Fix tty and io permission for userns
Signed-off-by: Michael Crosby <crosbymichael@gmail.com>
This commit is contained in:
Michael Crosby
parent
20a39bce97
commit
cf28969328
|
|
@ -157,11 +157,10 @@ func (p *process) delete() error {
|
|||
func (p *process) openIO() error {
|
||||
p.stdio = &stdio{}
|
||||
var (
|
||||
uid = int(p.state.User.UID)
|
||||
gid = int(p.state.User.GID)
|
||||
uid = p.state.RootUID
|
||||
gid = p.state.RootGID
|
||||
)
|
||||
if p.state.Terminal {
|
||||
// FIXME: this is wrong for user namespaces and will need to be translated
|
||||
console, err := libcontainer.NewConsole(uid, gid)
|
||||
if err != nil {
|
||||
return err
|
||||
|
|
|
|||
|
|
@ -161,7 +161,15 @@ func (c *container) Start(checkpoint string, s Stdio) (Process, error) {
|
|||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
p, err := newProcess(processRoot, InitProcessID, c, spec.Process, s)
|
||||
config := &processConfig{
|
||||
root: processRoot,
|
||||
id: InitProcessID,
|
||||
c: c,
|
||||
stdio: s,
|
||||
spec: spec,
|
||||
processSpec: spec.Process,
|
||||
}
|
||||
p, err := newProcess(config)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
|
@ -188,7 +196,14 @@ func (c *container) Exec(pid string, spec specs.Process, s Stdio) (Process, erro
|
|||
cmd.SysProcAttr = &syscall.SysProcAttr{
|
||||
Setpgid: true,
|
||||
}
|
||||
p, err := newProcess(processRoot, pid, c, spec, s)
|
||||
config := &processConfig{
|
||||
id: pid,
|
||||
root: processRoot,
|
||||
c: c,
|
||||
processSpec: spec,
|
||||
stdio: s,
|
||||
}
|
||||
p, err := newProcess(config)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
|
@ -312,3 +327,31 @@ func (c *container) Checkpoint(cpt Checkpoint) error {
|
|||
func (c *container) DeleteCheckpoint(name string) error {
|
||||
return os.RemoveAll(filepath.Join(c.bundle, "checkpoints", name))
|
||||
}
|
||||
|
||||
func getRootIDs(s *specs.LinuxSpec) (int, int, error) {
|
||||
if s == nil {
|
||||
return 0, 0, nil
|
||||
}
|
||||
var hasUserns bool
|
||||
for _, ns := range s.Linux.Namespaces {
|
||||
if ns.Type == specs.UserNamespace {
|
||||
hasUserns = true
|
||||
break
|
||||
}
|
||||
}
|
||||
if !hasUserns {
|
||||
return 0, 0, nil
|
||||
}
|
||||
uid := hostIDFromMap(0, s.Linux.UIDMappings)
|
||||
gid := hostIDFromMap(0, s.Linux.GIDMappings)
|
||||
return uid, gid, nil
|
||||
}
|
||||
|
||||
func hostIDFromMap(id uint32, mp []specs.IDMapping) int {
|
||||
for _, m := range mp {
|
||||
if (id >= m.ContainerID) && (id <= (m.ContainerID + m.Size - 1)) {
|
||||
return int(m.HostID + (id - m.ContainerID))
|
||||
}
|
||||
}
|
||||
return 0
|
||||
}
|
||||
|
|
|
|||
|
|
@ -40,32 +40,47 @@ type Process interface {
|
|||
SystemPid() int
|
||||
}
|
||||
|
||||
func newProcess(root, id string, c *container, s specs.Process, stdio Stdio) (*process, error) {
|
||||
type processConfig struct {
|
||||
id string
|
||||
root string
|
||||
processSpec specs.Process
|
||||
spec *specs.LinuxSpec
|
||||
c *container
|
||||
stdio Stdio
|
||||
}
|
||||
|
||||
func newProcess(config *processConfig) (*process, error) {
|
||||
p := &process{
|
||||
root: root,
|
||||
id: id,
|
||||
container: c,
|
||||
spec: s,
|
||||
stdio: stdio,
|
||||
root: config.root,
|
||||
id: config.id,
|
||||
container: config.c,
|
||||
spec: config.processSpec,
|
||||
stdio: config.stdio,
|
||||
}
|
||||
f, err := os.Create(filepath.Join(root, "process.json"))
|
||||
uid, gid, err := getRootIDs(config.spec)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
f, err := os.Create(filepath.Join(config.root, "process.json"))
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
defer f.Close()
|
||||
if err := json.NewEncoder(f).Encode(ProcessState{
|
||||
Process: s,
|
||||
Stdin: stdio.Stdin,
|
||||
Stdout: stdio.Stdout,
|
||||
Stderr: stdio.Stderr,
|
||||
Process: config.processSpec,
|
||||
RootUID: uid,
|
||||
RootGID: gid,
|
||||
Stdin: config.stdio.Stdin,
|
||||
Stdout: config.stdio.Stdout,
|
||||
Stderr: config.stdio.Stderr,
|
||||
}); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
exit, err := getExitPipe(filepath.Join(root, ExitFile))
|
||||
exit, err := getExitPipe(filepath.Join(config.root, ExitFile))
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
control, err := getControlPipe(filepath.Join(root, ControlFile))
|
||||
control, err := getControlPipe(filepath.Join(config.root, ControlFile))
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
|
|
|||
|
|
@ -44,9 +44,11 @@ type state struct {
|
|||
|
||||
type ProcessState struct {
|
||||
specs.Process
|
||||
Stdin string `json:"containerdStdin"`
|
||||
Stdout string `json:"containerdStdout"`
|
||||
Stderr string `json:"containerdStderr"`
|
||||
RootUID int `json:"rootUID"`
|
||||
RootGID int `json:"rootGID"`
|
||||
Stdin string `json:"containerdStdin"`
|
||||
Stdout string `json:"containerdStdout"`
|
||||
Stderr string `json:"containerdStderr"`
|
||||
}
|
||||
|
||||
type Stat struct {
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
language: go
|
||||
go:
|
||||
- 1.5.1
|
||||
- 1.5.3
|
||||
- 1.4.3
|
||||
- 1.3.3
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,217 @@
|
|||
OpenContainers Specifications
|
||||
|
||||
Changes with v0.3.0:
|
||||
Breaking changes:
|
||||
|
||||
* config: Single, unified config file, #284
|
||||
* config: cwd is a required default, and must be absolute, #286,
|
||||
#307, #308, #312
|
||||
* config: qualify the name of the version field, #309
|
||||
* config-linux: Convert classID from hex to uint32, #296
|
||||
* config-linux: Separate mknod from cgroups, #298
|
||||
|
||||
Additions:
|
||||
|
||||
* config-linux: Add NoNewPrivileges setting for linux, #290
|
||||
|
||||
Minor fixes and documentation:
|
||||
|
||||
* config-linux: clarify oom_score_adj, #236, #292
|
||||
* config-linux: Update links to cgroups documentation, #318
|
||||
* config-linux: Remove pointers for slices preferring omitempty
|
||||
tag instead, #316
|
||||
* README: add runtime, bundle, and hook author user, #280
|
||||
* ROADMAP: reshuffled and split into GitHub issues, #300, #301,
|
||||
#304, #306
|
||||
* style: Collect established styles in a discoverable location, #287, #311
|
||||
|
||||
Changes with v0.2.0:
|
||||
* Add Apparmor, Selinux and Seccomp
|
||||
* Add Apparmor, Selinux and Seccomp sections
|
||||
* Add bind mount example
|
||||
* Add fd section for linux container process
|
||||
* Add Go types for specification
|
||||
* *: adding a code of conduct
|
||||
* Adding cgroups path to the Spec.
|
||||
* .: Adding listing of implementations
|
||||
* .: adding travis file for future CI
|
||||
* Add license and DCO information for contributions
|
||||
* Add linux spec description
|
||||
* Add MAINTAINERS file
|
||||
* Add memory swappiness to linux spec
|
||||
* Add runtime state configuration and structs
|
||||
* Adds a section for user namespace mappings
|
||||
* Adds link to kernel cgroups documentation
|
||||
* Adds section for Linux Rlimits
|
||||
* Adds section for Linux Sysctl.
|
||||
* Adds user namespace to the list of namespaces
|
||||
* bundle: add initial run use case
|
||||
* bundle: Fix 'and any number of and other related' typo
|
||||
* bundle.md: clarify arbitrary/conventional dirnames
|
||||
* bundle.md: fix link formatting
|
||||
* bundle.md: fix off-by-one error
|
||||
* bundle.md: various updates to latest spec
|
||||
* bundle: Move 'Linux sysctl' header to its own line
|
||||
* Change commiter to committer
|
||||
* Change Device field order in spec_linux.go, 'Path' should be top of the 'Type' field, according to the different of the config-linux.md, 'Path' field is the unique key.
|
||||
* Change layout of mountpoints and mounts
|
||||
* Change the rlimit type to string instead of int
|
||||
* Clarify behavior around namespaces paths.
|
||||
* config: Add example additionalGids
|
||||
* config: Add example cwd
|
||||
* config: cleanup language on readonly parameter
|
||||
* config: fix links to go files
|
||||
* config-linux: specify the default devices/filesystems available
|
||||
* config.md: clarify destination for mounts
|
||||
* config.md: make the version a semver
|
||||
* config.md: make the version field example a semver
|
||||
* config.md: minor clean up of process specification
|
||||
* config.md: reformat into a standard style
|
||||
* config.md: update links to spec schema code
|
||||
* config.md: various cleanup/consistency fixes
|
||||
* config: minor cleanup
|
||||
* Deduplicate the field of RootfsPropagation
|
||||
* Define constants for Linux Namespace names
|
||||
* Fix LinuxRuntime field
|
||||
* Fix root object keys
|
||||
* Fix typos in config.md
|
||||
* Fix typos in the "Namespace types" section
|
||||
* Fix typos in the rlimits section
|
||||
* Fix Windows path escaping in example mount JSON
|
||||
* JSON objects are easier to parse/manipulate
|
||||
* made repo public. Added warning in README
|
||||
* Make namespaces match runc
|
||||
* make rootfs mount propagation mode settable
|
||||
* Makes namespaces description linux specific
|
||||
* *.md: markdown formatting
|
||||
* Modify the capabilities constants to match header files like other constants
|
||||
* Move linux specific options to linux spec
|
||||
* README: add a rule for paragraph formatting in markdown
|
||||
* README: Document BlueJeans and wiki archive for meetings
|
||||
* README: Document pre-meeting agenda alteration
|
||||
* README: Document YouTube and IRC backchannel for meetings
|
||||
* README: Focus on local runtime (create/start/stop)
|
||||
* README.md: Add a git commit style guide
|
||||
* README.md: contribution about discussion
|
||||
* README: releases section
|
||||
* README: Remove blank line from infrastructure-agnostic paragraph
|
||||
* removed boilerplate file
|
||||
* *: remove superfluous comma in code-of-conduct
|
||||
* Remove trailing whitespace
|
||||
* Rename SystemProperties to Sysctl
|
||||
* Rename the header "Access to devices" to "Devices" to fit with the config
|
||||
* *: re-org the spec
|
||||
* Replace Linux.Device with more specific config
|
||||
* restore formatting
|
||||
* Return golang compliant names for UID and GID in User
|
||||
* Return golint-compliant naming for mappings
|
||||
* runtime: Add prestart/poststop hooks
|
||||
* runtime_config: comments for golint
|
||||
* runtime-config-linux: Drop 'Linux' from headers
|
||||
* runtime_config_linux: Fix 'LinuxSpec' -> 'LinuxRuntimeSpec' in comment
|
||||
* runtime-config-linux: One sentence per line for opening two paragraphs
|
||||
* runtime-config: Remove blank lines from the end of files
|
||||
* runtime-config: Remove 'destination' docs from mounts
|
||||
* runtime.md: convert oc to runc
|
||||
* runtime: use opencontainer vs oci
|
||||
* *: small spelling fixes
|
||||
* Specific platform specific user struct for spec
|
||||
* spec: linux: add support for the PIDs cgroup
|
||||
* spec_linux: conform to `golint`
|
||||
* spec_linux.go: Rename IDMapping fields to follow syscall.SysProcIDMap
|
||||
* spec_linux: remove ending periods on one-line comments
|
||||
* spec: rename ocp to oci and add a link
|
||||
* specs: add json notation
|
||||
* specs: align the ascii graph
|
||||
* specs: fix the description for the [ug]idMappings
|
||||
* specs: introduce the concept of a runtime.json
|
||||
* .tools: cleanup the commit entry
|
||||
* .tools: repo validation tool
|
||||
* travis: fix DCO validation for merges
|
||||
* typo: containers -> container's
|
||||
* typo: the -> for
|
||||
* Update config-linux for better formatting on values
|
||||
* Update README.md
|
||||
* Update readme with weekly call and mailing list
|
||||
* Update runtime.md
|
||||
* Update runtime.md
|
||||
* Update runtime.md
|
||||
* version: more explicit version for comparison
|
||||
|
||||
Changes with v0.1.0:
|
||||
* Add Architecture field to Seccomp configuration in Linux runtime
|
||||
* Add @hqhq as maintainer
|
||||
* Add hyphen for host specific
|
||||
* Adding Vishnu Kannan as a Maintainer.
|
||||
* Add initial roadmap
|
||||
* Add lifecycle for containers
|
||||
* Add oom_score_adj to the runtime Spec.
|
||||
* Add post-start hooks
|
||||
* Add Seccomp constants to description of Linux runtime spec
|
||||
* Add Seccomp constants to Linux runtime config
|
||||
* Add some clarity around the state.json file
|
||||
* adds text describing the upper-case keywords used in the spec
|
||||
* add testing framework to ROADMAP
|
||||
* Appropriately mark optional fields as omitempty
|
||||
* cgroup: Add support for memory.kmem.tcp.limit_in_bytes
|
||||
* Change HugepageLimit.Limit type to uint64
|
||||
* Change the behavior when cgroupsPath is absent
|
||||
* Change version from 0.1.0 to 0.2.0
|
||||
* Clarify the semantics of hook elements
|
||||
* Cleanup bundle.md
|
||||
* Cleanup principles
|
||||
* config: linux: update description of PidsLimit
|
||||
* config: Require a new UTS namespace for config.json's hostname
|
||||
* config: Require the runtime to mount Spec.Mounts in order
|
||||
* convert **name** to **`name`**
|
||||
* Example lists "root' but text mentions "bundlePath"
|
||||
* Fix an extra space in VersionMinor
|
||||
* Fix golint warnings
|
||||
* Fix typo in BlockIO struct comment
|
||||
* Fix typo in Filesystem Bundle
|
||||
* Fix value of swappiness
|
||||
* glossary: Provide a quick overview of important terms
|
||||
* glossary: Specify UTF-8 for all our JSON
|
||||
* hooks: deduplicate the hooks docs
|
||||
* implementations: Link to kunalkushwaha/octool
|
||||
* implementations: Link to mrunalp/ocitools
|
||||
* lifecycle: Don't require /run/opencontainer/<runtime>/containers
|
||||
* lifecycle: Mention runtime.json
|
||||
* lifecycle: no hypens
|
||||
* MAINTAINERS: add tianon per the charter
|
||||
* MAINTAINERS: correct Vish's github account
|
||||
* Makefile: Add glossary to DOC_FILES
|
||||
* Make optional Cgroup related config params pointers along with `omitempty` json tag.
|
||||
* Mark RootfsPropagation as omitempty
|
||||
* *.md: update TOC and links
|
||||
* move the description of Rlimits before example
|
||||
* move the description of user ns mapping to proper file
|
||||
* principles: Give principles their own home
|
||||
* *: printable documents
|
||||
* Project: document release process
|
||||
* README: Fix some headers
|
||||
* README: make header more concise
|
||||
* remove blank char from blank line
|
||||
* Remove the unneeded build tag from the config_linux.go
|
||||
* Remove trailing comma in hooks json example
|
||||
* Rename State's Root to Bundle
|
||||
* ROADMAP.md: remove the tail spaces
|
||||
* roadmap: update links and add wiki reference
|
||||
* runtime: Add 'version' to the state.json example
|
||||
* runtime-config: add example label before json exmaple
|
||||
* runtime-config: add section about Hooks
|
||||
* runtime: config: linux: add cgroups information
|
||||
* runtime: config: linux: Edit BlockIO struct
|
||||
* runtime: config: linux: Fix typo and trailing commas in json example
|
||||
* runtime_config_linux.go: add missing pointer
|
||||
* runtime-config-linux.md: fix the type of cpus and mems
|
||||
* runtime.md: fix spacing
|
||||
* Talk about host specific/independent instead of mutability
|
||||
* .tools: commit validator is a separate project
|
||||
* .tools: make GetFetchHeadCommit do what it says
|
||||
* .travis.yml: add go 1.5.1, update from 1.4.2 to 1.4.3
|
||||
* Update readme with wiki link to minutes
|
||||
* Update Typo in ROADMAP.md
|
||||
* Use unsigned for IDs
|
||||
* version: introduce a string for dev indication
|
||||
|
||||
|
|
@ -4,6 +4,7 @@ DOC_FILES := \
|
|||
README.md \
|
||||
code-of-conduct.md \
|
||||
principles.md \
|
||||
style.md \
|
||||
ROADMAP.md \
|
||||
implementations.md \
|
||||
bundle.md \
|
||||
|
|
@ -11,11 +12,11 @@ DOC_FILES := \
|
|||
runtime-linux.md \
|
||||
config.md \
|
||||
config-linux.md \
|
||||
runtime-config.md \
|
||||
runtime-config-linux.md \
|
||||
glossary.md
|
||||
EPOCH_TEST_COMMIT := 041eb73d2e0391463894c04c8ac938036143eba3
|
||||
|
||||
docs: pdf html
|
||||
.PHONY: docs
|
||||
|
||||
pdf:
|
||||
@mkdir -p output/ && \
|
||||
|
|
@ -39,6 +40,22 @@ html:
|
|||
vbatts/pandoc -f markdown_github -t html5 -o /output/docs.html $(patsubst %,/input/%,$(DOC_FILES)) && \
|
||||
ls -sh $(shell readlink -f output/docs.html)
|
||||
|
||||
.PHONY: test .govet .golint .gitvalidation
|
||||
|
||||
test: .govet .golint .gitvalidation
|
||||
|
||||
# `go get golang.org/x/tools/cmd/vet`
|
||||
.govet:
|
||||
go vet -x ./...
|
||||
|
||||
# `go get github.com/golang/lint/golint`
|
||||
.golint:
|
||||
golint ./...
|
||||
|
||||
# `go get github.com/vbatts/git-validation`
|
||||
.gitvalidation:
|
||||
git-validation -q -run DCO,short-subject -v -range $(EPOCH_TEST_COMMIT)..HEAD
|
||||
|
||||
clean:
|
||||
rm -rf output/ *~
|
||||
|
||||
|
|
|
|||
|
|
@ -6,12 +6,11 @@
|
|||
Table of Contents
|
||||
|
||||
- [Container Principles](principles.md)
|
||||
- [Specification Style](style.md)
|
||||
- [Filesystem Bundle](bundle.md)
|
||||
- Configuration
|
||||
- [Container Configuration](config.md)
|
||||
- [Container Configuration (Linux-specific)](config-linux.md)
|
||||
- [Runtime Configuration](runtime-config.md)
|
||||
- [Runtime Configuration (Linux-specific)](runtime-config-linux.md)
|
||||
- [General](config.md)
|
||||
- [Linux-specific](config-linux.md)
|
||||
- [Runtime and Lifecycle](runtime.md)
|
||||
- [Linux Specific Runtime](runtime-linux.md)
|
||||
- [Implementations](implementations.md)
|
||||
|
|
@ -23,9 +22,20 @@ In the specifications in the above table of contents, the keywords "MUST", "MUST
|
|||
|
||||
To provide context for users the following section gives example use cases for each part of the spec.
|
||||
|
||||
## Filesystem Bundle & Configuration
|
||||
#### Application Bundle Builders
|
||||
|
||||
- A user can create a root filesystem and configuration, with low-level OS and host specific details, and launch it as a container under an Open Container runtime.
|
||||
Application bundle builders can create a [bundle](bundle.md) directory that includes all of the files required for launching an application as a container.
|
||||
The bundle contains an OCI [configuration file](config.md) where the builder can specify host-independent details such as [which executable to launch](config.md#process-configuration) and host-specific settings such as [mount](config.md#mounts) locations, [hook](config.md#hooks) paths, Linux [namespaces](config-linux.md#namespaces) and [cgroups](config-linux.md#control-groups).
|
||||
Because the configuration includes host-specific settings, application bundle directories copied between two hosts may require configuration adjustments.
|
||||
|
||||
#### Hook Developers
|
||||
|
||||
[Hook](config.md#hooks) developers can extend the functionality of an OCI-compliant runtime by hooking into a container's lifecycle with an external application.
|
||||
Example use cases include sophisticated network configuration, volume garbage collection, etc.
|
||||
|
||||
#### Runtime Developers
|
||||
|
||||
Runtime developers can build runtime implementations that run OCI-compliant bundles and container configuration, containing low-level OS and host specific details, on a particular platform.
|
||||
|
||||
# Releases
|
||||
|
||||
|
|
|
|||
|
|
@ -17,13 +17,6 @@ Although OCI doesn't define a transport method we should have a cryptographic di
|
|||
|
||||
*Owner:* philips
|
||||
|
||||
### Review the need for runtime.json
|
||||
|
||||
There are some discussions about having `runtime.json` being optional for containers and specifying defaults.
|
||||
Runtimes would use this standard set of defaults for containers and `runtime.json` would provide overrides for fine tuning of these extra host or platform specific settings.
|
||||
|
||||
*Owner:*
|
||||
|
||||
### Define Container Lifecycle
|
||||
|
||||
Containers have a lifecycle and being able to identify and document the lifecycle of a container is very helpful for implementations of the spec.
|
||||
|
|
@ -31,38 +24,29 @@ The lifecycle events of a container also help identify areas to implement hooks
|
|||
|
||||
*Owner:* mrunalp
|
||||
|
||||
### Define Standard Container Actions
|
||||
### Define Standard Container Actions (Target release: v0.3.0)
|
||||
|
||||
Define what type of actions a runtime can perform on a container without imposing hardships on authors of platforms that do not support advanced options.
|
||||
|
||||
*Owner:*
|
||||
|
||||
### Clarify rootfs requirement in base spec
|
||||
|
||||
Is the rootfs needed or should it just be expected in the bundle without having a field in the spec?
|
||||
|
||||
*Owner:*
|
||||
*Owner:* duglin
|
||||
|
||||
### Container Definition
|
||||
|
||||
Define what a software container is and its attributes in a cross platform way.
|
||||
|
||||
*Owner:*
|
||||
Could be solved by lifecycle/ops and create/start split discussions
|
||||
|
||||
*Owner:* vishh & duglin
|
||||
|
||||
### Live Container Updates
|
||||
|
||||
Should we allow dynamic container updates to runtime options?
|
||||
|
||||
*Owner:* vishh
|
||||
Proposal: make it an optional feature
|
||||
|
||||
### Protobuf Config
|
||||
*Owner:* hqhq (was vishh) robdolinms, bcorrie
|
||||
|
||||
We currently have only one language binding for the spec and that is Go.
|
||||
If we change the specs format in the respository to be something like protobuf then the generation for multiple language bindings become effortless.
|
||||
|
||||
*Owner:* vbatts
|
||||
|
||||
### Validation Tooling
|
||||
### Validation Tooling (Target release: v0.3.0)
|
||||
|
||||
Provide validation tooling for compliance with OCI spec and runtime environment.
|
||||
|
||||
|
|
@ -78,12 +62,18 @@ Provide a testing framework for compliance with OCI spec and runtime environment
|
|||
|
||||
Decide on a robust versioning schema for the spec as it evolves.
|
||||
|
||||
*Owner:*
|
||||
Resolved but release process could evolve. Resolved for v0.2.0, expect to revisit near v1.0.0
|
||||
|
||||
*Owner:* vbatts
|
||||
|
||||
### Printable/Compiled Spec
|
||||
|
||||
Regardless of how the spec is written, ensure that it is easy to read and follow for first time users.
|
||||
|
||||
Part of this is resolved. Produces an html & pdf.
|
||||
Done
|
||||
Would be nice to publish to the OCI web site as part of our release process.
|
||||
|
||||
*Owner:* vbatts
|
||||
|
||||
### Base Config Compatibility
|
||||
|
|
@ -96,9 +86,18 @@ Systems:
|
|||
* Windows
|
||||
* Linux
|
||||
|
||||
*Owner:*
|
||||
*Owner:* robdolinms as lead coordinator
|
||||
|
||||
### Full Lifecycle Hooks
|
||||
|
||||
Ensure that we have lifecycle hooks in the correct places with full coverage over the container lifecycle.
|
||||
|
||||
Will probably go away with Vish's work on splitting create and start, and if we have exec.
|
||||
|
||||
*Owner:*
|
||||
|
||||
### Distributable Format
|
||||
|
||||
A common format for serializing and distributing bundles.
|
||||
|
||||
*Owner:* vbatts
|
||||
|
|
|
|||
|
|
@ -8,23 +8,17 @@ See also [OS X application bundles](http://en.wikipedia.org/wiki/Bundle_%28OS_X%
|
|||
The definition of a bundle is only concerned with how a container, and its configuration data, are stored on a local file system so that it can be consumed by a compliant runtime.
|
||||
|
||||
A Standard Container bundle contains all the information needed to load and run a container.
|
||||
This includes the following three artifacts which MUST all reside in the same directory on the local filesystem:
|
||||
This includes the following artifacts which MUST all reside in the same directory on the local filesystem:
|
||||
|
||||
1. `config.json` : contains host-independent configuration data.
|
||||
This REQUIRED file, which MUST be named `config.json`, contains settings that are host-independent and application-specific such as security permissions, environment variables and arguments.
|
||||
1. `config.json` : contains configuration data.
|
||||
This REQUIRED file, which MUST be named `config.json`.
|
||||
When the bundle is packaged up for distribution, this file MUST be included.
|
||||
See [`config.json`](config.md) for more details.
|
||||
|
||||
2. `runtime.json` : contains host-specific configuration data.
|
||||
This REQUIRED file, which MUST be named `runtime.json`, contains settings that are host-specific such as mount sources and hooks.
|
||||
The goal is that the bundle can be moved as a unit to another runtime and run the same application once a host-specific `runtime.json` is defined.
|
||||
When the bundle is packaged up for distribution, this file MUST NOT be included.
|
||||
See [`runtime.json`](runtime-config.md) for more details.
|
||||
|
||||
3. A directory representing the root filesystem of the container.
|
||||
2. A directory representing the root filesystem of the container.
|
||||
While the name of this REQUIRED directory may be arbitrary, users should consider using a conventional name, such as `rootfs`.
|
||||
When the bundle is packaged up for distribution, this directory MUST be included.
|
||||
This directory MUST be referenced from within the `config.json` file.
|
||||
|
||||
While these three artifacts MUST all be present in a single directory on the local filesystem, that directory itself is not part of the bundle.
|
||||
While these artifacts MUST all be present in a single directory on the local filesystem, that directory itself is not part of the bundle.
|
||||
In other words, a tar archive of a *bundle* will have these artifacts at the root of the archive, not nested within a top-level directory.
|
||||
|
|
|
|||
|
|
@ -16,24 +16,594 @@ Valid values are the strings for capabilities defined in [the man page](http://m
|
|||
]
|
||||
```
|
||||
|
||||
## Default Devices and File Systems
|
||||
## Default File Systems
|
||||
|
||||
The Linux ABI includes both syscalls and several special file paths.
|
||||
Applications expecting a Linux environment will very likely expect these files paths to be setup correctly.
|
||||
|
||||
The following devices and filesystems MUST be made available in each application's filesystem
|
||||
The following filesystems MUST be made available in each application's filesystem
|
||||
|
||||
| Path | Type | Notes |
|
||||
| ------------ | ------ | ------- |
|
||||
| /proc | [procfs](https://www.kernel.org/doc/Documentation/filesystems/proc.txt) | |
|
||||
| /sys | [sysfs](https://www.kernel.org/doc/Documentation/filesystems/sysfs.txt) | |
|
||||
| /dev/null | [device](http://man7.org/linux/man-pages/man4/null.4.html) | |
|
||||
| /dev/zero | [device](http://man7.org/linux/man-pages/man4/zero.4.html) | |
|
||||
| /dev/full | [device](http://man7.org/linux/man-pages/man4/full.4.html) | |
|
||||
| /dev/random | [device](http://man7.org/linux/man-pages/man4/random.4.html) | |
|
||||
| /dev/urandom | [device](http://man7.org/linux/man-pages/man4/random.4.html) | |
|
||||
| /dev/tty | [device](http://man7.org/linux/man-pages/man4/tty.4.html) | |
|
||||
| /dev/console | [device](http://man7.org/linux/man-pages/man4/console.4.html) | |
|
||||
| /dev/pts | [devpts](https://www.kernel.org/doc/Documentation/filesystems/devpts.txt) | |
|
||||
| /dev/ptmx | [device](https://www.kernel.org/doc/Documentation/filesystems/devpts.txt) | Bind-mount or symlink of /dev/pts/ptmx |
|
||||
| /dev/shm | [tmpfs](https://www.kernel.org/doc/Documentation/filesystems/tmpfs.txt) | |
|
||||
| Path | Type |
|
||||
| -------- | ------ |
|
||||
| /proc | [procfs](https://www.kernel.org/doc/Documentation/filesystems/proc.txt) |
|
||||
| /sys | [sysfs](https://www.kernel.org/doc/Documentation/filesystems/sysfs.txt) |
|
||||
| /dev/pts | [devpts](https://www.kernel.org/doc/Documentation/filesystems/devpts.txt) |
|
||||
| /dev/shm | [tmpfs](https://www.kernel.org/doc/Documentation/filesystems/tmpfs.txt) |
|
||||
|
||||
## Namespaces
|
||||
|
||||
A namespace wraps a global system resource in an abstraction that makes it appear to the processes within the namespace that they have their own isolated instance of the global resource.
|
||||
Changes to the global resource are visible to other processes that are members of the namespace, but are invisible to other processes.
|
||||
For more information, see [the man page](http://man7.org/linux/man-pages/man7/namespaces.7.html).
|
||||
|
||||
Namespaces are specified as an array of entries inside the `namespaces` root field.
|
||||
The following parameters can be specified to setup namespaces:
|
||||
|
||||
* **`type`** *(string, required)* - namespace type. The following namespaces types are supported:
|
||||
* **`pid`** processes inside the container will only be able to see other processes inside the same container
|
||||
* **`network`** the container will have its own network stack
|
||||
* **`mount`** the container will have an isolated mount table
|
||||
* **`ipc`** processes inside the container will only be able to communicate to other processes inside the same container via system level IPC
|
||||
* **`uts`** the container will be able to have its own hostname and domain name
|
||||
* **`user`** the container will be able to remap user and group IDs from the host to local users and groups within the container
|
||||
|
||||
* **`path`** *(string, optional)* - path to namespace file
|
||||
|
||||
If a path is specified, that particular file is used to join that type of namespace.
|
||||
Also, when a path is specified, a runtime MUST assume that the setup for that particular namespace has already been done and error out if the config specifies anything else related to that namespace.
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"namespaces": [
|
||||
{
|
||||
"type": "pid",
|
||||
"path": "/proc/1234/ns/pid"
|
||||
},
|
||||
{
|
||||
"type": "network",
|
||||
"path": "/var/run/netns/neta"
|
||||
},
|
||||
{
|
||||
"type": "mount"
|
||||
},
|
||||
{
|
||||
"type": "ipc"
|
||||
},
|
||||
{
|
||||
"type": "uts"
|
||||
},
|
||||
{
|
||||
"type": "user"
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
## User namespace mappings
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"uidMappings": [
|
||||
{
|
||||
"hostID": 1000,
|
||||
"containerID": 0,
|
||||
"size": 10
|
||||
}
|
||||
],
|
||||
"gidMappings": [
|
||||
{
|
||||
"hostID": 1000,
|
||||
"containerID": 0,
|
||||
"size": 10
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
uid/gid mappings describe the user namespace mappings from the host to the container.
|
||||
The mappings represent how the bundle `rootfs` expects the user namespace to be setup and the runtime SHOULD NOT modify the permissions on the rootfs to realize the mapping.
|
||||
*hostID* is the starting uid/gid on the host to be mapped to *containerID* which is the starting uid/gid in the container and *size* refers to the number of ids to be mapped.
|
||||
There is a limit of 5 mappings which is the Linux kernel hard limit.
|
||||
|
||||
## Devices
|
||||
|
||||
`devices` is an array specifying the list of devices that MUST be available in the container.
|
||||
The runtime may supply them however it likes (with [mknod][mknod.2], by bind mounting from the runtime mount namespace, etc.).
|
||||
|
||||
The following parameters can be specified:
|
||||
|
||||
* **`type`** *(char, required)* - type of device: `c`, `b`, `u` or `p`.
|
||||
More info in [mknod(1)][mknod.1].
|
||||
* **`path`** *(string, required)* - full path to device inside container.
|
||||
* **`major, minor`** *(int64, required unless **`type`** is `p`)* - [major, minor numbers][devices] for the device.
|
||||
* **`fileMode`** *(uint32, optional)* - file mode for the device.
|
||||
You can also control access to devices [with cgroups](#device-whitelist).
|
||||
* **`uid`** *(uint32, optional)* - id of device owner.
|
||||
* **`gid`** *(uint32, optional)* - id of device group.
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"devices": [
|
||||
{
|
||||
"path": "/dev/fuse",
|
||||
"type": "c",
|
||||
"major": 10,
|
||||
"minor": 229,
|
||||
"fileMode": 0666,
|
||||
"uid": 0,
|
||||
"gid": 0
|
||||
},
|
||||
{
|
||||
"path": "/dev/sda",
|
||||
"type": "b",
|
||||
"major": 8,
|
||||
"minor": 0,
|
||||
"fileMode": 0660,
|
||||
"uid": 0,
|
||||
"gid": 0
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
###### Default Devices
|
||||
|
||||
In addition to any devices configured with this setting, the runtime MUST also supply:
|
||||
|
||||
* [`/dev/null`][null.4]
|
||||
* [`/dev/zero`][zero.4]
|
||||
* [`/dev/full`][full.4]
|
||||
* [`/dev/random`][random.4]
|
||||
* [`/dev/urandom`][random.4]
|
||||
* [`/dev/tty`][tty.4]
|
||||
* [`/dev/console`][console.4]
|
||||
* [`/dev/ptmx`][pts.4].
|
||||
A [bind-mount or symlink of the container's `/dev/pts/ptmx`][devpts].
|
||||
|
||||
## Control groups
|
||||
|
||||
Also known as cgroups, they are used to restrict resource usage for a container and handle device access.
|
||||
cgroups provide controls to restrict cpu, memory, IO, pids and network for the container.
|
||||
For more information, see the [kernel cgroups documentation][cgroup-v1].
|
||||
|
||||
The path to the cgroups can be specified in the Spec via `cgroupsPath`.
|
||||
`cgroupsPath` is expected to be relative to the cgroups mount point.
|
||||
If `cgroupsPath` is not specified, implementations can define the default cgroup path.
|
||||
Implementations of the Spec can choose to name cgroups in any manner.
|
||||
The Spec does not include naming schema for cgroups.
|
||||
The Spec does not support [split hierarchy][cgroup-v2].
|
||||
The cgroups will be created if they don't exist.
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"cgroupsPath": "/myRuntime/myContainer"
|
||||
```
|
||||
|
||||
`cgroupsPath` can be used to either control the cgroups hierarchy for containers or to run a new process in an existing container.
|
||||
|
||||
You can configure a container's cgroups via the `resources` field of the Linux configuration.
|
||||
Do not specify `resources` unless limits have to be updated.
|
||||
For example, to run a new process in an existing container without updating limits, `resources` need not be specified.
|
||||
|
||||
#### Device whitelist
|
||||
|
||||
`devices` is an array of entries to control the [device whitelist][cgroup-v1-devices].
|
||||
The runtime MUST apply entries in the listed order.
|
||||
|
||||
The following parameters can be specified:
|
||||
|
||||
* **`allow`** *(boolean, required)* - whether the entry is allowed or denied.
|
||||
* **`type`** *(char, optional)* - type of device: `a` (all), `c` (char), or `b` (block).
|
||||
`null` or unset values mean "all", mapping to `a`.
|
||||
* **`major, minor`** *(int64, optional)* - [major, minor numbers][devices] for the device.
|
||||
`null` or unset values mean "all", mapping to [`*` in the filesystem API][cgroup-v1-devices].
|
||||
* **`access`** *(string, optional)* - cgroup permissions for device.
|
||||
A composition of `r` (read), `w` (write), and `m` (mknod).
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"devices": [
|
||||
{
|
||||
"allow": false,
|
||||
"access": "rwm"
|
||||
},
|
||||
{
|
||||
"allow": true,
|
||||
"type": "c",
|
||||
"major": 10,
|
||||
"minor": 229,
|
||||
"access": "rw"
|
||||
},
|
||||
{
|
||||
"allow": true,
|
||||
"type": "b",
|
||||
"major": 8,
|
||||
"minor": 0,
|
||||
"access": "r"
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
#### Disable out-of-memory killer
|
||||
|
||||
`disableOOMKiller` contains a boolean (`true` or `false`) that enables or disables the Out of Memory killer for a cgroup.
|
||||
If enabled (`false`), tasks that attempt to consume more memory than they are allowed are immediately killed by the OOM killer.
|
||||
The OOM killer is enabled by default in every cgroup using the `memory` subsystem.
|
||||
To disable it, specify a value of `true`.
|
||||
For more information, see [the memory cgroup man page][cgroup-v1-memory].
|
||||
|
||||
* **`disableOOMKiller`** *(bool, optional)* - enables or disables the OOM killer
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"disableOOMKiller": false
|
||||
```
|
||||
|
||||
#### Set oom_score_adj
|
||||
|
||||
`oomScoreAdj` sets heuristic regarding how the process is evaluated by the kernel during memory pressure.
|
||||
For more information, see [the proc filesystem documentation section 3.1](https://www.kernel.org/doc/Documentation/filesystems/proc.txt).
|
||||
This is a kernel/system level setting, where as `disableOOMKiller` is scoped for a memory cgroup.
|
||||
For more information on how these two settings work together, see [the memory cgroup documentation section 10. OOM Contol][cgroup-v1-memory].
|
||||
|
||||
* **`oomScoreAdj`** *(int, optional)* - adjust the oom-killer score
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"oomScoreAdj": 0
|
||||
```
|
||||
|
||||
#### Memory
|
||||
|
||||
`memory` represents the cgroup subsystem `memory` and it's used to set limits on the container's memory usage.
|
||||
For more information, see [the memory cgroup man page][cgroup-v1-memory].
|
||||
|
||||
The following parameters can be specified to setup the controller:
|
||||
|
||||
* **`limit`** *(uint64, optional)* - sets limit of memory usage
|
||||
|
||||
* **`reservation`** *(uint64, optional)* - sets soft limit of memory usage
|
||||
|
||||
* **`swap`** *(uint64, optional)* - sets limit of memory+Swap usage
|
||||
|
||||
* **`kernel`** *(uint64, optional)* - sets hard limit for kernel memory
|
||||
|
||||
* **`kernelTCP`** *(uint64, optional)* - sets hard limit for kernel memory in tcp using
|
||||
|
||||
* **`swappiness`** *(uint64, optional)* - sets swappiness parameter of vmscan (See sysctl's vm.swappiness)
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"memory": {
|
||||
"limit": 0,
|
||||
"reservation": 0,
|
||||
"swap": 0,
|
||||
"kernel": 0,
|
||||
"kernelTCP": 0,
|
||||
"swappiness": 0
|
||||
}
|
||||
```
|
||||
|
||||
#### CPU
|
||||
|
||||
`cpu` represents the cgroup subsystems `cpu` and `cpusets`.
|
||||
For more information, see [the cpusets cgroup man page][cgroup-v1-cpusets].
|
||||
|
||||
The following parameters can be specified to setup the controller:
|
||||
|
||||
* **`shares`** *(uint64, optional)* - specifies a relative share of CPU time available to the tasks in a cgroup
|
||||
|
||||
* **`quota`** *(uint64, optional)* - specifies the total amount of time in microseconds for which all tasks in a cgroup can run during one period (as defined by **`period`** below)
|
||||
|
||||
* **`period`** *(uint64, optional)* - specifies a period of time in microseconds for how regularly a cgroup's access to CPU resources should be reallocated (CFS scheduler only)
|
||||
|
||||
* **`realtimeRuntime`** *(uint64, optional)* - specifies a period of time in microseconds for the longest continuous period in which the tasks in a cgroup have access to CPU resources
|
||||
|
||||
* **`realtimePeriod`** *(uint64, optional)* - same as **`period`** but applies to realtime scheduler only
|
||||
|
||||
* **`cpus`** *(string, optional)* - list of CPUs the container will run in
|
||||
|
||||
* **`mems`** *(string, optional)* - list of Memory Nodes the container will run in
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"cpu": {
|
||||
"shares": 0,
|
||||
"quota": 0,
|
||||
"period": 0,
|
||||
"realtimeRuntime": 0,
|
||||
"realtimePeriod": 0,
|
||||
"cpus": "",
|
||||
"mems": ""
|
||||
}
|
||||
```
|
||||
|
||||
#### Block IO Controller
|
||||
|
||||
`blockIO` represents the cgroup subsystem `blkio` which implements the block io controller.
|
||||
For more information, see [the kernel cgroups documentation about blkio][cgroup-v1-blkio].
|
||||
|
||||
The following parameters can be specified to setup the controller:
|
||||
|
||||
* **`blkioWeight`** *(uint16, optional)* - specifies per-cgroup weight. This is default weight of the group on all devices until and unless overridden by per-device rules. The range is from 10 to 1000.
|
||||
|
||||
* **`blkioLeafWeight`** *(uint16, optional)* - equivalents of `blkioWeight` for the purpose of deciding how much weight tasks in the given cgroup has while competing with the cgroup's child cgroups. The range is from 10 to 1000.
|
||||
|
||||
* **`blkioWeightDevice`** *(array, optional)* - specifies the list of devices which will be bandwidth rate limited. The following parameters can be specified per-device:
|
||||
* **`major, minor`** *(int64, required)* - major, minor numbers for device. More info in `man mknod`.
|
||||
* **`weight`** *(uint16, optional)* - bandwidth rate for the device, range is from 10 to 1000
|
||||
* **`leafWeight`** *(uint16, optional)* - bandwidth rate for the device while competing with the cgroup's child cgroups, range is from 10 to 1000, CFQ scheduler only
|
||||
|
||||
You must specify at least one of `weight` or `leafWeight` in a given entry, and can specify both.
|
||||
|
||||
* **`blkioThrottleReadBpsDevice`**, **`blkioThrottleWriteBpsDevice`**, **`blkioThrottleReadIOPSDevice`**, **`blkioThrottleWriteIOPSDevice`** *(array, optional)* - specify the list of devices which will be IO rate limited. The following parameters can be specified per-device:
|
||||
* **`major, minor`** *(int64, required)* - major, minor numbers for device. More info in `man mknod`.
|
||||
* **`rate`** *(uint64, required)* - IO rate limit for the device
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"blockIO": {
|
||||
"blkioWeight": 0,
|
||||
"blkioLeafWeight": 0,
|
||||
"blkioWeightDevice": [
|
||||
{
|
||||
"major": 8,
|
||||
"minor": 0,
|
||||
"weight": 500,
|
||||
"leafWeight": 300
|
||||
},
|
||||
{
|
||||
"major": 8,
|
||||
"minor": 16,
|
||||
"weight": 500
|
||||
}
|
||||
],
|
||||
"blkioThrottleReadBpsDevice": [
|
||||
{
|
||||
"major": 8,
|
||||
"minor": 0,
|
||||
"rate": 600
|
||||
}
|
||||
],
|
||||
"blkioThrottleWriteIOPSDevice": [
|
||||
{
|
||||
"major": 8,
|
||||
"minor": 16,
|
||||
"rate": 300
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
#### Huge page limits
|
||||
|
||||
`hugepageLimits` represents the `hugetlb` controller which allows to limit the
|
||||
HugeTLB usage per control group and enforces the controller limit during page fault.
|
||||
For more information, see the [kernel cgroups documentation about HugeTLB][cgroup-v1-hugetlb].
|
||||
|
||||
`hugepageLimits` is an array of entries, each having the following structure:
|
||||
|
||||
* **`pageSize`** *(string, required)* - hugepage size
|
||||
|
||||
* **`limit`** *(uint64, required)* - limit in bytes of *hugepagesize* HugeTLB usage
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"hugepageLimits": [
|
||||
{
|
||||
"pageSize": "2MB",
|
||||
"limit": 9223372036854771712
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
#### Network
|
||||
|
||||
`network` represents the cgroup subsystems `net_cls` and `net_prio`.
|
||||
For more information, see [the net\_cls cgroup man page][cgroup-v1-net-cls] and [the net\_prio cgroup man page][cgroup-v1-net-prio].
|
||||
|
||||
The following parameters can be specified to setup these cgroup controllers:
|
||||
|
||||
* **`classID`** *(uint32, optional)* - is the network class identifier the cgroup's network packets will be tagged with
|
||||
|
||||
* **`priorities`** *(array, optional)* - specifies a list of objects of the priorities assigned to traffic originating from
|
||||
processes in the group and egressing the system on various interfaces. The following parameters can be specified per-priority:
|
||||
* **`name`** *(string, required)* - interface name
|
||||
* **`priority`** *(uint32, required)* - priority applied to the interface
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"network": {
|
||||
"classID": 1048577,
|
||||
"priorities": [
|
||||
{
|
||||
"name": "eth0",
|
||||
"priority": 500
|
||||
},
|
||||
{
|
||||
"name": "eth1",
|
||||
"priority": 1000
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
#### PIDs
|
||||
|
||||
`pids` represents the cgroup subsystem `pids`.
|
||||
For more information, see [the pids cgroup man page][cgroup-v1-pids].
|
||||
|
||||
The following paramters can be specified to setup the controller:
|
||||
|
||||
* **`limit`** *(int64, required)* - specifies the maximum number of tasks in the cgroup
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"pids": {
|
||||
"limit": 32771
|
||||
}
|
||||
```
|
||||
|
||||
## Sysctl
|
||||
|
||||
sysctl allows kernel parameters to be modified at runtime for the container.
|
||||
For more information, see [the man page](http://man7.org/linux/man-pages/man8/sysctl.8.html)
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"sysctl": {
|
||||
"net.ipv4.ip_forward": "1",
|
||||
"net.core.somaxconn": "256"
|
||||
}
|
||||
```
|
||||
|
||||
## Rlimits
|
||||
|
||||
rlimits allow setting resource limits.
|
||||
`type` is a string with a value from those defined in [the man page](http://man7.org/linux/man-pages/man2/setrlimit.2.html).
|
||||
The kernel enforces the `soft` limit for a resource while the `hard` limit acts as a ceiling for that value that could be set by an unprivileged process.
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"rlimits": [
|
||||
{
|
||||
"type": "RLIMIT_NPROC",
|
||||
"soft": 1024,
|
||||
"hard": 102400
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
## SELinux process label
|
||||
|
||||
SELinux process label specifies the label with which the processes in a container are run.
|
||||
For more information about SELinux, see [Selinux documentation](http://selinuxproject.org/page/Main_Page)
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"selinuxProcessLabel": "system_u:system_r:svirt_lxc_net_t:s0:c124,c675"
|
||||
```
|
||||
|
||||
## Apparmor profile
|
||||
|
||||
Apparmor profile specifies the name of the apparmor profile that will be used for the container.
|
||||
For more information about Apparmor, see [Apparmor documentation](https://wiki.ubuntu.com/AppArmor)
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"apparmorProfile": "acme_secure_profile"
|
||||
```
|
||||
|
||||
## seccomp
|
||||
|
||||
Seccomp provides application sandboxing mechanism in the Linux kernel.
|
||||
Seccomp configuration allows one to configure actions to take for matched syscalls and furthermore also allows matching on values passed as arguments to syscalls.
|
||||
For more information about Seccomp, see [Seccomp kernel documentation](https://www.kernel.org/doc/Documentation/prctl/seccomp_filter.txt)
|
||||
The actions, architectures, and operators are strings that match the definitions in seccomp.h from [libseccomp](https://github.com/seccomp/libseccomp) and are translated to corresponding values.
|
||||
A valid list of constants as of Libseccomp v2.2.3 is contained below.
|
||||
|
||||
Architecture Constants
|
||||
* `SCMP_ARCH_X86`
|
||||
* `SCMP_ARCH_X86_64`
|
||||
* `SCMP_ARCH_X32`
|
||||
* `SCMP_ARCH_ARM`
|
||||
* `SCMP_ARCH_AARCH64`
|
||||
* `SCMP_ARCH_MIPS`
|
||||
* `SCMP_ARCH_MIPS64`
|
||||
* `SCMP_ARCH_MIPS64N32`
|
||||
* `SCMP_ARCH_MIPSEL`
|
||||
* `SCMP_ARCH_MIPSEL64`
|
||||
* `SCMP_ARCH_MIPSEL64N32`
|
||||
|
||||
Action Constants:
|
||||
* `SCMP_ACT_KILL`
|
||||
* `SCMP_ACT_TRAP`
|
||||
* `SCMP_ACT_ERRNO`
|
||||
* `SCMP_ACT_TRACE`
|
||||
* `SCMP_ACT_ALLOW`
|
||||
|
||||
Operator Constants:
|
||||
* `SCMP_CMP_NE`
|
||||
* `SCMP_CMP_LT`
|
||||
* `SCMP_CMP_LE`
|
||||
* `SCMP_CMP_EQ`
|
||||
* `SCMP_CMP_GE`
|
||||
* `SCMP_CMP_GT`
|
||||
* `SCMP_CMP_MASKED_EQ`
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"seccomp": {
|
||||
"defaultAction": "SCMP_ACT_ALLOW",
|
||||
"architectures": [
|
||||
"SCMP_ARCH_X86"
|
||||
],
|
||||
"syscalls": [
|
||||
{
|
||||
"name": "getcwd",
|
||||
"action": "SCMP_ACT_ERRNO"
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
## Rootfs Mount Propagation
|
||||
|
||||
rootfsPropagation sets the rootfs's mount propagation.
|
||||
Its value is either slave, private, or shared.
|
||||
[The kernel doc](https://www.kernel.org/doc/Documentation/filesystems/sharedsubtree.txt) has more information about mount propagation.
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"rootfsPropagation": "slave",
|
||||
```
|
||||
|
||||
## No new privileges
|
||||
|
||||
Setting `noNewPrivileges` to true prevents the processes in the container from gaining additional privileges.
|
||||
[The kernel doc](https://www.kernel.org/doc/Documentation/prctl/no_new_privs.txt) has more information on how this is achieved using a prctl system call.
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"noNewPrivileges": true,
|
||||
```
|
||||
|
||||
[cgroup-v1]: https://www.kernel.org/doc/Documentation/cgroup-v1/cgroups.txt
|
||||
[cgroup-v1-blkio]: https://www.kernel.org/doc/Documentation/cgroup-v1/blkio-controller.txt
|
||||
[cgroup-v1-cpusets]: https://www.kernel.org/doc/Documentation/cgroup-v1/cpusets.txt
|
||||
[cgroup-v1-devices]: https://www.kernel.org/doc/Documentation/cgroup-v1/devices.txt
|
||||
[cgroup-v1-hugetlb]: https://www.kernel.org/doc/Documentation/cgroup-v1/hugetlb.txt
|
||||
[cgroup-v1-memory]: https://www.kernel.org/doc/Documentation/cgroup-v1/memory.txt
|
||||
[cgroup-v1-net-cls]: https://www.kernel.org/doc/Documentation/cgroup-v1/net_cls.txt
|
||||
[cgroup-v1-net-prio]: https://www.kernel.org/doc/Documentation/cgroup-v1/net_prio.txt
|
||||
[cgroup-v1-pids]: https://www.kernel.org/doc/Documentation/cgroup-v1/pids.txt
|
||||
[cgroup-v2]: https://www.kernel.org/doc/Documentation/cgroup-v2.txt
|
||||
[devices]: https://www.kernel.org/doc/Documentation/devices.txt
|
||||
[devpts]: https://www.kernel.org/doc/Documentation/filesystems/devpts.txt
|
||||
|
||||
[mknod.1]: http://man7.org/linux/man-pages/man1/mknod.1.html
|
||||
[mknod.2]: http://man7.org/linux/man-pages/man2/mknod.2.html
|
||||
[console.4]: http://man7.org/linux/man-pages/man4/console.4.html
|
||||
[full.4]: http://man7.org/linux/man-pages/man4/full.4.html
|
||||
[null.4]: http://man7.org/linux/man-pages/man4/null.4.html
|
||||
[pts.4]: http://man7.org/linux/man-pages/man4/pts.4.html
|
||||
[random.4]: http://man7.org/linux/man-pages/man4/random.4.html
|
||||
[tty.4]: http://man7.org/linux/man-pages/man4/tty.4.html
|
||||
[zero.4]: http://man7.org/linux/man-pages/man4/zero.4.html
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@ package specs
|
|||
// bundle is packaged for distribution.
|
||||
type Spec struct {
|
||||
// Version is the version of the specification that is supported.
|
||||
Version string `json:"version"`
|
||||
Version string `json:"ociVersion"`
|
||||
// Platform is the host information for OS and Arch.
|
||||
Platform Platform `json:"platform"`
|
||||
// Process is the container's main process.
|
||||
|
|
@ -15,7 +15,9 @@ type Spec struct {
|
|||
// Hostname is the container's host name.
|
||||
Hostname string `json:"hostname,omitempty"`
|
||||
// Mounts profile configuration for adding mounts to the container's filesystem.
|
||||
Mounts []MountPoint `json:"mounts"`
|
||||
Mounts []Mount `json:"mounts"`
|
||||
// Hooks are the commands run at various lifecycle events of the container.
|
||||
Hooks Hooks `json:"hooks"`
|
||||
}
|
||||
|
||||
// Process contains information to start a specific application inside the container.
|
||||
|
|
@ -30,7 +32,7 @@ type Process struct {
|
|||
Env []string `json:"env,omitempty"`
|
||||
// Cwd is the current working directory for the process and must be
|
||||
// relative to the container's root.
|
||||
Cwd string `json:"cwd,omitempty"`
|
||||
Cwd string `json:"cwd"`
|
||||
}
|
||||
|
||||
// Root contains information about the container's root filesystem on the host.
|
||||
|
|
@ -50,10 +52,33 @@ type Platform struct {
|
|||
Arch string `json:"arch"`
|
||||
}
|
||||
|
||||
// MountPoint describes a directory that may be fullfilled by a mount in the runtime.json.
|
||||
type MountPoint struct {
|
||||
// Name is a unique descriptive identifier for this mount point.
|
||||
Name string `json:"name"`
|
||||
// Path specifies the path of the mount. The path and child directories MUST exist, a runtime MUST NOT create directories automatically to a mount point.
|
||||
Path string `json:"path"`
|
||||
// Mount specifies a mount for a container.
|
||||
type Mount struct {
|
||||
// Destination is the path where the mount will be placed relative to the container's root. The path and child directories MUST exist, a runtime MUST NOT create directories automatically to a mount point.
|
||||
Destination string `json:"destination"`
|
||||
// Type specifies the mount kind.
|
||||
Type string `json:"type"`
|
||||
// Source specifies the source path of the mount. In the case of bind mounts on
|
||||
// linux based systems this would be the file on the host.
|
||||
Source string `json:"source"`
|
||||
// Options are fstab style mount options.
|
||||
Options []string `json:"options,omitempty"`
|
||||
}
|
||||
|
||||
// Hook specifies a command that is run at a particular event in the lifecycle of a container
|
||||
type Hook struct {
|
||||
Path string `json:"path"`
|
||||
Args []string `json:"args,omitempty"`
|
||||
Env []string `json:"env,omitempty"`
|
||||
}
|
||||
|
||||
// Hooks for container setup and teardown
|
||||
type Hooks struct {
|
||||
// Prestart is a list of hooks to be run before the container process is executed.
|
||||
// On Linux, they are run after the container namespaces are created.
|
||||
Prestart []Hook `json:"prestart,omitempty"`
|
||||
// Poststart is a list of hooks to be run after the container process is started.
|
||||
Poststart []Hook `json:"poststart,omitempty"`
|
||||
// Poststop is a list of hooks to be run after the container process exits.
|
||||
Poststop []Hook `json:"poststop,omitempty"`
|
||||
}
|
||||
|
|
|
|||
|
|
@ -8,14 +8,17 @@ This includes the process to run, environment variables to inject, sandboxing fe
|
|||
|
||||
Below is a detailed description of each field defined in the configuration format.
|
||||
|
||||
## Manifest version
|
||||
## Specification version
|
||||
|
||||
* **`version`** (string, required) must be in [SemVer v2.0.0](http://semver.org/spec/v2.0.0.html) format and specifies the version of the OCF specification with which the container bundle complies. The Open Container spec follows semantic versioning and retains forward and backward compatibility within major versions. For example, if an implementation is compliant with version 1.0.1 of the spec, it is compatible with the complete 1.x series.
|
||||
* **`ociVersion`** (string, required) must be in [SemVer v2.0.0](http://semver.org/spec/v2.0.0.html) format and specifies the version of the OpenContainer specification with which the bundle complies.
|
||||
The OpenContainer spec follows semantic versioning and retains forward and backward compatibility within major versions.
|
||||
For example, if an implementation is compliant with version 1.0.1 of the spec, it is compatible with the complete 1.x series.
|
||||
NOTE that there is no guarantee for forward or backward compatibility for version 0.x.
|
||||
|
||||
*Example*
|
||||
|
||||
```json
|
||||
"version": "0.1.0"
|
||||
"ociVersion": "0.1.0"
|
||||
```
|
||||
|
||||
## Root Configuration
|
||||
|
|
@ -34,42 +37,56 @@ Each container has exactly one *root filesystem*, specified in the *root* object
|
|||
}
|
||||
```
|
||||
|
||||
## Mount Points
|
||||
## Mounts
|
||||
|
||||
You can add array of mount points inside container as `mounts`.
|
||||
Each record in this array must have configuration in [runtime config](runtime-config.md#mount-configuration).
|
||||
The runtime MUST mount entries in the listed order.
|
||||
The parameters are similar to the ones in [the Linux mount system call](http://man7.org/linux/man-pages/man2/mount.2.html).
|
||||
|
||||
* **`name`** (string, required) Name of mount point. Used for config lookup.
|
||||
* **`path`** (string, required) Destination of mount point: path inside container.
|
||||
* **`destination`** (string, required) Destination of mount point: path inside container.
|
||||
* **`type`** (string, required) Linux, *filesystemtype* argument supported by the kernel are listed in */proc/filesystems* (e.g., "minix", "ext2", "ext3", "jfs", "xfs", "reiserfs", "msdos", "proc", "nfs", "iso9660"). Windows: ntfs
|
||||
* **`source`** (string, required) a device name, but can also be a directory name or a dummy. Windows, the volume name that is the target of the mount point. \\?\Volume\{GUID}\ (on Windows source is called target)
|
||||
* **`options`** (list of strings, optional) in the fstab format [https://wiki.archlinux.org/index.php/Fstab](https://wiki.archlinux.org/index.php/Fstab).
|
||||
|
||||
*Example*
|
||||
### Linux Example
|
||||
|
||||
```json
|
||||
"mounts": [
|
||||
{
|
||||
"name": "proc",
|
||||
"path": "/proc"
|
||||
"destination": "/tmp",
|
||||
"type": "tmpfs",
|
||||
"source": "tmpfs",
|
||||
"options": ["nosuid","strictatime","mode=755","size=65536k"]
|
||||
},
|
||||
{
|
||||
"name": "dev",
|
||||
"path": "/dev"
|
||||
},
|
||||
{
|
||||
"name": "devpts",
|
||||
"path": "/dev/pts"
|
||||
},
|
||||
{
|
||||
"name": "data",
|
||||
"path": "/data"
|
||||
"destination": "/data",
|
||||
"type": "bind",
|
||||
"source": "/volumes/testing",
|
||||
"options": ["rbind","rw"]
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
### Windows Example
|
||||
|
||||
```json
|
||||
"mounts": [
|
||||
"myfancymountpoint": {
|
||||
"destination": "C:\\Users\\crosbymichael\\My Fancy Mount Point\\",
|
||||
"type": "ntfs",
|
||||
"source": "\\\\?\\Volume\\{2eca078d-5cbc-43d3-aff8-7e8511f60d0e}\\",
|
||||
"options": []
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
See links for details about [mountvol](http://ss64.com/nt/mountvol.html) and [SetVolumeMountPoint](https://msdn.microsoft.com/en-us/library/windows/desktop/aa365561(v=vs.85).aspx) in Windows.
|
||||
|
||||
|
||||
## Process configuration
|
||||
|
||||
* **`terminal`** (bool, optional) specifies whether you want a terminal attached to that process. Defaults to false.
|
||||
* **`cwd`** (string, optional) is the working directory that will be set for the executable.
|
||||
* **`cwd`** (string, required) is the working directory that will be set for the executable. This value MUST be an absolute path.
|
||||
* **`env`** (array of strings, optional) contains a list of variables that will be set in the process's environment prior to execution. Elements in the array are specified as Strings in the form "KEY=value". The left hand side must consist solely of letters, digits, and underscores `_` as outlined in [IEEE Std 1003.1-2001](http://pubs.opengroup.org/onlinepubs/009695399/basedefs/xbd_chap08.html).
|
||||
* **`args`** (string, required) executable to launch and any flags as an array. The executable is the first element and must be available at the given path inside of the rootfs. If the executable path is not an absolute path then the search $PATH is interpreted to find the executable.
|
||||
|
||||
|
|
@ -127,4 +144,72 @@ For Linux-based systems the user structure has the following fields:
|
|||
Interpretation of the platform section of the JSON file is used to find which platform-specific sections may be available in the document.
|
||||
For example, if `os` is set to `linux`, then a JSON object conforming to the [Linux-specific schema](config-linux.md) SHOULD be found at the key `linux` in the `config.json`.
|
||||
|
||||
## Hooks
|
||||
|
||||
Lifecycle hooks allow custom events for different points in a container's runtime.
|
||||
Presently there are `Prestart`, `Poststart` and `Poststop`.
|
||||
|
||||
* [`Prestart`](#prestart) is a list of hooks to be run before the container process is executed
|
||||
* [`Poststart`](#poststart) is a list of hooks to be run immediately after the container process is started
|
||||
* [`Poststop`](#poststop) is a list of hooks to be run after the container process exits
|
||||
|
||||
Hooks allow one to run code before/after various lifecycle events of the container.
|
||||
Hooks MUST be called in the listed order.
|
||||
The state of the container is passed to the hooks over stdin, so the hooks could get the information they need to do their work.
|
||||
|
||||
Hook paths are absolute and are executed from the host's filesystem.
|
||||
|
||||
### Prestart
|
||||
|
||||
The pre-start hooks are called after the container process is spawned, but before the user supplied command is executed.
|
||||
They are called after the container namespaces are created on Linux, so they provide an opportunity to customize the container.
|
||||
In Linux, for e.g., the network namespace could be configured in this hook.
|
||||
|
||||
If a hook returns a non-zero exit code, then an error including the exit code and the stderr is returned to the caller and the container is torn down.
|
||||
|
||||
### Poststart
|
||||
|
||||
The post-start hooks are called after the user process is started.
|
||||
For example this hook can notify user that real process is spawned.
|
||||
|
||||
If a hook returns a non-zero exit code, then an error is logged and the remaining hooks are executed.
|
||||
|
||||
### Poststop
|
||||
|
||||
The post-stop hooks are called after the container process is stopped.
|
||||
Cleanup or debugging could be performed in such a hook.
|
||||
If a hook returns a non-zero exit code, then an error is logged and the remaining hooks are executed.
|
||||
|
||||
*Example*
|
||||
|
||||
```json
|
||||
"hooks" : {
|
||||
"prestart": [
|
||||
{
|
||||
"path": "/usr/bin/fix-mounts",
|
||||
"args": ["fix-mounts", "arg1", "arg2"],
|
||||
"env": [ "key1=value1"]
|
||||
},
|
||||
{
|
||||
"path": "/usr/bin/setup-network"
|
||||
}
|
||||
],
|
||||
"poststart": [
|
||||
{
|
||||
"path": "/usr/bin/notify-start"
|
||||
}
|
||||
],
|
||||
"poststop": [
|
||||
{
|
||||
"path": "/usr/sbin/cleanup.sh",
|
||||
"args": ["cleanup.sh", "-f"]
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
`path` is required for a hook.
|
||||
`args` and `env` are optional.
|
||||
The semantics are the same as `Path`, `Args` and `Env` in [golang Cmd](https://golang.org/pkg/os/exec/#Cmd).
|
||||
|
||||
[uts-namespace]: http://man7.org/linux/man-pages/man7/namespaces.7.html
|
||||
|
|
|
|||
|
|
@ -1,5 +1,10 @@
|
|||
package specs
|
||||
|
||||
import "os"
|
||||
|
||||
// LinuxStateDirectory holds the container's state information
|
||||
const LinuxStateDirectory = "/run/opencontainer/containers"
|
||||
|
||||
// LinuxSpec is the full specification for linux containers.
|
||||
type LinuxSpec struct {
|
||||
Spec
|
||||
|
|
@ -11,6 +16,35 @@ type LinuxSpec struct {
|
|||
type Linux struct {
|
||||
// Capabilities are linux capabilities that are kept for the container.
|
||||
Capabilities []string `json:"capabilities"`
|
||||
// UIDMapping specifies user mappings for supporting user namespaces on linux.
|
||||
UIDMappings []IDMapping `json:"uidMappings,omitempty"`
|
||||
// GIDMapping specifies group mappings for supporting user namespaces on linux.
|
||||
GIDMappings []IDMapping `json:"gidMappings,omitempty"`
|
||||
// Rlimits specifies rlimit options to apply to the container's process.
|
||||
Rlimits []Rlimit `json:"rlimits,omitempty"`
|
||||
// Sysctl are a set of key value pairs that are set for the container on start
|
||||
Sysctl map[string]string `json:"sysctl,omitempty"`
|
||||
// Resources contain cgroup information for handling resource constraints
|
||||
// for the container
|
||||
Resources *Resources `json:"resources,omitempty"`
|
||||
// CgroupsPath specifies the path to cgroups that are created and/or joined by the container.
|
||||
// The path is expected to be relative to the cgroups mountpoint.
|
||||
// If resources are specified, the cgroups at CgroupsPath will be updated based on resources.
|
||||
CgroupsPath *string `json:"cgroupsPath,omitempty"`
|
||||
// Namespaces contains the namespaces that are created and/or joined by the container
|
||||
Namespaces []Namespace `json:"namespaces"`
|
||||
// Devices are a list of device nodes that are created for the container
|
||||
Devices []Device `json:"devices"`
|
||||
// ApparmorProfile specified the apparmor profile for the container.
|
||||
ApparmorProfile string `json:"apparmorProfile"`
|
||||
// SelinuxProcessLabel specifies the selinux context that the container process is run as.
|
||||
SelinuxProcessLabel string `json:"selinuxProcessLabel"`
|
||||
// Seccomp specifies the seccomp security settings for the container.
|
||||
Seccomp Seccomp `json:"seccomp"`
|
||||
// RootfsPropagation is the rootfs mount propagation mode for the container.
|
||||
RootfsPropagation string `json:"rootfsPropagation,omitempty"`
|
||||
// NoNewPrivileges controls whether additional privileges could be gained by processes in the container.
|
||||
NoNewPrivileges bool `json:"noNewPrivileges,omitempty"`
|
||||
}
|
||||
|
||||
// User specifies linux specific user and group information for the container's
|
||||
|
|
@ -23,3 +57,277 @@ type User struct {
|
|||
// AdditionalGids are additional group ids set for the container's process.
|
||||
AdditionalGids []uint32 `json:"additionalGids,omitempty"`
|
||||
}
|
||||
|
||||
// Namespace is the configuration for a linux namespace
|
||||
type Namespace struct {
|
||||
// Type is the type of Linux namespace
|
||||
Type NamespaceType `json:"type"`
|
||||
// Path is a path to an existing namespace persisted on disk that can be joined
|
||||
// and is of the same type
|
||||
Path string `json:"path,omitempty"`
|
||||
}
|
||||
|
||||
// NamespaceType is one of the linux namespaces
|
||||
type NamespaceType string
|
||||
|
||||
const (
|
||||
// PIDNamespace for isolating process IDs
|
||||
PIDNamespace NamespaceType = "pid"
|
||||
// NetworkNamespace for isolating network devices, stacks, ports, etc
|
||||
NetworkNamespace = "network"
|
||||
// MountNamespace for isolating mount points
|
||||
MountNamespace = "mount"
|
||||
// IPCNamespace for isolating System V IPC, POSIX message queues
|
||||
IPCNamespace = "ipc"
|
||||
// UTSNamespace for isolating hostname and NIS domain name
|
||||
UTSNamespace = "uts"
|
||||
// UserNamespace for isolating user and group IDs
|
||||
UserNamespace = "user"
|
||||
)
|
||||
|
||||
// IDMapping specifies UID/GID mappings
|
||||
type IDMapping struct {
|
||||
// HostID is the UID/GID of the host user or group
|
||||
HostID uint32 `json:"hostID"`
|
||||
// ContainerID is the UID/GID of the container's user or group
|
||||
ContainerID uint32 `json:"containerID"`
|
||||
// Size is the length of the range of IDs mapped between the two namespaces
|
||||
Size uint32 `json:"size"`
|
||||
}
|
||||
|
||||
// Rlimit type and restrictions
|
||||
type Rlimit struct {
|
||||
// Type of the rlimit to set
|
||||
Type string `json:"type"`
|
||||
// Hard is the hard limit for the specified type
|
||||
Hard uint64 `json:"hard"`
|
||||
// Soft is the soft limit for the specified type
|
||||
Soft uint64 `json:"soft"`
|
||||
}
|
||||
|
||||
// HugepageLimit structure corresponds to limiting kernel hugepages
|
||||
type HugepageLimit struct {
|
||||
// Pagesize is the hugepage size
|
||||
Pagesize *string `json:"pageSize,omitempty"`
|
||||
// Limit is the limit of "hugepagesize" hugetlb usage
|
||||
Limit *uint64 `json:"limit,omitempty"`
|
||||
}
|
||||
|
||||
// InterfacePriority for network interfaces
|
||||
type InterfacePriority struct {
|
||||
// Name is the name of the network interface
|
||||
Name string `json:"name"`
|
||||
// Priority for the interface
|
||||
Priority uint32 `json:"priority"`
|
||||
}
|
||||
|
||||
// blockIODevice holds major:minor format supported in blkio cgroup
|
||||
type blockIODevice struct {
|
||||
// Major is the device's major number.
|
||||
Major int64 `json:"major"`
|
||||
// Minor is the device's minor number.
|
||||
Minor int64 `json:"minor"`
|
||||
}
|
||||
|
||||
// WeightDevice struct holds a `major:minor weight` pair for blkioWeightDevice
|
||||
type WeightDevice struct {
|
||||
blockIODevice
|
||||
// Weight is the bandwidth rate for the device, range is from 10 to 1000
|
||||
Weight *uint16 `json:"weight,omitempty"`
|
||||
// LeafWeight is the bandwidth rate for the device while competing with the cgroup's child cgroups, range is from 10 to 1000, CFQ scheduler only
|
||||
LeafWeight *uint16 `json:"leafWeight,omitempty"`
|
||||
}
|
||||
|
||||
// ThrottleDevice struct holds a `major:minor rate_per_second` pair
|
||||
type ThrottleDevice struct {
|
||||
blockIODevice
|
||||
// Rate is the IO rate limit per cgroup per device
|
||||
Rate *uint64 `json:"rate,omitempty"`
|
||||
}
|
||||
|
||||
// BlockIO for Linux cgroup 'blkio' resource management
|
||||
type BlockIO struct {
|
||||
// Specifies per cgroup weight, range is from 10 to 1000
|
||||
Weight *uint16 `json:"blkioWeight,omitempty"`
|
||||
// Specifies tasks' weight in the given cgroup while competing with the cgroup's child cgroups, range is from 10 to 1000, CFQ scheduler only
|
||||
LeafWeight *uint16 `json:"blkioLeafWeight,omitempty"`
|
||||
// Weight per cgroup per device, can override BlkioWeight
|
||||
WeightDevice []WeightDevice `json:"blkioWeightDevice,omitempty"`
|
||||
// IO read rate limit per cgroup per device, bytes per second
|
||||
ThrottleReadBpsDevice []ThrottleDevice `json:"blkioThrottleReadBpsDevice,omitempty"`
|
||||
// IO write rate limit per cgroup per device, bytes per second
|
||||
ThrottleWriteBpsDevice []ThrottleDevice `json:"blkioThrottleWriteBpsDevice,omitempty"`
|
||||
// IO read rate limit per cgroup per device, IO per second
|
||||
ThrottleReadIOPSDevice []ThrottleDevice `json:"blkioThrottleReadIOPSDevice,omitempty"`
|
||||
// IO write rate limit per cgroup per device, IO per second
|
||||
ThrottleWriteIOPSDevice []ThrottleDevice `json:"blkioThrottleWriteIOPSDevice,omitempty"`
|
||||
}
|
||||
|
||||
// Memory for Linux cgroup 'memory' resource management
|
||||
type Memory struct {
|
||||
// Memory limit (in bytes).
|
||||
Limit *uint64 `json:"limit,omitempty"`
|
||||
// Memory reservation or soft_limit (in bytes).
|
||||
Reservation *uint64 `json:"reservation,omitempty"`
|
||||
// Total memory limit (memory + swap).
|
||||
Swap *uint64 `json:"swap,omitempty"`
|
||||
// Kernel memory limit (in bytes).
|
||||
Kernel *uint64 `json:"kernel,omitempty"`
|
||||
// Kernel memory limit for tcp (in bytes)
|
||||
KernelTCP *uint64 `json:"kernelTCP"`
|
||||
// How aggressive the kernel will swap memory pages. Range from 0 to 100.
|
||||
Swappiness *uint64 `json:"swappiness,omitempty"`
|
||||
}
|
||||
|
||||
// CPU for Linux cgroup 'cpu' resource management
|
||||
type CPU struct {
|
||||
// CPU shares (relative weight (ratio) vs. other cgroups with cpu shares).
|
||||
Shares *uint64 `json:"shares,omitempty"`
|
||||
// CPU hardcap limit (in usecs). Allowed cpu time in a given period.
|
||||
Quota *uint64 `json:"quota,omitempty"`
|
||||
// CPU period to be used for hardcapping (in usecs).
|
||||
Period *uint64 `json:"period,omitempty"`
|
||||
// How much time realtime scheduling may use (in usecs).
|
||||
RealtimeRuntime *uint64 `json:"realtimeRuntime,omitempty"`
|
||||
// CPU period to be used for realtime scheduling (in usecs).
|
||||
RealtimePeriod *uint64 `json:"realtimePeriod,omitempty"`
|
||||
// CPUs to use within the cpuset. Default is to use any CPU available.
|
||||
Cpus *string `json:"cpus,omitempty"`
|
||||
// List of memory nodes in the cpuset. Default is to use any available memory node.
|
||||
Mems *string `json:"mems,omitempty"`
|
||||
}
|
||||
|
||||
// Pids for Linux cgroup 'pids' resource management (Linux 4.3)
|
||||
type Pids struct {
|
||||
// Maximum number of PIDs. Default is "no limit".
|
||||
Limit *int64 `json:"limit,omitempty"`
|
||||
}
|
||||
|
||||
// Network identification and priority configuration
|
||||
type Network struct {
|
||||
// Set class identifier for container's network packets
|
||||
ClassID *uint32 `json:"classID"`
|
||||
// Set priority of network traffic for container
|
||||
Priorities []InterfacePriority `json:"priorities,omitempty"`
|
||||
}
|
||||
|
||||
// Resources has container runtime resource constraints
|
||||
type Resources struct {
|
||||
// Devices are a list of device rules for the whitelist controller
|
||||
Devices []DeviceCgroup `json:"devices"`
|
||||
// DisableOOMKiller disables the OOM killer for out of memory conditions
|
||||
DisableOOMKiller *bool `json:"disableOOMKiller,omitempty"`
|
||||
// Specify an oom_score_adj for the container.
|
||||
OOMScoreAdj *int `json:"oomScoreAdj,omitempty"`
|
||||
// Memory restriction configuration
|
||||
Memory *Memory `json:"memory,omitempty"`
|
||||
// CPU resource restriction configuration
|
||||
CPU *CPU `json:"cpu,omitempty"`
|
||||
// Task resource restriction configuration.
|
||||
Pids *Pids `json:"pids,omitempty"`
|
||||
// BlockIO restriction configuration
|
||||
BlockIO *BlockIO `json:"blockIO,omitempty"`
|
||||
// Hugetlb limit (in bytes)
|
||||
HugepageLimits []HugepageLimit `json:"hugepageLimits,omitempty"`
|
||||
// Network restriction configuration
|
||||
Network *Network `json:"network,omitempty"`
|
||||
}
|
||||
|
||||
// Device represents the mknod information for a Linux special device file
|
||||
type Device struct {
|
||||
// Path to the device.
|
||||
Path string `json:"path"`
|
||||
// Device type, block, char, etc.
|
||||
Type rune `json:"type"`
|
||||
// Major is the device's major number.
|
||||
Major int64 `json:"major"`
|
||||
// Minor is the device's minor number.
|
||||
Minor int64 `json:"minor"`
|
||||
// FileMode permission bits for the device.
|
||||
FileMode *os.FileMode `json:"fileMode,omitempty"`
|
||||
// UID of the device.
|
||||
UID *uint32 `json:"uid,omitempty"`
|
||||
// Gid of the device.
|
||||
GID *uint32 `json:"gid,omitempty"`
|
||||
}
|
||||
|
||||
// DeviceCgroup represents a device rule for the whitelist controller
|
||||
type DeviceCgroup struct {
|
||||
// Allow or deny
|
||||
Allow bool `json:"allow"`
|
||||
// Device type, block, char, etc.
|
||||
Type *rune `json:"type,omitempty"`
|
||||
// Major is the device's major number.
|
||||
Major *int64 `json:"major,omitempty"`
|
||||
// Minor is the device's minor number.
|
||||
Minor *int64 `json:"minor,omitempty"`
|
||||
// Cgroup access permissions format, rwm.
|
||||
Access *string `json:"access,omitempty"`
|
||||
}
|
||||
|
||||
// Seccomp represents syscall restrictions
|
||||
type Seccomp struct {
|
||||
DefaultAction Action `json:"defaultAction"`
|
||||
Architectures []Arch `json:"architectures"`
|
||||
Syscalls []Syscall `json:"syscalls,omitempty"`
|
||||
}
|
||||
|
||||
// Arch used for additional architectures
|
||||
type Arch string
|
||||
|
||||
// Additional architectures permitted to be used for system calls
|
||||
// By default only the native architecture of the kernel is permitted
|
||||
const (
|
||||
ArchX86 Arch = "SCMP_ARCH_X86"
|
||||
ArchX86_64 Arch = "SCMP_ARCH_X86_64"
|
||||
ArchX32 Arch = "SCMP_ARCH_X32"
|
||||
ArchARM Arch = "SCMP_ARCH_ARM"
|
||||
ArchAARCH64 Arch = "SCMP_ARCH_AARCH64"
|
||||
ArchMIPS Arch = "SCMP_ARCH_MIPS"
|
||||
ArchMIPS64 Arch = "SCMP_ARCH_MIPS64"
|
||||
ArchMIPS64N32 Arch = "SCMP_ARCH_MIPS64N32"
|
||||
ArchMIPSEL Arch = "SCMP_ARCH_MIPSEL"
|
||||
ArchMIPSEL64 Arch = "SCMP_ARCH_MIPSEL64"
|
||||
ArchMIPSEL64N32 Arch = "SCMP_ARCH_MIPSEL64N32"
|
||||
)
|
||||
|
||||
// Action taken upon Seccomp rule match
|
||||
type Action string
|
||||
|
||||
// Define actions for Seccomp rules
|
||||
const (
|
||||
ActKill Action = "SCMP_ACT_KILL"
|
||||
ActTrap Action = "SCMP_ACT_TRAP"
|
||||
ActErrno Action = "SCMP_ACT_ERRNO"
|
||||
ActTrace Action = "SCMP_ACT_TRACE"
|
||||
ActAllow Action = "SCMP_ACT_ALLOW"
|
||||
)
|
||||
|
||||
// Operator used to match syscall arguments in Seccomp
|
||||
type Operator string
|
||||
|
||||
// Define operators for syscall arguments in Seccomp
|
||||
const (
|
||||
OpNotEqual Operator = "SCMP_CMP_NE"
|
||||
OpLessThan Operator = "SCMP_CMP_LT"
|
||||
OpLessEqual Operator = "SCMP_CMP_LE"
|
||||
OpEqualTo Operator = "SCMP_CMP_EQ"
|
||||
OpGreaterEqual Operator = "SCMP_CMP_GE"
|
||||
OpGreaterThan Operator = "SCMP_CMP_GT"
|
||||
OpMaskedEqual Operator = "SCMP_CMP_MASKED_EQ"
|
||||
)
|
||||
|
||||
// Arg used for matching specific syscall arguments in Seccomp
|
||||
type Arg struct {
|
||||
Index uint `json:"index"`
|
||||
Value uint64 `json:"value"`
|
||||
ValueTwo uint64 `json:"valueTwo"`
|
||||
Op Operator `json:"op"`
|
||||
}
|
||||
|
||||
// Syscall is used to match a syscall in Seccomp
|
||||
type Syscall struct {
|
||||
Name string `json:"name"`
|
||||
Action Action `json:"action"`
|
||||
Args []Arg `json:"args,omitempty"`
|
||||
}
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@ A [directory structure](bundle.md) that is written ahead of time, distributed, a
|
|||
|
||||
## Configuration
|
||||
|
||||
The [`config.json`](config.md) and [`runtime.json`](runtime-config.md) files in a [bundle](#bundle) which define the intended [container](#container) and container process.
|
||||
The [`config.json`](config.md) file in a [bundle](#bundle) which defines the intended [container](#container) and container process.
|
||||
|
||||
## Container
|
||||
|
||||
|
|
|
|||
|
|
@ -1,535 +0,0 @@
|
|||
# Linux-specific Runtime Configuration
|
||||
|
||||
## Namespaces
|
||||
|
||||
A namespace wraps a global system resource in an abstraction that makes it appear to the processes within the namespace that they have their own isolated instance of the global resource.
|
||||
Changes to the global resource are visible to other processes that are members of the namespace, but are invisible to other processes.
|
||||
For more information, see [the man page](http://man7.org/linux/man-pages/man7/namespaces.7.html).
|
||||
|
||||
Namespaces are specified as an array of entries inside the `namespaces` root field.
|
||||
The following parameters can be specified to setup namespaces:
|
||||
|
||||
* **`type`** *(string, required)* - namespace type. The following namespaces types are supported:
|
||||
* **`pid`** processes inside the container will only be able to see other processes inside the same container
|
||||
* **`network`** the container will have its own network stack
|
||||
* **`mount`** the container will have an isolated mount table
|
||||
* **`ipc`** processes inside the container will only be able to communicate to other processes inside the same container via system level IPC
|
||||
* **`uts`** the container will be able to have its own hostname and domain name
|
||||
* **`user`** the container will be able to remap user and group IDs from the host to local users and groups within the container
|
||||
|
||||
* **`path`** *(string, optional)* - path to namespace file
|
||||
|
||||
If a path is specified, that particular file is used to join that type of namespace.
|
||||
Also, when a path is specified, a runtime MUST assume that the setup for that particular namespace has already been done and error out if the config specifies anything else related to that namespace.
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"namespaces": [
|
||||
{
|
||||
"type": "pid",
|
||||
"path": "/proc/1234/ns/pid"
|
||||
},
|
||||
{
|
||||
"type": "network",
|
||||
"path": "/var/run/netns/neta"
|
||||
},
|
||||
{
|
||||
"type": "mount"
|
||||
},
|
||||
{
|
||||
"type": "ipc"
|
||||
},
|
||||
{
|
||||
"type": "uts"
|
||||
},
|
||||
{
|
||||
"type": "user"
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
## User namespace mappings
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"uidMappings": [
|
||||
{
|
||||
"hostID": 1000,
|
||||
"containerID": 0,
|
||||
"size": 10
|
||||
}
|
||||
],
|
||||
"gidMappings": [
|
||||
{
|
||||
"hostID": 1000,
|
||||
"containerID": 0,
|
||||
"size": 10
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
uid/gid mappings describe the user namespace mappings from the host to the container.
|
||||
The mappings represent how the bundle `rootfs` expects the user namespace to be setup and the runtime SHOULD NOT modify the permissions on the rootfs to realize the mapping.
|
||||
*hostID* is the starting uid/gid on the host to be mapped to *containerID* which is the starting uid/gid in the container and *size* refers to the number of ids to be mapped.
|
||||
There is a limit of 5 mappings which is the Linux kernel hard limit.
|
||||
|
||||
## Devices
|
||||
|
||||
`devices` is an array specifying the list of devices to be created in the container.
|
||||
|
||||
The following parameters can be specified:
|
||||
|
||||
* **`type`** *(char, required)* - type of device: `c`, `b`, `u` or `p`. More info in `man mknod`.
|
||||
|
||||
* **`path`** *(string, optional)* - full path to device inside container
|
||||
|
||||
* **`major, minor`** *(int64, required)* - major, minor numbers for device. More info in `man mknod`. There is a special value: `-1`, which means `*` for `device` cgroup setup.
|
||||
|
||||
* **`permissions`** *(string, optional)* - cgroup permissions for device. A composition of `r` (*read*), `w` (*write*), and `m` (*mknod*).
|
||||
|
||||
* **`fileMode`** *(uint32, optional)* - file mode for device file
|
||||
|
||||
* **`uid`** *(uint32, optional)* - uid of device owner
|
||||
|
||||
* **`gid`** *(uint32, optional)* - gid of device owner
|
||||
|
||||
**`fileMode`**, **`uid`** and **`gid`** are required if **`path`** is given and are otherwise not allowed.
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"devices": [
|
||||
{
|
||||
"path": "/dev/random",
|
||||
"type": "c",
|
||||
"major": 1,
|
||||
"minor": 8,
|
||||
"permissions": "rwm",
|
||||
"fileMode": 0666,
|
||||
"uid": 0,
|
||||
"gid": 0
|
||||
},
|
||||
{
|
||||
"path": "/dev/urandom",
|
||||
"type": "c",
|
||||
"major": 1,
|
||||
"minor": 9,
|
||||
"permissions": "rwm",
|
||||
"fileMode": 0666,
|
||||
"uid": 0,
|
||||
"gid": 0
|
||||
},
|
||||
{
|
||||
"path": "/dev/null",
|
||||
"type": "c",
|
||||
"major": 1,
|
||||
"minor": 3,
|
||||
"permissions": "rwm",
|
||||
"fileMode": 0666,
|
||||
"uid": 0,
|
||||
"gid": 0
|
||||
},
|
||||
{
|
||||
"path": "/dev/zero",
|
||||
"type": "c",
|
||||
"major": 1,
|
||||
"minor": 5,
|
||||
"permissions": "rwm",
|
||||
"fileMode": 0666,
|
||||
"uid": 0,
|
||||
"gid": 0
|
||||
},
|
||||
{
|
||||
"path": "/dev/tty",
|
||||
"type": "c",
|
||||
"major": 5,
|
||||
"minor": 0,
|
||||
"permissions": "rwm",
|
||||
"fileMode": 0666,
|
||||
"uid": 0,
|
||||
"gid": 0
|
||||
},
|
||||
{
|
||||
"path": "/dev/full",
|
||||
"type": "c",
|
||||
"major": 1,
|
||||
"minor": 7,
|
||||
"permissions": "rwm",
|
||||
"fileMode": 0666,
|
||||
"uid": 0,
|
||||
"gid": 0
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
## Control groups
|
||||
|
||||
Also known as cgroups, they are used to restrict resource usage for a container and handle device access.
|
||||
cgroups provide controls to restrict cpu, memory, IO, pids and network for the container.
|
||||
For more information, see the [kernel cgroups documentation](https://www.kernel.org/doc/Documentation/cgroups/cgroups.txt).
|
||||
|
||||
The path to the cgroups can be specified in the Spec via `cgroupsPath`.
|
||||
`cgroupsPath` is expected to be relative to the cgroups mount point.
|
||||
If `cgroupsPath` is not specified, implementations can define the default cgroup path.
|
||||
Implementations of the Spec can choose to name cgroups in any manner.
|
||||
The Spec does not include naming schema for cgroups.
|
||||
The Spec does not support [split hierarchy](https://www.kernel.org/doc/Documentation/cgroups/unified-hierarchy.txt).
|
||||
The cgroups will be created if they don't exist.
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"cgroupsPath": "/myRuntime/myContainer"
|
||||
```
|
||||
|
||||
`cgroupsPath` can be used to either control the cgroups hierarchy for containers or to run a new process in an existing container.
|
||||
|
||||
You can configure a container's cgroups via the `resources` field of the Linux configuration.
|
||||
Do not specify `resources` unless limits have to be updated.
|
||||
For example, to run a new process in an existing container without updating limits, `resources` need not be specified.
|
||||
|
||||
#### Disable out-of-memory killer
|
||||
|
||||
`disableOOMKiller` contains a boolean (`true` or `false`) that enables or disables the Out of Memory killer for a cgroup.
|
||||
If enabled (`false`), tasks that attempt to consume more memory than they are allowed are immediately killed by the OOM killer.
|
||||
The OOM killer is enabled by default in every cgroup using the `memory` subsystem.
|
||||
To disable it, specify a value of `true`.
|
||||
For more information, see [the memory cgroup man page](https://www.kernel.org/doc/Documentation/cgroups/memory.txt).
|
||||
|
||||
* **`disableOOMKiller`** *(bool, optional)* - enables or disables the OOM killer
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"disableOOMKiller": false
|
||||
```
|
||||
|
||||
#### Set oom_score_adj
|
||||
|
||||
More information on `oom_score_adj` available [here](https://www.kernel.org/doc/Documentation/filesystems/proc.txt).
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"oomScoreAdj": 0
|
||||
```
|
||||
|
||||
#### Memory
|
||||
|
||||
`memory` represents the cgroup subsystem `memory` and it's used to set limits on the container's memory usage.
|
||||
For more information, see [the memory cgroup man page](https://www.kernel.org/doc/Documentation/cgroups/memory.txt).
|
||||
|
||||
The following parameters can be specified to setup the controller:
|
||||
|
||||
* **`limit`** *(uint64, optional)* - sets limit of memory usage
|
||||
|
||||
* **`reservation`** *(uint64, optional)* - sets soft limit of memory usage
|
||||
|
||||
* **`swap`** *(uint64, optional)* - sets limit of memory+Swap usage
|
||||
|
||||
* **`kernel`** *(uint64, optional)* - sets hard limit for kernel memory
|
||||
|
||||
* **`kernelTCP`** *(uint64, optional)* - sets hard limit for kernel memory in tcp using
|
||||
|
||||
* **`swappiness`** *(uint64, optional)* - sets swappiness parameter of vmscan (See sysctl's vm.swappiness)
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"memory": {
|
||||
"limit": 0,
|
||||
"reservation": 0,
|
||||
"swap": 0,
|
||||
"kernel": 0,
|
||||
"kernelTCP": 0,
|
||||
"swappiness": 0
|
||||
}
|
||||
```
|
||||
|
||||
#### CPU
|
||||
|
||||
`cpu` represents the cgroup subsystems `cpu` and `cpusets`.
|
||||
For more information, see [the cpusets cgroup man page](https://www.kernel.org/doc/Documentation/cgroups/cpusets.txt).
|
||||
|
||||
The following parameters can be specified to setup the controller:
|
||||
|
||||
* **`shares`** *(uint64, optional)* - specifies a relative share of CPU time available to the tasks in a cgroup
|
||||
|
||||
* **`quota`** *(uint64, optional)* - specifies the total amount of time in microseconds for which all tasks in a cgroup can run during one period (as defined by **`period`** below)
|
||||
|
||||
* **`period`** *(uint64, optional)* - specifies a period of time in microseconds for how regularly a cgroup's access to CPU resources should be reallocated (CFS scheduler only)
|
||||
|
||||
* **`realtimeRuntime`** *(uint64, optional)* - specifies a period of time in microseconds for the longest continuous period in which the tasks in a cgroup have access to CPU resources
|
||||
|
||||
* **`realtimePeriod`** *(uint64, optional)* - same as **`period`** but applies to realtime scheduler only
|
||||
|
||||
* **`cpus`** *(string, optional)* - list of CPUs the container will run in
|
||||
|
||||
* **`mems`** *(string, optional)* - list of Memory Nodes the container will run in
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"cpu": {
|
||||
"shares": 0,
|
||||
"quota": 0,
|
||||
"period": 0,
|
||||
"realtimeRuntime": 0,
|
||||
"realtimePeriod": 0,
|
||||
"cpus": "",
|
||||
"mems": ""
|
||||
}
|
||||
```
|
||||
|
||||
#### Block IO Controller
|
||||
|
||||
`blockIO` represents the cgroup subsystem `blkio` which implements the block io controller.
|
||||
For more information, see [the kernel cgroups documentation about blkio](https://www.kernel.org/doc/Documentation/cgroups/blkio-controller.txt).
|
||||
|
||||
The following parameters can be specified to setup the controller:
|
||||
|
||||
* **`blkioWeight`** *(uint16, optional)* - specifies per-cgroup weight. This is default weight of the group on all devices until and unless overridden by per-device rules. The range is from 10 to 1000.
|
||||
|
||||
* **`blkioLeafWeight`** *(uint16, optional)* - equivalents of `blkioWeight` for the purpose of deciding how much weight tasks in the given cgroup has while competing with the cgroup's child cgroups. The range is from 10 to 1000.
|
||||
|
||||
* **`blkioWeightDevice`** *(array, optional)* - specifies the list of devices which will be bandwidth rate limited. The following parameters can be specified per-device:
|
||||
* **`major, minor`** *(int64, required)* - major, minor numbers for device. More info in `man mknod`.
|
||||
* **`weight`** *(uint16, optional)* - bandwidth rate for the device, range is from 10 to 1000
|
||||
* **`leafWeight`** *(uint16, optional)* - bandwidth rate for the device while competing with the cgroup's child cgroups, range is from 10 to 1000, CFQ scheduler only
|
||||
|
||||
You must specify at least one of `weight` or `leafWeight` in a given entry, and can specify both.
|
||||
|
||||
* **`blkioThrottleReadBpsDevice`**, **`blkioThrottleWriteBpsDevice`**, **`blkioThrottleReadIOPSDevice`**, **`blkioThrottleWriteIOPSDevice`** *(array, optional)* - specify the list of devices which will be IO rate limited. The following parameters can be specified per-device:
|
||||
* **`major, minor`** *(int64, required)* - major, minor numbers for device. More info in `man mknod`.
|
||||
* **`rate`** *(uint64, required)* - IO rate limit for the device
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"blockIO": {
|
||||
"blkioWeight": 0,
|
||||
"blkioLeafWeight": 0,
|
||||
"blkioWeightDevice": [
|
||||
{
|
||||
"major": 8,
|
||||
"minor": 0,
|
||||
"weight": 500,
|
||||
"leafWeight": 300
|
||||
},
|
||||
{
|
||||
"major": 8,
|
||||
"minor": 16,
|
||||
"weight": 500
|
||||
}
|
||||
],
|
||||
"blkioThrottleReadBpsDevice": [
|
||||
{
|
||||
"major": 8,
|
||||
"minor": 0,
|
||||
"rate": 600
|
||||
}
|
||||
],
|
||||
"blkioThrottleWriteIOPSDevice": [
|
||||
{
|
||||
"major": 8,
|
||||
"minor": 16,
|
||||
"rate": 300
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
#### Huge page limits
|
||||
|
||||
`hugepageLimits` represents the `hugetlb` controller which allows to limit the
|
||||
HugeTLB usage per control group and enforces the controller limit during page fault.
|
||||
For more information, see the [kernel cgroups documentation about HugeTLB](https://www.kernel.org/doc/Documentation/cgroups/hugetlb.txt).
|
||||
|
||||
`hugepageLimits` is an array of entries, each having the following structure:
|
||||
|
||||
* **`pageSize`** *(string, required)* - hugepage size
|
||||
|
||||
* **`limit`** *(uint64, required)* - limit in bytes of *hugepagesize* HugeTLB usage
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"hugepageLimits": [
|
||||
{
|
||||
"pageSize": "2MB",
|
||||
"limit": 9223372036854771712
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
#### Network
|
||||
|
||||
`network` represents the cgroup subsystems `net_cls` and `net_prio`.
|
||||
For more information, see [the net\_cls cgroup man page](https://www.kernel.org/doc/Documentation/cgroups/net_cls.txt) and [the net\_prio cgroup man page](https://www.kernel.org/doc/Documentation/cgroups/net_prio.txt).
|
||||
|
||||
The following parameters can be specified to setup these cgroup controllers:
|
||||
|
||||
* **`classID`** *(string, optional)* - is the network class identifier the cgroup's network packets will be tagged with
|
||||
|
||||
* **`priorities`** *(array, optional)* - specifies a list of objects of the priorities assigned to traffic originating from
|
||||
processes in the group and egressing the system on various interfaces. The following parameters can be specified per-priority:
|
||||
* **`name`** *(string, required)* - interface name
|
||||
* **`priority`** *(uint32, required)* - priority applied to the interface
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"network": {
|
||||
"classID": "0x100001",
|
||||
"priorities": [
|
||||
{
|
||||
"name": "eth0",
|
||||
"priority": 500
|
||||
},
|
||||
{
|
||||
"name": "eth1",
|
||||
"priority": 1000
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
#### PIDs
|
||||
|
||||
`pids` represents the cgroup subsystem `pids`.
|
||||
For more information, see [the pids cgroup man page](https://www.kernel.org/doc/Documentation/cgroups/pids.txt
|
||||
).
|
||||
|
||||
The following paramters can be specified to setup the controller:
|
||||
|
||||
* **`limit`** *(int64, required)* - specifies the maximum number of tasks in the cgroup
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"pids": {
|
||||
"limit": 32771
|
||||
}
|
||||
```
|
||||
|
||||
## Sysctl
|
||||
|
||||
sysctl allows kernel parameters to be modified at runtime for the container.
|
||||
For more information, see [the man page](http://man7.org/linux/man-pages/man8/sysctl.8.html)
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"sysctl": {
|
||||
"net.ipv4.ip_forward": "1",
|
||||
"net.core.somaxconn": "256"
|
||||
}
|
||||
```
|
||||
|
||||
## Rlimits
|
||||
|
||||
rlimits allow setting resource limits.
|
||||
`type` is a string with a value from those defined in [the man page](http://man7.org/linux/man-pages/man2/setrlimit.2.html).
|
||||
The kernel enforces the `soft` limit for a resource while the `hard` limit acts as a ceiling for that value that could be set by an unprivileged process.
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"rlimits": [
|
||||
{
|
||||
"type": "RLIMIT_NPROC",
|
||||
"soft": 1024,
|
||||
"hard": 102400
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
## SELinux process label
|
||||
|
||||
SELinux process label specifies the label with which the processes in a container are run.
|
||||
For more information about SELinux, see [Selinux documentation](http://selinuxproject.org/page/Main_Page)
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"selinuxProcessLabel": "system_u:system_r:svirt_lxc_net_t:s0:c124,c675"
|
||||
```
|
||||
|
||||
## Apparmor profile
|
||||
|
||||
Apparmor profile specifies the name of the apparmor profile that will be used for the container.
|
||||
For more information about Apparmor, see [Apparmor documentation](https://wiki.ubuntu.com/AppArmor)
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"apparmorProfile": "acme_secure_profile"
|
||||
```
|
||||
|
||||
## seccomp
|
||||
|
||||
Seccomp provides application sandboxing mechanism in the Linux kernel.
|
||||
Seccomp configuration allows one to configure actions to take for matched syscalls and furthermore also allows matching on values passed as arguments to syscalls.
|
||||
For more information about Seccomp, see [Seccomp kernel documentation](https://www.kernel.org/doc/Documentation/prctl/seccomp_filter.txt)
|
||||
The actions, architectures, and operators are strings that match the definitions in seccomp.h from [libseccomp](https://github.com/seccomp/libseccomp) and are translated to corresponding values.
|
||||
A valid list of constants as of Libseccomp v2.2.3 is contained below.
|
||||
|
||||
Architecture Constants
|
||||
* `SCMP_ARCH_X86`
|
||||
* `SCMP_ARCH_X86_64`
|
||||
* `SCMP_ARCH_X32`
|
||||
* `SCMP_ARCH_ARM`
|
||||
* `SCMP_ARCH_AARCH64`
|
||||
* `SCMP_ARCH_MIPS`
|
||||
* `SCMP_ARCH_MIPS64`
|
||||
* `SCMP_ARCH_MIPS64N32`
|
||||
* `SCMP_ARCH_MIPSEL`
|
||||
* `SCMP_ARCH_MIPSEL64`
|
||||
* `SCMP_ARCH_MIPSEL64N32`
|
||||
|
||||
Action Constants:
|
||||
* `SCMP_ACT_KILL`
|
||||
* `SCMP_ACT_TRAP`
|
||||
* `SCMP_ACT_ERRNO`
|
||||
* `SCMP_ACT_TRACE`
|
||||
* `SCMP_ACT_ALLOW`
|
||||
|
||||
Operator Constants:
|
||||
* `SCMP_CMP_NE`
|
||||
* `SCMP_CMP_LT`
|
||||
* `SCMP_CMP_LE`
|
||||
* `SCMP_CMP_EQ`
|
||||
* `SCMP_CMP_GE`
|
||||
* `SCMP_CMP_GT`
|
||||
* `SCMP_CMP_MASKED_EQ`
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"seccomp": {
|
||||
"defaultAction": "SCMP_ACT_ALLOW",
|
||||
"architectures": [
|
||||
"SCMP_ARCH_X86"
|
||||
],
|
||||
"syscalls": [
|
||||
{
|
||||
"name": "getcwd",
|
||||
"action": "SCMP_ACT_ERRNO"
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
## Rootfs Mount Propagation
|
||||
|
||||
rootfsPropagation sets the rootfs's mount propagation.
|
||||
Its value is either slave, private, or shared.
|
||||
[The kernel doc](https://www.kernel.org/doc/Documentation/filesystems/sharedsubtree.txt) has more information about mount propagation.
|
||||
|
||||
###### Example
|
||||
|
||||
```json
|
||||
"rootfsPropagation": "slave",
|
||||
```
|
||||
|
|
@ -1,122 +0,0 @@
|
|||
# Runtime Configuration
|
||||
|
||||
## Hooks
|
||||
|
||||
Lifecycle hooks allow custom events for different points in a container's runtime.
|
||||
Presently there are `Prestart`, `Poststart` and `Poststop`.
|
||||
|
||||
* [`Prestart`](#prestart) is a list of hooks to be run before the container process is executed
|
||||
* [`Poststart`](#poststart) is a list of hooks to be run immediately after the container process is started
|
||||
* [`Poststop`](#poststop) is a list of hooks to be run after the container process exits
|
||||
|
||||
Hooks allow one to run code before/after various lifecycle events of the container.
|
||||
Hooks MUST be called in the listed order.
|
||||
The state of the container is passed to the hooks over stdin, so the hooks could get the information they need to do their work.
|
||||
|
||||
Hook paths are absolute and are executed from the host's filesystem.
|
||||
|
||||
### Prestart
|
||||
|
||||
The pre-start hooks are called after the container process is spawned, but before the user supplied command is executed.
|
||||
They are called after the container namespaces are created on Linux, so they provide an opportunity to customize the container.
|
||||
In Linux, for e.g., the network namespace could be configured in this hook.
|
||||
|
||||
If a hook returns a non-zero exit code, then an error including the exit code and the stderr is returned to the caller and the container is torn down.
|
||||
|
||||
### Poststart
|
||||
|
||||
The post-start hooks are called after the user process is started.
|
||||
For example this hook can notify user that real process is spawned.
|
||||
|
||||
If a hook returns a non-zero exit code, then an error is logged and the remaining hooks are executed.
|
||||
|
||||
### Poststop
|
||||
|
||||
The post-stop hooks are called after the container process is stopped.
|
||||
Cleanup or debugging could be performed in such a hook.
|
||||
If a hook returns a non-zero exit code, then an error is logged and the remaining hooks are executed.
|
||||
|
||||
*Example*
|
||||
|
||||
```json
|
||||
"hooks" : {
|
||||
"prestart": [
|
||||
{
|
||||
"path": "/usr/bin/fix-mounts",
|
||||
"args": ["fix-mounts", "arg1", "arg2"],
|
||||
"env": [ "key1=value1"]
|
||||
},
|
||||
{
|
||||
"path": "/usr/bin/setup-network"
|
||||
}
|
||||
],
|
||||
"poststart": [
|
||||
{
|
||||
"path": "/usr/bin/notify-start"
|
||||
}
|
||||
],
|
||||
"poststop": [
|
||||
{
|
||||
"path": "/usr/sbin/cleanup.sh",
|
||||
"args": ["cleanup.sh", "-f"]
|
||||
}
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
`path` is required for a hook.
|
||||
`args` and `env` are optional.
|
||||
The semantics are the same as `Path`, `Args` and `Env` in [golang Cmd](https://golang.org/pkg/os/exec/#Cmd).
|
||||
|
||||
## Mount Configuration
|
||||
|
||||
Additional filesystems can be declared as "mounts", specified in the *mounts* object.
|
||||
Keys in this object are names of mount points from portable config.
|
||||
Values are objects with configuration of mount points.
|
||||
The parameters are similar to the ones in [the Linux mount system call](http://man7.org/linux/man-pages/man2/mount.2.html).
|
||||
Only [mounts from the portable config](config.md#mount-points) will be mounted.
|
||||
|
||||
* **`type`** (string, required) Linux, *filesystemtype* argument supported by the kernel are listed in */proc/filesystems* (e.g., "minix", "ext2", "ext3", "jfs", "xfs", "reiserfs", "msdos", "proc", "nfs", "iso9660"). Windows: ntfs
|
||||
* **`source`** (string, required) a device name, but can also be a directory name or a dummy. Windows, the volume name that is the target of the mount point. \\?\Volume\{GUID}\ (on Windows source is called target)
|
||||
* **`options`** (list of strings, optional) in the fstab format [https://wiki.archlinux.org/index.php/Fstab](https://wiki.archlinux.org/index.php/Fstab).
|
||||
|
||||
*Example (Linux)*
|
||||
|
||||
```json
|
||||
"mounts": {
|
||||
"proc": {
|
||||
"type": "proc",
|
||||
"source": "proc",
|
||||
"options": []
|
||||
},
|
||||
"dev": {
|
||||
"type": "tmpfs",
|
||||
"source": "tmpfs",
|
||||
"options": ["nosuid","strictatime","mode=755","size=65536k"]
|
||||
},
|
||||
"devpts": {
|
||||
"type": "devpts",
|
||||
"source": "devpts",
|
||||
"options": ["nosuid","noexec","newinstance","ptmxmode=0666","mode=0620","gid=5"]
|
||||
},
|
||||
"data": {
|
||||
"type": "bind",
|
||||
"source": "/volumes/testing",
|
||||
"options": ["rbind","rw"]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
*Example (Windows)*
|
||||
|
||||
```json
|
||||
"mounts": {
|
||||
"myfancymountpoint": {
|
||||
"type": "ntfs",
|
||||
"source": "\\\\?\\Volume\\{2eca078d-5cbc-43d3-aff8-7e8511f60d0e}\\",
|
||||
"options": []
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
See links for details about [mountvol](http://ss64.com/nt/mountvol.html) and [SetVolumeMountPoint](https://msdn.microsoft.com/en-us/library/windows/desktop/aa365561(v=vs.85).aspx) in Windows.
|
||||
|
|
@ -38,8 +38,8 @@ This is provided so that consumers can find the container's configuration and ro
|
|||
The lifecycle describes the timeline of events that happen from when a container is created to when it ceases to exist.
|
||||
|
||||
1. OCI compliant runtime is invoked by passing the bundle path as argument.
|
||||
2. The container's runtime environment is created according to the configuration in `config.json` and `runtime.json`.
|
||||
Any updates to `config.json` or `runtime.json` after container is running do not affect the container.
|
||||
2. The container's runtime environment is created according to the configuration in [`config.json`](config.md).
|
||||
Any updates to `config.json` after container is running do not affect the container.
|
||||
3. The container's state.json file is written to the filesystem.
|
||||
4. The prestart hooks are invoked by the runtime.
|
||||
If any prestart hook fails, then the container is stopped and the lifecycle continues at step 8.
|
||||
|
|
@ -56,4 +56,4 @@ Note: The lifecycle is a WIP and it will evolve as we have more use cases and mo
|
|||
|
||||
## Hooks
|
||||
|
||||
See [runtime configuration for hooks](./runtime-config.md)
|
||||
See [runtime configuration for hooks](./config.md#hooks)
|
||||
|
|
|
|||
|
|
@ -1,42 +0,0 @@
|
|||
package specs
|
||||
|
||||
// RuntimeSpec contains host-specific configuration information for
|
||||
// a container. This information must not be included when the bundle
|
||||
// is packaged for distribution.
|
||||
type RuntimeSpec struct {
|
||||
// Mounts is a mapping of names to mount configurations.
|
||||
// Which mounts will be mounted and where should be chosen with MountPoints
|
||||
// in Spec.
|
||||
Mounts map[string]Mount `json:"mounts"`
|
||||
// Hooks are the commands run at various lifecycle events of the container.
|
||||
Hooks Hooks `json:"hooks"`
|
||||
}
|
||||
|
||||
// Hook specifies a command that is run at a particular event in the lifecycle of a container
|
||||
type Hook struct {
|
||||
Path string `json:"path"`
|
||||
Args []string `json:"args,omitempty"`
|
||||
Env []string `json:"env,omitempty"`
|
||||
}
|
||||
|
||||
// Hooks for container setup and teardown
|
||||
type Hooks struct {
|
||||
// Prestart is a list of hooks to be run before the container process is executed.
|
||||
// On Linux, they are run after the container namespaces are created.
|
||||
Prestart []Hook `json:"prestart,omitempty"`
|
||||
// Poststart is a list of hooks to be run after the container process is started.
|
||||
Poststart []Hook `json:"poststart,omitempty"`
|
||||
// Poststop is a list of hooks to be run after the container process exits.
|
||||
Poststop []Hook `json:"poststop,omitempty"`
|
||||
}
|
||||
|
||||
// Mount specifies a mount for a container
|
||||
type Mount struct {
|
||||
// Type specifies the mount kind.
|
||||
Type string `json:"type"`
|
||||
// Source specifies the source path of the mount. In the case of bind mounts on
|
||||
// linux based systems this would be the file on the host.
|
||||
Source string `json:"source"`
|
||||
// Options are fstab style mount options.
|
||||
Options []string `json:"options,omitempty"`
|
||||
}
|
||||
|
|
@ -1,306 +0,0 @@
|
|||
package specs
|
||||
|
||||
import "os"
|
||||
|
||||
// LinuxStateDirectory holds the container's state information
|
||||
const LinuxStateDirectory = "/run/opencontainer/containers"
|
||||
|
||||
// LinuxRuntimeSpec is the full specification for linux containers.
|
||||
type LinuxRuntimeSpec struct {
|
||||
RuntimeSpec
|
||||
// LinuxRuntime is platform specific configuration for linux based containers.
|
||||
Linux LinuxRuntime `json:"linux"`
|
||||
}
|
||||
|
||||
// LinuxRuntime hosts the Linux-only runtime information
|
||||
type LinuxRuntime struct {
|
||||
// UIDMapping specifies user mappings for supporting user namespaces on linux.
|
||||
UIDMappings []IDMapping `json:"uidMappings,omitempty"`
|
||||
// GIDMapping specifies group mappings for supporting user namespaces on linux.
|
||||
GIDMappings []IDMapping `json:"gidMappings,omitempty"`
|
||||
// Rlimits specifies rlimit options to apply to the container's process.
|
||||
Rlimits []Rlimit `json:"rlimits,omitempty"`
|
||||
// Sysctl are a set of key value pairs that are set for the container on start
|
||||
Sysctl map[string]string `json:"sysctl,omitempty"`
|
||||
// Resources contain cgroup information for handling resource constraints
|
||||
// for the container
|
||||
Resources *Resources `json:"resources,omitempty"`
|
||||
// CgroupsPath specifies the path to cgroups that are created and/or joined by the container.
|
||||
// The path is expected to be relative to the cgroups mountpoint.
|
||||
// If resources are specified, the cgroups at CgroupsPath will be updated based on resources.
|
||||
CgroupsPath *string `json:"cgroupsPath,omitempty"`
|
||||
// Namespaces contains the namespaces that are created and/or joined by the container
|
||||
Namespaces []Namespace `json:"namespaces"`
|
||||
// Devices are a list of device nodes that are created and enabled for the container
|
||||
Devices []Device `json:"devices"`
|
||||
// ApparmorProfile specified the apparmor profile for the container.
|
||||
ApparmorProfile string `json:"apparmorProfile"`
|
||||
// SelinuxProcessLabel specifies the selinux context that the container process is run as.
|
||||
SelinuxProcessLabel string `json:"selinuxProcessLabel"`
|
||||
// Seccomp specifies the seccomp security settings for the container.
|
||||
Seccomp Seccomp `json:"seccomp"`
|
||||
// RootfsPropagation is the rootfs mount propagation mode for the container
|
||||
RootfsPropagation string `json:"rootfsPropagation,omitempty"`
|
||||
}
|
||||
|
||||
// Namespace is the configuration for a linux namespace
|
||||
type Namespace struct {
|
||||
// Type is the type of Linux namespace
|
||||
Type NamespaceType `json:"type"`
|
||||
// Path is a path to an existing namespace persisted on disk that can be joined
|
||||
// and is of the same type
|
||||
Path string `json:"path,omitempty"`
|
||||
}
|
||||
|
||||
// NamespaceType is one of the linux namespaces
|
||||
type NamespaceType string
|
||||
|
||||
const (
|
||||
// PIDNamespace for isolating process IDs
|
||||
PIDNamespace NamespaceType = "pid"
|
||||
// NetworkNamespace for isolating network devices, stacks, ports, etc
|
||||
NetworkNamespace = "network"
|
||||
// MountNamespace for isolating mount points
|
||||
MountNamespace = "mount"
|
||||
// IPCNamespace for isolating System V IPC, POSIX message queues
|
||||
IPCNamespace = "ipc"
|
||||
// UTSNamespace for isolating hostname and NIS domain name
|
||||
UTSNamespace = "uts"
|
||||
// UserNamespace for isolating user and group IDs
|
||||
UserNamespace = "user"
|
||||
)
|
||||
|
||||
// IDMapping specifies UID/GID mappings
|
||||
type IDMapping struct {
|
||||
// HostID is the UID/GID of the host user or group
|
||||
HostID uint32 `json:"hostID"`
|
||||
// ContainerID is the UID/GID of the container's user or group
|
||||
ContainerID uint32 `json:"containerID"`
|
||||
// Size is the length of the range of IDs mapped between the two namespaces
|
||||
Size uint32 `json:"size"`
|
||||
}
|
||||
|
||||
// Rlimit type and restrictions
|
||||
type Rlimit struct {
|
||||
// Type of the rlimit to set
|
||||
Type string `json:"type"`
|
||||
// Hard is the hard limit for the specified type
|
||||
Hard uint64 `json:"hard"`
|
||||
// Soft is the soft limit for the specified type
|
||||
Soft uint64 `json:"soft"`
|
||||
}
|
||||
|
||||
// HugepageLimit structure corresponds to limiting kernel hugepages
|
||||
type HugepageLimit struct {
|
||||
// Pagesize is the hugepage size
|
||||
Pagesize *string `json:"pageSize,omitempty"`
|
||||
// Limit is the limit of "hugepagesize" hugetlb usage
|
||||
Limit *uint64 `json:"limit,omitempty"`
|
||||
}
|
||||
|
||||
// InterfacePriority for network interfaces
|
||||
type InterfacePriority struct {
|
||||
// Name is the name of the network interface
|
||||
Name string `json:"name"`
|
||||
// Priority for the interface
|
||||
Priority uint32 `json:"priority"`
|
||||
}
|
||||
|
||||
// blockIODevice holds major:minor format supported in blkio cgroup
|
||||
type blockIODevice struct {
|
||||
// Major is the device's major number.
|
||||
Major int64 `json:"major"`
|
||||
// Minor is the device's minor number.
|
||||
Minor int64 `json:"minor"`
|
||||
}
|
||||
|
||||
// WeightDevice struct holds a `major:minor weight` pair for blkioWeightDevice
|
||||
type WeightDevice struct {
|
||||
blockIODevice
|
||||
// Weight is the bandwidth rate for the device, range is from 10 to 1000
|
||||
Weight *uint16 `json:"weight,omitempty"`
|
||||
// LeafWeight is the bandwidth rate for the device while competing with the cgroup's child cgroups, range is from 10 to 1000, CFQ scheduler only
|
||||
LeafWeight *uint16 `json:"leafWeight,omitempty"`
|
||||
}
|
||||
|
||||
// ThrottleDevice struct holds a `major:minor rate_per_second` pair
|
||||
type ThrottleDevice struct {
|
||||
blockIODevice
|
||||
// Rate is the IO rate limit per cgroup per device
|
||||
Rate *uint64 `json:"rate,omitempty"`
|
||||
}
|
||||
|
||||
// BlockIO for Linux cgroup 'blkio' resource management
|
||||
type BlockIO struct {
|
||||
// Specifies per cgroup weight, range is from 10 to 1000
|
||||
Weight *uint16 `json:"blkioWeight,omitempty"`
|
||||
// Specifies tasks' weight in the given cgroup while competing with the cgroup's child cgroups, range is from 10 to 1000, CFQ scheduler only
|
||||
LeafWeight *uint16 `json:"blkioLeafWeight,omitempty"`
|
||||
// Weight per cgroup per device, can override BlkioWeight
|
||||
WeightDevice []*WeightDevice `json:"blkioWeightDevice,omitempty"`
|
||||
// IO read rate limit per cgroup per device, bytes per second
|
||||
ThrottleReadBpsDevice []*ThrottleDevice `json:"blkioThrottleReadBpsDevice,omitempty"`
|
||||
// IO write rate limit per cgroup per device, bytes per second
|
||||
ThrottleWriteBpsDevice []*ThrottleDevice `json:"blkioThrottleWriteBpsDevice,omitempty"`
|
||||
// IO read rate limit per cgroup per device, IO per second
|
||||
ThrottleReadIOPSDevice []*ThrottleDevice `json:"blkioThrottleReadIOPSDevice,omitempty"`
|
||||
// IO write rate limit per cgroup per device, IO per second
|
||||
ThrottleWriteIOPSDevice []*ThrottleDevice `json:"blkioThrottleWriteIOPSDevice,omitempty"`
|
||||
}
|
||||
|
||||
// Memory for Linux cgroup 'memory' resource management
|
||||
type Memory struct {
|
||||
// Memory limit (in bytes).
|
||||
Limit *uint64 `json:"limit,omitempty"`
|
||||
// Memory reservation or soft_limit (in bytes).
|
||||
Reservation *uint64 `json:"reservation,omitempty"`
|
||||
// Total memory limit (memory + swap).
|
||||
Swap *uint64 `json:"swap,omitempty"`
|
||||
// Kernel memory limit (in bytes).
|
||||
Kernel *uint64 `json:"kernel,omitempty"`
|
||||
// Kernel memory limit for tcp (in bytes)
|
||||
KernelTCP *uint64 `json:"kernelTCP"`
|
||||
// How aggressive the kernel will swap memory pages. Range from 0 to 100.
|
||||
Swappiness *uint64 `json:"swappiness,omitempty"`
|
||||
}
|
||||
|
||||
// CPU for Linux cgroup 'cpu' resource management
|
||||
type CPU struct {
|
||||
// CPU shares (relative weight (ratio) vs. other cgroups with cpu shares).
|
||||
Shares *uint64 `json:"shares,omitempty"`
|
||||
// CPU hardcap limit (in usecs). Allowed cpu time in a given period.
|
||||
Quota *uint64 `json:"quota,omitempty"`
|
||||
// CPU period to be used for hardcapping (in usecs).
|
||||
Period *uint64 `json:"period,omitempty"`
|
||||
// How much time realtime scheduling may use (in usecs).
|
||||
RealtimeRuntime *uint64 `json:"realtimeRuntime,omitempty"`
|
||||
// CPU period to be used for realtime scheduling (in usecs).
|
||||
RealtimePeriod *uint64 `json:"realtimePeriod,omitempty"`
|
||||
// CPUs to use within the cpuset. Default is to use any CPU available.
|
||||
Cpus *string `json:"cpus,omitempty"`
|
||||
// List of memory nodes in the cpuset. Default is to use any available memory node.
|
||||
Mems *string `json:"mems,omitempty"`
|
||||
}
|
||||
|
||||
// Pids for Linux cgroup 'pids' resource management (Linux 4.3)
|
||||
type Pids struct {
|
||||
// Maximum number of PIDs. Default is "no limit".
|
||||
Limit *int64 `json:"limit,omitempty"`
|
||||
}
|
||||
|
||||
// Network identification and priority configuration
|
||||
type Network struct {
|
||||
// Set class identifier for container's network packets
|
||||
// this is actually a string instead of a uint64 to overcome the json
|
||||
// limitation of specifying hex numbers
|
||||
ClassID string `json:"classID"`
|
||||
// Set priority of network traffic for container
|
||||
Priorities []InterfacePriority `json:"priorities"`
|
||||
}
|
||||
|
||||
// Resources has container runtime resource constraints
|
||||
type Resources struct {
|
||||
// DisableOOMKiller disables the OOM killer for out of memory conditions
|
||||
DisableOOMKiller *bool `json:"disableOOMKiller,omitempty"`
|
||||
// Specify an oom_score_adj for the container.
|
||||
OOMScoreAdj *int `json:"oomScoreAdj,omitempty"`
|
||||
// Memory restriction configuration
|
||||
Memory *Memory `json:"memory,omitempty"`
|
||||
// CPU resource restriction configuration
|
||||
CPU *CPU `json:"cpu,omitempty"`
|
||||
// Task resource restriction configuration.
|
||||
Pids *Pids `json:"pids,omitempty"`
|
||||
// BlockIO restriction configuration
|
||||
BlockIO *BlockIO `json:"blockIO,omitempty"`
|
||||
// Hugetlb limit (in bytes)
|
||||
HugepageLimits []HugepageLimit `json:"hugepageLimits,omitempty"`
|
||||
// Network restriction configuration
|
||||
Network *Network `json:"network,omitempty"`
|
||||
}
|
||||
|
||||
// Device represents the information on a Linux special device file
|
||||
type Device struct {
|
||||
// Path to the device.
|
||||
Path string `json:"path"`
|
||||
// Device type, block, char, etc.
|
||||
Type rune `json:"type"`
|
||||
// Major is the device's major number.
|
||||
Major int64 `json:"major"`
|
||||
// Minor is the device's minor number.
|
||||
Minor int64 `json:"minor"`
|
||||
// Cgroup permissions format, rwm.
|
||||
Permissions string `json:"permissions"`
|
||||
// FileMode permission bits for the device.
|
||||
FileMode os.FileMode `json:"fileMode"`
|
||||
// UID of the device.
|
||||
UID uint32 `json:"uid"`
|
||||
// Gid of the device.
|
||||
GID uint32 `json:"gid"`
|
||||
}
|
||||
|
||||
// Seccomp represents syscall restrictions
|
||||
type Seccomp struct {
|
||||
DefaultAction Action `json:"defaultAction"`
|
||||
Architectures []Arch `json:"architectures"`
|
||||
Syscalls []*Syscall `json:"syscalls"`
|
||||
}
|
||||
|
||||
// Arch used for additional architectures
|
||||
type Arch string
|
||||
|
||||
// Additional architectures permitted to be used for system calls
|
||||
// By default only the native architecture of the kernel is permitted
|
||||
const (
|
||||
ArchX86 Arch = "SCMP_ARCH_X86"
|
||||
ArchX86_64 Arch = "SCMP_ARCH_X86_64"
|
||||
ArchX32 Arch = "SCMP_ARCH_X32"
|
||||
ArchARM Arch = "SCMP_ARCH_ARM"
|
||||
ArchAARCH64 Arch = "SCMP_ARCH_AARCH64"
|
||||
ArchMIPS Arch = "SCMP_ARCH_MIPS"
|
||||
ArchMIPS64 Arch = "SCMP_ARCH_MIPS64"
|
||||
ArchMIPS64N32 Arch = "SCMP_ARCH_MIPS64N32"
|
||||
ArchMIPSEL Arch = "SCMP_ARCH_MIPSEL"
|
||||
ArchMIPSEL64 Arch = "SCMP_ARCH_MIPSEL64"
|
||||
ArchMIPSEL64N32 Arch = "SCMP_ARCH_MIPSEL64N32"
|
||||
)
|
||||
|
||||
// Action taken upon Seccomp rule match
|
||||
type Action string
|
||||
|
||||
// Define actions for Seccomp rules
|
||||
const (
|
||||
ActKill Action = "SCMP_ACT_KILL"
|
||||
ActTrap Action = "SCMP_ACT_TRAP"
|
||||
ActErrno Action = "SCMP_ACT_ERRNO"
|
||||
ActTrace Action = "SCMP_ACT_TRACE"
|
||||
ActAllow Action = "SCMP_ACT_ALLOW"
|
||||
)
|
||||
|
||||
// Operator used to match syscall arguments in Seccomp
|
||||
type Operator string
|
||||
|
||||
// Define operators for syscall arguments in Seccomp
|
||||
const (
|
||||
OpNotEqual Operator = "SCMP_CMP_NE"
|
||||
OpLessThan Operator = "SCMP_CMP_LT"
|
||||
OpLessEqual Operator = "SCMP_CMP_LE"
|
||||
OpEqualTo Operator = "SCMP_CMP_EQ"
|
||||
OpGreaterEqual Operator = "SCMP_CMP_GE"
|
||||
OpGreaterThan Operator = "SCMP_CMP_GT"
|
||||
OpMaskedEqual Operator = "SCMP_CMP_MASKED_EQ"
|
||||
)
|
||||
|
||||
// Arg used for matching specific syscall arguments in Seccomp
|
||||
type Arg struct {
|
||||
Index uint `json:"index"`
|
||||
Value uint64 `json:"value"`
|
||||
ValueTwo uint64 `json:"valueTwo"`
|
||||
Op Operator `json:"op"`
|
||||
}
|
||||
|
||||
// Syscall is used to match a syscall in Seccomp
|
||||
type Syscall struct {
|
||||
Name string `json:"name"`
|
||||
Action Action `json:"action"`
|
||||
Args []*Arg `json:"args"`
|
||||
}
|
||||
|
|
@ -0,0 +1,21 @@
|
|||
# Style and conventions
|
||||
|
||||
## Traditionally hex settings should use JSON integers, not JSON strings
|
||||
|
||||
For example, [`"classID": 1048577`][class-id] instead of `"classID": "0x100001"`.
|
||||
The config JSON isn't enough of a UI to be worth jumping through string <-> integer hoops to support an 0x… form ([source][integer-over-hex]).
|
||||
|
||||
## Constant names should keep redundant prefixes
|
||||
|
||||
For example, `CAP_KILL` instead of `KILL` in [**`linux.capabilities`**][capabilities]).
|
||||
The redundancy reduction from removing the namespacing prefix is not useful enough to be worth trimming the upstream identifier ([source][keep-prefix]).
|
||||
|
||||
## Optional settings should have pointer Go types
|
||||
|
||||
So we have a consistent way to identify unset values ([source][optional-pointer]).
|
||||
|
||||
[capabilities]: config-linux.md#capabilities
|
||||
[class-id]: config-linux.md#network
|
||||
[integer-over-hex]: https://github.com/opencontainers/specs/pull/267#discussion_r48360013
|
||||
[keep-prefix]: https://github.com/opencontainers/specs/pull/159#issuecomment-138728337
|
||||
[optional-pointer]: https://github.com/opencontainers/specs/pull/233#discussion_r47829711
|
||||
|
|
@ -6,10 +6,13 @@ const (
|
|||
// VersionMajor is for an API incompatible changes
|
||||
VersionMajor = 0
|
||||
// VersionMinor is for functionality in a backwards-compatible manner
|
||||
VersionMinor = 2
|
||||
VersionMinor = 3
|
||||
// VersionPatch is for backwards-compatible bug fixes
|
||||
VersionPatch = 0
|
||||
|
||||
// VersionDev indicates development branch. Releases will be empty string.
|
||||
VersionDev = ""
|
||||
)
|
||||
|
||||
// Version is the specification version that the package types support.
|
||||
var Version = fmt.Sprintf("%d.%d.%d", VersionMajor, VersionMinor, VersionPatch)
|
||||
var Version = fmt.Sprintf("%d.%d.%d%s", VersionMajor, VersionMinor, VersionPatch, VersionDev)
|
||||
|
|
|
|||
Loading…
Reference in New Issue