Tag Info

Hot answers tagged

48

The Server Fault community generally can't help you with capacity planning - the best answer we can offer is "Benchmark your code on hardware similar to what you'll be using in production, identify any bottlenecks, then determine how much of a workload your current hardware can handle, and/or how much hardware horsepower you need to handle your target ...


22

Virtual Machine Count planning When it comes to figuring out how many VMs you should plan for on a single host, there are actually no really good rules of thumb. In fact, there is only one, and it is only kinda good: Virtual-Machine counts are usually bounded by RAM, except for when they're not. Which isn't terribly helpful. If those VMs are going to ...


8

Honestly? I DON'T. When specing a server that will see any kind of real workload I cram in as much RAM as I can reasonably afford (systems are more likely to wind up RAM-constrained than CPU or Disk constrained - the only other guaranteed bottleneck is the front-side bus). If you want to figure out how much RAM your application may use a basic load test ...


5

since your apache server can be running on almost everything, ranging from a Nokia Internet Tablet to a fully loaded Sun E25K, and the fetching of messages can be from simply reading lines out of a file up to doing costly database queries, and your apache could be set up (mpm-wise) in a near-to-infinite number of ways; you should either: Provide more ...


3

There is no formula. The best method is try to get some test equipment, and setup an environment similar to the production environment and test.


3

No, nor can anyone else, but I can tell you how to think more clearly about the question. In some senses, your Apache MaxClients settings is how many concurrent users you can "handle"; likely you'll want to increase it, and the questions there are whether you have enough memory to run that many Apache processes without hitting swap (which, of course, ...


3

The term you're looking for is "backplane speed" for most switches. This is the maximum data a switch can move in an instant. Most switches you'd use in the office or datacenter should list this speed somewhere on the spec sheet. Things get more complicated in blade-style and stacked switches as that concept is more fuzzy, since each blade/stacked-switch can ...


2

vmware Capacity Planner would fit your needs. Once installed on your network it collects configuration and performance of your running servers over a time periods (say 30 days) in order to produce some reports that will show you how you can fit your servers into your hardware (this tool let you to insert your hardware configuration in terms of ...


2

Another thing you'll need to know is the ratio of sequential vs. random I/O requests. That can affect I/O op speed by a good degree. For rotational media, 100% random requests is your lower bound for I/O ops, and 100% sequential is your upper bound. Also, since you'll be working with RAID5, your read/write percentage will also affect I/O Ops. This can be ...


2

This depends mostly on the type of the application you will run and on the usage pattern of the users.


2

The speed degradation is to be expected as the number of files being accessed simultaneously increases. Hard disk drives do not like to be accessed in parallel: every time the read/write head needs to switch cylinders you lose several milliseconds. Even if two files are on the same cylinder, or even the same track, you may still have to wait a rotation to ...


2

No (fsck can fix corrupted filesystem metadata, not a broken disk, nor is it a defragmentation tool). Depends on the filesystem. With ext3, excruciatingly long, I'd reserve several hours. More modern filesystems such as ext4 or xfs can easily be an order of magnitude faster.


2

Most if not all manufacturers very clearly state their switches capabilities on a model-by-model basis. Let us know what make/model you're looking at and I'll find it for you.


1

Use something like JMeter to load test it. It is impossible to predict scaling with any accuracy because the bottlenecks you hit will depend on your individual implentation of both website and hardware.


1

Zoredache is right: you need to do real world testing with your application in order to do accurate capacity planning. But with that said... If you expect to get ten million requests per day, and each request is 20 KB, that works out to about 190 GB per day, or 5912 GB per month. To get a rough idea of bandwidth costs, Amazon charges $0.12/GB on their S3 ...


1

well, there is no exact formula, but based on the numbers you provided, one can estimate some of the specs needed. 10.000 Requests per Second 20KB per Request equals 200.000KB per Second So, ignoring storage and IO Bandwidth, you would at least saturate two 1GE Links. Without knowing the nature of the responses, i can not provide any estimation on ...


1

Adaptive Computing's Moab Suite may fit the bill as a scheduling and placement-enabling tool. While it does not handle provisioning on its own, it can easily integrate with a variety of other tools that can handle that for you, and it can keep track of your currently-used and -available assets. Disclosure: while I am not an employee, my employer is a ...


1

I'm not too familiar with Windows, so I can't tell you which tool specifically you'd use for this (I seem to remember there being some built in monitoring / statistics utility in Administrative Tools), but you should be able to get a good idea by simply watching "blocks written" to the device you want to back up. While some of the writes may not change the ...


1

If you're running a full, daily, backup, it won't matter how many blocks change per day. You'll be backing up 300gb each time. Otherwise, the amount of differential that you're looking at depends on the capabilities of the backup software, and the specific amount of churn for your system. There's no good guess in advance without historic knowledge of what ...



Only top voted, non community-wiki answers of a minimum length are eligible