Skip to content

transition to oos from oos for load balanced multinode rpc #66

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
yashnevatia merged 3 commits into from
Jul 29, 2025
Merged

transition to oos from oos for load balanced multinode rpc #66

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
890eeb8
transition to oos from oos
yashnevatia Jul 29, 2025
d6abe66
review
yashnevatia Jul 29, 2025
d128bc7
test
yashnevatia Jul 29, 2025
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
2 changes: 1 addition & 1 deletion multinode/node_fsm.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -239,7 +239,7 @@ func (n *node[CHAIN_ID, HEAD, RPC]) transitionToOutOfSync(fn func()) {
return
}
switch n.state {
case nodeStateAlive:
case nodeStateAlive, nodeStateOutOfSync:
n.rpc.Close()
n.state = nodeStateOutOfSync
default:
Expand Down
2 changes: 1 addition & 1 deletion multinode/node_fsm_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,7 @@ func TestUnit_Node_StateTransitions(t *testing.T) {
})
t.Run("transitionToOutOfSync", func(t *testing.T) {
const destinationState = nodeStateOutOfSync
allowedStates := []nodeState{nodeStateAlive}
allowedStates := []nodeState{nodeStateAlive, nodeStateOutOfSync}
rpc := newMockRPCClient[ID, Head](t)
rpc.On("Close")
testTransition(t, rpc, testNode.transitionToOutOfSync, destinationState, allowedStates...)
Expand Down
3 changes: 2 additions & 1 deletion multinode/node_lifecycle.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -461,7 +461,8 @@ func (n *node[CHAIN_ID, HEAD, RPC]) outOfSyncLoop(syncIssues syncStatus) {
if n.poolInfoProvider != nil {
if l, _ := n.poolInfoProvider.LatestChainInfo(); l < 1 {
if n.isLoadBalancedRPC {
n.declareUnreachable()
// in case all rpcs behind a load balanced rpc are out of sync, we need to declare out of sync to prevent false transition to alive
n.declareOutOfSync(syncIssues)
return
}
lggr.Criticalw("RPC endpoint is still out of sync, but there are no other available nodes. This RPC node will be forcibly moved back into the live pool in a degraded state", "syncIssues", syncIssues)
Expand Down
4 changes: 3 additions & 1 deletion multinode/node_lifecycle_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -227,7 +227,9 @@ func TestUnit_NodeLifecycle_aliveLoop(t *testing.T) {
rpc.On("ClientVersion", mock.Anything).Return("", pollError)
node.declareAlive()
tests.AssertLogEventually(t, observedLogs, fmt.Sprintf("RPC endpoint failed to respond to %d consecutive polls", pollFailureThreshold))
assert.Equal(t, nodeStateUnreachable, node.State())
tests.AssertEventually(t, func() bool {
return node.State() == nodeStateUnreachable
})
})
t.Run("when behind more than SyncThreshold, transitions to out of sync", func(t *testing.T) {
t.Parallel()
Expand Down
Loading