|
Hi There Michel,
Thanks for your response, i was hoping i could gather some interest just for a discussion. 
I have virtually solved the problem and have a nice working piece of software. Basically i turned to neighbor discovery protocols. In this Case The Cisco Discovery Protocol (CDP). There is a CDP MIB that provides me with a lot of information about what devices are connected to each interface and therefore, I am able to hop between devices because i know connected IP's.
Basically, my prgram jumps to the device the user specifies as the start IP, entering in the SNMP information and the network address they wish to map. My program then goes to that device, gathers all system information about the device, then gathers information about each local interface. Then my program looks into CDP MIB and looks at the CDP Cache (where neighbor details are stored), creates an entry in the database for each connected IP address, then assigns the connected interface entry to the local interface entry. My program then hops to the next device and does the same, so on and so forth. I have parameters in my code to make sure all IPs visited are noted, and a list of IPs to visit to prevent the oprogram from needlessly visiting the same device twice. This way i can track the hop count and limit it if required. At the end of the data collection, my program then analyses the data and draws a network map and listens for traps its a bit like a very basic network management system (extremley basic) but it works sweetly
Obviously this is not a perfect solution because CDP only operates on cisco devices and in some cases, CDP is disabled. There does exist a little protocol called the Link Layer Discovery Protocol (LLDP, refered to as 802.1ab i think). This is a vendor neutral neighbor discovery protocol and operates very much like CDP, but on any vendors device (Cisco, HP etc) providing the device supports it (my Catalyst 2950s do not, but the 2960's do). However, due to my limited budget the equipment i have does not support LLDP *sigh*
Since doing this for my uni project i have become particulary interested in network mapping and management. It really is quite a variedand detailed topic
Comments and thoughts are welcomed
|
|
|
|
|
Hi
I have bought raid controller Intel SASWT4I and computer with motherboard Gigabyte GA-EQ45M-S2.
I have a problem with installation windows xp professional. I installed controller to machine and created array. Array is ok. Now I'm trying to install windows. In bios controller I set boot option to OS only. Windows started installation, formated disk, copyied files and restarted after 15 sec. After restart windows again started installation from cd rom and want to format my disk.
What I have to do to continue installation of windows?
I've changed the boot option in bios controller to bios & os but result is the same.
ThanksI
|
|
|
|
|
When the machine reboots during the install remove the CD. Then when it complains about not having the files put the CD back in.
Morality is indistinguishable from social proscription
|
|
|
|
|
Does anyone know the difference in the capibilities between the Cisco call manager demo license and the production license?
Thanks,
Steve
|
|
|
|
|
Hi
I want to start playing around with facial recognition, but before I do, I would like to know what webcam I should get in terms of resolution? Is a high resolution webcam needed? I can get an expensive one that has a video capture resolution of 1280 x 1024, and then there is a less pricey one with a resolution of 800 x 600.
Any help would be appreciated.
|
|
|
|
|
| Here's[^] a link to one really serious article here on CP. He's using 640x480. My postings are a natural product. The slight variations in spelling and grammar enhance their individual character and beauty and are in no way to be considered flaws or defects.
|
|
|
|
|
Thanks for that. Though I couldn't make out much regarding resolution requirements. I think I'll just get a webcam with a high resolution. Or would facial recognition software not work then?
|
|
|
|
|
I have a barcode scanner which emulates the keyboard: when user scans a card with barcode, barcode text on the card appears in a textbox in my application.
The annoying thing is, when user touches the keyboard while scanning, whatever key the user presses will also appear in the textbox messing up the barcode text, causing "invalid input" error in my application. I told uers not to touch the keyboard while scanning, but that does not stop them, of course.
So I want to disable the keyboard. Here[^] is a solution I found (modifying windows registry). However, when I tried it, it disabled the keyboard and the barcode scanner so no barcode text will appear in my textbox.
How do I disable only the real keyboard and keep the barcode scanner working?
P.S. The barcode scanner and my application are running on a laptop, I can't just unplug the keyboard. Besides physically destroying the keyboard with hot coffee or liquid nitrogen, what else can I try?
|
|
|
|
|
Xiangyang Liu 刘向阳 wrote: How do I disable only the real keyboard and keep the barcode scanner working?
If your keyboard and scanner is USB based, then look into USB methods for disabling the keyboard. Warning! This will NOT be a simple call to a function to turn it on and off. You'll have to use the Setup API to do this. And frankly, this is a bad solution to the problem because this will turn the keyboard off for the entire system, not just your app. Now, what if your app crashes, or something else happens, after you turn off the keyboard, but before you turn it back on?? Not a good place to be...
How on earth are your users hitting the keyboard in the middle of a scan code that only takes a fraction of a second to show up??
You do not have to have users put the cursor in the correct box if your scanner supports (most do) prefixing and postfixing start and stop sequences to the scanned code. Your form code (with KeyPreview turned on) should look at each keystroke, looking for the prefix characters. If it's not part of the sequence, the keystroke gets passed on to the control it's destined for. If so, start looking for the stop code, but adding each character not part of the code to a string, until you see the stop code. These keystrokes do not get passed on to the destination code. Now you've got the code without having to use a TextBox. For the barcodes I was using, this normally took less than a tenth of a second.
|
|
|
|
|
Dave Kreskowiak wrote: How on earth are your users hitting the keyboard in the middle of a scan code that only takes a fraction of a second to show up??
Very good quesiton. 
I understand your suggestion: The best solution is modifying my code to get rid of the problematic key presses from the user. Ok, I will do that.
Thanks a lot.
|
|
|
|
|
And then there's the hard way!
If I remember correctly your scanner could also emulate a serial port...
I guess Daves solution is better.My postings are a natural product. The slight variations in spelling and grammar enhance their individual character and beauty and are in no way to be considered flaws or defects.
|
|
|
|
|
Jörgen Andersson wrote: If I remember correctly your scanner could also emulate a serial port...
Nah, I prefer hot coffee or liquid nitrogen, but thanks anyway. 
|
|
|
|
|
|
Bookmarked  My postings are a natural product. The slight variations in spelling and grammar enhance their individual character and beauty and are in no way to be considered flaws or defects.
|
|
|
|
|
This is a common arrangement and the best method is to unplug the keyboard and use a mouse for the rest of the system.
The other alternative is to use a serial port barcdoe scanner which appears as a separate device and does not inject characters into the keyboard queue.
|
|
|
|
|
Suppose my process creates a new thread on a Quad-Core system. The OS decides to run the thread on the first core, for example.
My question is: will the thread keep running on the first core, no matter what, until it terminates (even if the second core becomes completely idle, while the first core is used for many threads simultaneously)? Or can the OS decide to "move" the execution of an existing thread from one core to another?
I've googled a lot but found no answer...
Thanks!
|
|
|
|
|
Ofer Gross wrote: will the thread keep running on the first core, no matter what?
No, it will prefer to continue on the same core (cache efficiency!), but does not have to (unless you start fiddling with "thread affinities", which I do not recommend).
 Luc Pattyn [Forum Guidelines] [Why QA sucks] [My Articles]
I only read code that is properly formatted, adding PRE tags is the easiest way to obtain that. All Toronto weekends should be extremely wet until we get it automated in regular forums, not just QA.
|
|
|
|
|
I would say why do you want to know this, and if you did, I deffinitely wouldnt make assumptions based on such knowledge in code.
Morality is indistinguishable from social proscription
|
|
|
|
|
Adaptec no longer supports their game bridge products and only build their driver software for the XP sp2 environment.
Running an installer in compatibility mode as an administrator does nothing on Vista-64bit
The core problem here, Vista 64-bit does not recognize the drivers.
What is the process to rewrite these drivers from a 32-bit to a 64-bit OS?
There is a HUGE cry for them on several forums.
I have the complete install CD in ISO and in ZIP format on my domain here:
http://www.illuminatilegion.com/gamebridge/[^]
|
|
|
|
|
| Unless you have the source code and a lot of experience writing driver level code then I doubt that you can do it. If you do have both these requirements then it should be a fairly simple but repetitive task to identify all the code portions that need changing. txtspeak is the realm of 9 year old children, not developers. Christian Graus
|
|
|
|
|
I'm having a hard time locating a low-profile, PCI Express video card that's using the small (x1) connector--and has a VGA connection. The more common (x16) connector won't do.
This needs to be low-profile, as the "taller" bracket at the back wouldn't fit my case.
Can anyone recommend something?
|
|
|
|
|
Unfortunately as you've noticed 1x cards are few, far between, and expensive.
If you have a steady hand the cheap option is to buy a cheap 16x low profile card and cut a notch in the connector after the contacts for the first lane so that it will fit in the 1x slot.
If you can't find a card with a VGA connector you can get a DVI-VGA adapter for a few bucks if your card doesn't come with one.3x12=36
2x12=24
1x12=12
0x12=18
|
|
|
|
|
Cut a notch? Seriously, Dan?
What the heck are the additional contacts for then?
|
|
|
|
|
Daniel Desormeaux wrote: Cut a notch? Seriously, Dan?
Yes. Totally. You could also cut out the back of the slot so that the card hung out the back; but oopsing on a mobo is more expensive than a bottom tier GFX card. Just make sure you make your cut past the last contact of the first lane and don't cut into the main part of the PCB.
Daniel Desormeaux wrote: What the heck are the additional contacts for then?
The other 15 lanes.
PCIe devices will negotiate the number of lanes downward if they don't have full contact. At 16x card will run at 8, 4, 2, or 1x if it only has that many lanes available. Due to the limited number of lanes available on chipsets 16x physical/8 (or 4) electrical slots are common. High end cards will bottleneck severely in a 1x slot; but low end cards have much lower bandwidth requirements. In any event it's no worse than if you bought one of the highly overpriced cards that only have a 1x physical connector.3x12=36
2x12=24
1x12=12
0x12=18
|
|
|
|
|
I like it! 
It may sound daft but this will follow PCI Express specs as long as the power and ground requirements are met.
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
