Database

Re: Error: Can't delete row or update row in SQL Server ?

11-Jul-14 23:32

Have you done what the error message suggested?

Never underestimate the power of human stupidity
RAH

taibc13-Jul-14 20:36

taibc

13-Jul-14 20:36

Hi,

I checked the log error file. For the select query, I got the below error:

Error: 7886, Severity: 20, State: 1.
2014-07-14 11:27:01.50 spid52 A read operation on a large object failed while sending data to the client. A common cause for this is if the application is running in READ UNCOMMITTED isolation level. This connection will be terminated.

For the delete statement, I got the message:

Error: 824, Severity: 24, State: 2.
2014-07-14 13:34:10.12 spid51 SQL Server detected a logical consistency-based I/O error: incorrect checksum (expected: 0x4da7af2c; actual: 0xda5e9af7). It occurred during a read of page (1:40403) in database ID 6 at offset 0x00000013ba6000 in file 'D:\CLCData\23_01_2013\CLC_LIS_Data.mdf'. Additional messages in the SQL Server error log or system event log may provide more detail. This is a severe error condition that threatens database integrity and must be corrected immediately. Complete a full database consistency check (DBCC CHECKDB). This error can be caused by many factors; for more information, see SQL Server Books Online

But, I don't know how to fix it.

Re: Error: Can't delete row or update row in SQL Server ?

Mycroft Holmes13-Jul-14 21:06

Re: Error: Can't delete row or update row in SQL Server ?

13-Jul-14 21:06

Execute DBCC CHECKDB int SQL Server Management Studio, just like the error message tells you, then see what the results of the check are.

Never underestimate the power of human stupidity
RAH

ZurdoDev14-Jul-14 10:14

ZurdoDev

14-Jul-14 10:14

You have a damaged data file or the disk is damaged. You'll want to run the DBCC as the error suggests and see if you get additional details.

There are only 10 types of people in the world, those who understand binary and those who don't.

JOIN vs. WHERE

Klaus-Werner Konrad11-Jul-14 9:22

11-Jul-14 9:22

I quite don't understand why noone is using the WHERE-Syntax for table joining ...

I always see something like

SQL

SELECT  O.Order_No, C.Address, F.Address 
FROM    Orders O
JOIN    Address C
    ON  O.Customer = C.ID
JOIN    Address F 
    ON  O.Forwarder = C.ID

For me, the most irritating thig is the spreading of table names and aliases all over the Statement.

I prefer

SQL

SELECT O.Order_No, C.Address, F.Address
FROM Orders O, Address C, Address F 
WHERE O.Customer = C.ID 
AND O.Forwarder = F.ID

- It's shorter
- All table names and aliases are together

Arguments, anyone ?

Mycroft Holmes11-Jul-14 14:24

11-Jul-14 14:24

Klaus-Werner Konrad wrote:
Arguments,

Nope, I call them Oracle joins (I loathe Oracle) because that is the way I was taught in the 90s then I moved to SQL SErver and was introduced to the JOIN and have never used it since.

I will refactor any procedure I see using them and have a short, sharp discussion with the dev that uses it. Use join or quit.

Never underestimate the power of human stupidity
RAH

Klaus-Werner Konrad12-Jul-14 9:08

12-Jul-14 9:08

Mycroft Holmes wrote:
Nope, I call them Oracle joins

Yeah - a really qualified Response ...
I ask for arguments, an your resposne is

Mycroft Holmes wrote:
I will [...] have a short, sharp discussion with the dev that uses it

THIS is my Intention - to have a DISCUSSION about it !
But you have obvoiously no arguments, but prejudices against it - not the ideal base for discussions.
What would be your arguments in a discussion with your developer - do you even have any arguments ?
Note: I asked politely for arguments for - or against - my preferation, because (as every of us) I want to improve my abilities, and also to give some impressions to SQL newbies to decide what to do, and not to do.
So ...
HAVE VOU ARGUMENTS, or are you just felt to open your mouth ... ?

Mycroft Holmes12-Jul-14 14:13

12-Jul-14 14:13

Klaus-Werner Konrad wrote:
THIS is my Intention - to have a DISCUSSION about it !

So we are supposed to be telepathic so we can identify your INTENTIONS.

You stated that you prefer the JOIN format, then you asked for arguments to that position. Nowhere did you mention discussion.

I stated that I had no argument and qualified why. In other words I was supporting your preference!

I did not down vote your question or response (was not even aware you had been) as the question was valid and the response just means you are a bit pissy this morning.

Never underestimate the power of human stupidity
RAH

Klaus-Werner Konrad13-Jul-14 0:08

13-Jul-14 0:08

Well - the title should be clear enough, and I presented JOIN syntax and WHERE syntax,
expressing my worry about noone seems using WHERE.

THEN I asked for arguments - obviously (I thought so) WHY noone is using WHERE syntax,
and NOT to support my preference.

In other words: Are there any points (other than preference) to not using WHERE syntax ??

data modeling guy11-Jul-14 19:53

data modeling guy

11-Jul-14 19:53

Klause,

theoretically, the first approach is more optimized and can give better performance while working with large data sets.

WHY?
In first approach, the intermediate tables are expressed clearly and the steps to arrive the result is evident.

eg:
step1 -> Create Intermediate table I : O join C on ID
step2 -> Result R : I join F on ID

this is optimum route to reach the result.

How about second approach?

In a simple case, SQL optimizer might arrive at same steps by analyzing the tables and columns used in WHERE clause but not always. Especially when the WHERE clause is relatively complex.

Mycroft Holmes11-Jul-14 23:29

11-Jul-14 23:29

I was under the impression there was no difference by the time the optimizer had done it's job so I have always based my ~~bigotry~~ opinion on the readability.

Never underestimate the power of human stupidity
RAH

Jörgen Andersson12-Jul-14 9:42

12-Jul-14 9:42

Generally there isn't, but in specific cases there are.

Wrong is evil and must be defeated. - Jeff Ello[^]

Jörgen Andersson12-Jul-14 10:25

12-Jul-14 10:25

The downvote you got is stupid because the question is valid.

The problem is though that readability isn't the same as clarity of intention, and there is more to it than you see at the first glance.

Firstly, when using an ANSI Join you specify which TABLES to join.
When using an implicit join you specify which fields to join on.

This is normally not making any difference, but it might in some specific cases.

Consider this query:

SQL

SELECT O.Order_No, C.Address, F.Address
FROM Orders O, Address C, Address F 
WHERE O.Customer = C.ID 
AND O.Forwarder = F.ID(+)
AND F.OtherID = 1

Is it the same as:

SQL

SELECT  O.Order_No, C.Address, F.Address 
FROM    Orders O
JOIN    Address C
    ON  O.Customer = C.ID
LEFT OUTER JOIN Address F 
    ON  O.Forwarder = F.ID
    AND F.OtherID = 1

or:

SQL

SELECT  O.Order_No, C.Address, F.Address 
FROM    Orders O
JOIN    Address C
    ON  O.Customer = C.ID
LEFT OUTER JOIN Address F 
    ON  O.Forwarder = F.ID
WHERE   F.OtherID = 1

The difference is crucial as the results differ.

Secondly, when using an implicit join there is no way to force the optimizer to do the joins in a certain order, which normally is a good thing. The optimizer is usually better than many people on that.
But sometime you know better than the optimizer and can force the joining order as such:

SQL

SELECT  O.Order_No, C.Address, F.Address 
FROM    (
    Orders O JOIN  Address C
    ON  O.Customer = C.ID
    )   JOIN    Address F 
    ON  O.Forwarder = C.ID

My personal pet peeve is that a field should always have the same name everywhere in a database just like the ISO standard says. Smile | :)

Wrong is evil and must be defeated. - Jeff Ello[^]

Mycroft Holmes12-Jul-14 14:22

12-Jul-14 14:22

I'm curious, and lazy, which result does the first query match. I no longer remember the relevance of the (+), left outer join I believe whereas the intention may have been to filter the forwarders.

Never underestimate the power of human stupidity
RAH

Jörgen Andersson12-Jul-14 20:44

12-Jul-14 20:44

The second one, to match the first one the query would need to look like this:

SQL

SELECT O.Order_No, C.Address, F.Address
FROM Orders O, Address C, Address F 
WHERE O.Customer = C.ID 
AND O.Forwarder = F.ID(+)
AND F.OtherID(+) = 1

Wrong is evil and must be defeated. - Jeff Ello[^]

Jörgen Andersson12-Jul-14 20:55

12-Jul-14 20:55

When it comes to the relevance of the (+), think of it as the side that allows nulls (+ nulls)

Wrong is evil and must be defeated. - Jeff Ello[^]

Klaus-Werner Konrad13-Jul-14 0:35

13-Jul-14 0:35

Wrong - it's the OPPOSITE side that can be NULL, as in O.Forwarder = F.ID(+)

Here, O.Forwarder my be NULL, but F.ID can NEVER be NULL (it's usually the primary key)

Jörgen Andersson13-Jul-14 1:09

13-Jul-14 1:09

Have a look here[^]
Want to change your mind?.

Wrong is evil and must be defeated. - Jeff Ello[^]

data modeling guy13-Jul-14 5:57

data modeling guy

13-Jul-14 5:57

Klaus,

(+) is deprecated OUTER JOIN syntax. It's not about allowing or not allowing NULL.

O.Forwarder = F.ID(+) means include all rows from O even if there is no match in F.

O.Forwarder(+) = F.ID means include all rows from F even if there is no match in O

Klaus-Werner Konrad13-Jul-14 1:08

13-Jul-14 1:08

Thanks for your thoughts, Jörgen.

Of course the results differ, and to achive the correct result,
one have to write

SQL

AND NVL( F.OtherID, 1 ) = 1

Quote:
My personal pet peeve is that a field should always have the same name everywhere in a database just like the ISO standard says

Don't know where you read this, but it cannot be right ...

Even in my original simple example you have two addresses in tho ORDERS table, so there is no chance in having 'the same field always the same name'.
Maybe you meant that a field with the same MEANING should have always the same name, like CUSTOMER, FORWARDER etc. ?

Jörgen Andersson13-Jul-14 1:46

How to create an audit table?

13-Jul-14 1:46

That would of course depend on which result is the correct one. I would also go very far to avoid a function in the where clause, for performance reasons.

The ISO standard I'm referring to is ISO-11179[^].
Considering the amount of text, I can't be bothered to find the actual paragraph that I'm referring to.

But the gist is that if you have a Customer Table the Surrogate Key should be named CustomerID in all tables using it no matter if it's the primary key or a foreign key.
It shouldn't be CustomerID in one table, CID in another, customer in a third, or just ID in the Customer Table. Same name everywhere to avoid confusion.

This also allows you to use the using construct[^] or even a Natural Join[^]. Personally I avoid both as I don't find that they add any clarity.

There are as always exceptions. An obvious one is when you have a Person table where the person have a work address and a home address, both columns referring to the same address table, they can't both be AddressID.

Wrong is evil and must be defeated. - Jeff Ello[^]

Bastien Vandamme10-Jul-14 0:30

Bastien Vandamme

10-Jul-14 0:30

Do you know if it exist a document or recommendation to create audit table or metadata elements on a database.

I ask this question because I just saw this :

SQL

CREATE TABLE client (
    id char(36)  NOT NULL,
    first_name varchar(255)  NOT NULL,
    last_name varchar(255)  NOT NULL,
    creation_date timestamp  NOT NULL,
    update_date timestamp  NOT NULL,
    CONSTRAINT client_pk PRIMARY KEY (id)
);

I don't like the idea to have metadata like creation_date and update_date in a business oriented table. Actually these two fields exists in all tables of this database.

What if I create a audit table like this:

SQL

CREATE TABLE audit (
    table_name char(32)  NOT NULL,
    fk char(36)  NOT NULL,
    update_date timestamp  NOT NULL
);

I don't need a creation date because the creation date is my first record with table_name and fk in this table. I could add a columns to add insert, update, delete information. With thi table I keep all my update dates and not only the last one.

Is this audit table a god practice ?
Can I also use this audit table to avoid conflict. You know when two users update the same record at the same time. It's possible to use the last update time to warn them there is a conflict.

Re: How to create an audit table?

Eddy Vluggen10-Jul-14 8:14

Eddy Vluggen

10-Jul-14 8:14

B413 wrote:
I don't like the idea to have metadata like creation_date and update_date in a business oriented table.

It's just a good idea to do so. Makes sorting by creation-order easier, makes it easy to see when the table last was updated - but it's not an audit. It doesn't show who changed what, it merely shows when the object was created, and when it was last modified. You'll find those two attributes on a lot of things.

Fetching the top(update_date) gives a fast indication whether the table has changed since you last loaded it into memory.

B413 wrote:
Is this audit table a good practice ?

Depends; who's responsible for entering data into the new table? Does it happen automatically (using a trigger), or do you depend on the cooperation of the DAL-programmer?

I'd simply be dumping a copy of the entire record (in a separate table, different access-rights), including the user-name and domain. It'd be wasting less space if you only keep a track of the fields that are actually modified then when one makes a complete copy. OTOH, space is cheap nowadays Smile | :)

B413 wrote:
Can I also use this audit table to avoid conflict. You know when two users
update the same record at the same time. It's possible to use the last update
time to warn them there is a conflict.

..and then what? Ask the user to undo the work he's done and type it again? Merge the changes? What if they modified the same field?

It's a bit sweeter to "check out" (or lock) the record once a user starts editing. What sourcesafe does with files works equally well with records.

Bastard Programmer from Hell Suspicious | :suss:

If you can't read my code, try converting it here[^]

Re: How to create an audit table?

Mycroft Holmes10-Jul-14 14:15