What is fastest way to Improve database performance? aim straight to my target (5000 users)? Or first use artificial milestones?

When improving database performance, What is the fastest way?

should I go straight to my target (5000 users)? Or should I go through artificial milestones - (for example - first 1000 users, only then 2500...)?

we have a performance problem. For the purpose of the question, suppose the only bottleneck is the Database and all other resources consume zero time.

Facts:

• Database performance for 50 concurrent users is good
• Database performance for more then 50 is not acceptable and by that I mean database requests takes too long. Instead of ~0.5 sec they usually take between ~2 and ~7 sec, and sometimes even ~30 sec
• On about 70 users, the system stop w开发者_开发技巧orking at all, most database requests takes more then ~30 sec
• Database is implemented in SQL SERVER 2005\8

Requirement: The application need to support 5000 concurrent users.

From my understanding, and please correct me if I'm wrong or there is something missing, the best practise for database performance improvement is:

1. Define performance objective targets.
2. Establish testing environment identical (as much as possible) to production environment

3. Check if the performance targets is OK. if not do the following until performance targets is OK

   3.1 Improve performance (on at a time) by - server re-configuration, indexes improvements ,code improvements, database structure improvements and more, using trace and monitor tools such as - performance counters, SQL Server profiler, logs and more

   3.2 Test and analyse the affects of the change and accept or reject it

My question is: Assuming that getting the system to work on anything else then 5000, say for example 1000, or even 2500 users Doesn't provide any business value, What is the fastest way to get to 5000 users?

1. Getting there directly?
2. Or first get to smaller milestones? for example - first target 500 users, then 1000, then 2500 ....
3. Something else??

Do I get any technical value from using milestones, that will eventually take me to 5000 users faster?

Tuning up to 500 users, for example, can lead you to solutions that won't be effective when you increase to 1000 users. Example: let's imagine that you can tune cache for 500 users, perhaps you won't have enought RAM to get a good result for 5,000.

Go for your goal.

I don't see that artificial milestones really add any value, if the requirement if 5000 concurrent users, go straight for that, otherwise you run the risk of wasting time making optimisations which don't scale.

I would say that getting small milestone would make you a problem, imagine that you get a small number of users (or a very big one) you would have to find a point where the milestones are not too big nor too small. That can be tricky.