HACKING.md

Hacking on OpenShift

Building a Release

To build an OpenShift release you run the hack/build-release.sh script on a system with Docker, which will create a build environment image and then execute a cross platform Go build within it. The build output will be copied to _output/releases as a set of tars containing each version. It will also build the openshift/origin-base image which is the common parent image for all OpenShift Docker images.

$ hack/build-release.sh

NOTE: Only committed code is built.

Once the release has been built the official Docker images can be generated with hack/build-images.sh. The resulting images can then be pushed to a Docker registry.

$ hack/build-images.sh

NOTE: You only need to run this script if your code changes are part of any images OpenShift runs internally such as origin-sti-builder, origin-docker-builder, origin-deployer, etc.

To build the base and release images, run:

$ hack/build-base-images.sh

Once a release has been created, it can be pushed:

$ hack/push-release.sh

To cut an official tag release, we generally use the images built by ci.openshift.redhat.com under the devenv_ami job.

1. Create a new git tag git tag vX.X.X -a -m "vX.X.X" HEAD
2. Push the tag to GitHub git push origin --tags where origin is github.com/openshift/origin.git
3. Run the "devenv_ami" job
4. Once the images are pushed to the repository, run OS_PUSH_TAG="vX.X.X" hack/push-release.sh. Your tag must match the Git tag.
5. Upload the binary artifacts generated by that build to GitHub release page
6. Send an email to the dev list, including the important changes prior to the release.

We generally cut a release before disruptive changes land.

Test Suites

OpenShift uses three levels of testing - unit tests, integration test, and end-to-end tests (much like Kubernetes).

Unit tests

Unit tests follow standard Go conventions and are intended to test the behavior and output of a single package in isolation. All code is expected to be easily testable with mock interfaces and stubs, and when they are not it usually means that there's a missing interface or abstraction in the code. A unit test should focus on testing that branches and error conditions are properly returned and that the interface and code flows work as described. Unit tests can depend on other packages but should not depend on other components (an API test should not be writing to etcd).

The unit tests for an entire package should not take more than 0.5s to run, and if they do, are probably not really unit tests or need to be rewritten to avoid sleeps or pauses. Coverage on a unit test should be above 70% unless the units are a special case.

See pkg/template/generator for examples of unit tests. Unit tests should follow Go conventions.

Run the unit tests with:

$ hack/test-go.sh

or an individual package unit test with:

$ hack/test-go.sh pkg/build

or an individual package and all packages nested under it:

$ hack/test-go.sh pkg/build/...

To run only a certain regex of tests in a package, use:

$ hack/test-go.sh pkg/build -test.run=SynchronizeBuildRunning

To get verbose output add -v to the end:

$ hack/test-go.sh pkg/build -test.run=SynchronizeBuildRunning -v

To run all tests with verbose output:

$ hack/test-go.sh "" -v

To enable running the kubernetes unit tests:

$ TEST_KUBE=1 hack/test-go.sh

To run unit test for an individual kubernetes package:

$ TEST_KUBE=1 hack/test-go.sh Godeps/_workspace/src/k8s.io/kubernetes/examples

To turn off or change the coverage mode, which is -cover -covermode=atomic by default, use:

$ KUBE_COVER="" hack/test-go.sh

To run tests without the go race detector, which is on by default, use:

$ KUBE_RACE="" hack/test-go.sh

A line coverage report is run by default when testing a single package. To create a coverage report for all packages:

$ OUTPUT_COVERAGE=/path/to/dir hack/test-go.sh pkg/build

After that you can open /path/to/dir/coverage.html in the browser.

Integration tests

Integration tests cover multiple components acting together (generally, 2 or 3). These tests should focus on ensuring that naturally related components work correctly. They should not be extensively testing branches or error conditions inside packages (that's what unit tests do), but they should validate that important success and error paths work across layers (especially when errors are being converted from lower level errors). Integration tests should not be testing details of the inter-component connections - API tests should not test that the JSON serialized to the wire is correctly converted back and forth (unit test responsibility), but they should test that those connections have the expected outcomes. The underlying goal of integration tests is to wire together the most important components in isolation. Integration tests should be as fast as possible in order to enable them to be run repeatedly during testing. Integration tests that take longer than 0.5s are probably trying to test too much together and should be reorganized into separate tests. Integration tests should generally be written so that they are starting from a clean slate, but if that involves costly setup those components should be tested in isolation.

We break integration tests into two categories, those that use Docker and those that do not. In general, high-level components that depend on the behavior of code running inside a Docker container should have at least one or two integration tests that test all the way down to Docker, but those should be part of their own test suite. Testing the API and high level API functions should generally not depend on calling into Docker. They are denoted by special test tags and should be in their own files so we can selectively build them.

All integration tests are located under test/integration/*. All integration tests must set the integration build tag at the top of their source file, and also declare whether they need etcd with the etcd build tag and whether they need Docker with the docker build tag. For special function sets please create sub directories like test/integration/deployimages.

Run the integration tests with:

$ hack/test-integration.sh

The script launches an instance of etcd and then invokes the integration tests. If you need to execute a subset of integration tests, run:

$ hack/test-integration.sh <regex>

Where <regex> is some regular expression that matches the names of all of the tests you want to run. The regular expression is passed into grep -E, so ensure that the syntax or features you use are supported. The default regular expression used is Test, which matches all tests.

Each integration function is executed in its own process so that it cleanly shuts down any background goroutines. You will not be able to run more than a single test within a single process.

There is a CLI integration test suite which covers general non-Docker functionality of the CLI tool working against the API. Run it with:

$ hack/test-cmd.sh

This suite comprises many smaller suites, which are found under test/cmd and can be run individually by specifying them using a regex filter, passed through grep -E like with integration tests above:

$ hack/test-cmd.sh <regex>

End-to-End (e2e) Tests

The final test category is end to end tests (e2e) which should verify a long set of flows in the product as a user would see them. Two e2e tests should not overlap more than 10% of function, and are not intended to test error conditions in detail. The project examples should be driven by e2e tests. e2e tests can also test external components working together.

End to end tests should be Go tests with the build tag e2e in the test/e2e directory.

Run the end to end tests with:

$ hack/test-end-to-end.sh

Installing Godep

OpenShift and Kubernetes use Godep for dependency management. Godep allows versions of dependent packages to be locked at a specific commit by vendoring them (checking a copy of them into Godeps/_workspace/). This means that everything you need for OpenShift is checked into this repository. To install godep locally run:

$ go get github.com/tools/godep

If you are not updating packages you should not need godep installed.

Cherry-picking an upstream commit into Origin

You can use hack/cherry-pick.sh to generate patches for Origin from upstream commits. To use this command, be sure to setup remote branches like https://gist.github.com/piscisaureus/3342247 so that git show origin/pr/<number> displays information about your branch after a git fetch. You must also have the Kubernetes repository checked out in your GOPATH (visible as ../../../k8s.io/kubernetes) and have no modified or uncommitted files in either repository.

To pull an upstream commit, run:

$ hack/cherry-pick.sh <pr_number>

This will attempt to create a patch from the current Kube rebase version in Origin that contains the commits added in the PR. If the PR has already been merged to the Kube version, you'll get an error. If there are conflicts, you'll have to resolve them in the upstream repo, then hit ENTER to continue. The end result will be a single commit in your Origin repo that contains the changes.

If you want to run without a rebase option, set NO_REBASE=1 before the command is run. You can also specify a commit range directly with:

$ hack/cherry-pick.sh origin/master...<some_branch>

All upstream commits should have a commit message where the first line is:

UPSTREAM: <PR number|drop|carry>: <short description>

drop indicates the commit should be removed during the next rebase. carry means that the change cannot go into upstream, and we should continue to use it during the next rebase.

You can also target repositories other than Kube by setting UPSTREAM_REPO and UPSTREAM_PACKAGE env vars. UPSTREAM_REPO should be the full name of the Git repo as Go sees it, i.e. github.com/coreos/etcd, and UPSTREAM_PACKAGE must be a package inside that repo that is currently part of the Godeps.json file. Example:

$ UPSTREAM_REPO=github.com/coreos/etcd UPSTREAM_PACKAGE=store hack/cherry-pick.sh <pr_number>

By default hack/cherry-pick.sh uses git remote named origin to fetch kubernetes repository, if your git configuration is different, you can pass the git remote name by setting UPSTREAM_REMOTE env var:

$ UPSTREAM_REMOTE=upstream hack/cherry-pick.sh <pr_number>

Moving a commit you developed in Origin to an upstream

The hack/move-upstream.sh script takes the current feature branch, finds any changes to the requested upstream project (as defined by UPSTREAM_REPO and UPSTREAM_PACKAGE) that differ from origin/master, and then creates a new commit in that upstream project on a branch with the same name as your current branch.

For example, to upstream a commit to OpenShift source-to-image while working from Origin:

$ git checkout my_feature_branch_in_origin
$ git log --oneline
70ffe7e Docker and STI builder support binary extraction
75a22de UPSTREAM: <sti>: Allow prepared directories to be passed to STI
86eefdd UPSTREAM: 14618: Refactor exec to allow reuse from server

# we want to move our STI changes to upstream
$ UPSTREAM_REPO=github.com/openshift/source-to-image UPSTREAM_PACKAGE=pkg/api hack/move-upstream.sh
...

# All changes to source-to-image in Godeps/. are now in a commit UPSTREAMED in s2i repo

$ cd ../source-to-image
$ git log --oneline
c0029f6 UPSTREAMED
... # older commits

The default is to work against Kube.

Updating Kubernetes from upstream

There are a few steps involved in rebasing Origin to a new version of Kubernetes. We need to make sure that not only the Kubernetes packages were updated correctly into Godeps, but also that all tests are still running without errors and code changes, refactorings or the inclusion/removal of attributes were properly reflected in the Origin codebase.

1. Preparation

Before you begin, make sure you have both openshift/origin and kubernetes/kubernetes in your $GOPATH. You may want to work on a separate $GOPATH just for the rebase:

$ go get github.com/openshift/origin
$ go get k8s.io/kubernetes

Check out the version of Kubernetes you want to rebase as a branch or tag named stable_proposed in kubernetes/kubernetes. For example, if you are going to rebase the latest master of Kubernetes:

$ cd $GOPATH/src/k8s.io/kubernetes
$ git checkout master
$ git pull
$ git checkout -b stable_proposed

2. Rebase Origin to the new Kubernetes version

2.1. First option (preferred): using the rebase-kube.sh script

If all requirements described in Preparation were correctly attended, you should not have any trouble with rebasing the Kubernetes code using the script that automates this process.

$ cd $GOPATH/src/github.com/openshift/origin
$ hack/rebase-kube.sh

Read over the changes with git status and make sure it looks reasonable. Check specially the Godeps/Godeps.json file to make sure no dependency is unintentionally missing.

Commit using the message bump(k8s.io/kubernetes):<commit SHA>, where <commit SHA> is the commit id for the Kubernetes version we are including in our Godeps. It can be found in our Godeps/Godeps.json in the declaration of any Kubernetes package.

2.2. Second option: manually

If for any reason you had trouble rebasing using the script, you may need to to do it manually. After following all requirements described in the Preparation topic, you will need to run godep restore from both the Origin and the Kubernetes directories and then godep save ./... from the Origin directory. Follow these steps:

1. $ cd $GOPATH/src/github.com/openshift/origin
2. make clean ; godep restore will restore the package versions specified in the Godeps/Godeps.json of Origin to your GOPATH.
3. $ cd $GOPATH/src/k8s.io/kubernetes
4. $ git checkout stable_proposed will checkout the desired version of Kubernetes as branched in Preparation.
5. $ godep restore will restore the package versions specified in the Godeps/Godeps.json of Kubernetes to your GOPATH.
6. $ cd $GOPATH/src/github.com/openshift/origin.
7. $ make clean ; godep save ./... will save a list of the checked-out dependencies to the file Godeps/Godeps.json, and copy their source code into Godeps/_workspace.
8. If in the previous step godep complaints about the checked out revision of a package being different than the wanted revision, this probably means there are new packages in Kubernetes that we need to add. Do a godep save <pkgname> with the package specified by the error message and then $ godep save ./... again.
9. Read over the changes with git status and make sure it looks reasonable. Check specially the Godeps/Godeps.json file to make sure no dependency is unintentionally missing. The whole Godeps directory will be added to version control, including _workspace.
10. Commit using the message bump(k8s.io/kubernetes):<commit SHA>, where <commit SHA> is the commit id for the Kubernetes version we are including in our Godeps. It can be found in our Godeps/Godeps.json in the declaration of any Kubernetes package.

If in the process of rebasing manually you found any corner case not attended by the hack/rebase-kube.sh script, make sure you update it accordingly to help future rebases.

3. cherry-pick upstream changes pushed to the Origin repo

Eventually during the development cycle we introduce changes to dependencies right in the Origin repository. This is not a largely recommended practice, but it's useful if we need something that, for example, is in the Kubernetes repository but we are not doing a rebase yet. So, when doing the next rebase, we need to make sure we get all these changes otherwise they will be overridden by godep save.

1. Check the Godeps directory commits history for commits tagged with the UPSTREAM keyword. We will need to cherry-pick all UPSTREAM commits since the last Kubernetes rebase (remember you can find the last rebase commit looking for a message like bump(k8s.io/kubernetes):...).
2. For every commit tagged UPSTREAM, do git cherry-pick <commit SHA>.
3. Notice that eventually the cherry-pick will be empty. This probably means the given change were already merged in Kubernetes and we don't need to specifically add it to our Godeps. Nice!
4. Read over the commit history and make sure you have every UPSTREAM commit since the last rebase (except only for the empty ones).

4. Refactor Origin to be compliant with upstream changes

After making sure we have all the dependencies in place and up-to-date, we need to work in the Origin codebase to make sure the compilation is not broken, all tests pass and it's compliant with any refactorings, architectural changes or behavior changes introduced in Kubernetes. Make sure:

1. make clean ; hack/build-go.sh compiles without errors and the standalone server starts correctly.
2. all of our generated code is up to date by running all hack/update-* scripts.
3. hack/verify-open-ports.sh runs without errors.
4. hack/copy-kube-artifacts.sh so Kubernetes tests can be fully functional. The diff resulting from this script should be squashed into the Kube bump commit.
5. TEST_KUBE=1 hack/test-go.sh runs without errors.
6. hack/test-cmd.sh runs without errors.
7. hack/test-integration.sh runs without errors.
8. hack/test-end-to-end.sh runs without errors. See Building a Release above for setting up the environment for the test-end-to-end.sh tests.

It is helpful to look at the Kubernetes commit history to be aware of the major topics. Although it can potentially break or change any part of Origin, the most affected parts are usually:

1. https://github.com/openshift/origin/blob/master/pkg/cmd/server/start.go
2. https://github.com/openshift/origin/blob/master/pkg/cmd/server/kubernetes/master.go
3. https://github.com/openshift/origin/blob/master/pkg/cmd/server/origin/master.go
4. https://github.com/openshift/origin/blob/master/pkg/cmd/cli/cmd/factory.go
5. https://github.com/openshift/origin/blob/master/pkg/cmd/cli/cli.go
6. https://github.com/openshift/origin/blob/master/pkg/api/meta/multimapper.go

Place all your changes in a commit called "Refactor to match changes upstream".

5. Pull request

A typical pull request for your Kubernetes rebase will contain:

1. One commit for the Kuberentes Godeps bump (bump(k8s.io/kubernetes):<commit SHA>).
2. Zero, one, or more bump commits for any shared dependencies between Origin and Kubernetes that have been bumped. Any transitive dependencies coming from Kubernetes should be squashed in the Kube bump commit.
3. Zero, one, or more cherry-picked commits tagged UPSTREAM.
4. One commit "Boring refactor to match changes upstream" that includes boring changes like imports rewriting, etc.
5. One commit "Interesting refactor to match changes upstream" that includes interesting changes like new plugins or controller changes.

Updating other Godeps from upstream

To update to a new version of a dependency that's not already included in Kubernetes, checkout the correct version in your GOPATH and then run godep save <pkgname>. This should create a new version of Godeps/Godeps.json, and update Godeps/_workspace/src. Create a commit that includes both of these changes with message bump(<pkgname>): <pkgcommit>.

Troubleshooting

If you run into difficulties running OpenShift, start by reading through the troubleshooting guide.

RPM Packaging

A specfile is included in this repo which can be used to produce RPMs including the openshift binary. While the specfile will be kept up to date with build requirements the version is not updated. You will need to either update the Version, %commit, and %ldflags values on your own or you may use tito to build and tag releases.

Swagger API Documentation

OpenShift and Kubernetes integrate with the Swagger 2.0 API framework which aims to make it easier to document and write clients for RESTful APIs. When you start OpenShift, the Swagger API endpoint is exposed at https://localhost:8443/swaggerapi. The Swagger UI makes it easy to view your documentation - to view the docs for your local version of OpenShift start the server with CORS enabled:

$ openshift start --cors-allowed-origins=.*

and then browse to http://openshift3swagger-claytondev.rhcloud.com (which runs a copy of the Swagger UI that points to localhost:8080 by default). Expand the operations available on v1beta3 to see the schemas (and to try the API directly).

Note: Hosted API documentation can be found here.

Performance debugging

OpenShift integrates the go pprof tooling to make it easy to capture CPU and heap dumps for running systems. The following modes are available for the openshift binary (including all the CLI variants):

• OPENSHIFT_PROFILE environment variable:
  • cpu - will start a CPU profile on startup and write ./cpu.pprof. Contains samples for the entire run at the native sampling resolution (100hz). Note: CPU profiling for Go does not currently work on Mac OS X - the stats are not correctly sampled
  • mem - generate a running heap dump that tracks allocations to ./mem.pprof
  • web - start the pprof webserver in process at http://127.0.0.1:6060/debug/pprof (you can open this in a browser)

In order to start the server in CPU profiling mode, run:

$ OPENSHIFT_PROFILE=cpu sudo ./_output/local/bin/linux/amd64/openshift start

Or, if running OpenShift under systemd, append this to /etc/sysconfig/openshift-master

OPENSHIFT_PROFILE=cpu

To view profiles, you use pprof which is part of go tool. You must pass the binary you are debugging (for symbols) and a captured pprof. For instance, to view a cpu profile from above, you would run OpenShift to completion, and then run:

$ go tool pprof ./_output/local/bin/linux/amd64/openshift cpu.pprof
or
$ go tool pprof /bin/openshift /var/lib/openshift/cpu.pprof

This will open the pprof shell, and you can then run:

# see the top 20 results
(pprof) top20

# see the top 50 results
(pprof) top50

# show the top20 sorted by cumulative time
(pprof) cum=true
(pprof) top20

to see the top20 CPU consuming fields or

(pprof) web

to launch a web browser window showing you where CPU time is going.

pprof supports CLI arguments for looking at profiles in different ways - memory profiles by default show allocated space:

$ go tool pprof ./_output/local/bin/linux/amd64/openshift mem.pprof

but you can also see the allocated object counts:

$ go tool pprof --alloc_objects ./_output/local/bin/linux/amd64/openshift mem.pprof

Finally, when using the web profile mode, you can have the go tool directly fetch your profiles via HTTP:

# for a 30s CPU trace
$ go tool pprof ./_output/local/bin/linux/amd64/openshift http://127.0.0.1:6060/debug/pprof/profile

# for a snapshot heap dump at the current time, showing total allocations
$ go tool pprof --alloc_space ./_output/local/bin/linux/amd64/openshift http://127.0.0.1:6060/debug/pprof/heap

See debugging Go programs for more info. pprof has many modes and is very powerful (try tree) - you can pass a regex to many arguments to limit your results to only those samples that match the regex (basically the function name or the call stack).