|
I work with both SQL Server Express 2008 and Microsoft Visual Web Studio Express 2008. However the two programs don't seem to be "in sync" properly. 
Probably this is because I set up the database wrong, but I'm not sure. I first add a new database and a table in VWD (Visual Web), which creates two files, a MDF and a log file under
Documents\VisualWebStudio2008Express\Websites\Website\APP folder.
Next, I tried attaching that database file in SQL Server Management Studio Express. Since the Express version could not access any document saved under My Documents (which I later found out), I copied the two files and pasted them directly under my C:\ directory, and successfully attached the database into SQL Server Management by pointing its path to the database under C:\.
Now here's where all the weird things started happening.
1. The file path of the newly attached database in SQL Server Management Studio shows that it's now pointing to
Documents\VisualWebStudio2008Express\Websites\Website\APP folder
instead of C:\, which was where I originally pointed to. Hmm, strange...
2. To test it out, I inserted some data into the database via SQL Server, and when going back to VWD and opening up the table, surprisingly the file is updated accordingly. 
3. Thinking that I wouldn't need the two files in C:\ anymore, I deleted them. But now going back to SQL Server, I found that the database is now gone!  Of course in VWD I could still open the database because it's pointing to the file under Documents\VisualWebStudio....
This is all very confusing, and I couldn't figure out what's pointing at what actually.
Could you guys please help me out? I'd greatly appreciate it.
Thanks!!
|
|
|
|
|
You should not delete MDF and LDF database files. You should only tell the database to limit log file sizes and shrink the log file if it is already too big.
|
|
|
|
|
Thank you Ted, though I'm still confused about why in SQL Server Management Studio, it shows that it's pointing to the database under the VWD folder rather than the C:\ folder, and when I delete the files in the C:\ folder, I don't see them anymore in SQL Server Management Studio? 
|
|
|
|
|
Hi,
I have got a test table in A database with user details. Now i have imported temp table in B database with user details.
Now i want to match if test & temp table contains same set of users, if not then display the extra number of users in either of the table.
In temp and test table only matching value could be email id.
How can i achieve this ?
Thank You
Andyyy
|
|
|
|
|
Try something like this:
select emailID,'Missing from B' from db_A.dbo.table1 where emailID not in
(select emailID from db_B.dbo.table2)
UNION
select emailID,'Missing from A' from db_B.dbo.table2 where emailID not in
(select emailID from db_A.dbo.table1)
That should show you the differences.
|
|
|
|
|
Hi,
When a large transaction is updating thousands of rows in a table, other transactions that wants to insert/update data into this table waits until the former transaction is finished.
(Please verify if my understanding is incorrect).
I'm saying this in the context of web application with multiple functions updating the same table, some of which are "bulk updates" which users sometimes use to update a large amount of data which takes a good 30 minutes to run. In this case, all other users are stuck and could not use functions that updates the same table.
Is there a way to solve this problem (other than reducing the 30-min runtime)?
Thanks!
Rafferty
|
|
|
|
|
Is it essential for these bulk updates to run as a single transaction? If not, then your solution could be to make these transactions smaller.
Bob
Ashfield Consultants Ltd
Proud to be a 2009 Code Project MVP
|
|
|
|
|
Hi Bob,
Thanks for your reply.
Is this the only way? The effort to do this is currently high, the table contains a trigger which will need to somehow be made "smaller" as well.
Rafferty
Rafferty
|
|
|
|
|
Its the only way I could think of.
Basically, any transaction will lock the table to other updates, so the only way is to use small transactions. I would be very reluctant to implement something that has a 30 minute transaction anyway - consider the imapct of a failure after 29 minutes. The transaction will have to rollback completely before any further updates can be done, and that would probably be close to another 30 minutes.
Bite the bullet and do it right - it will pay off in the long run 
Bob
Ashfield Consultants Ltd
Proud to be a 2009 Code Project MVP
|
|
|
|
|
Hi Bob,
I'm trying to do this by implementing the smaller transactions in C#. However, I realize that I still encapsulated everything in transaction.BeginTransaction() and transaction.Commit() statements.
My question is, does this do the trick?
Or is it better to do some sort of "checking" at the beginning first (which checks for possible errors) and then do each update in separate transactions?
This is tricky because the the function that I'm working on updates a tree of objects (parent-child relationships) which may contain thousands of nodes.
Thanks again for your help.
Rafferty
|
|
|
|
|
Its hard to say without knowing more about your data structure, but if you have a tree of objects to update then each parent item needs to be a transaction, so it all works or all fails and rolls back. Think of it in terms of atomic transactions i.e. each transaction is a single unit of work, no matter how many tables are impacted.
Bob
Ashfield Consultants Ltd
Proud to be a 2009 Code Project MVP
|
|
|
|
|
I see.
Basically my test data contains a single parent with children, grand children, great grand children (up to the 6th level) totaling 1200 nodes.
2 tables are affected: The main table where the data is contained and another table which just contains the parent/child ids relationships. Only the main table is updated.
The previous code generates the tree, traverses and updates each node using a stored procedure.
I now just moved the tree generation and traversal to C# code and keep a simple stored procedure to update each data.
Then I enclosed the entire thing in a single transaction (using the SqlTransaction class).
Any comments about this?
My concern is that, since it is a single transaction... I may still experience the same problem that we currently have, which is that when the data is updating, other users who are updating data in the same SQL table are stuck until this finishes updating.
Thanks again.
Rafferty
|
|
|
|
|
You may already be doing this or something more sophisticated... Depending on how you are loading the data and if you can check constraints/triggers without database access, you may be able to drop constraints and triggers temporarily. Then afterwards you reapply the constraints and triggers. This may be faster and also let you recover from certain errors as you would log only those rows that you could not load.
|
|
|
|
|
Consider this,
Create an indicator somehow that could be interrogated prior to making a change to the table. If the "bulk update" indicator is true then maybe you could warn the user that the database is currently being updated and they want to try their update at a later time. Or, if you want to get sophiticated, maybe you could create a pending transaction table where you could temporarily store their transaction until the "bulk update" is finished and apply it when done.
Basically, you would be creating a Queue for updates on your table.
Look at sp_GetAppLock as a possible tool for creating your "bulk update" inidcator.
Just a thought.
|
|
|
|
|
All depends how optimistic you want to be.
If you perform the updates using the (RowLock) hint it may restrict the locking. Though a half hour transaction will still end up locking everything in sight until it is done,
The only other thing would be to run your selects using the (NoLock) hint, with the corresponding risk that you will read some updated data that will later get rolled back and so have never existed.
What is more important, stopping the locking, or getting guaranteed data? Your choice.
Having said that Unless I have guaranteed single user access to a database, such as in an overnight job, there is no way I would allow any transaction to lock records for more than a few milliseconds. In my experience, if the Application hangs for half an hour waiting for database access the end users will buy a new system.
|
|
|
|
|
Thanks all for your ideas. Looks like the best way is really to reduce this bulk update into smaller transactions.
Let's see if our client agrees with the change.
Thanks again! You're all very helpful!
Rafferty
|
|
|
|
|
Hello again,
I converted the large stored procedure into smaller ones, by placing the tree generation and traversal business logic in C# code and just using stored procedures for simple checks and updates. The entire operation, then, is enclosed in a single transaction.
The good news is that the 30-minute operation was optimized to 15 minutes.
The bad news is that the new c# code made the web server too busy that other users couldn't use the application (even though multi-threading is automatically done by the IIS).
What I plan to do is to implement multi-threading manually for this function. Do you think it will solve my problem?
Any other suggestions?
Thanks again.
Rafferty
|
|
|
|
|
In store procedure.i want to display a message.ie
Alter procedure CheckForValidUser
(
@Username varchar(20),
@Password varchar(10)
)
as
select ltrim(rtrim(name_first + ' '+ isnull(name_last,''))) as name,rolename,p.pid, date_exit from hms_person p, HMS_personell pl where pl.username = @Username and password = @Password and pl.pid=p.pid ;
I'm passing two parameters but to display three arguments,i want to get a message to display whether the date_exit is not null is it possible to display as popup
regards
Kankeyan
|
|
|
|
|
AFAIK no.
1. You must be doing all these checks in the business layer of your application.
2. In case something goes wrong in the stored procedure, send the message back to the calling method and it shaould take care of showing it to the user. (Not the exact message but a user freindly one)
50-50-90 rule: Anytime I have a 50-50 chance of getting something right, there's a 90% probability I'll get it wrong...!!
|
|
|
|
|
Danish is correct, you need to trap the error and deal with it in the client.
Remember SQL Server runs on the server, who is going to see a message box ON THE SERVER, you need to do all the work on the client
Never underestimate the power of human stupidity
RAH
|
|
|
|
|
is it possible to display in client side
|
|
|
|
|
I would again say, you should not let that null date to reach your DB. Check it beforehand. For other exception, you can have something like this:
You can use try/catch in your stored procedure. Then, if it fails, you should send the exception back to your data access layer. That or business should inturn change the message to a user friendly one. Also, before doing this make sure you log it in somewhere for future reference.
Once your message has reached UI layer, use MessageBox or Alert as applicable.
In order to understand ho try catch works in SQL, use google and you will find a lot of help.
50-50-90 rule: Anytime I have a 50-50 chance of getting something right, there's a 90% probability I'll get it wrong...!!
|
|
|
|
|
Only through your client application.
Bob
Ashfield Consultants Ltd
Proud to be a 2009 Code Project MVP
|
|
|
|
|
If this is required for debugging purpose, you can use the print statement, or if you want to notify your application users, you need to pass an appropriate value to the client and show the popup in the client application (such as a WinForms Form or an ASP.NET page).
|
|
|
|
|
Hi All,
I Developed an Application in vb.net 2005 using sql server 2005 express. So far I installed in single PCs and is working fine.
But now i want the application to be access by client PCs but update the SQL database on a centralized server PC.
e.g. MASTER_PC will have the SQL database & the main application will run on PC1, PC2 and PC3; so that users can access the database from their respective PCs.
Overall to say, I just need a central location where the SQL database can be stored, and all employees can run and modify the database through their application via internet/LAN(or some other source)
Please suggest me how to go ahead with this:
1) As I have 4 PCs in my office, Do i need to create a LAN ?
2) Do I need to do any major modifications in my application?
Any links/tutorial/references will be highly appriciated.
Thanks
R.S.
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
