mirror of
https://github.com/moby/moby.git
synced 2022-11-09 12:21:53 -05:00
7120976d74
Since the commit d88fe447df ("Add support for sharing /dev/shm/ and
/dev/mqueue between containers") container's /dev/shm is mounted on the
host first, then bind-mounted inside the container. This is done that
way in order to be able to share this container's IPC namespace
(and the /dev/shm mount point) with another container.
Unfortunately, this functionality breaks container checkpoint/restore
(even if IPC is not shared). Since /dev/shm is an external mount, its
contents is not saved by `criu checkpoint`, and so upon restore any
application that tries to access data under /dev/shm is severily
disappointed (which usually results in a fatal crash).
This commit solves the issue by introducing new IPC modes for containers
(in addition to 'host' and 'container:ID'). The new modes are:
- 'shareable': enables sharing this container's IPC with others
(this used to be the implicit default);
- 'private': disables sharing this container's IPC.
In 'private' mode, container's /dev/shm is truly mounted inside the
container, without any bind-mounting from the host, which solves the
issue.
While at it, let's also implement 'none' mode. The motivation, as
eloquently put by Justin Cormack, is:
> I wondered a while back about having a none shm mode, as currently it is
> not possible to have a totally unwriteable container as there is always
> a /dev/shm writeable mount. It is a bit of a niche case (and clearly
> should never be allowed to be daemon default) but it would be trivial to
> add now so maybe we should...
...so here's yet yet another mode:
- 'none': no /dev/shm mount inside the container (though it still
has its own private IPC namespace).
Now, to ultimately solve the abovementioned checkpoint/restore issue, we'd
need to make 'private' the default mode, but unfortunately it breaks the
backward compatibility. So, let's make the default container IPC mode
per-daemon configurable (with the built-in default set to 'shareable'
for now). The default can be changed either via a daemon CLI option
(--default-shm-mode) or a daemon.json configuration file parameter
of the same name.
Note one can only set either 'shareable' or 'private' IPC modes as a
daemon default (i.e. in this context 'host', 'container', or 'none'
do not make much sense).
Some other changes this patch introduces are:
1. A mount for /dev/shm is added to default OCI Linux spec.
2. IpcMode.Valid() is simplified to remove duplicated code that parsed
'container:ID' form. Note the old version used to check that ID does
not contain a semicolon -- this is no longer the case (tests are
modified accordingly). The motivation is we should either do a
proper check for container ID validity, or don't check it at all
(since it is checked in other places anyway). I chose the latter.
3. IpcMode.Container() is modified to not return container ID if the
mode value does not start with "container:", unifying the check to
be the same as in IpcMode.IsContainer().
3. IPC mode unit tests (runconfig/hostconfig_test.go) are modified
to add checks for newly added values.
[v2: addressed review at https://github.com/moby/moby/pull/34087#pullrequestreview-51345997]
[v3: addressed review at https://github.com/moby/moby/pull/34087#pullrequestreview-53902833]
[v4: addressed the case of upgrading from older daemon, in this case
container.HostConfig.IpcMode is unset and this is valid]
[v5: document old and new IpcMode values in api/swagger.yaml]
[v6: add the 'none' mode, changelog entry to docs/api/version-history.md]
Signed-off-by: Kir Kolyshkin <kolyshkin@gmail.com>
88 lines
3.3 KiB
Go
88 lines
3.3 KiB
Go
// +build linux freebsd
|
|
|
|
package config
|
|
|
|
import (
|
|
"fmt"
|
|
|
|
containertypes "github.com/docker/docker/api/types/container"
|
|
"github.com/docker/docker/opts"
|
|
units "github.com/docker/go-units"
|
|
)
|
|
|
|
const (
|
|
// DefaultIpcMode is default for container's IpcMode, if not set otherwise
|
|
DefaultIpcMode = "shareable" // TODO: change to private
|
|
)
|
|
|
|
// Config defines the configuration of a docker daemon.
|
|
// It includes json tags to deserialize configuration from a file
|
|
// using the same names that the flags in the command line uses.
|
|
type Config struct {
|
|
CommonConfig
|
|
|
|
// These fields are common to all unix platforms.
|
|
CommonUnixConfig
|
|
|
|
// Fields below here are platform specific.
|
|
CgroupParent string `json:"cgroup-parent,omitempty"`
|
|
EnableSelinuxSupport bool `json:"selinux-enabled,omitempty"`
|
|
RemappedRoot string `json:"userns-remap,omitempty"`
|
|
Ulimits map[string]*units.Ulimit `json:"default-ulimits,omitempty"`
|
|
CPURealtimePeriod int64 `json:"cpu-rt-period,omitempty"`
|
|
CPURealtimeRuntime int64 `json:"cpu-rt-runtime,omitempty"`
|
|
OOMScoreAdjust int `json:"oom-score-adjust,omitempty"`
|
|
Init bool `json:"init,omitempty"`
|
|
InitPath string `json:"init-path,omitempty"`
|
|
SeccompProfile string `json:"seccomp-profile,omitempty"`
|
|
ShmSize opts.MemBytes `json:"default-shm-size,omitempty"`
|
|
NoNewPrivileges bool `json:"no-new-privileges,omitempty"`
|
|
IpcMode string `json:"default-ipc-mode,omitempty"`
|
|
}
|
|
|
|
// BridgeConfig stores all the bridge driver specific
|
|
// configuration.
|
|
type BridgeConfig struct {
|
|
commonBridgeConfig
|
|
|
|
// These fields are common to all unix platforms.
|
|
commonUnixBridgeConfig
|
|
|
|
// Fields below here are platform specific.
|
|
EnableIPv6 bool `json:"ipv6,omitempty"`
|
|
EnableIPTables bool `json:"iptables,omitempty"`
|
|
EnableIPForward bool `json:"ip-forward,omitempty"`
|
|
EnableIPMasq bool `json:"ip-masq,omitempty"`
|
|
EnableUserlandProxy bool `json:"userland-proxy,omitempty"`
|
|
UserlandProxyPath string `json:"userland-proxy-path,omitempty"`
|
|
FixedCIDRv6 string `json:"fixed-cidr-v6,omitempty"`
|
|
}
|
|
|
|
// IsSwarmCompatible defines if swarm mode can be enabled in this config
|
|
func (conf *Config) IsSwarmCompatible() error {
|
|
if conf.ClusterStore != "" || conf.ClusterAdvertise != "" {
|
|
return fmt.Errorf("--cluster-store and --cluster-advertise daemon configurations are incompatible with swarm mode")
|
|
}
|
|
if conf.LiveRestoreEnabled {
|
|
return fmt.Errorf("--live-restore daemon configuration is incompatible with swarm mode")
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func verifyDefaultIpcMode(mode string) error {
|
|
const hint = "Use \"shareable\" or \"private\"."
|
|
|
|
dm := containertypes.IpcMode(mode)
|
|
if !dm.Valid() {
|
|
return fmt.Errorf("Default IPC mode setting (%v) is invalid. "+hint, dm)
|
|
}
|
|
if dm != "" && !dm.IsPrivate() && !dm.IsShareable() {
|
|
return fmt.Errorf("IPC mode \"%v\" is not supported as default value. "+hint, dm)
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// ValidatePlatformConfig checks if any platform-specific configuration settings are invalid.
|
|
func (conf *Config) ValidatePlatformConfig() error {
|
|
return verifyDefaultIpcMode(conf.IpcMode)
|
|
}
|