引见

memwatch是一个c++扩大，重要用来视察nodejs内存泄漏题目，基础用法以下：

const memwatch = require('@airbnb/memwatch');
function LeakingClass() {
}

memwatch.gc();
var arr = [];
var hd = new memwatch.HeapDiff();
for (var i = 0; i < 10000; i++) arr.push(new LeakingClass);
var hde = hd.end();
console.log(JSON.stringify(hde, null, 2));

完成剖析

剖析的版本为@airbnb/memwatch。首先从binding.gyp最先入手:

{
  'targets': [
    {
      'target_name': 'memwatch',
      'include_dirs': [
        "<!(node -e \"require('nan')\")"
      ],
      'sources': [
        'src/heapdiff.cc',
        'src/init.cc',
        'src/memwatch.cc',
        'src/util.cc'
      ]
    }
  ]
}

这份设置示意其天生的目的是memwatch.node,源码是src目次下的heapdiff.cc、init.cc、memwatch.cc、util.cc,在项目编译的过程当中还需要include分外的nan目次，nan目次经由过程实行node -e "require('nan')根据node模块体系寻觅nan依靠，<! 示意背面是一条指令。

memwatch的进口函数在init.cc文件中，经由过程NODE_MODULE(memwatch, init);举行声明。当实行require('@airbnb/memwatch')的时刻会首先挪用init函数：

void init (v8::Handle<v8::Object> target)
{
    Nan::HandleScope scope;
    heapdiff::HeapDiff::Initialize(target);

    Nan::SetMethod(target, "upon_gc", memwatch::upon_gc);
    Nan::SetMethod(target, "gc", memwatch::trigger_gc);

    Nan::AddGCPrologueCallback(memwatch::before_gc);
    Nan::AddGCEpilogueCallback(memwatch::after_gc);
}

init函数的进口参数v8:Handle<v8:Object> target可以类比nodejs中的module.exports的exports对象。函数内部做的完成可以分为三块，初始化target、给target绑定upon_gc和gc两个函数、在nodejs的gc前后离别挂上对应的钩子函数。

Initialize完成

到heapdiff.cc文件中来看heapdiff::HeapDiff::Initialize(target);的完成。

void heapdiff::HeapDiff::Initialize ( v8::Handle<v8::Object> target )
{
    Nan::HandleScope scope;
    
    v8::Local<v8::FunctionTemplate> t = Nan::New<v8::FunctionTemplate>(New);
    t->InstanceTemplate()->SetInternalFieldCount(1);
    t->SetClassName(Nan::New<v8::String>("HeapDiff").ToLocalChecked());

    Nan::SetPrototypeMethod(t, "end", End);
    target->Set(Nan::New<v8::String>("HeapDiff").ToLocalChecked(), t->GetFunction());
}

Initialize函数中建立一个叫做HeapDiff的函数t，同时在t的原型链上绑了end要领，使得js层面可以实行vat hp = new memwatch.HeapDiff();hp.end()。

new memwatch.HeapDiff完成

当js实行new memwatch.HeapDiff();的时刻，c++层面会实行heapdiff::HeapDiff::New函数，去掉解释和不必要的宏，New函数精简以下：

NAN_METHOD(heapdiff::HeapDiff::New)
{
    if (!info.IsConstructCall()) {
        return Nan::ThrowTypeError("Use the new operator to create instances of this object.");
    }

    Nan::HandleScope scope;

    HeapDiff * self = new HeapDiff();
    self->Wrap(info.This());

    s_inProgress = true;
    s_startTime = time(NULL);
    
    self->before = v8::Isolate::GetCurrent()->GetHeapProfiler()->TakeHeapSnapshot(NULL);

    s_inProgress = false;

    info.GetReturnValue().Set(info.This());
}

可以看到用户在js层面实行var hp = new memwatch.HeapDiff();的时刻，c++层面会挪用nodejs中的v8的api对对堆上内存打一个snapshot保留到self->before中，并将当前对象返回出去。

memwatch.HeapDiff.End完成

当用户实行hp.end()的时刻，会实行原型链上的end要领，也就是c++的heapdiff::HeapDiff::End要领。一样去掉冗余的解释以及宏，End要领可以精简以下：

NAN_METHOD(heapdiff::HeapDiff::End)
{
    Nan::HandleScope scope;

    HeapDiff *t = Unwrap<HeapDiff>( info.This() );

    if (t->ended) {
        return Nan::ThrowError("attempt to end() a HeapDiff that was already ended");
    }
    t->ended = true;

    s_inProgress = true;
    t->after = v8::Isolate::GetCurrent()->GetHeapProfiler()->TakeHeapSnapshot(NULL);
    s_inProgress = false;

    v8::Local<Value> comparison = compare(t->before, t->after);
    
    ((HeapSnapshot *) t->before)->Delete();
    t->before = NULL;
    ((HeapSnapshot *) t->after)->Delete();
    t->after = NULL;

    info.GetReturnValue().Set(comparison);
}

在End函数中，拿到当前的HeapDiff对象以后，再对当前的堆上内存再打一个snapshot，挪用compare函数对前后两个snapshot对照后获得comparison后，将前后两次snapshot对象释放掉，并将效果关照给js。

下面剖析下compare函数的细致完成：
compare函数内部会递归挪用buildIDSet函数获得终究堆快照的diff效果。

static v8::Local<Value>
compare(const v8::HeapSnapshot * before, const v8::HeapSnapshot * after)
{
    Nan::EscapableHandleScope scope;
    int s, diffBytes;

    Local<Object> o = Nan::New<v8::Object>();

    // first let's append summary information
    Local<Object> b = Nan::New<v8::Object>();
    b->Set(Nan::New("nodes").ToLocalChecked(), Nan::New(before->GetNodesCount()));
    //b->Set(Nan::New("time"), s_startTime);
    o->Set(Nan::New("before").ToLocalChecked(), b);

    Local<Object> a = Nan::New<v8::Object>();
    a->Set(Nan::New("nodes").ToLocalChecked(), Nan::New(after->GetNodesCount()));
    //a->Set(Nan::New("time"), time(NULL));
    o->Set(Nan::New("after").ToLocalChecked(), a);

    // now let's get allocations by name
    set<uint64_t> beforeIDs, afterIDs;
    s = 0;
    buildIDSet(&beforeIDs, before->GetRoot(), s);
    b->Set(Nan::New("size_bytes").ToLocalChecked(), Nan::New(s));
    b->Set(Nan::New("size").ToLocalChecked(), Nan::New(mw_util::niceSize(s).c_str()).ToLocalChecked());

    diffBytes = s;
    s = 0;
    buildIDSet(&afterIDs, after->GetRoot(), s);
    a->Set(Nan::New("size_bytes").ToLocalChecked(), Nan::New(s));
    a->Set(Nan::New("size").ToLocalChecked(), Nan::New(mw_util::niceSize(s).c_str()).ToLocalChecked());

    diffBytes = s - diffBytes;

    Local<Object> c = Nan::New<v8::Object>();
    c->Set(Nan::New("size_bytes").ToLocalChecked(), Nan::New(diffBytes));
    c->Set(Nan::New("size").ToLocalChecked(), Nan::New(mw_util::niceSize(diffBytes).c_str()).ToLocalChecked());
    o->Set(Nan::New("change").ToLocalChecked(), c);

    // before - after will reveal nodes released (memory freed)
    vector<uint64_t> changedIDs;
    setDiff(beforeIDs, afterIDs, changedIDs);
    c->Set(Nan::New("freed_nodes").ToLocalChecked(), Nan::New<v8::Number>(changedIDs.size()));

    // here's where we'll collect all the summary information
    changeset changes;

    // for each of these nodes, let's aggregate the change information
    for (unsigned long i = 0; i < changedIDs.size(); i++) {
        const HeapGraphNode * n = before->GetNodeById(changedIDs[i]);
        manageChange(changes, n, false);
    }

    changedIDs.clear();

    // after - before will reveal nodes added (memory allocated)
    setDiff(afterIDs, beforeIDs, changedIDs);

    c->Set(Nan::New("allocated_nodes").ToLocalChecked(), Nan::New<v8::Number>(changedIDs.size()));

    for (unsigned long i = 0; i < changedIDs.size(); i++) {
        const HeapGraphNode * n = after->GetNodeById(changedIDs[i]);
        manageChange(changes, n, true);
    }

    c->Set(Nan::New("details").ToLocalChecked(), changesetToObject(changes));

    return scope.Escape(o);
}

该函数中组织了两个对象b(before)、a(after)用于保留前后两个快照的细致信息。用一个js对象形貌以下:

// b(before) / a(after)
{
    nodes: // heap snapshot中对象节点个数
    size_bytes: // heap snapshot的对象大小(bytes)
    size: // heap snapshot的对象大小(kb、mb)
    
}

进一步对前后两次的快照举行剖析可以获得o，o中的before、after对象就是前后两次的snapshot对象的援用：

// o 
{
    before: { // before的堆snapshot
        nodes:
        size_bytes:
        size: 
    },
    after: { // after的堆snapshot
        nodes:
        size_bytes:
        size: 
    },
    change: {
        freed_nodes: // gc掉的节点数目
        allocated_nodes: // 新增节点数目
        details: [ // 根据范例String、Array聚合出来的细致信息
            {
                Array : {
                    what: // 范例
                    size_bytes: // 字节数bytes
                    size: // kb、mb
                    +: // 新增数目
                    -: // gc数目
                }
            },
            {}
        ]
    }
}

获得两次snapshot对照的效果后将o返回出去，在End函数中经由过程info.GetReturnValue().Set(comparison);将效果通报到js层面。

下面来细致说下compare函数中的buildIDSet、setDiff以及manageChange函数的完成。
buildIDSet的用法：buildIDSet(&beforeIDs, before->GetRoot(), s);，该函数会从堆snapshot的根节点动身，递归的寻觅一切可以接见的子节点，加入到鸠合seen中，做DFS统计一切可达节点的同时，也会对一切节点的shallowSize（对象自身占用的内存，不包括援用的对象所占内存）举行累加，统计当前堆所占用的内存大小。其细致完成以下：

static void buildIDSet(set<uint64_t> * seen, const HeapGraphNode* cur, int & s)
{
    Nan::HandleScope scope;
    if (seen->find(cur->GetId()) != seen->end()) {
        return;
    }
    if (cur->GetType() == HeapGraphNode::kObject &&
        handleToStr(cur->GetName()).compare("HeapDiff") == 0)
    {
        return;
    }
    s += cur->GetShallowSize();
    seen->insert(cur->GetId());
    for (int i=0; i < cur->GetChildrenCount(); i++) {
        buildIDSet(seen, cur->GetChild(i)->GetToNode(), s);
    }
}

setDiff函数用法：setDiff(beforeIDs, afterIDs, changedIDs);重要用来盘算鸠合差集用的，细致完成很简单，这里直接贴代码，不再赘述：

typedef set<uint64_t> idset;

// why doesn't STL work?
// XXX: improve this algorithm
void setDiff(idset a, idset b, vector<uint64_t> &c)
{
    for (idset::iterator i = a.begin(); i != a.end(); i++) {
        if (b.find(*i) == b.end()) c.push_back(*i);
    }
}

manageChange函数用法：manageChange(changes, n, false);,其作用在于做数据的聚合。对某个指定的set，根据set中对象的范例，聚合出每种对象建立了若干、销毁了若干，完成以下：

static void manageChange(changeset & changes, const HeapGraphNode * node, bool added)
{
    std::string type;
    switch(node->GetType()) {
        case HeapGraphNode::kArray:
            type.append("Array");
            break;
        case HeapGraphNode::kString:
            type.append("String");
            break;
        case HeapGraphNode::kObject:
            type.append(handleToStr(node->GetName()));
            break;
        case HeapGraphNode::kCode:
            type.append("Code");
            break;
        case HeapGraphNode::kClosure:
            type.append("Closure");
            break;
        case HeapGraphNode::kRegExp:
            type.append("RegExp");
            break;
        case HeapGraphNode::kHeapNumber:
            type.append("Number");
            break;
        case HeapGraphNode::kNative:
            type.append("Native");
            break;
        case HeapGraphNode::kHidden:
        default:
            return;
    }

    if (changes.find(type) == changes.end()) {
        changes[type] = change();
    }

    changeset::iterator i = changes.find(type);
    i->second.size += node->GetShallowSize() * (added ? 1 : -1);
    if (added) i->second.added++;
    else i->second.released++;
    return;
}

upon_gc和gc完成

这两个要领的在init函数中声明以下：

Nan::SetMethod(target, "upon_gc", memwatch::upon_gc);
Nan::SetMethod(target, "gc", memwatch::trigger_gc);

先看gc要领的完成，现实上对应memwatch::trigger_gc，完成以下：

NAN_METHOD(memwatch::trigger_gc) {
    Nan::HandleScope scope;
    int deadline_in_ms = 500;
    if (info.Length() >= 1 && info[0]->IsNumber()) {
        deadline_in_ms = (int)(info[0]->Int32Value()); 
    }
    Nan::IdleNotification(deadline_in_ms);
    Nan::LowMemoryNotification();
    info.GetReturnValue().Set(Nan::Undefined());
}

经由过程Nan::IdleNotification和Nan::LowMemoryNotification触发v8的gc功用。
再来看upon_gc要领，该要领现实上会绑定一个函数，当实行到gc要领时，就会触发该函数：

NAN_METHOD(memwatch::upon_gc) {
    Nan::HandleScope scope;
    if (info.Length() >= 1 && info[0]->IsFunction()) {
        uponGCCallback = new UponGCCallback(info[0].As<v8::Function>());
    }
    info.GetReturnValue().Set(Nan::Undefined());
}

个中info[0]就是用户传入的回调函数。挪用new UponGCCallback的时刻，其对应的组织函数内部会实行：

UponGCCallback(v8::Local<v8::Function> callback_) : Nan::AsyncResource("memwatch:upon_gc") {
        callback.Reset(callback_);
}

把用户传入的callback_函数设置到UponGCCallback类的成员变量callback上。upon_gc回调的触发与gc的钩子有关，细致看下一节剖析。

gc前、后钩子函数的完成

gc钩子的挂载以下：

Nan::AddGCPrologueCallback(memwatch::before_gc);
Nan::AddGCEpilogueCallback(memwatch::after_gc);

先来看memwatch::before_gc函数的完成，内部给gc最先纪录了时候：

NAN_GC_CALLBACK(memwatch::before_gc) {
    currentGCStartTime = uv_hrtime();
}

再来看memwatch::after_gc函数的完成，内部会在gc后纪录gc的效果到GCStats构造体中:

struct GCStats {
    // counts of different types of gc events
    size_t gcScavengeCount; // gc 扫描次数
    uint64_t gcScavengeTime; // gc 扫描事宜

    size_t gcMarkSweepCompactCount; //  gc标记消灭整顿的个数
    uint64_t gcMarkSweepCompactTime; // gc标记消灭整顿的时候

    size_t gcIncrementalMarkingCount;  // gc增量标记的个数
    uint64_t gcIncrementalMarkingTime; // gc增量标记的时候

    size_t gcProcessWeakCallbacksCount; // gc处置惩罚weakcallback的个数
    uint64_t gcProcessWeakCallbacksTime; // gc处置惩罚weakcallback的时候
};

对gc要求举行统计后，经由过程v8的api猎取堆的运用情况，终究将效果保留到barton中，barton内部保护了一个uv_work_t的变量req，req的data字段指向barton对象自身。

NAN_GC_CALLBACK(memwatch::after_gc) {
    if (heapdiff::HeapDiff::InProgress()) return;
    uint64_t gcEnd = uv_hrtime();
    uint64_t gcTime = gcEnd - currentGCStartTime;
    switch(type) {
        case kGCTypeScavenge:
            s_stats.gcScavengeCount++;
            s_stats.gcScavengeTime += gcTime;
            return;
        case kGCTypeMarkSweepCompact:
        case kGCTypeAll:
            break;
    }

    if (type == kGCTypeMarkSweepCompact) {
        s_stats.gcMarkSweepCompactCount++;
        s_stats.gcMarkSweepCompactTime += gcTime;

        Nan::HandleScope scope;

        Baton * baton = new Baton;
        v8::HeapStatistics hs;

        Nan::GetHeapStatistics(&hs);

        timeval tv;
        gettimeofday(&tv, NULL);

        baton->gc_ts = (tv.tv_sec * 1000000) + tv.tv_usec;

        baton->total_heap_size = hs.total_heap_size();
        baton->total_heap_size_executable = hs.total_heap_size_executable();
        baton->req.data = (void *) baton;

        uv_queue_work(uv_default_loop(), &(baton->req),
            noop_work_func, (uv_after_work_cb)AsyncMemwatchAfter);
    }
}

在前面事情完成的基础上，将效果丢到libuv的loop中，比及适宜的现实触发还调函数，在回调函数中可以拿到req对象，经由过程接见req.data对其做强迫范例装换可以获得barton对象，在loop的回调函数中，将barton中封装的数据顺次取出来，保留到stats对象中，并挪用uponGCCallback的Call要领，传入字面量stats和stats对象。

static void AsyncMemwatchAfter(uv_work_t* request) {
    Nan::HandleScope scope;

    Baton * b = (Baton *) request->data;
    // if there are any listeners, it's time to emit!
    if (uponGCCallback) {
        Local<Value> argv[2];

        Local<Object> stats = Nan::New<v8::Object>();

        stats->Set(Nan::New("gc_ts").ToLocalChecked(), javascriptNumber(b->gc_ts));

        stats->Set(Nan::New("gcProcessWeakCallbacksCount").ToLocalChecked(), javascriptNumberSize(b->stats.gcProcessWeakCallbacksCount));
        stats->Set(Nan::New("gcProcessWeakCallbacksTime").ToLocalChecked(), javascriptNumber(b->stats.gcProcessWeakCallbacksTime));

        stats->Set(Nan::New("peak_malloced_memory").ToLocalChecked(), javascriptNumberSize(b->peak_malloced_memory));
        stats->Set(Nan::New("gc_time").ToLocalChecked(), javascriptNumber(b->gc_time));

        // the type of event to emit
        argv[0] = Nan::New("stats").ToLocalChecked();
        argv[1] = stats;
        uponGCCallback->Call(2, argv);
    }

    delete b;
}

末了在Call函数的内部挪用js传入的callback_函数，并将字面量stats和stats对象通报到js层面，供上层用户运用。

void Call(int argc, Local<v8::Value> argv[]) {
        v8::Isolate *isolate = v8::Isolate::GetCurrent();
        runInAsyncScope(isolate->GetCurrentContext()->Global(), Nan::New(callback), argc, argv);
}