diff --git a/packages/system/linstor/images/piraeus-server/Dockerfile b/packages/system/linstor/images/piraeus-server/Dockerfile index 049a3f47..f93e494f 100644 --- a/packages/system/linstor/images/piraeus-server/Dockerfile +++ b/packages/system/linstor/images/piraeus-server/Dockerfile @@ -61,6 +61,8 @@ RUN test -d .gradlehome && echo ".gradlehome found in tarball" || (echo ".gradle # Build DEB packages from tarball # Override GRADLE_FLAGS to remove --offline flag, allowing Gradle to download missing dependencies RUN sed -i 's/GRADLE_FLAGS = --offline/GRADLE_FLAGS =/' debian/rules || true +# Skip dh_strip_nondeterminism to avoid failures on some JAR files (logback-core) +RUN printf '\noverride_dh_strip_nondeterminism:\n\ttrue\n' >> debian/rules RUN LD_LIBRARY_PATH='' dpkg-buildpackage -rfakeroot -b -uc # Copy built .deb packages to a location accessible from final image diff --git a/packages/system/linstor/images/piraeus-server/patches/README.md b/packages/system/linstor/images/piraeus-server/patches/README.md index 5ee29318..558fdfeb 100644 --- a/packages/system/linstor/images/piraeus-server/patches/README.md +++ b/packages/system/linstor/images/piraeus-server/patches/README.md @@ -8,7 +8,7 @@ Custom patches for piraeus-server (linstor-server) v1.32.3. - Upstream: [#475](https://github.com/LINBIT/linstor-server/pull/475) - **force-metadata-check-on-disk-add.diff** — Create metadata during toggle-disk from diskless to diskful - Upstream: [#474](https://github.com/LINBIT/linstor-server/pull/474) -- **fix-duplicate-tcp-ports.diff** — Prevent duplicate TCP ports after toggle-disk operations - - Upstream: [#476](https://github.com/LINBIT/linstor-server/pull/476) +- **fix-duplicate-tcp-ports.diff** — Preserve TCP ports during toggle-disk to prevent port mismatch between controller and satellites + - Upstream: [#476](https://github.com/LINBIT/linstor-server/pull/476) (superseded by this expanded fix) - **skip-adjust-when-device-inaccessible.diff** — Fix resources stuck in StandAlone after reboot, Unknown state race condition, and encrypted resource deletion - Upstream: [#477](https://github.com/LINBIT/linstor-server/pull/477) diff --git a/packages/system/linstor/images/piraeus-server/patches/fix-duplicate-tcp-ports.diff b/packages/system/linstor/images/piraeus-server/patches/fix-duplicate-tcp-ports.diff index 07cd9eac..b34a2500 100644 --- a/packages/system/linstor/images/piraeus-server/patches/fix-duplicate-tcp-ports.diff +++ b/packages/system/linstor/images/piraeus-server/patches/fix-duplicate-tcp-ports.diff @@ -1,80 +1,131 @@ -From 1250abe99d64a0501795e37d3b6af62410002239 Mon Sep 17 00:00:00 2001 +From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001 From: Andrei Kvapil -Date: Mon, 12 Jan 2026 13:44:46 +0100 -Subject: [PATCH] fix(drbd): prevent duplicate TCP ports after toggle-disk - operations +Date: Fri, 28 Mar 2026 13:00:00 +0100 +Subject: [PATCH] fix(drbd): preserve TCP ports during toggle-disk operations -Remove redundant ensureStackDataExists() call with empty payload from -resetStoragePools() method that was causing TCP port conflicts after -toggle-disk operations. +Prevent TCP port mismatches after toggle-disk operations by preserving +existing TCP ports when rebuilding DrbdRscData. Root Cause: ----------- -The resetStoragePools() method, introduced in 2019 (commit 95cc17d0b8), -calls ensureStackDataExists() with an empty LayerPayload. This worked -correctly when TCP ports were stored at RscDfn level. +During toggle-disk operations, removeLayerData() deletes DrbdRscData +(freeing its TCP ports from the number pool), then ensureStackDataExists() +creates new DrbdRscData. Since the payload has no explicit tcpPorts, +the controller allocates new ports from the pool -- which may differ from +the old ports if other resources claimed them in the meantime. -After the TCP port migration to per-node level (commit f754943463, May -2025), this empty payload results in DrbdRscData being created without -TCP ports assigned. The controller then sends a Pojo with an empty port -Set to satellites. +The controller correctly avoids collisions in its own number pool, but +the satellite may miss the update (e.g. during controller restart or +network issues). When this happens, the satellite keeps the old ports +while peers receive the new ones, causing DRBD connection failures +(StandAlone/Connecting state). -On satellites, when DrbdRscData is initialized with an empty port list, -initPorts() uses preferredNewPortsRef from peer resources. Since -SatelliteDynamicNumberPool.tryAllocate() always returns true (no-op), -any port from preferredNewPortsRef is accepted without conflict checking, -leading to duplicate TCP port assignments. - -Impact: -------- -This regression affects toggle-disk operations, particularly: -- Snapshot creation/restore operations -- Manual toggle-disk operations -- Any operation calling resetStoragePools() - -Symptoms include: -- DRBD resources failing to adjust with "port is also used" errors -- Resources stuck in StandAlone or Connecting states -- Multiple resources on the same node using identical TCP ports +Additionally, remove the redundant ensureStackDataExists() call from +resetStoragePools() -- the caller already invokes it with the correct +payload. Solution: --------- -Remove the ensureStackDataExists() call from resetStoragePools() as it -is redundant. The calling code (e.g., CtrlRscToggleDiskApiCallHandler -line 1071) already invokes ensureStackDataExists() with the correct -payload immediately after resetStoragePools(). +1. Add copyDrbdTcpPortsIfExists() to save existing TCP ports into the + LayerPayload before removeLayerData() deletes them. +2. Call it from copyDrbdNodeIdIfExists() (covers both toggle-disk paths) + and from the needsDeactivate path (shared storage pool case). +3. Remove the redundant ensureStackDataExists() from resetStoragePools(). -This fix ensures: -1. resetStoragePools() only resets storage pool assignments -2. Layer data creation with proper TCP ports happens via the caller's - ensureStackDataExists() with correct payload -3. No DrbdRscData objects are created without TCP port assignments - -Related Issues: ---------------- -Fixes #454 - Duplicate TCP ports after backup/restore operations -Related to user reports of resources stuck in StandAlone after node -reboots when toggle-disk or backup operations were in progress. - -Testing: --------- -Verified that: -- Toggle-disk operations no longer create resources without TCP ports -- Backup/restore operations complete without TCP port conflicts -- Resources maintain unique TCP ports across toggle-disk cycles +This ensures the same TCP ports are reused when DrbdRscData is recreated, +eliminating the window for port mismatch between controller and satellites. Co-Authored-By: Claude Signed-off-by: Andrei Kvapil --- - .../linbit/linstor/layer/resource/CtrlRscLayerDataFactory.java | 2 -- - 1 file changed, 2 deletions(-) + .../controller/CtrlRscToggleDiskApiCallHandler.java | 40 +++++++++++++++++++-- + .../linstor/layer/resource/CtrlRscLayerDataFactory.java | 2 -- + 2 files changed, 38 insertions(+), 4 deletions(-) +diff --git a/controller/src/main/java/com/linbit/linstor/core/apicallhandler/controller/CtrlRscToggleDiskApiCallHandler.java b/controller/src/main/java/com/linbit/linstor/core/apicallhandler/controller/CtrlRscToggleDiskApiCallHandler.java +index ccdb0cee5..b0554c2ec 100644 +--- a/controller/src/main/java/com/linbit/linstor/core/apicallhandler/controller/CtrlRscToggleDiskApiCallHandler.java ++++ b/controller/src/main/java/com/linbit/linstor/core/apicallhandler/controller/CtrlRscToggleDiskApiCallHandler.java +@@ -58,6 +58,7 @@ import com.linbit.linstor.stateflags.StateFlags; + import com.linbit.linstor.storage.StorageException; + import com.linbit.linstor.storage.data.adapter.drbd.DrbdRscData; + import com.linbit.linstor.storage.interfaces.categories.resource.AbsRscLayerObject; ++import com.linbit.linstor.core.types.TcpPortNumber; + import com.linbit.linstor.storage.interfaces.categories.resource.VlmProviderObject; + import com.linbit.linstor.storage.kinds.DeviceLayerKind; + import com.linbit.linstor.storage.kinds.DeviceProviderKind; +@@ -88,6 +89,7 @@ import java.util.LinkedHashMap; + import java.util.List; + import java.util.Map.Entry; + import java.util.Set; ++import java.util.TreeSet; + + import org.reactivestreams.Publisher; + import reactor.core.publisher.Flux; +@@ -587,8 +589,9 @@ public class CtrlRscToggleDiskApiCallHandler implements CtrlSatelliteConnectionL + + /* + * We also have to remove the currently diskless DrbdRscData and free up the node-id as now we must +- * use the shared resource's node-id ++ * use the shared resource's node-id. We still need to preserve TCP ports though. + */ ++ copyDrbdTcpPortsIfExists(rsc, payload); + } + else + { +@@ -726,7 +729,7 @@ public class CtrlRscToggleDiskApiCallHandler implements CtrlSatelliteConnectionL + /** + * Although we need to rebuild the layerData as the layerList might have changed, if we do not + * deactivate (i.e. down) the current resource, we need to make sure that deleting DrbdRscData +- * and recreating a new DrbdRscData ends up with the same node-id as before. ++ * and recreating a new DrbdRscData ends up with the same node-id and TCP ports as before. + */ + private void copyDrbdNodeIdIfExists(Resource rsc, LayerPayload payload) throws ImplementationError + { +@@ -743,6 +746,37 @@ public class CtrlRscToggleDiskApiCallHandler implements CtrlSatelliteConnectionL + DrbdRscData drbdRscData = (DrbdRscData) drbdRscDataSet.iterator().next(); + payload.drbdRsc.nodeId = drbdRscData.getNodeId().value; + } ++ copyDrbdTcpPortsIfExists(rsc, payload); ++ } ++ ++ /** ++ * Preserves existing TCP ports during toggle-disk operations. ++ * ++ * When removeLayerData() deletes DrbdRscData, the TCP ports are freed from the number pool. ++ * If ensureStackDataExists() then allocates different ports, and the satellite misses the update ++ * (e.g. due to controller restart or connectivity issues), the satellite keeps the old ports ++ * while peers get the new ones, causing DRBD connections to fail with StandAlone state. ++ */ ++ private void copyDrbdTcpPortsIfExists(Resource rsc, LayerPayload payload) throws ImplementationError ++ { ++ Set> drbdRscDataSet = LayerRscUtils.getRscDataByLayer( ++ getLayerData(apiCtx, rsc), ++ DeviceLayerKind.DRBD ++ ); ++ if (!drbdRscDataSet.isEmpty()) ++ { ++ DrbdRscData drbdRscData = (DrbdRscData) drbdRscDataSet.iterator().next(); ++ Collection tcpPorts = drbdRscData.getTcpPortList(); ++ if (tcpPorts != null && !tcpPorts.isEmpty()) ++ { ++ Set portInts = new TreeSet<>(); ++ for (TcpPortNumber port : tcpPorts) ++ { ++ portInts.add(port.value); ++ } ++ payload.drbdRsc.tcpPorts = portInts; ++ } ++ } + } + + private List removeLayerData(Resource rscRef) diff --git a/controller/src/main/java/com/linbit/linstor/layer/resource/CtrlRscLayerDataFactory.java b/controller/src/main/java/com/linbit/linstor/layer/resource/CtrlRscLayerDataFactory.java index 3538b380c..4f589145e 100644 --- a/controller/src/main/java/com/linbit/linstor/layer/resource/CtrlRscLayerDataFactory.java +++ b/controller/src/main/java/com/linbit/linstor/layer/resource/CtrlRscLayerDataFactory.java @@ -276,8 +276,6 @@ public class CtrlRscLayerDataFactory - + rscDataToProcess.addAll(rscData.getChildren()); } - @@ -82,6 +133,6 @@ index 3538b380c..4f589145e 100644 } catch (AccessDeniedException exc) { --- +-- 2.39.5 (Apple Git-154)