|
Look at my article on unsafe Grayscale conversion. If you modify my code you should be able to write a simple pixel offset arithmetic to edit only one pixel very quickly.
File Not Found
|
|
|
|
|
My image processing project nearing completion is built using VS2003, and intentionally uses a huge amount of memory (100's of data arrays loaded) which does not get fully released until I restart my app process: I can live that for now. I've read the various articles here on memory management, and the main issue appears to be the way the Large Object Pool is (mis)managed by NET 1.1. NET 2.0 apparantly fixes some of this, and XP64 or Vista fixes the rest(?).
So, several questions I can't locate simple answers to.
Can I update VS2003 to build with build with NET 2.0, or do I have to upgrade to VS2005 or later to get NET 2.0? What about NET 3.0? I'd REALLY not like to have to do this at this point.
As I run the app, I can watch the memory usage increase, but what I find odd is the Page File usage also increases. This is on a Core 2 Extreme (quad core) with 4GB of ram. Is this just an effect of the NET 1.1 memory management or what?
I also note that XPsp2 renders the top 750MB of my 4GB ram unusable to (according to MS) allow for "memory mapped I/O devices that MIGHT be installed". Well, I don't have any cards that need this, so is there any way that some of this 750MB of ram can be identified to XP as actually usable?
Thanks for any suggestions...
Stewart DIBBS
|
|
|
|
|
The 750 megs of unused space is for Memory Mapped IO and makes up a nice week in your Architecture class from the Computer Science degree. It is inherent in all memory mapped systems. (The limit may be different based on the processor and/or bus)
If your code will compile in 2005 (and it should) you can download the express edition or just the sdk and build it using the csc command line utility.
Page File usage is related to virtual memory usage. Memory mismanagement as well as significant use can cause the pf usage to go up.
File Not Found
|
|
|
|
|
I understand the use of Memory Mapped IO, and, yes, it was a nice week in my Architecture class back in '86 ... (what was that girl's name again <grin>)
My issue with is that (according to MS) this 750MB was allocated as of XPsp2, and of course is not an issue in XP64 or Vista, as Memory Mapped IO is now (once again) at the top end of a 64 bit address space.
So my question remains: is there any way that this 750MB of Memory Mapped IO space can be reduced if its not required?
Stewart DIBBS
|
|
|
|
|
You can use the full four gigs in XP on a 32 bit machine if you use /PAE and have an application that takes advantage of the memory extensions api. There is a lot of information on it online.
As for reducing it no. (I could be wrong) The PAE option put the 750megs on top of the 4g. So you have a 0 to 3.5 gig block and then a 4.0 gig to 4.5 gig block.
File Not Found
|
|
|
|
|
/PAE is enabled by default with the /noexecute=optin boot.inij parameter.
From what I read of the AWE API, I would have to write some low level code so my C# app can understand it. Anyone know if NET 1.1 or 2.0 Framework has issues with or can actually use AWE commands?
Stewart DIBBS
|
|
|
|
|
You c# application gets 4 gigs of addresses space only and can in fact address 4 gigs of memory even if the memory does not exist and unless you reduce the kernal size allocated to Windows only a max of 2 gigs will be real memory devoted to your app.
The AWE is api code as you have already read.
File Not Found
|
|
|
|
|
hi ,
the last visit time wich is shown below the discusion forums........
did you see ?
Any body please tell me time zone of this...
is it time zone for client or server?
and where i will found how to feed back ...
|
|
|
|
|
This would be better asked in a different forum, perhaps the General Discussions or Lounge.
|
|
|
|
|
oh!
really i dont know that. however thanks.
so i put
subject as wwww.codeproject.com
once again thank u lot.
|
|
|
|
|
needhelpinnet wrote: wwww.codeproject.com
Can not find server or DNS error 
|
|
|
|
|
Anyone confirm this is thread safe please?
internal static List<string> GetList(string xmlString)
{
List<string> list = new List<string>();
BuildList(xmlString, list);
return list;
}
private static void BuildList(string xmlString, List<string> list)
{
string someXml = ModifyXml(xmlString);
list.Add(GetString(someXml));
if (GetBool(someXml))
BuildList(someXml, list);
}
Thanks much..
|
|
|
|
|
Looks thread safe to me. All of the methods you're calling are static; no instance objects are involved. Looks reentrant. I think you're safe.
EDIT-> When I say "instance objects," I'm refering to objects that persist at the instance level of a class. That is to say that none of the objects that I see used in the static methods persist at that level. So it looks safe.
-- modified at 14:22 Tuesday 6th March, 2007
|
|
|
|
|
|
I thought were clear - You meant no instance variable of the class as opposed to an instance declared local to the method.
Thanks.
|
|
|
|
|
Abisodun wrote: I thought were clear - You meant no instance variable of the class as opposed to an instance declared local to the method.
Exactly. 
|
|
|
|
|
Your statement's been bugging me now I realize why. This code will cause a compilation error:
class MyClass
{
internal string stringVariable = string.Empty;
internal static void MyFunction()
{
stringVariable += "a";
}
}
Did you mean static variable of the class?
Instance variable always refers to a non static variable.
i.e.
class MyClass
{
internal string stringVariable = string.Empty;
internal static void MyFunction()
{
MyClass myClass = new MyClass();
myClass.stringVariable += "a";
}
}
which should not be a problem in a static method of the same class.
|
|
|
|
|
Abisodun wrote: Did you mean static variable of the class?
Instance variable always refers to a non static variable.
Yeah, I should have just said that since the methods are static, it's thread safe. I confused the issue by mentioning instance objects. The instance variables of a class can't be accessed from a static method, so there was no need to bring them into the discussion.
The main thing to watch out for with static methods and thread safety are objects that are passed into the method. Something like this:
public static void DoSomething(SomeObject obj)
{
obj.Change();
}
This isn't tread safe. The reason being that two threads could call this method at the same time (relatively speaking), and the "Change" method may be performing some thread unsafe operation. The example you gave in your original post didn't do this, so it's thread safe. But also, if an object is a class level variable, you still want to be careful:
public class MyClass
{
private static SomeObject obj = new SomeObject();
public static void DoSomething()
{
obj.Change();
}
}
This isn't thread safe for the same reason the first example isn't thread safe.
In your original post, all of the objects that were used were created within the static method. This means that if two threads called the method at the same time, the objects each thread uses is unique to the thread. So your original example is thread safe.
Does this help? Hopefully, I haven't made it more confusing.
|
|
|
|
|
No it's been very helpful. I was really only concerned about "List<string> list" being passed between static methods and recursively. But each new call stack starting with GetList in the first example should have it's own instance of "List<string> list".
I appreciate your help.
|
|
|
|
|
Hey All,
I'm trying to update a database using .Net remoting. I am using SQL server code that includes variables like the following: @StudentFirstName.
When I run the program and hit the update button, which contains the following code:
this.dgResults.DataSource = dbc.ExecuteQuery("UPDATE Student SET FirstName=@StudentFirstName,LastName=@StudentLastName,Address=@StudentAddress,Phone=@StudentPhone,GPA=@StudentGPA WHERE StudentID = @StudentID AND FirstName=@OriginalFirstName AND LastName=@OriginalLastName AND Address=@OriginalAddress AND Phone=@OriginalPhone AND GPA=@OriginalGPA");
dgResults.DataMember = "Results";
I get an error saying that @StudentFirstName must be declared. I am wondering how you declare @StudentFirstName in C# using .Net Remoting. Anyone got any ideas or answers?
|
|
|
|
|
Since you are passing in a string into your ExecuteQuery, you really need the actual values that you want to update your student table with. So if you have parameters getting passed into this method say:
p_studentFirstName,
p_studentLastName,
p_studentAddress ...
Then your update would be:
this.dgResults.DataSource = dbc.ExecuteQuery("UPDATE Student SET FirstName="+p_studentFirstName+",LastName="+p_studentLastName+",Address="+p_studentAddress+...
Anyway, hope that helps.
Ben
|
|
|
|
|
I would like to hear about intellectual property protection issues experienced by .Net commercial product developers and users of commercial 3rd party products protected by applications such as .NET Reactor:
http://www.eziriz.com/[^]
I want impervious intellectual property protection and a perfect user experience. Can do?
|
|
|
|
|
|
Thanks so much, Glen.
Glen Harvy wrote: I have had one user try to run a .Net Reactor program compiled with the All CPU flag enabled on a 64 bit XP system without any luck. Eziriz said it should work on 64 bit as a 32 bit program but it apparently doesn't.
Is it possible they have some level (.Net configuration, OS configuration, etc.) configured to run 64-bit only?
Glen Harvy wrote: If someone can get to my code after it has been through .Net Reactor then I should feel flattered that they have gone to the trouble of doing so
Perhaps. But (unas Dylan said it) *if* "we have something to protect," it needs to be the other way around -- truly undefeatable.
The issue I have at the moment is with custom licensing, and handling the licensing scheme. I just don't find much information in the documentation as to custom features... handling additional fields... that sort of thing. Do you use the SDK for such purposes?
Glen Harvy wrote: One funny thing though - when you use .Net Reactor I found that it seemed "to easy" to use and so fast compared to the others. A bit like "Surely it can't be that easy"
That's a pretty strong recommendation. I tried the trial issue and built a distributable in little time, but am left with some stupid questions. What is a bona fide test system, and how should we go about testing so as to determine everything is working as it should? What does the user have to do on their end to process the license?
In other words, what I am wanting to do is collect the CurrentUser name and email address to which the validated will be returned, and to process that in validation process. Does the user have to manually run HID.exe or what? I mean, is it just a matter of determining that HID.exe has to go and remain with your distributables?
Another issue is how much performance might be degraded (if at all), compared to obsfucation? There might not be much difference there, but if there is, I'd like to know about it.
|
|
|
|
|
mike montagne wrote: The issue I have at the moment is with custom licensing, and handling the licensing scheme. I just don't find much information in the documentation as to custom features... handling additional fields... that sort of thing. Do you use the SDK for such purposes?
I am using 2.7.1.5 and have just visited their site and notice the newer version - which I shall look at shortly.
I agree - the documentation is poor and frankly after reading a fair bit of their competitor's help/manuals it left me wondering if their program would do what it claimed. If you boil it all down though, their competitors help/manuals need to be considerably thicker because they allow far more options/fine tuning. Having said that, that is also why their competitors programs take so much longer.
I tested out the licencing part of the package AFTER I had already incorporated my own into my program. I figured that providing my program couldn't be de-compiled then that was sufficient for me to use my own method of key generation/validation. I looked at the licencing SDK but didn't use it for that reason. My program is one that probably wouldn't be used by a "hacker", reports are hard-coded etc so that was good enough for me.
mike montagne wrote: That's a pretty strong recommendation.
It is and I mean it  . Adding .dll's is easy and cuts down on distribution. As far as scrambling my code is concerned it's a breeze. I don't need all the bells and whistles and I don't need to convince a boss that loves to see confusing screens, multilayed and configurable levels, pick and chose which strings to obfuscate etc.
I don't think you can customise the licencing side of it very well at all (at least I didn't think so). It was/is one of the reasons I don't use their licencing module. I also don't like linking my program to a computer (and this may detract from your product sales). Having said that, geting a user to use HID.exe shouldn't be a problem. HID just identifies some hardware components and creates a code based on that hardware. HID is not used again unless the user makes a hardware change. I believe .Net Reactor checks the hardware itself and compares the supplied code if you have configured it to use hardware checking.
You shouldn't be issuing a key until after they have paid so running HID.exe and sending you the resultant code shouldn't be a problem. I haven't tried it but you could include HID in your distributable and have your own program run it and send you the code without any difficulty.
Performance should not be an issue at all. There must be some degredation but I haven't had any adverse comments nor have I noticed any degredation - except of course a minor unnoticable (to the user)delay at startup. It's so minor I couldn't really bother to measure it.
I'll have a look at Version 3 and let you know if I have any other comments to make.
Another point about the licencing module is you should check with whoever is going to collect the funds/issue the keys as to their requirements. If your doing it yourself then no worries .
Let me know how you go - your the first person I know of that's actually using (or at least thinking) of using it. I have searched the net high and low for feedback etc without any luck.
Regards,
Glen Harvy
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
