A newdeploy backend which uses new deployment to serve requests. This is the second phase of #193 and builds on top of changes in #384 . * Executor layer added on top of pool manager * Removed the external server for executor * Minor changes to keep existing semantics as much possible * Separating the executor vs. poolmgr backend functionality and associated data members * Executor logic separated from Poolmgr backend completely, placeholder for new backend * Changed references to poolmgr in tests * Moved poolmgr to it's package, as a side effect moved Cache to its's package (was causing cyclical dependency) and had to make some data structures exposed outside package * Rebased from master and changed references to tpr -> crd * Executor layer added on top of pool manager * Executor logic separated from Poolmgr backend completely, placeholder for new backend * Changed podName to a generic objectReference in fscache (#391) Changed podName to a generic objectReference in function service cache implementation. * Moved poolmgr to it's package, as a side effect moved Cache to its's package (was causing cyclical dependency) and had to make some data structures exposed outside package * Rebased from master and changed references to tpr -> crd * Merged from master with latest changes * Executor layer added on top of pool manager * Removed the external server for executor * Minor changes to keep existing semantics as much possible * Separating the executor vs. poolmgr backend functionality and associated data members * Executor logic separated from Poolmgr backend completely, placeholder for new backend * Changed references to poolmgr in tests * update compiling.md to use helm * Compile instructions: changed pullPolicy to IfNotPresent (#378) Containers will get stuck in ErrImagePull/ImagePullBackOff state otherwise * Moved poolmgr to it's package, as a side effect moved Cache to its's package (was causing cyclical dependency) and had to make some data structures exposed outside package * Fetcher called when pod is created for newDeploy backend but also supports older way, this is WIP and still needs pod specialization and creating & exposing a service so the URL can be hit by end user * WIP Specializing the POD as part of startup along with fetching * Working specialization of a new deployment. Needs some work on caching, cleanup etc. * Switched to service based address instead of POD address * Minor formating issue fixed * Added logging to pods and a readiness check, the readiness check is flaky though ATM * Fixed some rebase issues that were failing build * Better names for K8S objects and methods * Switched usage of FuncSvc in backends from pod to api.ObjectReference * Adding retry to fetcher request, for now just using default retry client which might need tweaking in future * Switching to plain old retry, some issue in getting retryablehttp with glide import * Removed stale executor service & deployment from previous merge * Addressed review comments, still testing some areas * Added types in FunctionSpec * Resolved conflicts due to merge from executor_abstraction branch * Added backend type on EnvironmentSpec along with operations for create/list/update, the pools are created/destroyed based on change in backend type * Backend from types and a minor err return issue fixed * Draft version of CPU and memory parameters added to environment * Added resourceReq to newDeploy, though it has some issues * Issue with resourceName fixed, now newdeploy pods also pick up resources from the environment config * Adding scale params, removing validation on CPU params for now * Fixed a formatting issue * Checking if slight more delay helps in the test which is currently failing for internal routes * The resourceList newly added in Env can not be compared by compiler, hence must use breakdown comparison instead * Added strategy selection on client side * Added caching, informers, delete operations for newdeploy backend functions * Deleted a stale directory * A simple HPA based on scale parameters, testing still WIP * Fixed a small issue in delete function, added HPA delete too when deleting a function * Previous merge missed the pkg flag for update fn command somehow, fixed that * Fixed comments from review * Changed poolmgr cleanup to be generic cleanup and moved to executor, added instanceID labels to newdeploy so that cleanup works * Moved instanceIdLabel to types to avoid cyclic dependency * More review fixes * Tweaking sleep to see results * If user does not provide poolsize, then it should not default to zero * Switched to naming convention for now, fixed default poolsize if not provided * Changed error return behaviour in delete fn, also changed cleanup to look based on obj type though support for additional type will need more work * Changed check location so avoid false logging * Test for newdeploy backend * Adding tests for poolmgr backend * Fixed an issue with glide dependency version, already fixed in master * Added instanceId for NewDeploy, Initial cleanup now cleans older objects of newdeploy backend, removed eagercreate flag and instead using minScale to drive eager creation * Moved cleanup to executor layer with cleanup for newDeploy backend, changes to use the new Cache impl * Cleaning up pod & rs along with deployment for newdeploy backend * Enhanced fn and env listing to show min/maxscale and resuorces respectively * Added conditional heapster deployment and fixed a small issue with resources for fetcher container in function pod * Addressed review comments from previous change * Addressed some more review comments - majorly create only on NotFoundError * Added TargetCPU as an input for scaling * Bumped target CPU to be greater than 0 and added a default value * Min replicas should be 1 even if the minScale is 0 when creating deployment * Changed name from 'backend' to executorType, added additional test for minscale 0 case, changed TargetCPU to TargetCPUPercent
181 lines
4.7 KiB
Go
181 lines
4.7 KiB
Go
/*
|
|
Copyright 2016 The Fission Authors.
|
|
|
|
Licensed under the Apache License, Version 2.0 (the "License");
|
|
you may not use this file except in compliance with the License.
|
|
You may obtain a copy of the License at
|
|
|
|
http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
Unless required by applicable law or agreed to in writing, software
|
|
distributed under the License is distributed on an "AS IS" BASIS,
|
|
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
See the License for the specific language governing permissions and
|
|
limitations under the License.
|
|
*/
|
|
|
|
package poolmgr
|
|
|
|
import (
|
|
"log"
|
|
"time"
|
|
|
|
metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
|
|
"k8s.io/client-go/kubernetes"
|
|
|
|
"github.com/fission/fission"
|
|
"github.com/fission/fission/crd"
|
|
"github.com/fission/fission/executor/fscache"
|
|
)
|
|
|
|
type requestType int
|
|
|
|
const (
|
|
GET_POOL requestType = iota
|
|
CLEANUP_POOLS
|
|
)
|
|
|
|
type (
|
|
GenericPoolManager struct {
|
|
pools map[string]*GenericPool
|
|
kubernetesClient *kubernetes.Clientset
|
|
namespace string
|
|
|
|
fissionClient *crd.FissionClient
|
|
fsCache *fscache.FunctionServiceCache
|
|
instanceId string
|
|
requestChannel chan *request
|
|
}
|
|
request struct {
|
|
requestType
|
|
env *crd.Environment
|
|
envList []crd.Environment
|
|
responseChannel chan *response
|
|
}
|
|
response struct {
|
|
error
|
|
pool *GenericPool
|
|
}
|
|
)
|
|
|
|
func MakeGenericPoolManager(
|
|
fissionClient *crd.FissionClient,
|
|
kubernetesClient *kubernetes.Clientset,
|
|
fissionNamespace string,
|
|
functionNamespace string,
|
|
fsCache *fscache.FunctionServiceCache,
|
|
instanceId string) *GenericPoolManager {
|
|
|
|
gpm := &GenericPoolManager{
|
|
pools: make(map[string]*GenericPool),
|
|
kubernetesClient: kubernetesClient,
|
|
namespace: functionNamespace,
|
|
fissionClient: fissionClient,
|
|
fsCache: fsCache,
|
|
instanceId: instanceId,
|
|
requestChannel: make(chan *request),
|
|
}
|
|
go gpm.service()
|
|
go gpm.eagerPoolCreator()
|
|
|
|
return gpm
|
|
}
|
|
|
|
func (gpm *GenericPoolManager) service() {
|
|
for {
|
|
req := <-gpm.requestChannel
|
|
switch req.requestType {
|
|
case GET_POOL:
|
|
var err error
|
|
pool, ok := gpm.pools[crd.CacheKey(&req.env.Metadata)]
|
|
if !ok {
|
|
var poolSize = int32(req.env.Spec.Poolsize)
|
|
switch req.env.Spec.AllowedFunctionsPerContainer {
|
|
case fission.AllowedFunctionsPerContainerInfinite:
|
|
poolSize = 1
|
|
}
|
|
|
|
pool, err = MakeGenericPool(
|
|
gpm.fissionClient, gpm.kubernetesClient, req.env, poolSize,
|
|
gpm.namespace, gpm.fsCache, gpm.instanceId)
|
|
if err != nil {
|
|
req.responseChannel <- &response{error: err}
|
|
continue
|
|
}
|
|
gpm.pools[crd.CacheKey(&req.env.Metadata)] = pool
|
|
}
|
|
req.responseChannel <- &response{pool: pool}
|
|
case CLEANUP_POOLS:
|
|
latestEnvSet := make(map[string]bool)
|
|
latestEnvPoolsize := make(map[string]int)
|
|
for _, env := range req.envList {
|
|
latestEnvSet[crd.CacheKey(&env.Metadata)] = true
|
|
latestEnvPoolsize[crd.CacheKey(&env.Metadata)] = env.Spec.Poolsize
|
|
}
|
|
for key, pool := range gpm.pools {
|
|
_, ok := latestEnvSet[key]
|
|
poolsize := latestEnvPoolsize[key]
|
|
if !ok || poolsize == 0 {
|
|
// Env no longer exists or pool size changed to zero
|
|
|
|
log.Printf("Destroying generic pool for environment [%v]", key)
|
|
delete(gpm.pools, key)
|
|
|
|
// and delete the pool asynchronously.
|
|
go pool.destroy()
|
|
}
|
|
}
|
|
// no response, caller doesn't wait
|
|
}
|
|
}
|
|
}
|
|
|
|
func (gpm *GenericPoolManager) GetPool(env *crd.Environment) (*GenericPool, error) {
|
|
c := make(chan *response)
|
|
gpm.requestChannel <- &request{
|
|
requestType: GET_POOL,
|
|
env: env,
|
|
responseChannel: c,
|
|
}
|
|
resp := <-c
|
|
return resp.pool, resp.error
|
|
}
|
|
|
|
func (gpm *GenericPoolManager) CleanupPools(envs []crd.Environment) {
|
|
gpm.requestChannel <- &request{
|
|
requestType: CLEANUP_POOLS,
|
|
envList: envs,
|
|
}
|
|
}
|
|
|
|
func (gpm *GenericPoolManager) eagerPoolCreator() {
|
|
pollSleep := time.Duration(2 * time.Second)
|
|
for {
|
|
time.Sleep(pollSleep)
|
|
|
|
// get list of envs from controller
|
|
envs, err := gpm.fissionClient.Environments(metav1.NamespaceAll).List(metav1.ListOptions{})
|
|
if err != nil {
|
|
log.Fatalf("Failed to get environment list: %v", err)
|
|
}
|
|
|
|
// Create pools for all envs. TODO: we should make this a bit less eager, only
|
|
// creating pools for envs that are actually used by functions. Also we might want
|
|
// to keep these eagerly created pools smaller than the ones created when there are
|
|
// actual function calls.
|
|
for i := range envs.Items {
|
|
env := envs.Items[i]
|
|
// Create pool only if poolsize greater than zero
|
|
if env.Spec.Poolsize > 0 {
|
|
_, err := gpm.GetPool(&envs.Items[i])
|
|
if err != nil {
|
|
log.Printf("eager-create pool failed: %v", err)
|
|
}
|
|
}
|
|
}
|
|
|
|
// Clean up pools whose env was deleted
|
|
gpm.CleanupPools(envs.Items)
|
|
}
|
|
}
|