Mobile/Fennec/Android/Profiling: Difference between revisions

Mobile/Fennec/Android/Profiling (view source)

Revision as of 22:10, 2 September 2011

6,121 bytes added , 2 September 2011

→‎systemtap

Nchen

Confirmed users

507

edits

@@ Line 619: / Line 619: @@
 = systemtap =
+== Compiling systemtap ==
+Think of the children, get the [http://www.jnchen.com/_media/projects/mozilla/moz-systemtap-1.5.tar.bz2 prebuilt version]. Extract it to your host machine, and to /data on your device.
+Basically running systemtap consists of the host portion and the target portion. For the host portion you use a standard systemtap installation to cross compile your script into a kernel module. For the target portion you transfer the kernel module to your device and run it on the device.
+The host portion you can get through apt-get. The target portion you have to compile (use the [http://www.codesourcery.com/sgpp/lite/arm/portal/subscription?@template=lite CodeSourcery ARM GNU/Linux toolchain]):
+ LDFLAGS=-static \
+   ac_cv_file__usr_include_avahi_common=no \
+   ac_cv_file__usr_include_avahi_client=no \
+   ac_cv_file__usr_include_nspr=no \
+   ac_cv_file__usr_include_nspr4=no \
+   ac_cv_file__usr_include_nss=no \
+   ac_cv_file__usr_include_nss3=no \
+   ./configure --prefix=/data/systemtap --host=arm-none-linux-gnueabi \
+     --disable-translator --disable-nls
+ make install
+Note that prefix has to be /data/systemtap (or another path that matches Android file system) so you need to make a /data directory on your host machine before you run make install.
+You might need libelf. Get the latest elfutils release, then compile:
+ ./configure --host=arm-none-linux-gnueabi --disable-nls \
+   --prefix=/PATH/TO/TOOLCHAIN/arm-none-linux-gnueabi/libc/usr
+ cd libelf
+ make install
+Where /PATH/TO/TOOLCHAIN is the path to your CodeSourcery toolchain.
+== Using systemtap ==
+Before you start, you need the source of your device's kernel. See the oprofile section for one example way to get the kernel source.
+To compile your script on the host, make sure you have the NDK toolchain (r5 or above), then run
+ stap -gv -a arm -B CROSS_COMPILE=arm-linux-androideabi- \
+   -r /PATH/TO/KERNEL -R /PATH/TO/SYSTEMTAP/RUNTIME \
+   -m NAME -B CFLAGS_MODULE="-DMODULE -fno-pic" NAME.stp
+where NAME is the name of your script, /PATH/TO/KERNEL is the path to your kernel source, and /PATH/TO/SYSTEMTAP/RUNTIME is the path to your target systemtap runtime (for example if you're using the prebuilt version above, /PATH/TO/SYSTEMTAP/RUNTIME = systemtap/share/systemtap/runtime)
+adb push your kernel module to your device, then run
+ staprun -x PID NAME.ko
+where PID is the pid of fennec process
+== Sample systemtap scripts ==
+=== glandium's I/O tracking script ===
+ global targetpid;
+ global file_path;
+ probe begin {
+   targetpid = target();
+ }
+ probe kernel.function("__do_page_cache_readahead") {
+   if (targetpid == pid())
+     file_path[tid()] = d_path(&$filp->f_path);
+ }
+ probe kernel.function("do_mpage_readpage") {
+   if (targetpid == pid() && (tid() in file_path)) {
+     now = gettimeofday_us();
+     printf("%d %s %d\n", now, file_path[tid()], $page->index*4096);
+   }
+ }
+ probe kernel.function("__do_page_cache_readahead").return {
+   if (targetpid == pid())
+     delete file_path[tid()];
+ }
+=== jchen's I/O tracking script ===
+Note that this script accesses the hardware timer directly to overcome limitations in the systemtap gettimeofday() resolution (basically in systemtap, gettimeofday() is limited to jiffy resolution).
+This also means to run it on a processor other than a MSM7x30, get_rawtime() will need to change.
+ %{
+ #include <arch/arm/include/asm/io.h>
+ #define MSM_CSR_BASE ((void*)0xF8001000)
+ #define MSM_TMR_BASE MSM_CSR_BASE
+ #define MSM_GPT_BASE (MSM_TMR_BASE + 0x04)
+ #define MSM_DGT_BASE (MSM_TMR_BASE + 0x24)
+ #define TIMER_COUNT_VAL 0x0004
+ %}
+ function get_rawtime:long () %{ /* pure */ /* unprivileged */
+   cycles_t c = readl(MSM_DGT_BASE + TIMER_COUNT_VAL);
+   THIS->__retvalue = ((int64_t) (int32_t) c) - global.s_origin_time;
+ %}
+ global parentid, childid;
+ global start_time, total_time;
+ global origin_time;
+ global creation_time;
+ probe begin {
+   parentid = 0;
+   childid = 0;
+   origin_time = get_rawtime()
+ }
+ function is_parent:long () {
+   if (pid() == parentid)
+     return parentid;
+   if (0 == parentid && isinstr(execname(), "fennec")) {
+     parentid = pid();
+     return parentid;
+   }
+   return 0;
+ }
+ function is_child:long () {
+   if (pid() == childid)
+     return childid;
+   if (0 == childid && isinstr(execname(), "plugin")) {
+     childid = pid();
+     return childid;
+   }
+   return 0;
+ }
+ probe syscall.fork.return {
+   if (is_parent() || is_child()) {
+     if ($return != 0) {
+       thdid = is_parent() ? $return : -$return;
+       creation_time[thdid] = get_rawtime();
+       total_time[thdid, "", creation_time[thdid] / 8192] = -1;
+     }
+   }
+ }
+ probe syscall.execve.return {
+   if (is_parent() || is_child()) {
+     thdid = is_parent() ? tid() : -tid();
+     creation_time[thdid] = get_rawtime();
+     total_time[thdid, "", creation_time[thdid] / 8192] = -1;
+   }
+ }
+ probe syscall.exit {
+   if (is_parent() || is_child()) {
+     thdid = is_parent() ? tid() : -tid();
+     total_time[thdid, "", creation_time[thdid] / 8192] =
+         get_rawtime() - creation_time[thdid];
+   }
+ }
+ probe vfs.read {
+   if (bytes_to_read > 0 && (is_parent() || is_child())) {
+     thdid = is_parent() ? tid() : -tid();
+     start_time[thdid] = get_rawtime();
+   }
+ }
+ probe vfs.read.return {
+   if (bytes_to_read > 0 && (is_parent() || is_child())) {
+     thdid = is_parent() ? tid() : -tid();
+     fn = "rd:" . __file_filename(file);
+     st = start_time[thdid];
+     total_time[thdid, fn, st / 8192] += get_rawtime() - st;
+   }
+ }
+ probe kernel.function("filemap_fault") {
+   if (is_parent() || is_child()) {
+     thdid = is_parent() ? tid() : -tid();
+     start_time[thdid] = get_rawtime();
+   }
+ }
+ probe kernel.function("filemap_fault").return {
+   if (is_parent() || is_child()) {
+     thdid = is_parent() ? tid() : -tid();
+     fn = "mm:" . __file_filename($vma->vm_file);
+     st = start_time[thdid];
+     total_time[thdid, fn, st / 8192] += get_rawtime() - st;
+   }
+ }
+ probe end {
+   foreach ([t, fn, st] in total_time) {
+     printf("%d, %s, %d, %d\n", t, fn, st, total_time[t, fn, st]);
+   }
+ }