|
What's the strategy of backup programs when files are in use?
If you back up a file during use, your backup may end up useless because of inconsistent data.
So, should a backup program should attempt exclusive access on every file it backs up?
And if it can't gain exclusive access, maybe come back to that file later?
The difficult we do right away...
...the impossible takes slightly longer.
|
|
|
|
|
That is the way most backup systems work. If any files still cannot be accessed after some predetermined number of retry attempts then the program would report that fact in its log.
I must get a clever new signature for 2011.
|
|
|
|
|
As you have pointed-out; a backup of files alone is not enough to guarantee synchronisation on restore. Even if all files can be accessed there is still the time-sync/event-sync problem.
A backup from which an app can restore itself is usually called a checkpoint. Such a "backup" would involve a transaction history file and a log file, as well as a "checkpoint" copy of pertinent files. Such backups are always built-into the app itself. The restore phase restores the files and then runs the app forward using the transaction history elements as input. The app must be suspended for the time it takes to perform the checpoint. There are techniques for minimising the timespan of the suspension, such as file twinning.
A system-wide backup is not in my ken for today's platforms. However, anti-malware apps perform system-wide scans all the time, so I don't think file access is an issue, here.
So what kind of backup do you have in mind?
Tadeusz Westawic
Sumi quid sum.
|
|
|
|
|
I want to perform a standard type of file backup where the files are compressed and encrypted into a single backup file.
I think I'll simply keep a log file of which files I couldn't open for exclusive access, and leave it to the user to close whatever application is using the file.
The difficult we do right away...
...the impossible takes slightly longer.
|
|
|
|
|
This may sound very simple, but these parts of my brain are a bit rusty from disuse. I need to report on insurance policies, stating whether a policy is current, in advance/credit, or behind/in arrears. Am I correct in presuming it is as simple as below, providing the monthly payments remain constant?
Received = Tally of all monthly payments on the policy.
Expected = Policy age in months x monthly premium.
If Received < Expected, policy is in arrears.
If Received > Expected, policy is paid in advance.
If Received == Expected, policy is current.
|
|
|
|
|
Yes.
Will Rogers never met me.
|
|
|
|
|
Unless I am missing something, don't you have monthly payment object where you track due date, payment day, payment amount, payment made etc. If so you should be able to query month by month.
If you are trying to do a quick check, then you logic is correct. I am assuming you meant
Received = Tally of all monthly payments on the policy [for the policy period]
|
|
|
|
|
Thing is, even if this month, I received the full monthly payment, before the due date, the policy will be current for this month, but if I missed last month's payment, it is overall still in arrears, unless I include a brought-forward amount. I think it's more accurate and practical to sum all payments made on the policy, instead of implementing an extra brought-forward field, and having to keep this up to date at the end of each month. This would in fact required a monthly run, where this system is only intended for MIS and on demand, not monthly, reports.
I don't understand your qualification [for the policy period]. There surely should not be any payments for policy outside the policy period?
|
|
|
|
|
How does the business define being in arrears?
My guess is that you should use the expected sum to date compared with the actual sum to date.
So I think you are right - it is that simple.
Regards
David R
---------------------------------------------------------------
"Every program eventually becomes rococo, and then rubble." - Alan Perlis
The only valid measurement of code quality: WTFs/minute.
|
|
|
|
|
I don't have any definition from the business, and I haven't been able to elicit one yet, so for the first, prototype release I'm goinf with arrears == expected > actual.
|
|
|
|
|
Brady Kelly wrote: I don't understand your qualification [for the policy period]. There surely should not be any payments for policy outside the policy period?
Here is my understanding here in US. This is personal experience and I have not worked in the insurance industry.
I've a car insurance, which is my policy. I happen to buy it on the month of December. So my policy period runs from Dec'10 to Dec'11 for the current year. So, when they are calculating my payment to figure out the status they only need to look into the policy period. Last years policy period is irrelevant. Of course by the end of the policy period last year, I must have been current otherwise the insurance company would not have renewed it for this year.
Brady Kelly wrote: Thing is, even if this month, I received the full monthly payment, before the due date, the policy will be current for this month, but if I missed last month's payment, it is overall still in arrears, unless I include a brought-forward amount.
I agree, in fact if you go back and see my original post, what I said was this method will give you a quick way of checking the status of the policy. But you won't be able to know why it is so.
|
|
|
|
|
Looks like what I'm working on is life, not auto, so it doesn't have a yearly renewal, but a payout date, so it's actually assurance, but the 'spec' is in Afrikaans, which I read and speak well, but doesn't translate that well into a business spec for me, and I'm not in direct contact with the user. I'm working through an intermediary who has not been very available this week.
|
|
|
|
|
Ah, the plot thickens!
My first answer assumed the whole scenario was as simple as explained. But in most businesses, and in accounting generally, an aging report breaks amounts into groups - Current, 30 days, 60 days, 90 days, and >90 days in arrears. This is very likely what your client wants to see. Of course, it's a lot more work, but it gives a much better report.
Will Rogers never met me.
|
|
|
|
|
Roger Wright wrote: Current, 30 days, 60 days, 90 days, and >90 days
No, it's not the actual finance software, it's just a sort of basic 'dashboard' for the broker. They probably use an accounting package for the real aging, the brokers probably use a pen. I'll leave room for more detail though - take this baby Enterprise. Mwaahaaaahaaa.
|
|
|
|
|
Brady Kelly wrote: just a sort of basic 'dashboard'
Oh, then I'll stick with my original answer - comparing the sums is a good way to do it.
Will Rogers never met me.
|
|
|
|
|
I'm a little tired of staring at these few lines and not seeing the problem. Take this code:
volatile int WorkingBuff = 0;
volatile int NextBuff = 1;
volatile int RenderBuff = 1;
void stuff()
{
NextBuff = WorkingBuff;
int usedId = 0;
do
{
usedId = RenderBuff;
for(int i=0; i<3; i++)
{
if(i != NextBuff && i != usedId)
WorkingBuff = i;
}
} while(RenderBuff != usedId);
}
void render()
{
RenderBuff = NextBuff;
}
Could anybody point out the situation where WorkingBuff and RenderBuff have the same value? I'm just not seeing it.
|
|
|
|
|
1. NextBuff = WorkingBuff; in Thread A.
2. Thread A is blocked and Thread B starts.
3. RenderBuff = NextBuff; in Thread B.
|
|
|
|
|
Sorry, I should have elaborated a bit. I mean after the do-while loop had run.
I'm having a problem it seems, where I'm trying to render with stuff I'm in the middle of updating.
|
|
|
|
|
You could use lock () around the places you absolutely don't want to execute concurrently. This would remove all the uncertainty and make your code more reliable.
|
|
|
|
|
True, but I was aiming for a lock-free solution as they are surprisingly expensive.
|
|
|
|
|
It's surprisingly complex for such a short fragment because of the possible interactions between threads, and the shuffling of values among four variables. Maybe it could be rewritten in a simpler way.
A useful step in analyzing code like this is identifying invariant conditions, that are guaranteed to always be true at some point in the code. But it looks like the variable shuffling makes this impossible.
|
|
|
|
|
Yeah, I've temporarily gone with a lock which solves the problem for now. Then I'm going to try Luc's suggestion of using a couple of queues. I already have a lock-free queue that's working elsewhere which I should be able to use, since there would only be one producer for each queue (a limitation for lock-free queues it would seem).
|
|
|
|
|
SK Genius wrote: there would only be one producer ... a limitation for lock-free queues it would seem
a limitation for lock-free whatevers I would say. 
Luc Pattyn [Forum Guidelines] [My Articles] Nil Volentibus Arduum
Please use <PRE> tags for code snippets, they preserve indentation, improve readability, and make me actually look at the code.
|
|
|
|
|
I am sure you can find a solution for adding more producers, if you are good at lock-free algorithms. This page suggest that it is not impossible.
http://www.1024cores.net/home/lock-free-algorithms/queues
|
|
|
|
|
when you have a producer, a consumer, and a number (at least 2) of equivalent buffers, I find it most easy to have two queues, one holding "empty" buffers (emptied by the consumer, to be filled by the producer), one holding "full" buffers (filled by the producer, to be processed by the consumer). That is an approach that is simple to understand; it works well, it doesn't create new objects once initialized, and it doesn't really need locking, except the Queue.Dequeue operation should wait for a buffer being returned.
In pseudo-code:
emptyQ=CreateQueue();
fullQ=CreateQueue();
for(N times) emptyQ.Queue(new Buffer());
forever {
buf=emptyQ.Dequeue();
...fill buf
fullQ.Queue(buf);
}
forever {
buf=fullQ.Dequeue();
... process buf
emptyQ.Queue(buf);
}
Luc Pattyn [Forum Guidelines] [My Articles] Nil Volentibus Arduum
Please use <PRE> tags for code snippets, they preserve indentation, improve readability, and make me actually look at the code.
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
