fix(cluster): gossiped-role predicates compare case-insensitively — a miscased peer no longer un-elects the Primary
This commit is contained in:
@@ -6,6 +6,7 @@
|
||||
@attribute [Authorize(Policy = AdminUiPolicies.AuthenticatedRead)]
|
||||
@rendermode RenderMode.InteractiveServer
|
||||
@using Microsoft.EntityFrameworkCore
|
||||
@using ZB.MOM.WW.OtOpcUa.Cluster
|
||||
@using ZB.MOM.WW.OtOpcUa.Commons.Interfaces
|
||||
@using ZB.MOM.WW.OtOpcUa.Configuration
|
||||
@using ZB.MOM.WW.OtOpcUa.Configuration.Entities
|
||||
@@ -146,7 +147,7 @@ else
|
||||
|
||||
// Union with current Akka driver members so a freshly-joined node that has no
|
||||
// NodeDeploymentState row yet still appears as "waiting".
|
||||
var akkaDrivers = Cluster.MembersWithRole("driver")
|
||||
var akkaDrivers = Cluster.MembersWithRole(RoleParser.Driver)
|
||||
.Select(n => n.Value).ToHashSet(StringComparer.OrdinalIgnoreCase);
|
||||
var allNodes = byNode.Keys.Union(akkaDrivers, StringComparer.OrdinalIgnoreCase)
|
||||
.OrderBy(s => s, StringComparer.OrdinalIgnoreCase).ToList();
|
||||
@@ -156,7 +157,7 @@ else
|
||||
byNode.TryGetValue(nodeId, out var state);
|
||||
return new NodeRow(
|
||||
NodeId: nodeId,
|
||||
Roles: akkaDrivers.Contains(nodeId) ? new[] { "driver" } : Array.Empty<string>(),
|
||||
Roles: akkaDrivers.Contains(nodeId) ? new[] { RoleParser.Driver } : Array.Empty<string>(),
|
||||
Status: state?.Status,
|
||||
StartedAtUtc: state?.StartedAtUtc,
|
||||
AppliedAtUtc: state?.AppliedAtUtc,
|
||||
|
||||
+4
-2
@@ -181,10 +181,12 @@ public sealed class ClusterNodeAddressReconcilerActor : ReceiveActor, IWithTimer
|
||||
public static IReadOnlyList<(string Host, int Port)> FilterOwnClusterDriverMembers(
|
||||
IEnumerable<Member> members, string? ownClusterRole)
|
||||
{
|
||||
// R3-04 (01/C-9): GossipedRolesHave, not ordinal Contains — a peer gossiping a miscased
|
||||
// 'Driver' (rolling-upgrade window) must not read as a phantom RunningNodeHasNoRow finding.
|
||||
var driverMembers = members
|
||||
.Where(m => m.Status == MemberStatus.Up && m.Roles.Contains(DriverRole));
|
||||
.Where(m => m.Status == MemberStatus.Up && RoleParser.GossipedRolesHave(m.Roles, DriverRole));
|
||||
if (!string.IsNullOrEmpty(ownClusterRole))
|
||||
driverMembers = driverMembers.Where(m => m.Roles.Contains(ownClusterRole));
|
||||
driverMembers = driverMembers.Where(m => RoleParser.GossipedRolesHave(m.Roles, ownClusterRole));
|
||||
return driverMembers
|
||||
.Select(m => (Host: m.Address.Host ?? string.Empty, Port: m.Address.Port ?? 0))
|
||||
.Where(a => !string.IsNullOrWhiteSpace(a.Host) && a.Port > 0)
|
||||
|
||||
@@ -3,6 +3,7 @@ using Akka.Actor;
|
||||
using Akka.Cluster;
|
||||
using Microsoft.Extensions.Logging;
|
||||
using ZB.MOM.WW.Audit;
|
||||
using ZB.MOM.WW.OtOpcUa.Cluster;
|
||||
|
||||
namespace ZB.MOM.WW.OtOpcUa.ControlPlane.Redundancy;
|
||||
|
||||
@@ -122,7 +123,9 @@ public sealed class ManualFailoverService : IManualFailoverService
|
||||
}
|
||||
|
||||
private static List<Member> OrderedDrivers(IEnumerable<Member> members) => members
|
||||
.Where(m => m.Status == MemberStatus.Up && m.Roles.Contains(RedundancyStateActor.DriverRole))
|
||||
// R3-04 (01/C-9): GossipedRolesHave, not ordinal Contains — a peer gossiping a miscased
|
||||
// 'Driver' (rolling-upgrade window) must still be a manual-failover candidate.
|
||||
.Where(m => m.Status == MemberStatus.Up && RoleParser.GossipedRolesHave(m.Roles, RedundancyStateActor.DriverRole))
|
||||
.OrderBy(m => m, Member.AgeOrdering)
|
||||
.ToList();
|
||||
}
|
||||
|
||||
@@ -190,7 +190,15 @@ public sealed class RedundancyStateActor : ReceiveActor, IWithTimers
|
||||
if (string.IsNullOrWhiteSpace(host)) continue;
|
||||
|
||||
var isPrimary = driverPrimary is not null && driverPrimary == member.Address;
|
||||
var role = member.Roles.Contains(DriverRole)
|
||||
// R3-04 (01/C-9): GossipedRolesHave, not ordinal Contains — a peer running an older build
|
||||
// can still gossip a miscased 'Driver' during a rolling upgrade, and this list is what
|
||||
// /hosts and /fleet render, so a miscased-but-genuinely-driver member must not read as
|
||||
// Detached. NOTE: this does NOT reach SelectDriverPrimary/driverPrimary above — that
|
||||
// delegates to ClusterActiveNode.OldestUpMember (ZB.MOM.WW.Health.Akka), which matches via
|
||||
// Akka's own ordinal Member.HasRole and is not this repo's to change (see R3-04 execution
|
||||
// notes). So a member gossiping only 'Driver' now classifies Secondary rather than
|
||||
// Detached, but a PAIR that BOTH gossip 'Driver' still elects no Primary.
|
||||
var role = RoleParser.GossipedRolesHave(member.Roles, DriverRole)
|
||||
? (isPrimary ? CommonsRedundancyRole.Primary : CommonsRedundancyRole.Secondary)
|
||||
: CommonsRedundancyRole.Detached;
|
||||
|
||||
|
||||
@@ -5,6 +5,7 @@ using Akka.Event;
|
||||
using Microsoft.EntityFrameworkCore;
|
||||
using Microsoft.Extensions.Logging;
|
||||
using Microsoft.Extensions.Logging.Abstractions;
|
||||
using ZB.MOM.WW.OtOpcUa.Cluster;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Engines;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Interfaces;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Admin;
|
||||
@@ -1608,8 +1609,12 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers, IWithUnboundedS
|
||||
if (_driverMemberCountProvider is not null) return _driverMemberCountProvider();
|
||||
try
|
||||
{
|
||||
// R3-04 (01/C-9): GossipedRolesHave, not ordinal Contains — a peer gossiping a miscased
|
||||
// 'Driver' (rolling-upgrade window) must still count toward the R2-04 primary-gate member
|
||||
// count, or a genuine 2-node pair silently takes the single-node allow branch.
|
||||
return Akka.Cluster.Cluster.Get(Context.System).State.Members
|
||||
.Count(m => m.Status == Akka.Cluster.MemberStatus.Up && m.Roles.Contains(ServiceCollectionExtensions.DriverRole));
|
||||
.Count(m => m.Status == Akka.Cluster.MemberStatus.Up
|
||||
&& RoleParser.GossipedRolesHave(m.Roles, ServiceCollectionExtensions.DriverRole));
|
||||
}
|
||||
catch (Exception)
|
||||
{
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
using Akka.Actor;
|
||||
using Akka.Cluster.Tools.PublishSubscribe;
|
||||
using Akka.Event;
|
||||
using ZB.MOM.WW.OtOpcUa.Cluster;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Alerts;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Redundancy;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Observability;
|
||||
@@ -516,8 +517,11 @@ public sealed class ScriptedAlarmHostActor : ReceiveActor
|
||||
if (_driverMemberCountProvider is not null) return _driverMemberCountProvider();
|
||||
try
|
||||
{
|
||||
// R3-04 (01/C-9): GossipedRolesHave, not ordinal Contains — a peer gossiping a miscased
|
||||
// 'Driver' (rolling-upgrade window) must still count toward the alerts-emit gate.
|
||||
return Akka.Cluster.Cluster.Get(Context.System).State.Members
|
||||
.Count(m => m.Status == Akka.Cluster.MemberStatus.Up && m.Roles.Contains(ServiceCollectionExtensions.DriverRole));
|
||||
.Count(m => m.Status == Akka.Cluster.MemberStatus.Up
|
||||
&& RoleParser.GossipedRolesHave(m.Roles, ServiceCollectionExtensions.DriverRole));
|
||||
}
|
||||
catch (Exception)
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user