IO
1121 display will display \emph{each} IO generated, with the time (seconds)
1123 number of blocks transferred in the IO represented along the Z-axis.
