add pres for perf

Signed-off-by: Manuel Traut <manut@mecka.net>

2 files changed, 133 insertions, 0 deletions

diff --git a/kernel-devel/kernel-perf/Makefile b/kernel-devel/kernel-perf/Makefile
new file mode 100644
index 0000000..d641258
--- /dev/null
+++ b/kernel-devel/kernel-perf/Makefile
@@ -0,0 +1,9 @@
+all:
+	for pdf in `ls -1 *.tex` ; do \
+		TEXINPUTS=`pwd`/../..:.:..:$(TEXINPUTS) pdflatex $$pdf; \
+		TEXINPUTS=`pwd`/../..:.:..:$(TEXINPUTS) pdflatex $$pdf; \
+	done
+
+clean:
+	rm -f *.aux *.log *.pdf *.log *.snm *.toc *.vrb *.nav *.out
+
diff --git a/kernel-devel/kernel-perf/pres_kernel-perf_en.tex b/kernel-devel/kernel-perf/pres_kernel-perf_en.tex
new file mode 100644
index 0000000..893aa70
--- /dev/null
+++ b/kernel-devel/kernel-perf/pres_kernel-perf_en.tex
@@ -0,0 +1,124 @@
+\input{configpres}
+
+\title{perf}
+\section{Performance Analyzation}
+\maketitle
+
+\begin{frame}
+\frametitle{What is perf?}
+Perf is a profiler tool for Linux 2.6+ based systems.
+\begin{itemize}
+\item perf\_events interface of the Linux kernel
+\item perf userspace tool
+\end{itemize}
+\end{frame}
+
+\begin{frame}
+\frametitle{perf events}
+\begin{itemize}
+\item hardware performance counters (PMU of Host CPU)
+\item tracepoint events (from ftrace)
+\item dynamic probes (e.g. kprobes or uprobes)
+\end{itemize}
+\end{frame}
+
+\begin{frame}
+\frametitle{perf subcommands I}
+\begin{description}
+\item[list]     list available events
+\item[stat]     measure total event count for single program or for system, for
+                  some time
+\item[top]      top-like dynamic view of hottest functions
+\item[record]   measure and save sampling data for single program
+\item[report]   analyze file generated by perf record;
+                  can generate flat, or graph profile
+\item[diff]     Read two perf.data files and display the differential profile
+\end{description}
+\end{frame}
+
+\begin{frame}
+\frametitle{perf subcommands II}
+\begin{description}
+\item[sched]    tracing/measuring of scheduler actions and latencies
+\item[lock]     analyze lock events
+\item[timechart]tool to visualize total system behavior during a workload
+\end{description}
+\end{frame}
+
+\begin{frame}[fragile]
+\frametitle{Example: live-view of page-fault event}
+\begin{lstlisting}
+# perf stat chromium
+ Performance counter stats for 'chromium':
+
+       3733.112825 task-clock                #    0.716 CPUs utilized
+             8,696 context-switches          #    0.002 M/sec
+             1,063 cpu-migrations            #    0.285 K/sec
+           134,686 page-faults               #    0.036 M/sec
+     9,102,760,996 cycles                    #    2.438 GHz
+[83.59%]
+     6,217,623,412 stalled-cycles-frontend   #   68.30% frontend cycles idle
+[83.32%]
+     4,755,104,208 stalled-cycles-backend    #   52.24% backend  cycles idle
+[67.20%]
+     7,262,564,269 instructions              #    0.80  insns per cycle
+                                             #    0.86  stalled cycles per insn
+[83.72%]
+     1,495,191,394 branches                  #  400.521 M/sec
+[83.38%]
+        26,037,805 branch-misses             #    1.74% of all branches
+[83.04%]
+
+       5.214978731 seconds time elapsed
+\end{lstlisting}
+\end{frame}
+
+\begin{frame}[fragile]
+\frametitle{Example: live-view of page-fault event}
+\begin{lstlisting}
+# sudo perf top -e page-faults
+Samples: 562  of event 'page-faults', Event count (approx.): 4557
+ 62.32%  libc-2.17.so              [.] __memcpy_ssse3_back
+ 20.36%  libc-2.17.so              [.] _int_malloc
+  3.16%  module.so                 [.] evas_gl_common_context_font_push
+  2.83%  libevas.so.1.7.7          [.] 0x0000000000083237
+  2.37%  libdricore9.0.2.so.1.0.0  [.] 0x0000000000126050
+  1.80%  libxul.so (deleted)       [.] 0x000000000182e48f
+  1.12%  [kernel]                  [k] file_read_actor
+  0.92%  libfontconfig.so.1.6.2    [.] 0x000000000001bd43
+  0.88%  libdrm_intel.so.1.0.0     [.] 0x0000000000008503
+  0.79%  libc-2.17.so              [.] __memset_sse2
+  0.75%  libeet.so.1.7.7           [.] eet_data_image_header_decode_cipher
+  0.61%  module.so                 [.] evas_gl_common_context_image_push
+  0.42%  libfreetype.so.6.10.0     [.] FT_Stream_ReadFields
+  0.42%  libecore_x.so.1.7.7       [.] ecore_x_netwm_icons_set
+  0.24%  libelementary.so.1.7.7    [.] 0x000000000005ae60
+\end{lstlisting}
+\end{frame}
+
+
+\begin{frame}[fragile]
+\frametitle{Example: count CPU cycles of a ls call}
+\begin{lstlisting}
+# perf record -e cpu-cycles ls
+<output of ls>
+[ perf record: Woken up 1 times to write data ]
+[ perf record: Captured and wrote 0.008 MB perf.data (~334 samples) ]
+# perf report
+Samples: 24  of event 'cpu-cycles', Event count (approx.): 12333055
+ 21.67%  ls  [kernel.kallsyms]  [k] get_unmapped_area
+ 20.77%  ls  ld-2.17.so         [.] _dl_map_object_deps
+ 17.21%  ls  [kernel.kallsyms]  [k] __slab_free
+ 15.73%  ls  [kernel.kallsyms]  [k] tty_insert_flip_string_fixed_flag
+ 12.65%  ls  [kernel.kallsyms]  [k] unlock_page
+  6.94%  ls  libc-2.17.so       [.] __strlen_sse2
+  3.41%  ls  [kernel.kallsyms]  [k] count.isra.17.constprop.28
+  1.02%  ls  [kernel.kallsyms]  [k] get_pageblock_flags_group
+  0.41%  ls  [kernel.kallsyms]  [k] perf_event_context_sched_in
+  0.13%  ls  [kernel.kallsyms]  [k] perf_ctx_unlock
+  0.07%  ls  [kernel.kallsyms]  [k] native_write_msr_safe
+\end{lstlisting}
+\end{frame}
+
+
+\input{tailpres}