Skip to content
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.

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

Fix indefinite memory and CPU consumption when waiting fleet to be ready #5034

Merged
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
# Kind can be one of:
# - breaking-change: a change to previously-documented behavior
# - deprecation: functionality that is being removed in a later release
# - bug-fix: fixes a problem in a previous version
# - enhancement: extends functionality but does not break or fix existing behavior
# - feature: new functionality
# - known-issue: problems that we are aware of in a given version
# - security: impacts on the security of a product or a user’s deployment.
# - upgrade: important information for someone upgrading from a prior version
# - other: does not fit into any of the other categories
kind: bug-fix

# Change summary; a 80ish characters long description of the change.
summary: Fix indefinite memory and CPU consumption when waiting fleet to be ready

# Long description; in case the summary is not enough to describe the change
# this field accommodate a description without length limits.
# NOTE: This field will be rendered only for breaking-change and known-issue kinds at the moment.
#description:

# Affected component; a word indicating the component this changeset affects.
component:

# PR URL; optional; the PR number that added the changeset.
# If not present is automatically filled by the tooling finding the PR where this changelog fragment has been added.
# NOTE: the tooling supports backports, so it's able to fill the original PR number instead of the backport PR number.
# Please provide it if you are adding a fragment for a different PR.
pr: https://github.com/elastic/elastic-agent/pull/5034

# Issue URL; optional; the GitHub issue related to this changeset (either closes or is part of).
# If not present is automatically filled by the tooling with the issue linked to the PR number.
issue: https://github.com/elastic/elastic-agent/issues/5033
10 changes: 9 additions & 1 deletion internal/pkg/agent/cmd/enroll_cmd.go
Original file line number Diff line number Diff line change
Expand Up @@ -751,8 +751,16 @@ func waitForFleetServer(ctx context.Context, agentSubproc <-chan *os.ProcessStat
msg := ""
msgCount := 0
backExp := expBackoffWithContext(innerCtx, 1*time.Second, maxBackoff)

for {
backExp.Wait()
// if the timeout is reached, no response was sent on `res`, therefore
// send an error
if !backExp.Wait() {
resChan <- waitResult{err: fmt.Errorf(
"timed out waiting for Fleet Server to start after %s",
timeout)}
}

state, err := getDaemonState(innerCtx)
if errors.Is(err, context.Canceled) {
resChan <- waitResult{err: err}
Expand Down
22 changes: 22 additions & 0 deletions internal/pkg/agent/cmd/enroll_cmd_test.go
Original file line number Diff line number Diff line change
Expand Up @@ -577,6 +577,28 @@ func TestDaemonReloadWithBackoff(t *testing.T) {
}
}

func TestWaitForFleetServer_timeout(t *testing.T) {
log, _ := logger.NewTesting("TestWaitForFleetServer_timeout")
timeout := 5 * time.Second
testTimeout := 2 * timeout

ctx, cancel := context.WithTimeout(context.Background(), timeout)
defer cancel()
var got string
var err error
require.Eventuallyf(t,
func() bool {
got, err = waitForFleetServer(ctx, make(chan *os.ProcessState, 1), log, timeout)
return true
},
testTimeout,
500*time.Millisecond,
"waitForFleetServer never returned")

assert.Empty(t, got, "waitForFleetServer should have returned and empty enrollmentToken")
assert.Error(t, err, "waitForFleetServer should have returned an error")
}

func withServer(
m func(t *testing.T) *http.ServeMux,
test func(t *testing.T, host string),
Expand Down
5 changes: 4 additions & 1 deletion internal/pkg/core/backoff/exponential.go
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,10 @@ func (b *ExpBackoff) NextWait() time.Duration {
return nextWait
}

// Wait block until either the timer is completed or channel is done.
// Wait blocks until either the exponential backoff timer is completed or the
// done channel is closed.
// Wait returns true until done is closed. When done is closed, wait returns
// immediately, therefore callers should always check the return value.
func (b *ExpBackoff) Wait() bool {
b.duration = b.NextWait()

Expand Down