Ensure handling for specialization failure in pool manager (#2788)

* Add fixes for failure in specialization
* reduce specialization in progress and remove expired requests from queue when specialization is timed out
* rename markSpecializationFailure and remove logger from the queue
* refactor clean up code in api.go and add test case for queue

Details:

- Cleanup svc waiting for the counter in the pool manager if specialization fails
- Cleanup active requests counter in pool manager if client exists the demand for function service while we have allocated function service
- Consider specialization timeout if pod ready timeout > specialization timeout in waiting for ready pod. We also consider if the request to choosePod is cancelled.
- We ensure if we have requests waiting for service requests but if there is no pod in the specialization we clean up those.
---------

Signed-off-by: Sanket Sudake <sanketsudake@gmail.com>
Co-authored-by: Pranoy Kundu <pranoy1998k@gmail.com>
This commit is contained in:
Sanket Sudake
2023-05-11 21:03:57 +05:30
committed by GitHub
co-authored by Pranoy Kundu
parent 31c81e132e
commit 6c431e4d9b
10 changed files with 177 additions and 2 deletions
+19
View File
@@ -31,8 +31,10 @@ import (
"go.uber.org/zap"
fv1 "github.com/fission/fission/pkg/apis/core/v1"
"github.com/fission/fission/pkg/crd"
ferror "github.com/fission/fission/pkg/error"
"github.com/fission/fission/pkg/executor/client"
"github.com/fission/fission/pkg/executor/fscache"
"github.com/fission/fission/pkg/utils/httpserver"
"github.com/fission/fission/pkg/utils/metrics"
otelUtils "github.com/fission/fission/pkg/utils/otel"
@@ -148,7 +150,24 @@ func (executor *Executor) getServiceForFunction(ctx context.Context, fn *fv1.Fun
respChan: respChan,
}
resp := <-respChan
cleanUp := func(funcSvc *fscache.FuncSvc) {
et, ok := executor.executorTypes[fn.Spec.InvokeStrategy.ExecutionStrategy.ExecutorType]
if !ok {
executor.logger.Error("unknown executor type received in function service", zap.Any("executor", funcSvc.Executor))
return
}
if funcSvc != nil {
et.UnTapService(ctx, crd.CacheKey(funcSvc.Function), resp.funcSvc.Address)
} else {
et.MarkSpecializationFailure(ctx, crd.CacheKey(&fn.ObjectMeta))
}
}
if errors.Is(ctx.Err(), context.Canceled) {
cleanUp(resp.funcSvc)
return "", ferror.MakeError(499, "client leave early in the process of getServiceForFunction")
}
if resp.err != nil {
cleanUp(resp.funcSvc)
return "", resp.err
}
return resp.funcSvc.Address, resp.err