ad7355e58b
When claiming a CSI volume, we need to ensure the CSI node plugin is running before we send any CSI RPCs. This extends even to the controller publish RPC because it requires the storage provider's "external node ID" for the client. This primarily impacts client restarts but also is a problem if the node plugin exits (and fingerprints) while the allocation that needs a CSI volume claim is being placed. Unfortunately there's no mapping of volume to plugin ID available in the jobspec, so we don't have enough information to wait on plugins until we either get the volume from the server or retrieve the plugin ID from data we've persisted on the client. If we always require getting the volume from the server before making the claim, a client restart for disconnected clients will cause all the allocations that need CSI volumes to fail. Even while connected, checking in with the server to verify the volume's plugin before trying to make a claim RPC is inherently racy, so we'll leave that case as-is and it will fail the claim if the node plugin needed to support a newly-placed allocation is flapping such that the node fingerprint is changing. This changeset persists a minimum subset of data about the volume and its plugin in the client state DB, and retrieves that data during the CSI hook's prerun to avoid re-claiming and remounting the volume unnecessarily. This changeset also updates the RPC handler to use the external node ID from the claim whenever it is available. Fixes: #13028
143 lines
3.7 KiB
Go
143 lines
3.7 KiB
Go
// Copyright (c) HashiCorp, Inc.
|
|
// SPDX-License-Identifier: MPL-2.0
|
|
|
|
package state
|
|
|
|
import (
|
|
arstate "github.com/hashicorp/nomad/client/allocrunner/state"
|
|
"github.com/hashicorp/nomad/client/allocrunner/taskrunner/state"
|
|
dmstate "github.com/hashicorp/nomad/client/devicemanager/state"
|
|
"github.com/hashicorp/nomad/client/dynamicplugins"
|
|
driverstate "github.com/hashicorp/nomad/client/pluginmanager/drivermanager/state"
|
|
"github.com/hashicorp/nomad/client/serviceregistration/checks"
|
|
cstructs "github.com/hashicorp/nomad/client/structs"
|
|
"github.com/hashicorp/nomad/nomad/structs"
|
|
)
|
|
|
|
// NoopDB implements a StateDB that does not persist any data.
|
|
type NoopDB struct{}
|
|
|
|
func (n NoopDB) Name() string {
|
|
return "noopdb"
|
|
}
|
|
|
|
func (n NoopDB) Upgrade() error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) GetAllAllocations() ([]*structs.Allocation, map[string]error, error) {
|
|
return nil, nil, nil
|
|
}
|
|
|
|
func (n NoopDB) PutAllocation(alloc *structs.Allocation, opts ...WriteOption) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) GetDeploymentStatus(allocID string) (*structs.AllocDeploymentStatus, error) {
|
|
return nil, nil
|
|
}
|
|
|
|
func (n NoopDB) PutDeploymentStatus(allocID string, ds *structs.AllocDeploymentStatus) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) GetNetworkStatus(allocID string) (*structs.AllocNetworkStatus, error) {
|
|
return nil, nil
|
|
}
|
|
|
|
func (n NoopDB) PutNetworkStatus(allocID string, ds *structs.AllocNetworkStatus, opts ...WriteOption) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) PutAcknowledgedState(allocID string, state *arstate.State, opts ...WriteOption) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) GetAcknowledgedState(allocID string) (*arstate.State, error) { return nil, nil }
|
|
|
|
func (n NoopDB) PutAllocVolumes(allocID string, state *arstate.AllocVolumes, opts ...WriteOption) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) GetAllocVolumes(allocID string) (*arstate.AllocVolumes, error) { return nil, nil }
|
|
|
|
func (n NoopDB) GetTaskRunnerState(allocID string, taskName string) (*state.LocalState, *structs.TaskState, error) {
|
|
return nil, nil, nil
|
|
}
|
|
|
|
func (n NoopDB) PutTaskRunnerLocalState(allocID string, taskName string, val *state.LocalState) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) PutTaskState(allocID string, taskName string, state *structs.TaskState) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) DeleteTaskBucket(allocID, taskName string) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) DeleteAllocationBucket(allocID string, opts ...WriteOption) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) PutDevicePluginState(ps *dmstate.PluginState) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) GetDevicePluginState() (*dmstate.PluginState, error) {
|
|
return nil, nil
|
|
}
|
|
|
|
func (n NoopDB) PutDriverPluginState(ps *driverstate.PluginState) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) GetDriverPluginState() (*driverstate.PluginState, error) {
|
|
return nil, nil
|
|
}
|
|
|
|
func (n NoopDB) PutDynamicPluginRegistryState(ps *dynamicplugins.RegistryState) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) GetDynamicPluginRegistryState() (*dynamicplugins.RegistryState, error) {
|
|
return nil, nil
|
|
}
|
|
|
|
func (n NoopDB) PutCheckResult(allocID string, qr *structs.CheckQueryResult) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) GetCheckResults() (checks.ClientResults, error) {
|
|
return nil, nil
|
|
}
|
|
|
|
func (n NoopDB) DeleteCheckResults(allocID string, checkIDs []structs.CheckID) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) PurgeCheckResults(allocID string) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) PutNodeMeta(map[string]*string) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) GetNodeMeta() (map[string]*string, error) {
|
|
return nil, nil
|
|
}
|
|
|
|
func (n NoopDB) PutNodeRegistration(reg *cstructs.NodeRegistration) error {
|
|
return nil
|
|
}
|
|
|
|
func (n NoopDB) GetNodeRegistration() (*cstructs.NodeRegistration, error) {
|
|
return nil, nil
|
|
}
|
|
|
|
func (n NoopDB) Close() error {
|
|
return nil
|
|
}
|