So we make use of TeamCity as a CI server (v 7.1.1). And we use MS' own web deployment tool as a means of publishing to our servers (standard ASP.NET fare). However, I've noticed that the batch files that are generated by web deploy seem to play badly with TeamCity.
This is what appears in the build log:
http://dpaste.com/826346/
The script clearly says an error has happened. However, TC seems unable to detect this, as no red lights come on. Is there a (good) way to fix and detect this, so we don't get incorrect build runner status reports? TC is currently setup so that the deployment script is executed by a Command Line runner.
To fix it, change the IIS site AppPool to .net version 4.0 - Your error message says that the app expects 4.0 but web deployment tool is finding 2.0
To detect it, I think you can configure the Build Failure Condition, to fail a build when "an error message is logged by build runner".
Related
I am trying to use Specflow with Playwright in order to do BDD on a portal app developed but I am facing a small problem.
The Specflow project is a separate project with the ASP.Net core server that has the Api of the portal app (it is in Vue). Since the tests are pointing to a specific URL (currently localhost), before running the tests, I need to run the ASP.Net core & Vue project locally. Otherwise, Specflow & Playwright will not be able to do the test (as it will not find the localhost).
Is it any way I can force the run of the Web Server project? I tried to run it from outside Visual Studio with dotnet build and then dotnet run commands but somehow they are missing parameters (that exist while running it from inside VS) and apart from that, these commands must somehow be triggered while trying to run the tests.
I have seen solutions like creating a Docker image from a Docker Compose file in order to pack a .Net project & server in it before running the Specflow tests. Then in the BeforeTestRun hook using the FluentDocker to spin-up the server but I am not quite sure it is the easier (or best) solution.
Does anyone know how I can trigger running the .net core project (with the Vue pages)?
This is actually a pretty big question, with a pretty big answer, however this is well-trodden ground. The issue isn't so much a "specflow" issue as a general automated testing issue. Development practices like continuous integration and continuous delivery can help. Each one is too big for a single question, however I can answer this in more general terms.
In its simplest form, running automated tests locally involves these steps:
Build the application
Deploy the application to a real web server
Run tests
I'm going to assume you are developing in a Windows environment, however every operating system has some sort of command line scripting solution available. The scripting language might change, but the overall idea will not.
Configure a web server. In Windows, this would be Internet Information Services (IIS).
Add a new "application" (or "IIS app" as some people call it) to your localhost web server. Point the physical directory to the root directory for the web project. Repeat this for each web site or web app your system requires.
Write a PowerShell script that gives you an easy way to build and deploy the applications to your local web server.
This script should use publish profiles set up in Visual Studio, which allows you to publish directly from Visual Studio before invoking tests manually through Test Explorer.
Write a PowerShell script used has a "harness" script to coordinate building, deploying locally, and then invoking dotnet test.
Running tests locally just requires a single line of PowerShell to invoke your test harness script:
.\Scripts\Run-Tests.ps1 -solutionDir . -tags BlogPosts,Create
# Skip deploying in case web apps haven't changed:
.\Scripts\Run-Tests.ps1 -solutionDir . -tags BlogPosts,Create -deploy:False
I've followed this guide to have my TeamCity build running some JMeter tests, but I'm not seeing the "RemotePerfMon" tab for the server statistics. I have the "Performance Statistics" tab, and I can see that the statistics are definitely being collected, as there is a monitoring.csv file being created and populated in the build agent's work directory.
Any ideas on how I can get the tab to display?
I'm using TeamCity v9.1.6 with JMeter plugin version 83, everything running on Windows 8.
Additional Info:
I've found that there is an open issue on Github for this problem, so I'm obviously not the only one facing this issue.
Make sure TeamCity is NOT running as Administrator
After quite a while playing around with it, I discovered that the problem was that both the TeamCity Server and the TeamCity build agent were running on the same machine, but the Build agent was running as Administrator. Stopping both the services and restarting them as a regular user fixed the issue.
I believe the root of the issue was that the monitoring.csv file was created by the Build Agent as Administrator, then wen the non-admin server agent attempted to parse it, it failed. This error doesn't seem to get logged anywhere, and TeamCity responds to the error by simply not displaying the tab.
I've connected Visual Studio Team Services to an Azure Website to enable automatic deployments. New Relic is running as a system process and therefore NewRelic.Agent.Core.dll is locked which prevents successful builds from being deployed.
I've tried adding a wpp.targets file to the solution in order to utilize MSDeploy to copy an app_offline document to the site before deployment, then delete it when deployment is done like seen here. However, it doesn't seem as if it is executing. I don't see anything in the build logs and my deployments continue to fail.
How do I take the app offline when using the VS Team Services/Azure CI process?
I came across this old post and there are now build tasks to start and stop an app service. See the Azure App Service Manage under the deployment tasks in the build task catalog.
Slightly different to what you are asking but what you could do is to login to your Azure website and set COR_ENABLE_PROFILING to 0 before your build runs. You then deploy as normal. Once done you set COR_ENABLE_PROFILING back to 1.
The act of changing the setting will cause an IIS reset and setting it to zero will disable the file from being locked again before the publish finishes.
Source: https://discuss.newrelic.com/t/visual-studio-online-azure-website-continuous-integration-fails/3825
We're working on setting up a TFS server for our work, and I'm in charge of getting the build working. I have had no experience with TFS before, but setting the build controller and agents up using the wizards was easy enough. We have the TFS server on one machine, and a build controller and build agent on another machine registered to the TFS server.
When I start a build from my developer machine, the build reports as having started and the status of the controller changes to something like "running build vstfs://Build/Build/16". However, the status of the Agent never changes from "Ready" and the build hangs indefinitely. If I stop the build from my developer machine, it reports that the "build was forcefully stopped by the server because the build machine did not respond to a stop request", and the build controller still has the status of "running build". I need to restart the build controller in order to reset the status.
I've checked that port 9191 is unblocked, and I can telnet into the port from my developer machine. The server also seems to be able to communicate with the build machine, as the controller is receiving build requests, but I have no idea what to do from here. Any TFS experts have any idea what might be happening?
Thanks,
Zach
Found the problem.
Under the build service properties, We had the value "Listen for build agent communication on:" set to [BUILDAGENT.companydomain.com:9191/Build/v5.0/Services. We needed the value to be just [BUILDAGENT:9191/Build/v5.0/Services]
I'm developing a project in C# using VS2010. I'm using svn 1.7 for my version control. What I want is a (FREE) tool that runs on the build server and checks for fresh commits. If the commit breaks the trunk then I want email notifications sent (I have a sendmail openbsd server on the network I can use). I also want this tool (or another tool) to run all my MSTest tests periodically and send emails if there is a failed test.
Any suggestions? I already built my own crude windows service to check for failed builds. But this was before I heard that tools for this sort of thing already exist. I could easily have this thing run all my tests with mstest.exe and then parse the xml results files, but I'm wondering if my time would be better spent just installing and configuring a proper tool for all of this.
There will be at most 4 developers.
Thanks in advance for the help!
I have some experience with TeamCity and Hudson/Jenkins.
I found TeamCity fairly easy to setup and it seems to meet your needs of:
MSTest integration out of the box
Email notifications
TeamCity is free for up to 20 build configurations and has an easy to use Web/GUI interface.
Have a look at CruiseControl.Net
built in support for Subversion
no limits on number of build configurations
email notifications using the 'Email Publisher'
web interface and desktop build notifications via CCTray