This is good, because it means your application isn’t tightly coupled to Prometheus. It uses a set of instructions, to determine which applications to fetch metrics from, and how to do it. So you can run a single instance of Prometheus, and it can fetch and store metrics from dozens of your apps.Īnd this is an important point: Prometheus uses a pull-based approach for getting metrics. Prometheus runs separately from your application. So in other words, time-series analysis allows you to look at a set of data over time, and see trends, how you’re performing, and perhaps make some estimations about the future. It is done to diagnose past behavior as well as to predict future behavior. Time series analysis is the endeavor of extracting meaningful summary and statistical information from points arranged in chronological order. What is time-series analysis?įrom the book Practical Time Series Analysis, by Aileen Nielsen: And this allows you to perform time-series analysis of metrics. It’s generally used to store metrics and performance data from your applications. It is a time-series database, which stores a sequence of data points, across time. Prometheus is one way of solving this problem. So, is there a tool that can help us record technical metrics, and make it easy to see trends? We want to measure the success of our applications, and learn from the results. One of the key tenets of DevOps is measurement and learning. And part of this expectation is being able to see clear metrics about how well software is doing.Īnd finally, the DevOps age is upon us. Secondly, the business now expects much more return from its investment in software. Apps are getting smaller (I’m talking about those ubiquitous microservices), and there are simply far more of them. Advertisementsįirstly, the number of applications that we are deploying is growing so much larger. Unless you wanted to spend a lot of money on enterprisey software and install a bunch of agents everywhere, you probably had to roll your own solution.īut in the last few years, people have started to realise that finding a standard way of monitoring applications is becoming rather essential. Historically, it’s been quite difficult to implement a standard way of monitoring many different types of applications.Įach language and framework has its own way of doing things. So, to be a bit more proactive, and head off these issues early, we realised the need to monitor our applications. Why is the app unresponsive? Why is it so slow? Why have users been phoning the helpdesk all morning and raised 1,000 Jira tickets already!? Whenever this happens, the first challenge is always trying to find out why. I would just sort of sit there, nervously, in the part of the office where all the developers sit, just wondering… and waiting…Įventually, a bug report would come in, or someone from the production operations team would come over to my desk, and tell me that something’s not quite right with the application, but… they’re not quite sure what.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |