open-nomad/nomad/structs/operator.go

265 lines
8.4 KiB
Go
Raw Normal View History

package structs
import (
2020-04-24 14:47:43 +00:00
"fmt"
"time"
"github.com/hashicorp/raft"
)
// RaftServer has information about a server in the Raft configuration.
type RaftServer struct {
// ID is the unique ID for the server. These are currently the same
// as the address, but they will be changed to a real GUID in a future
// release of Nomad.
ID raft.ServerID
// Node is the node name of the server, as known by Nomad, or this
// will be set to "(unknown)" otherwise.
Node string
// Address is the IP:port of the server, used for Raft communications.
Address raft.ServerAddress
// Leader is true if this server is the current cluster leader.
Leader bool
// Voter is true if this server has a vote in the cluster. This might
// be false if the server is staging and still coming online, or if
// it's a non-voting server, which will be added in a future release of
// Nomad.
Voter bool
// RaftProtocol is the version of the Raft protocol spoken by this server.
RaftProtocol string
}
2018-03-11 17:48:04 +00:00
// RaftConfigurationResponse is returned when querying for the current Raft
// configuration.
type RaftConfigurationResponse struct {
// Servers has the list of servers in the Raft configuration.
Servers []*RaftServer
// Index has the Raft index of this configuration.
Index uint64
}
// RaftPeerByAddressRequest is used by the Operator endpoint to apply a Raft
// operation on a specific Raft peer by address in the form of "IP:port".
type RaftPeerByAddressRequest struct {
// Address is the peer to remove, in the form "IP:port".
Address raft.ServerAddress
// WriteRequest holds the Region for this request.
WriteRequest
}
2018-01-16 21:35:32 +00:00
// RaftPeerByIDRequest is used by the Operator endpoint to apply a Raft
// operation on a specific Raft peer by ID.
type RaftPeerByIDRequest struct {
// ID is the peer ID to remove.
ID raft.ServerID
// WriteRequest holds the Region for this request.
WriteRequest
}
// AutopilotSetConfigRequest is used by the Operator endpoint to update the
// current Autopilot configuration of the cluster.
type AutopilotSetConfigRequest struct {
// Datacenter is the target this request is intended for.
Datacenter string
// Config is the new Autopilot configuration to use.
Config AutopilotConfig
// CAS controls whether to use check-and-set semantics for this request.
CAS bool
// WriteRequest holds the ACL token to go along with this request.
WriteRequest
}
// RequestDatacenter returns the datacenter for a given request.
func (op *AutopilotSetConfigRequest) RequestDatacenter() string {
return op.Datacenter
}
// AutopilotConfig is the internal config for the Autopilot mechanism.
type AutopilotConfig struct {
// CleanupDeadServers controls whether to remove dead servers when a new
// server is added to the Raft peers.
CleanupDeadServers bool
// ServerStabilizationTime is the minimum amount of time a server must be
// in a stable, healthy state before it can be added to the cluster. Only
// applicable with Raft protocol version 3 or higher.
ServerStabilizationTime time.Duration
// LastContactThreshold is the limit on the amount of time a server can go
// without leader contact before being considered unhealthy.
LastContactThreshold time.Duration
// MaxTrailingLogs is the amount of entries in the Raft Log that a server can
// be behind before being considered unhealthy.
MaxTrailingLogs uint64
2020-02-16 21:23:20 +00:00
// MinQuorum sets the minimum number of servers required in a cluster
// before autopilot can prune dead servers.
MinQuorum uint
// (Enterprise-only) EnableRedundancyZones specifies whether to enable redundancy zones.
EnableRedundancyZones bool
// (Enterprise-only) DisableUpgradeMigration will disable Autopilot's upgrade migration
// strategy of waiting until enough newer-versioned servers have been added to the
// cluster before promoting them to voters.
DisableUpgradeMigration bool
// (Enterprise-only) EnableCustomUpgrades specifies whether to enable using custom
// upgrade versions when performing migrations.
EnableCustomUpgrades bool
// CreateIndex/ModifyIndex store the create/modify indexes of this configuration.
CreateIndex uint64
ModifyIndex uint64
}
// SchedulerAlgorithm is an enum string that encapsulates the valid options for a
// SchedulerConfiguration stanza's SchedulerAlgorithm. These modes will allow the
// scheduler to be user-selectable.
type SchedulerAlgorithm string
const (
// SchedulerAlgorithmBinpack indicates that the scheduler should spread
// allocations as evenly as possible over the available hardware.
2020-04-24 14:47:43 +00:00
SchedulerAlgorithmBinpack SchedulerAlgorithm = "binpack"
// SchedulerAlgorithmSpread indicates that the scheduler should spread
// allocations as evenly as possible over the available hardware.
2020-04-24 14:47:43 +00:00
SchedulerAlgorithmSpread SchedulerAlgorithm = "spread"
)
// SchedulerConfiguration is the config for controlling scheduler behavior
type SchedulerConfiguration struct {
// SchedulerAlgorithm lets you select between available scheduling algorithms.
2020-04-24 14:47:43 +00:00
SchedulerAlgorithm SchedulerAlgorithm `hcl:"scheduler_algorithm"`
// PreemptionConfig specifies whether to enable eviction of lower
// priority jobs to place higher priority jobs.
PreemptionConfig PreemptionConfig `hcl:"preemption_config"`
Allow configuring memory oversubscription (#10466) Cluster operators want to have better control over memory oversubscription and may want to enable/disable it based on their experience. This PR adds a scheduler configuration field to control memory oversubscription. It's additional field that can be set in the [API via Scheduler Config](https://www.nomadproject.io/api-docs/operator/scheduler), or [the agent server config](https://www.nomadproject.io/docs/configuration/server#configuring-scheduler-config). I opted to have the memory oversubscription be an opt-in, but happy to change it. To enable it, operators should call the API with: ```json { "MemoryOversubscriptionEnabled": true } ``` If memory oversubscription is disabled, submitting jobs specifying `memory_max` will get a "Memory oversubscription is not enabled" warnings, but the jobs will be accepted without them accessing the additional memory. The warning message is like: ``` $ nomad job run /tmp/j Job Warnings: 1 warning(s): * Memory oversubscription is not enabled; Task cache.redis memory_max value will be ignored ==> Monitoring evaluation "7c444157" Evaluation triggered by job "example" ==> Monitoring evaluation "7c444157" Evaluation within deployment: "9d826f13" Allocation "aa5c3cad" created: node "9272088e", group "cache" Evaluation status changed: "pending" -> "complete" ==> Evaluation "7c444157" finished with status "complete" # then you can examine the Alloc AllocatedResources to validate whether the task is allowed to exceed memory: $ nomad alloc status -json aa5c3cad | jq '.AllocatedResources.Tasks["redis"].Memory' { "MemoryMB": 256, "MemoryMaxMB": 0 } ```
2021-04-30 02:09:56 +00:00
MemoryOversubscriptionEnabled bool `hcl:"memory_oversubscription_enabled"`
// CreateIndex/ModifyIndex store the create/modify indexes of this configuration.
CreateIndex uint64
ModifyIndex uint64
}
2020-04-24 14:47:43 +00:00
func (s *SchedulerConfiguration) EffectiveSchedulerAlgorithm() SchedulerAlgorithm {
if s == nil || s.SchedulerAlgorithm == "" {
return SchedulerAlgorithmBinpack
}
return s.SchedulerAlgorithm
}
func (s *SchedulerConfiguration) Canonicalize() {
if s != nil && s.SchedulerAlgorithm == "" {
s.SchedulerAlgorithm = SchedulerAlgorithmBinpack
}
}
2020-04-24 14:47:43 +00:00
func (s *SchedulerConfiguration) Validate() error {
if s == nil {
return nil
}
switch s.SchedulerAlgorithm {
case "", SchedulerAlgorithmBinpack, SchedulerAlgorithmSpread:
default:
return fmt.Errorf("invalid scheduler algorithm: %v", s.SchedulerAlgorithm)
}
return nil
}
// SchedulerConfigurationResponse is the response object that wraps SchedulerConfiguration
type SchedulerConfigurationResponse struct {
// SchedulerConfig contains scheduler config options
SchedulerConfig *SchedulerConfiguration
QueryMeta
}
// SchedulerSetConfigurationResponse is the response object used
// when updating scheduler configuration
type SchedulerSetConfigurationResponse struct {
// Updated returns whether the config was actually updated
// Only set when the request uses CAS
Updated bool
WriteMeta
}
// PreemptionConfig specifies whether preemption is enabled based on scheduler type
type PreemptionConfig struct {
// SystemSchedulerEnabled specifies if preemption is enabled for system jobs
SystemSchedulerEnabled bool `hcl:"system_scheduler_enabled"`
// SysBatchSchedulerEnabled specifies if preemption is enabled for sysbatch jobs
SysBatchSchedulerEnabled bool `hcl:"sysbatch_scheduler_enabled"`
// BatchSchedulerEnabled specifies if preemption is enabled for batch jobs
BatchSchedulerEnabled bool `hcl:"batch_scheduler_enabled"`
// ServiceSchedulerEnabled specifies if preemption is enabled for service jobs
ServiceSchedulerEnabled bool `hcl:"service_scheduler_enabled"`
}
// SchedulerSetConfigRequest is used by the Operator endpoint to update the
// current Scheduler configuration of the cluster.
type SchedulerSetConfigRequest struct {
// Config is the new Scheduler configuration to use.
Config SchedulerConfiguration
// CAS controls whether to use check-and-set semantics for this request.
CAS bool
// WriteRequest holds the ACL token to go along with this request.
WriteRequest
}
2020-05-21 14:05:04 +00:00
// SnapshotSaveRequest is used by the Operator endpoint to get a Raft snapshot
type SnapshotSaveRequest struct {
QueryOptions
}
// SnapshotSaveResponse is the header for the streaming snapshot endpoint,
// and followed by the snapshot file content.
type SnapshotSaveResponse struct {
// SnapshotChecksum returns the checksum of snapshot file in the format
// `<algo>=<base64>` (e.g. `sha-256=...`)
SnapshotChecksum string
// ErrorCode is an http error code if an error is found, e.g. 403 for permission errors
ErrorCode int `codec:",omitempty"`
// ErrorMsg is the error message if an error is found, e.g. "Permission Denied"
ErrorMsg string `codec:",omitempty"`
QueryMeta
}
2020-06-04 21:14:43 +00:00
type SnapshotRestoreRequest struct {
WriteRequest
}
type SnapshotRestoreResponse struct {
ErrorCode int `codec:",omitempty"`
ErrorMsg string `codec:",omitempty"`
QueryMeta
}