优化你的DiscuzNT3.0，让它跑起来（6）在线人数和Regex.IsMatch()引发的hang
注：本文仅针对 DiscuzNT3.0, sqlserver 2000版本，其他版本请勿对号入座。
你没看错标题，的确是 在线人数和Regex.IsMatch()引发的hang。事情是这样的，就在今天我们的论坛出现的挂起问题，当时刚好赶上了抓dump文件。于是就有了今天这篇文章。
我们先用windbg看看论坛当时在干什么吧。
1. 打开文件，运行 .load sos, 因为是hang，所以当然是要运行 !syncblk ， 下面是运行结果：
0:000> .load sos
0:000> !syncblk
Index SyncBlock MonitorHeld Recursion Owning Thread Info SyncBlock Owner
202 000fe87c 1 1 1c3d2c98 d28 48 02413704System.Collections.Generic.LinkedList`1[[System.Text.RegularExpressions.CachedCodeEntry, System]]
-----------------------------
Total 419
CCW 2
RCW 0
ComClassFactory 0
Free 354
从上面看到，持有锁的线程是48 ，持有的对象是System.Collections.Generic.LinkedList，
2. 我们看看线程48在干什么, ~48s 切换到线程，!clrstack 看看执行的代码。
0:000> ~48s
eax=000006d7 ebx=1c3d2c98 ecx=000fe87c edx=044ec5c3 esi=00000354 edi=00000000
eip=7c9585ec esp=1d8eeee4 ebp=1d8eef54 iopl=0 nv up ei pl zr na pe nc
cs=001b ss=0023 ds=0023 es=0023 fs=003b gs=0000 efl=00000246
ntdll!KiFastSystemCallRet:
7c9585ec c3 ret
0:048> !clrstack
OS Thread Id: 0xd28 (48)
ESP EIP
1d8ef060 7c9585ec [GCFrame: 1d8ef060]
1d8ef0fc 7c9585ec [HelperMethodFrame: 1d8ef0fc] System.Threading.Monitor.Enter(System.Object)
1d8ef150 7a4aed85 System.Text.RegularExpressions.Regex.LookupCachedAndUpdate(System.String)
1d8ef180 7a4aec91 System.Text.RegularExpressions.Regex..ctor(System.String, System.Text.RegularExpressions.RegexOptions, Boolean)
1d8ef1b4 7a4bf480 System.Text.RegularExpressions.Regex.IsMatch(System.String, System.String)
1d8ef1c4 1ba6c3cc Discuz.Common.TypeConverter.StrToInt(System.String, Int32)
1d8ef1e0 1ba6f6c2 Discuz.Common.TypeConverter.ObjectToInt(System.Object)
1d8ef1e4 1d50a215 Discuz.Data.OnlineUsers.LoadSingleOnlineUser(System.Data.IDataReader)
1d8ef1f4 1d50a111 Discuz.Data.OnlineUsers.GetOnlineUserCollection()
1d8ef204 1d509f73 Discuz.Forum.OnlineUsers.GetOnlineUserCollection(Int32 ByRef, Int32 ByRef, Int32 ByRef, Int32 ByRef)
1d8ef25c 1d30b291 Discuz.Web.website.ShowPage()
1d8ef274 1ba6d837 Discuz.Forum.PageBase..ctor()
1d8ef318 1d37e2d1 Discuz.Web.website..ctor()
1d8ef324 1d37e0f0 ASP.aspx_2_website_aspx..ctor()
。。。。。。这里省略若干字
--------------------------
我们从上面看到程序调用了
Discuz.Common.TypeConverter.StrToInt() 这个方法，然后进入 System.Text.RegularExpressions.dll，最后停留在System.Text.RegularExpressions.Regex.LookupCachedAndUpdate() 方法, 我们从dnt3.0的程序一步步来看看。
1 /// <summary>
2 /// 将对象转换为Int32类型
3 /// </summary>
4 /// <param name="str">要转换的字符串</param>
5 /// <param name="defValue">缺省值</param>
6 /// <returns>转换后的int类型结果</returns>
7 public static int StrToInt(string str, int defValue)
8 {
9 if (string.IsNullOrEmpty(str) || str.Trim().Length >= 11 || !Regex.IsMatch(str.Trim(), @"^([-]|[0-9])[0-9]*(\.\w*)?$"))
10 return defValue;
11
12 int rv;
13 if (Int32.TryParse(str, out rv))
14 return rv;
15
16 return Convert.ToInt32(StrToFloat(str, defValue));
2 /// 将对象转换为Int32类型
3 /// </summary>
4 /// <param name="str">要转换的字符串</param>
5 /// <param name="defValue">缺省值</param>
6 /// <returns>转换后的int类型结果</returns>
7 public static int StrToInt(string str, int defValue)
8 {
9 if (string.IsNullOrEmpty(str) || str.Trim().Length >= 11 || !Regex.IsMatch(str.Trim(), @"^([-]|[0-9])[0-9]*(\.\w*)?$"))
10 return defValue;
11
12 int rv;
13 if (Int32.TryParse(str, out rv))
14 return rv;
15
16 return Convert.ToInt32(StrToFloat(str, defValue));
17 }
请出reflector
1 public static bool IsMatch(string input, string pattern)
2 {
3 return new Regex(pattern, RegexOptions.None, true).IsMatch(input);
2 {
3 return new Regex(pattern, RegexOptions.None, true).IsMatch(input);
4 }
继续reflector
1 private Regex(string pattern, RegexOptions options, bool useCache)
2 {
3 CachedCodeEntry cachedAndUpdate = null;
4 string threeLetterWindowsLanguageName = null;
5 if (pattern == null)
6 {
7 throw new ArgumentNullException("pattern");
8 }
9 if ((options < RegexOptions.None) || ((((int) options) >> 10) != 0))
10 {
11 throw new ArgumentOutOfRangeException("options");
12 }
13 if (((options & RegexOptions.ECMAScript) != RegexOptions.None) && ((options & ~(RegexOptions.CultureInvariant | RegexOptions.ECMAScript | RegexOptions.Compiled | RegexOptions.Multiline | RegexOptions.IgnoreCase)) != RegexOptions.None))
14 {
15 throw new ArgumentOutOfRangeException("options");
16 }
17 if ((options & RegexOptions.CultureInvariant) != RegexOptions.None)
18 {
19 threeLetterWindowsLanguageName = CultureInfo.InvariantCulture.ThreeLetterWindowsLanguageName;
20 }
21 else
22 {
23 threeLetterWindowsLanguageName = CultureInfo.CurrentCulture.ThreeLetterWindowsLanguageName;
24 }
25 string[] strArray = new string[] { ((int) options).ToString(NumberFormatInfo.InvariantInfo), ":", threeLetterWindowsLanguageName, ":", pattern };
26 string key = string.Concat(strArray);
27 cachedAndUpdate = LookupCachedAndUpdate(key);
28 this.pattern = pattern;
29 this.roptions = options;
30 if (cachedAndUpdate == null)
31 {
32 RegexTree t = RegexParser.Parse(pattern, this.roptions);
33 this.capnames = t._capnames;
34 this.capslist = t._capslist;
35 this.code = RegexWriter.Write(t);
36 this.caps = this.code._caps;
37 this.capsize = this.code._capsize;
38 this.InitializeReferences();
39 t = null;
40 if (useCache)
41 {
42 cachedAndUpdate = this.CacheCode(key);
43 }
44 }
45 else
46 {
47 this.caps = cachedAndUpdate._caps;
48 this.capnames = cachedAndUpdate._capnames;
49 this.capslist = cachedAndUpdate._capslist;
50 this.capsize = cachedAndUpdate._capsize;
51 this.code = cachedAndUpdate._code;
52 this.factory = cachedAndUpdate._factory;
53 this.runnerref = cachedAndUpdate._runnerref;
54 this.replref = cachedAndUpdate._replref;
55 this.refsInitialized = true;
56 }
57 if (this.UseOptionC() && (this.factory == null))
58 {
59 this.factory = this.Compile(this.code, this.roptions);
60 if (useCache && (cachedAndUpdate != null))
61 {
62 cachedAndUpdate.AddCompiled(this.factory);
63 }
64 this.code = null;
65 }
2 {
3 CachedCodeEntry cachedAndUpdate = null;
4 string threeLetterWindowsLanguageName = null;
5 if (pattern == null)
6 {
7 throw new ArgumentNullException("pattern");
8 }
9 if ((options < RegexOptions.None) || ((((int) options) >> 10) != 0))
10 {
11 throw new ArgumentOutOfRangeException("options");
12 }
13 if (((options & RegexOptions.ECMAScript) != RegexOptions.None) && ((options & ~(RegexOptions.CultureInvariant | RegexOptions.ECMAScript | RegexOptions.Compiled | RegexOptions.Multiline | RegexOptions.IgnoreCase)) != RegexOptions.None))
14 {
15 throw new ArgumentOutOfRangeException("options");
16 }
17 if ((options & RegexOptions.CultureInvariant) != RegexOptions.None)
18 {
19 threeLetterWindowsLanguageName = CultureInfo.InvariantCulture.ThreeLetterWindowsLanguageName;
20 }
21 else
22 {
23 threeLetterWindowsLanguageName = CultureInfo.CurrentCulture.ThreeLetterWindowsLanguageName;
24 }
25 string[] strArray = new string[] { ((int) options).ToString(NumberFormatInfo.InvariantInfo), ":", threeLetterWindowsLanguageName, ":", pattern };
26 string key = string.Concat(strArray);
27 cachedAndUpdate = LookupCachedAndUpdate(key);
28 this.pattern = pattern;
29 this.roptions = options;
30 if (cachedAndUpdate == null)
31 {
32 RegexTree t = RegexParser.Parse(pattern, this.roptions);
33 this.capnames = t._capnames;
34 this.capslist = t._capslist;
35 this.code = RegexWriter.Write(t);
36 this.caps = this.code._caps;
37 this.capsize = this.code._capsize;
38 this.InitializeReferences();
39 t = null;
40 if (useCache)
41 {
42 cachedAndUpdate = this.CacheCode(key);
43 }
44 }
45 else
46 {
47 this.caps = cachedAndUpdate._caps;
48 this.capnames = cachedAndUpdate._capnames;
49 this.capslist = cachedAndUpdate._capslist;
50 this.capsize = cachedAndUpdate._capsize;
51 this.code = cachedAndUpdate._code;
52 this.factory = cachedAndUpdate._factory;
53 this.runnerref = cachedAndUpdate._runnerref;
54 this.replref = cachedAndUpdate._replref;
55 this.refsInitialized = true;
56 }
57 if (this.UseOptionC() && (this.factory == null))
58 {
59 this.factory = this.Compile(this.code, this.roptions);
60 if (useCache && (cachedAndUpdate != null))
61 {
62 cachedAndUpdate.AddCompiled(this.factory);
63 }
64 this.code = null;
65 }
66 }
这个代码量较大，找到关键点 LookupCachedAndUpdate
private static CachedCodeEntry LookupCachedAndUpdate(string key)
{
lock (livecode)
{
for (LinkedListNode<CachedCodeEntry> node = livecode.First; node != null; node = node.Next)
{
if (node.Value._key == key)
{
livecode.Remove(node);
livecode.AddFirst(node);
return node.Value;
}
}
}
return null;
{
lock (livecode)
{
for (LinkedListNode<CachedCodeEntry> node = livecode.First; node != null; node = node.Next)
{
if (node.Value._key == key)
{
livecode.Remove(node);
livecode.AddFirst(node);
return node.Value;
}
}
}
return null;
}
终于找到这个lock的对象了，看看他是什么类型的，和我们通过windbg看到的一样吗
internal static LinkedList<CachedCodeEntry> livecode;
果然一样， 这下应该放心了，就是这里的lock引起了hang，但是我们应该经常用Regex.IsMatch()的，也没见引起这个问题啊，为什么这里？？？
我们看看在线人数有多少，如果在线人数比较多，访问的人数也多，那可能性就很大了，我们来看看到底有多少人在线。
运行 !dso,看看本线程对象。
0:048> !dso
OS Thread Id: 0xd28 (48)
ESP/REG Object Name
1d8ef094 02413704 System.Collections.Generic.LinkedList`1[[System.Text.RegularExpressions.CachedCodeEntry, System]]
1d8ef0b8 074b8c54 System.String 0:CHS:^([-]|[0-9])[0-9]*(\.\w*)?$
1d8ef0bc 074b94ac System.String 114.247.10.127
1d8ef0d0 074b94ac System.String 114.247.10.127
1d8ef150 02413704 System.Collections.Generic.LinkedList`1[[System.Text.RegularExpressions.CachedCodeEntry, System]]
1d8ef170 074b8c20 System.Text.RegularExpressions.Regex
1d8ef184 0a3fcd1c System.String ^([-]|[0-9])[0-9]*(\.\w*)?$
1d8ef190 074b8c54 System.String 0:CHS:^([-]|[0-9])[0-9]*(\.\w*)?$
1d8ef19c 074b8c08 System.String -1
1d8ef1a0 074b8c20 System.Text.RegularExpressions.Regex
1d8ef1a4 0a3fcd1c System.String ^([-]|[0-9])[0-9]*(\.\w*)?$
1d8ef1b4 068e2dc4 Discuz.Common.Generic.List`1[[Discuz.Entity.OnlineUserInfo, Discuz.Entity]]
1d8ef1b8 074b8c08 System.String -1
1d8ef1d4 074b8bac Discuz.Entity.OnlineUserInfo
1d8ef1d8 068e2f64 System.Data.SqlClient.SqlDataReader
。。。。。。省略若干字
----------------------
找到上面的
Discuz.Common.Generic.List 的地址 068e2dc4 ， 运行 !do 068e2dc4
0:048> !do 068e2dc4
Name: Discuz.Common.Generic.List`1[[Discuz.Entity.OnlineUserInfo, Discuz.Entity]]
MethodTable: 1ceb7084
EEClass: 1bb39dd0
Size: 28(0x1c) bytes
(C:\WINDOWS\Microsoft.NET\Framework\v2.0.50727\Temporary ASP.NET Files\root\9932c999\b8dfff59\assembly\dl3\21614a1e\486ed665_6d88ca01\Discuz.Common.DLL)
Fields:
MT Field Offset Type VT Attr Value Name
79124228 400099d 4 System.Object[] 0 instance 0f1b254c _items
790fed1c 400099e c System.Int32 0 instance 472 _size
790fed1c 400099f 10 System.Int32 0 instance 472 _version
790f9c18 40009a0 8 System.Object 0 instance 00000000 _syncRoot
79124228 40009a1 0 System.Object[] 0 shared static _emptyArray
>> Domain:Value dynamic statics NYI
000e1008:NotInit dynamic statics NYI
00107038:NotInit <<
790fed1c 400000c 14 System.Int32 0 instance 0 _fixedsize
从上面的size可以看到在线人数是472人，就是说这个48这个线程要lock 472 次，如果有n个人访问那后面的人真的要等不少时候了。
话说StrToInt()这个方法为什么要用Regex.IsMatch()呢，string 转换成 int 一般 int.TryParse()也足够了。不过从这里我才发现Regex.IsMatch() 里面原来还有个lock，不然还真不知道，也算是收获不小啊。
