Files
podman/libpod/define/healthchecks.go
Jan Rodák d8eef21167 [v5.2-rhel] Add --health-max-log-count, --health-max-log-size,
--health-log-destination flags

These flags can affect the output of the HealtCheck log. Currently, when a container is configured with HealthCheck, the output from the HealthCheck command is only logged to the container status file, which is accessible via `podman inspect`.
It is also limited to the last five executions and the first 500 characters per execution.

This makes debugging past problems very difficult, since the only information available about the failure of the HealthCheck command is the generic `healthcheck service failed` record.

- The `--health-log-destination` flag sets the destination of the HealthCheck log.
  - `none`: (default behavior) `HealthCheckResults` are stored in overlay containers. (For example: `$runroot/healthcheck.log`)
  - `directory`: creates a log file named `<container-ID>-healthcheck.log` with JSON `HealthCheckResults` in the specified directory.
  - `events_logger`: The log will be written with logging mechanism set by events_loggeri. It also saves the log to a default directory, for performance on a system with a large number of logs.

- The `--health-max-log-count` flag sets the maximum number of attempts in the HealthCheck log file.
  - A value of `0` indicates an infinite number of attempts in the log file.
  - The default value is `5` attempts in the log file.
- The `--health-max-log-size` flag sets the maximum length of the log stored.
  - A value of `0` indicates an infinite log length.
  - The default value is `500` log characters.

Add --health-max-log-count flag

Signed-off-by: Jan Rodák <hony.com@seznam.cz>

Add --health-max-log-size flag

Signed-off-by: Jan Rodák <hony.com@seznam.cz>

Add --health-log-destination flag

Signed-off-by: Jan Rodák <hony.com@seznam.cz>
(cherry picked from commit de856dab99ef8816392972347678fcb49ae57e50)
Signed-off-by: Jan Rodák <hony.com@seznam.cz>
2024-10-09 22:31:01 +02:00

158 lines
5.9 KiB
Go

package define
import (
"fmt"
"strings"
"github.com/containers/image/v5/manifest"
)
const (
// HealthCheckHealthy describes a healthy container
HealthCheckHealthy string = "healthy"
// HealthCheckUnhealthy describes an unhealthy container
HealthCheckUnhealthy string = "unhealthy"
// HealthCheckStarting describes the time between when the container starts
// and the start-period (time allowed for the container to start and application
// to be running) expires.
HealthCheckStarting string = "starting"
// HealthCheckReset describes reset of HealthCheck logs
HealthCheckReset string = "reset"
)
// HealthCheckStatus represents the current state of a container
type HealthCheckStatus int
const (
// HealthCheckSuccess means the health worked
HealthCheckSuccess HealthCheckStatus = iota
// HealthCheckFailure means the health ran and failed
HealthCheckFailure HealthCheckStatus = iota
// HealthCheckContainerStopped means the health check cannot
// be run because the container is stopped
HealthCheckContainerStopped HealthCheckStatus = iota
// HealthCheckContainerNotFound means the container could
// not be found in local store
HealthCheckContainerNotFound HealthCheckStatus = iota
// HealthCheckNotDefined means the container has no health
// check defined in it
HealthCheckNotDefined HealthCheckStatus = iota
// HealthCheckInternalError means some something failed obtaining or running
// a given health check
HealthCheckInternalError HealthCheckStatus = iota
// HealthCheckDefined means the healthcheck was found on the container
HealthCheckDefined HealthCheckStatus = iota
// HealthCheckStartup means the healthcheck was unhealthy, but is still
// either within the startup HC or the startup period of the healthcheck
HealthCheckStartup HealthCheckStatus = iota
)
// Healthcheck defaults. These are used both in the cli as well in
// libpod and were moved from cmd/podman/common
const (
// DefaultHealthCheckInterval default value
DefaultHealthCheckInterval = "30s"
// DefaultHealthCheckRetries default value
DefaultHealthCheckRetries uint = 3
// DefaultHealthCheckStartPeriod default value
DefaultHealthCheckStartPeriod = "0s"
// DefaultHealthCheckTimeout default value
DefaultHealthCheckTimeout = "30s"
// DefaultHealthMaxLogCount default value
DefaultHealthMaxLogCount uint = 5
// DefaultHealthMaxLogSize default value
DefaultHealthMaxLogSize uint = 500
// DefaultHealthCheckLocalDestination default value
DefaultHealthCheckLocalDestination string = "local"
)
const HealthCheckEventsLoggerDestination string = "events_logger"
// HealthConfig.Test options
const (
// HealthConfigTestNone disables healthcheck
HealthConfigTestNone = "NONE"
// HealthConfigTestCmd execs arguments directly
HealthConfigTestCmd = "CMD"
// HealthConfigTestCmdShell runs commands with the system's default shell
HealthConfigTestCmdShell = "CMD-SHELL"
)
// HealthCheckOnFailureAction defines how Podman reacts when a container's health
// status turns unhealthy.
type HealthCheckOnFailureAction int
// Healthcheck on-failure actions.
const (
// HealthCheckOnFailureActionNonce instructs Podman to not react on an unhealthy status.
HealthCheckOnFailureActionNone = iota // Must be first iota for backwards compatibility
// HealthCheckOnFailureActionInvalid denotes an invalid on-failure policy.
HealthCheckOnFailureActionInvalid = iota
// HealthCheckOnFailureActionNonce instructs Podman to kill the container on an unhealthy status.
HealthCheckOnFailureActionKill = iota
// HealthCheckOnFailureActionNonce instructs Podman to restart the container on an unhealthy status.
HealthCheckOnFailureActionRestart = iota
// HealthCheckOnFailureActionNonce instructs Podman to stop the container on an unhealthy status.
HealthCheckOnFailureActionStop = iota
)
// String representations for on-failure actions.
const (
strHealthCheckOnFailureActionNone = "none"
strHealthCheckOnFailureActionInvalid = "invalid"
strHealthCheckOnFailureActionKill = "kill"
strHealthCheckOnFailureActionRestart = "restart"
strHealthCheckOnFailureActionStop = "stop"
)
// SupportedHealthCheckOnFailureActions lists all supported healthcheck restart policies.
var SupportedHealthCheckOnFailureActions = []string{
strHealthCheckOnFailureActionNone,
strHealthCheckOnFailureActionKill,
strHealthCheckOnFailureActionRestart,
strHealthCheckOnFailureActionStop,
}
// String returns the string representation of the HealthCheckOnFailureAction.
func (h HealthCheckOnFailureAction) String() string {
switch h {
case HealthCheckOnFailureActionNone:
return strHealthCheckOnFailureActionNone
case HealthCheckOnFailureActionKill:
return strHealthCheckOnFailureActionKill
case HealthCheckOnFailureActionRestart:
return strHealthCheckOnFailureActionRestart
case HealthCheckOnFailureActionStop:
return strHealthCheckOnFailureActionStop
default:
return strHealthCheckOnFailureActionInvalid
}
}
// ParseHealthCheckOnFailureAction parses the specified string into a HealthCheckOnFailureAction.
// An error is returned for an invalid input.
func ParseHealthCheckOnFailureAction(s string) (HealthCheckOnFailureAction, error) {
switch s {
case "", strHealthCheckOnFailureActionNone:
return HealthCheckOnFailureActionNone, nil
case strHealthCheckOnFailureActionKill:
return HealthCheckOnFailureActionKill, nil
case strHealthCheckOnFailureActionRestart:
return HealthCheckOnFailureActionRestart, nil
case strHealthCheckOnFailureActionStop:
return HealthCheckOnFailureActionStop, nil
default:
err := fmt.Errorf("invalid on-failure action %q for health check: supported actions are %s", s, strings.Join(SupportedHealthCheckOnFailureActions, ","))
return HealthCheckOnFailureActionInvalid, err
}
}
// StartupHealthCheck is the configuration of a startup healthcheck.
type StartupHealthCheck struct {
manifest.Schema2HealthConfig
// Successes are the number of successes required to mark the startup HC
// as passed.
// If set to 0, a single success will mark the HC as passed.
Successes int `json:",omitempty"`
}