Searched refs:emph (Results 1 – 25 of 27) sorted by relevance
12
46 run in \emph{live} mode directly outputs data collected by blktrace.75 A patch for a \emph{specific Linux kernel} is provided in bt/kernel (where76 \emph{bt} is the name of the directory from the above git sequence). The96 \emph{Support for tracing block io actions.} To do this, run102 and navigate through \emph{Device Drivers} and \emph{Block devices}103 and then down to \emph{Support for tracing block io actions} and hit Y.186 A \emph{btrace} script is included in the distribution to ease live193 By default, \emph{btrace} runs the trace in quiet mode so it will not194 include statistics when you break the run. Add the \emph{-S} option to201 by applications using the SCSI Generic (\emph{sg}) interface.[all …]
48 \emph on 99 \emph on 101 \emph default 117 \emph on 119 \emph default 168 \emph on 170 \emph default 184 \emph on 186 \emph default 190 \emph on [all …]
62 one is able to \emph{replay} the IO again on the same machine or another71 the only traces you are interested in are \emph{QUEUE} requests --106 IOs during the sample workload. \texttt{btreplay} \emph{attempts} to115 during replays. In addition the actual ordering of IOs \emph{between}133 multiple sequential (in time) IOs and put them in a single \emph{bunch} of134 IOs that will be processed as a single \emph{asynchronous IO} call to the138 code, and thus are submitted to the block IO layer with \emph{very small}139 time intervals between issues.}. To manage the size of the \emph{bunches},145 for \emph{bunching.} The default time is 10 milliseconds (10,000,000149 \item[\texttt{--max-pkts}] A \emph{bunch} size can be anywhere from[all …]
18 \emph{OzLabs, IBM Linux Technology Center}}25 \newcommand{\fixme}[1]{$\bigstar$\emph{\textbf{\large #1}}$\bigstar$\xspace}76 Each node contains \emph{properties}, name--value pairs that give136 \item \emph{relocatable}: the bootloader or kernel should be able to140 \item \emph{insert and delete}: sometimes the bootloader might want to147 \item \emph{compact}: embedded systems are frequently short of161 \texttt{0x04} & \emph{totalsize} \\\cline{2-2}162 \texttt{0x08} & \emph{off\_struct} & \\\cline{2-2}163 \texttt{0x0C} & \emph{off\_strs} & \\\cline{2-2}164 \texttt{0x10} & \emph{off\_rsvmap} & \\\cline{2-2}[all …]
81 -- utilizing \texttt{btt} on \emph{unclean} trace files produces116 This is denoted as \emph{Q2I} time.119 occasion there are also some time spent \emph{sleeping} waiting124 \item[Q2G] Time needed to \emph{get} a request (get request131 For \emph{merged} requests -- an incoming request that is merged132 with a previously submitted request -- we calculate \emph{Q2M}, the139 Referred to as \emph{I2D} time\footnote{The \emph{issue} trace142 \emph{insert} traces.}.148 This is referred to as the \emph{D2C} time\154 \item \emph{Q2Q} which measures the time between queue traces[all …]
67 within a running program. This is called \emph{local} unwinding. Say71 initialize an \emph{unwind~cursor} based on this snapshot. This is104 by definition, only the \emph{preserved} machine state can be accessed106 \emph{callee-saved} (``preserved'') registers. However, in some108 \emph{caller-saved} (``scratch'') registers are preserved in the stack178 arguments: a pointer to a set of \emph{accessor} routines and an208 We call the machine that is running \Prog{libunwind} the \emph{host}210 \emph{target}. If the host and the target platform are the same, we211 call it \emph{native} unwinding. If they differ, we call it212 \emph{cross-platform} unwinding.[all …]
14 the \emph{frame state} of each frame in a call-chain. The frame state16 \emph{frame registers} (typically the instruction-pointer and the23 emitting \emph{unwind-info} which provides the minimum amount of30 For the purpose of this discussion, a \emph{procedure} is defined to31 be an arbitrary piece of \emph{contiguous} code. Normally, each41 A procedure logically consists of a sequence of \emph{regions}.45 \emph{prologue}, a \emph{body}, and an \emph{epilogue}. Each of them138 the \emph{demangled} version of the name.174 the \emph{demangled} version of the name.229 negative value indicates that the region covers the last \emph{N}[all …]
34 reverse is \emph{not} true and it is \emph{not} safe to use structures
31 \Func{\_U\_dyn\_cancel}() is thread-safe but \emph{not} safe to use
32 \Func{\_U\_dyn\_register}() is thread-safe but \emph{not} safe to use
31 instruction \emph{beyond} the end of the procedure. If this address39 handler routine. This is sometimes called the \emph{personality}
28 but \emph{never} less. In other words, \Func{unw\_flush\_cache}() may
42 gain access to the machine-state and virtual memory of \emph{another}64 initialization. Also, when using \Var{\_UPT\_accessors}, \emph{all}
56 \Func{unw\_set\_caching\_policy}() is thread-safe but \emph{not} safe
36 in \emph{any} process, including the local process in which the
53 Note that \Func{unw\_resume}() does \emph{not} invoke any unwind
108 \Func{find\_proc\_info}(). Note that \Prog{libunwind} does \emph{not}245 \Func{unw\_create\_addr\_space}() is thread-safe but \emph{not}
48 accessible when. In case of doubt, it is always safe to \emph{try} to
284 \emph on286 \emph default288 \emph on290 \emph default304 \emph on306 \emph default768 \emph on770 \emph default
318 if isinstance(f, Emph) or f in conf.emph:1005 if isinstance(f, Emph) or f in conf.emph:1187 if self.__class__ in conf.emph:1190 if f in conf.emph:
429 emph = Emphasize() variable in Conf
307 parameter, rather than in an external variable. @emph{Provide grammatical522 Honeywell Information Systems, for not killing off the @emph{Multics}
1784 \let\emph=\smartitalic3376 \definedummyword\emph
1255 <xsl:template match="spanx[@style='emph' or not(@style)]">