Skip to content

Test fix: number of running requests can be one request less when scheduling requests #231

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 27, 2025
Merged

Test fix: number of running requests can be one request less when scheduling requests #231

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 9 additions & 5 deletions pkg/llm-d-inference-sim/worker_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -411,12 +411,14 @@ var _ = Describe("Simulator requests scheduling", Ordered, func() {

// We sent 2500 requests, after about 2.5 seconds
// number of running requests should be 1000
// and the number of waiting requests should be less than 1000
// and the number of waiting requests should be less than 1000.
// Since we are in the middle of requests scheduling,
// the number of running requests can be 999.
runningStr = findMetric(metrics, runningMetric)
Expect(runningStr).NotTo(Equal(""))
running, err = strconv.Atoi(runningStr)
Expect(err).NotTo(HaveOccurred())
Expect(running).To(Equal(1000))
Expect(running).To(Or(Equal(1000), Equal(999)))
waitingStr = findMetric(metrics, waitingMetric)
waiting, err = strconv.Atoi(waitingStr)
Expect(err).NotTo(HaveOccurred())
Expand All @@ -431,13 +433,15 @@ var _ = Describe("Simulator requests scheduling", Ordered, func() {
Expect(err).NotTo(HaveOccurred())
metrics = strings.Split(string(data), "\n")

// number of running requests should be 1000
// and the number of waiting requests should be less than 1000
// The number of running requests should be 1000
// and the number of waiting requests should be less than 1000.
// Since we are in the middle of requests scheduling,
// the number of running requests can be 999.
runningStr = findMetric(metrics, runningMetric)
Expect(runningStr).NotTo(Equal(""))
running, err = strconv.Atoi(runningStr)
Expect(err).NotTo(HaveOccurred())
Expect(running).To(Equal(1000))
Expect(running).To(Or(Equal(1000), Equal(999)))
waitingStr = findMetric(metrics, waitingMetric)
waiting, err = strconv.Atoi(waitingStr)
Expect(err).NotTo(HaveOccurred())
Expand Down