Performance/MemShrink/DMD

From MozillaWiki
Jump to navigation Jump to search

DMD (short for "dark matter detector") is a tool that tracks the contents of the heap, including which heap blocks have been reported by memory reporters. It helps us reduce the "heap-unclassified" value in Firefox's about:memory page, and also detects if any heap blocks are reported twice. It also can be used for general heap profiling.

Building and Running

Desktop Firefox (Linux)

Build

Build with these options: 

 ac_add_options --enable-dmd

If building via try server, modify browser/config/mozconfigs/linux64/common-opt or a similar file before pushing.

Launch

Use mach run --dmd. Add --debug to run under gdb.

Trigger

Visit about:memory and click the DMD button (depending on how old your build is, it might be labelled "Save" or "Analyze reports" or "DMD"). The button won't be present in non-DMD builds, and will be grayed out in DMD builds if DMD isn't enabled at start-up.

This triggers all the memory reporters and then DMD analyzes the reports, printing this commentary: 

 DMD[11420] opened /tmp/dmd-1409885041-22021.txt.gz for writing
 DMD[11420] AnalyzeReports 1 {
 DMD[11420]   gathering stack trace records...
 DMD[11420]   creating and sorting twice-reported stack trace record array...
 DMD[11420]   creating and sorting unreported stack trace record array...
 DMD[11420]   printing unreported stack trace record array...
 DMD[11420]   creating and sorting once-reported stack trace record array...
 DMD[11420]   printing once-reported stack trace record array...
 DMD[11420] }

In an e10s-enabled build, you'll see separate output for each process.

If you see the "opened" line, it tells you where the file was saved. If you're on an older build and don't see that, it'll be saved in a file in your current working directory with a .dmd suffix.

Desktop Firefox (Mac)

Build

Build with these options: 

 ac_add_options --enable-debug
 ac_add_options --enable-dmd

Note: non-debug DMD builds do not currently work on Mac. see bug 995443.

If building via try server, modify browser/config/mozconfigs/macosx64/common-opt or a similar file before pushing.

Launch

Use mach run --dmd. Add --debug to run under lldb.

Trigger

Follow the Trigger instructions for Linux. Note that on Mac this step can take 30+ seconds.

Desktop Firefox (Windows)

Build

Build with these options: 

 ac_add_options --enable-dmd
 ac_add_options --enable-profiling

If building via try server, modify browser/config/mozconfigs/win32/common-opt. Also, add this line to build/mozconfig.common: 

 MOZ_CRASHREPORTER_UPLOAD_FULL_SYMBOLS=1

Launch

On a local build, use mach run --dmd.

On a build done by the try server, follow these instructions instead.

Trigger

Follow the Trigger instructions for Linux.

B2G

Build

First, update your B2G checkout with git pull or git fetch && git merge origin/master. ./repo sync is not sufficient! You must git pull to get the latest version of the relevant tools.

For B2G device builds, we don't usually modify the mozconfig (although you can; it's hiding under gonk-misc/default-gecko-config). Instead, modify your .userconfig and add 

  export MOZ_DMD=1

You probably need to clobber your objdir (rm -rf objdir-gecko). Then build normally.

Launch

Your build will then automatically launch with DMD enabled. (The b2g.sh script figures out whether to enable DMD by checking for the presence of libdmd.so in /system/b2g.) You'll see a message in logcat when a process starts up: 

  I/DMD     (  305): $DMD = '1'
  I/DMD     (  305): DMD is enabled

The run-gdb.sh script also knows to start DMD builds with DMD enabled, so you don't need to do anything special.

If you want to run B2G on a device with non-default options, you'll need to modify the value of DMD in the gonk-misc/b2g.sh script and then push it to the device like so: 

  adb shell stop b2g
  adb remount
  adb push b2g.sh /system/bin
  adb shell chmod 0755 /system/bin/b2g.sh
  adb shell start b2g

If you want to run B2G on the device under GDB with non-default options, modify the run-gdb.sh script. You don't need to push anything.

Trigger

When you want to analyze the contents of memory, run tools/get_about_memory.py. You should see output like the following: 

   $ ./get_about_memory.py 
   Got 3/3 files.
   Pulled files into about-memory-18.
   Got 3 DMD dump(s).
   [...]
   Done processing DMD files.  Have a look in about-memory-18.

Note: If you are not using the default GECKO_OBJDIR you'll need to pass that into get_about_memory.py 

   $ ./get_about_memory.py --gecko-objdir $OBJDIR

get_about_memory.py invokes fix_b2g_stack.py to post-process stack traces, so you shouldn't need to run it yourself, but it's there in case you need it.

See get_about_memory.py --help for more options, but you probably won't need anything other than the defaults.

B2G Desktop Client (Linux)

Build

Build the B2G Desktop Client, adding these options to the mozconfig file: 

 ac_add_options --enable-debug
 ac_add_options --enable-dmd

Launch

Start b2g like this: 

 LD_PRELOAD=$OBJDIR/dist/bin/libdmd.so \
 LD_LIBRARY_PATH=$OBJDIR/dist/bin/ \
 DMD=1 \    # or replace the '1' with one or more DMD options (see below)
 $OBJDIR/dist/bin/b2g -profile $GAIA/profile-debug

Trigger

Send signal 34 to the b2g process: 

 $ killall -34 b2g

The dmd gzipped log is written to the /tmp directory, e.g. /tmp/dmd-1406557150-14443.txt.gz.

Fennec

Due to bug 823354, you may get empty stack traces on Fennec, rendering DMD's output largely unhelpful. Sorry.

Build

Build with these options: 

 ac_add_options --enable-dmd

Launch

Launch with the following commands (be sure to replace "org.mozilla.fennec" with the app identifier as appropriate; this will usually be org.mozilla.fennec_$USERNAME for a local build). 

 adb push $OBJDIR/dist/bin/libdmd.so /sdcard/
 adb shell am start -n org.mozilla.fennec/.App \
   --es env0 MOZ_REPLACE_MALLOC_LIB=/sdcard/libdmd.so \
   --es env1 DMD=1   # or replace the '1' with one or more DMD options (see below)

The commentary on Fennec goes to logcat, and looks like this: 

 I/DMD  (27314): $DMD = '1'
 I/DMD  (27314): DMD is enabled

The number in the parentheses is the process ID.

Trigger

Use the existing memory-report dumping hook: 

 adb shell am broadcast -a org.mozilla.gecko.MEMORY_DUMP

In logcat, you should see output similar to this: 

 E/GeckoConsole (27314): nsIMemoryInfoDumper dumped reports to /data/data/org.mozilla.fennec_kats/app_tmp/memory-report-default-27314.json.gz

The path (should always be /data/data/$APPID/app_tmp/) is where the memory reports and DMD reports get dumped to. You can pull them like so: 

 adb pull /data/data/org.mozilla.fennec_kats/app_tmp/memory-report-default-27314.json.gz
 adb pull /data/data/org.mozilla.fennec_kats/app_tmp/dmd-default-27314.txt.gz

Processing the output

DMD outputs a gzipped JSON file that contains a description of the heap. You can analyze it (either gzipped or not) using $OBJDIR/dist/bin/dmd.py.

Some platforms (Linux, Mac) require stack fixing, which adds missing filename, function name and line number information. This will occur automatically the first time you run dmd.py on the output file. This can take several minutes to complete. (This will fail if your build does not contain symbols. However, if you have crash reporter symbols for your build -- as tryserver builds do -- you can use this script instead: clone the whole repo, edit the paths at the top of resymbolicate_dmd.py and run it.)

If you invoke dmd.py without arguments you will get output that describes how the live heap blocks are covered by memory reports. This output is broken into multiple sections.

  1. "Invocation". This tells you how DMD was invoked, i.e. what options were used.
  2. "Twice-reported stack trace records". This tells you which heap blocks were reported twice or more. The presence of any such records indicates bugs in one or more memory reporters.
  3. "Unreported stack trace records". This tells you which heap blocks were not reported, which indicate where additional memory reporters would be most helpful.
  4. "Once-reported stack trace records": like the "Unreported stack trace records" section, but for blocks reported once.
  5. "Summary": gives measurements of the total heap, and the unreported/once-reported/twice-reported portions of it.

The "Twice-reported stack trace records" and "Unreported stack trace records" sections are the most important, because they indicate ways in which the memory reporters can be improved.

Here's an example stack trace record from the "Unreported stack trace records" section. 

Unreported: 3 blocks in stack trace record 209 of 1,891
 36,864 bytes (26,184 requested / 10,680 slop)
 0.03% of the heap (64.55% cumulative);  0.04% of unreported (86.78% cumulative)
 Allocated at
   malloc (/home/njn/moz/mi2/memory/build/replace_malloc.c:151) 0x417170
   PR_Malloc (/home/njn/moz/mi2/nsprpub/pr/src/malloc/prmem.c:435) 0x7f68650f423c
   PL_ArenaAllocate (/home/njn/moz/mi2/nsprpub/lib/ds/plarena.c:200) 0x7f68652463e1
   nsFixedSizeAllocator::Alloc(unsigned long) (/home/njn/moz/mi2/xpcom/ds/nsFixedSizeAllocator.cpp:95) 0x7f6860f528dc
   nsNodeInfo::Create(nsIAtom*, nsIAtom*, int, unsigned short, nsIAtom*, nsNodeInfoManager*) (/home/njn/moz/mi2/content/base/src/nsNodeInfo.cpp:64) 0x7f685f640933
   nsNodeInfoManager::GetNodeInfo(nsIAtom*, nsIAtom*, int, unsigned short, nsIAtom*) (/home/njn/moz/mi2/content/base/src/nsNodeInfoManager.cpp:225) 0x7f685f642d05
   mozilla::dom::Element::SetAttrAndNotify(int, nsIAtom*, nsIAtom*, nsAttrValue const&, nsAttrValue&, unsigned char, bool, bool, bool) (/home/njn/moz/mi2/content/base/src/Element.cpp:1862) 0x7f685f60ad87
   mozilla::dom::Element::SetAttr(int, nsIAtom*, nsIAtom*, nsAString_internal const&, bool) (/home/njn/moz/mi2/content/base/src/Element.cpp:1778) 0x7f685f60a9b3
   nsXMLContentSink::AddAttributes(unsigned short const**, nsIContent*) (/home/njn/moz/mi2/content/xml/document/src/nsXMLContentSink.cpp:1464) 0x7f685fa76c5c
   nsXBLContentSink::AddAttributes(unsigned short const**, nsIContent*) (/home/njn/moz/mi2/content/xbl/src/nsXBLContentSink.cpp:882) 0x7f685fb3ad42
   nsXMLContentSink::HandleStartElement(unsigned short const*, unsigned short const**, unsigned int, int, unsigned int, bool) (/home/njn/moz/mi2/content/xml/document/src/nsXMLContentSink.cpp:1018) 0x7f685fa73db5
   nsXMLContentSink::HandleStartElement(unsigned short const*, unsigned short const**, unsigned int, int, unsigned int) (/home/njn/moz/mi2/content/xml/document/src/nsXMLContentSink.cpp:947) 0x7f685fa7370a
   nsXBLContentSink::HandleStartElement(unsigned short const*, unsigned short const**, unsigned int, int, unsigned int) (/home/njn/moz/mi2/content/xbl/src/nsXBLContentSink.cpp:258) 0x7f685fb37cc0

It tells you that there were 3 heap blocks that were allocated from the program point indicated by the "Allocated at" stack trace, that these blocks took up 36,864 bytes, and that 10,680 of those bytes were "slop" (wasted space caused by the heap allocator rounding up request sizes). It also indicates what percentage of the total heap size and the unreported portion of the heap these blocks represent.

Within each section, records are listed from largest to smallest.

Once-reported and twice-reported stack trace records also have stack traces for the report point(s). For example: 

Reported at
  mozilla::dmd::Report(void const*) (/home/njn/moz/mi2/memory/replace/dmd/DMD.cpp:1740) 0x7f68652581ca
  CycleCollectorMallocSizeOf(void const*) (/home/njn/moz/mi2/xpcom/base/nsCycleCollector.cpp:3008) 0x7f6860fdfe02
  nsPurpleBuffer::SizeOfExcludingThis(unsigned long (*)(void const*)) const (/home/njn/moz/mi2/xpcom/base/nsCycleCollector.cpp:933) 0x7f6860fdb7af
  nsCycleCollector::SizeOfIncludingThis(unsigned long (*)(void const*), unsigned long*, unsigned long*, unsigned long*, unsigned long*, unsigned long*) const (/home/njn/moz/mi2/xpcom/base/nsCycleCollector.cpp:3029) 0x7f6860fdb6b1
  CycleCollectorMultiReporter::CollectReports(nsIMemoryMultiReporterCallback*, nsISupports*) (/home/njn/moz/mi2/xpcom/base/nsCycleCollector.cpp:3075) 0x7f6860fde432
  nsMemoryInfoDumper::DumpMemoryReportsToFileImpl(nsAString_internal const&) (/home/njn/moz/mi2/xpcom/base/nsMemoryInfoDumper.cpp:626) 0x7f6860fece79
  nsMemoryInfoDumper::DumpMemoryReportsToFile(nsAString_internal const&, bool, bool) (/home/njn/moz/mi2/xpcom/base/nsMemoryInfoDumper.cpp:344) 0x7f6860febaf9
  mozilla::(anonymous namespace)::DumpMemoryReportsRunnable::Run() (/home/njn/moz/mi2/xpcom/base/nsMemoryInfoDumper.cpp:58) 0x7f6860fefe03

You can tell which memory reporter made the report by the name of the MallocSizeOf function near the top of the stack trace. In this case it was the cycle collector's reporter.

By default, DMD measures heap blocks above a certain size precisely, but uses sampling to measure blocks below that size. Any measurements that involve sampled blocks (even if combined with non-sampled measurements) are approximate, and this is indicated by a preceding '~'. For example: 

Unreported: ~273 blocks in block group 17 of 14,611
 ~1,125,590 bytes (~1,117,936 requested / ~7,654 slop)
 0.07% of the heap (2.58% cumulative);  0.43% of unreported (16.36% cumulative)

The sampling threshold can be adjusted with an option (see below). This will affect the precision of the output and the speed at which Firefox+DMD runs.

Options

Setting the DMD environment variable to 1 gives default options. But you can also specify non-default options by setting DMD to a whitespace separated list of --option=val entries.

--sample-below=<1..n>

By default, DMD samples blocks with a sample-below size of 4093. I.e. it ignores some small allocations in order to run (much) faster.

If you want DMD to record all allocations precisely, pass --sample-below=1. Otherwise, you should probably leave it unchanged. If you do pick a different value, prime numbers work best.

--max-frames=<1..24>

By default, DMD stack traces do not exceed 24 frames. You can reduce this.

--show-dump-stats=<yes|no>

You can request statistics on each dump with this option.

--mode=<normal|test|stress>

--mode=<normal|test|stress> can be used to invoke "test" or "stress" mode, which are only useful if you're hacking on DMD. The default is normal mode.

"test" and "stress" modes set their own --sample-below values, so you should never have to specify both --sample-below and --mode.

Which heap blocks are reported?

At this stage you might wonder how DMD knows which allocations have been reported and which haven't. DMD only knows about heap blocks that are measured via a function created with one of the following two macros: 

 MOZ_DEFINE_MALLOC_SIZE_OF
 MOZ_DEFINE_MALLOC_SIZE_OF_ON_ALLOC

Fortunately, most of the existing memory reporters do this. See Platform/Memory_Reporting for more details about how memory reporters are written.

Troubleshooting

Contact Nick Nethercote ("njn" on IRC) or Nathan Froyd ("froydnj" on IRC).

Retrieved from "https://wiki.allizom.org/index.php?title=Performance/MemShrink/DMD&oldid=1024042"