Compare commits
No commits in common. "c8" and "c8-beta" have entirely different histories.
@ -1,31 +0,0 @@
|
||||
From 8dc0d9b43343919edf4f4011ceecfd6b6765b4a4 Mon Sep 17 00:00:00 2001
|
||||
From: Ken Gaillot <kgaillot@redhat.com>
|
||||
Date: Wed, 8 May 2024 11:18:50 -0500
|
||||
Subject: [PATCH] Low: libcib: avoid memory leak in async calls
|
||||
|
||||
Never in a release
|
||||
---
|
||||
lib/cib/cib_native.c | 7 ++++---
|
||||
1 file changed, 4 insertions(+), 3 deletions(-)
|
||||
|
||||
diff --git a/lib/cib/cib_native.c b/lib/cib/cib_native.c
|
||||
index 0e502155bc..b014223112 100644
|
||||
--- a/lib/cib/cib_native.c
|
||||
+++ b/lib/cib/cib_native.c
|
||||
@@ -94,9 +94,10 @@ cib_native_perform_op_delegate(cib_t *cib, const char *op, const char *host,
|
||||
|
||||
if (!(call_options & cib_sync_call)) {
|
||||
crm_trace("Async call, returning %d", cib->call_id);
|
||||
- CRM_CHECK(cib->call_id != 0, return -ENOMSG);
|
||||
- free_xml(op_reply);
|
||||
- return cib->call_id;
|
||||
+ CRM_CHECK(cib->call_id != 0,
|
||||
+ rc = -ENOMSG; goto done);
|
||||
+ rc = cib->call_id;
|
||||
+ goto done;
|
||||
}
|
||||
|
||||
rc = pcmk_ok;
|
||||
--
|
||||
2.41.0
|
||||
|
@ -1,121 +0,0 @@
|
||||
From d7c233090057d4f660fa458a2ff97896b15ea951 Mon Sep 17 00:00:00 2001
|
||||
From: Reid Wahl <nrwahl@protonmail.com>
|
||||
Date: Thu, 11 Jul 2024 12:43:49 -0700
|
||||
Subject: [PATCH] Refactor: various: Don't set cluster-layer node ID as XML ID
|
||||
|
||||
Currently, we call the pcmk__xe_set_id() function using a stringified
|
||||
version of the numeric cluster-layer node ID. However, pcmk__xe_set_id()
|
||||
tries to sanitize its input to a valid XML ID. An XML ID cannot begin
|
||||
with a digit.
|
||||
|
||||
crm_xml_set_id() does not sanitize comprehensively, and in particular,
|
||||
it does not care whether its argument begins with a digit. So the
|
||||
current code doesn't cause a problem.
|
||||
|
||||
Still, as a best practice, set the PCMK_XA_ID attribute using
|
||||
crm_xml_add_ll() instead.
|
||||
|
||||
Ref T848
|
||||
|
||||
Signed-off-by: Reid Wahl <nrwahl@protonmail.com>
|
||||
---
|
||||
daemons/controld/controld_messages.c | 6 +++++-
|
||||
lib/cluster/corosync.c | 2 +-
|
||||
lib/common/ipc_client.c | 2 +-
|
||||
lib/common/ipc_controld.c | 9 ++++++---
|
||||
tools/crm_node.c | 4 ++--
|
||||
5 files changed, 15 insertions(+), 8 deletions(-)
|
||||
|
||||
diff --git a/daemons/controld/controld_messages.c b/daemons/controld/controld_messages.c
|
||||
index bd5237e..0b0f25b 100644
|
||||
--- a/daemons/controld/controld_messages.c
|
||||
+++ b/daemons/controld/controld_messages.c
|
||||
@@ -893,7 +893,11 @@ handle_node_info_request(const xmlNode *msg)
|
||||
pcmk_is_set(controld_globals.flags,
|
||||
controld_has_quorum));
|
||||
|
||||
- // Check whether client requested node info by ID and/or name
|
||||
+ /* Check whether client requested node info by ID and/or name
|
||||
+ *
|
||||
+ * @TODO A Corosync-layer node ID is of type uint32_t. We should be able to
|
||||
+ * handle legitimate node IDs greater than INT_MAX, but currently we do not.
|
||||
+ */
|
||||
crm_element_value_int(msg, XML_ATTR_ID, &node_id);
|
||||
if (node_id < 0) {
|
||||
node_id = 0;
|
||||
diff --git a/lib/cluster/corosync.c b/lib/cluster/corosync.c
|
||||
index 374250f..fc33cce 100644
|
||||
--- a/lib/cluster/corosync.c
|
||||
+++ b/lib/cluster/corosync.c
|
||||
@@ -650,7 +650,7 @@ pcmk__corosync_add_nodes(xmlNode *xml_parent)
|
||||
if (xml_parent) {
|
||||
xmlNode *node = create_xml_node(xml_parent, XML_CIB_TAG_NODE);
|
||||
|
||||
- crm_xml_set_id(node, "%u", nodeid);
|
||||
+ crm_xml_add_ll(node, XML_ATTR_ID, (long long) nodeid);
|
||||
crm_xml_add(node, XML_ATTR_UNAME, name);
|
||||
}
|
||||
}
|
||||
diff --git a/lib/common/ipc_client.c b/lib/common/ipc_client.c
|
||||
index 5e64e23..7696a69 100644
|
||||
--- a/lib/common/ipc_client.c
|
||||
+++ b/lib/common/ipc_client.c
|
||||
@@ -769,7 +769,7 @@ create_purge_node_request(const pcmk_ipc_api_t *api, const char *node_name,
|
||||
request = create_request(CRM_OP_RM_NODE_CACHE, NULL, NULL,
|
||||
pcmk_ipc_name(api, false), client, NULL);
|
||||
if (nodeid > 0) {
|
||||
- crm_xml_set_id(request, "%lu", (unsigned long) nodeid);
|
||||
+ crm_xml_add_ll(request, XML_ATTR_ID, (unsigned long) nodeid);
|
||||
}
|
||||
crm_xml_add(request, XML_ATTR_UNAME, node_name);
|
||||
break;
|
||||
diff --git a/lib/common/ipc_controld.c b/lib/common/ipc_controld.c
|
||||
index 8e2016e..e4284f5 100644
|
||||
--- a/lib/common/ipc_controld.c
|
||||
+++ b/lib/common/ipc_controld.c
|
||||
@@ -9,9 +9,12 @@
|
||||
|
||||
#include <crm_internal.h>
|
||||
|
||||
-#include <stdio.h>
|
||||
-#include <stdbool.h>
|
||||
#include <errno.h>
|
||||
+#include <inttypes.h> // PRIu32
|
||||
+#include <stdbool.h>
|
||||
+#include <stdint.h> // uint32_t
|
||||
+#include <stdio.h>
|
||||
+
|
||||
#include <libxml/tree.h>
|
||||
|
||||
#include <crm/crm.h>
|
||||
@@ -412,7 +415,7 @@ pcmk_controld_api_node_info(pcmk_ipc_api_t *api, uint32_t nodeid)
|
||||
return EINVAL;
|
||||
}
|
||||
if (nodeid > 0) {
|
||||
- crm_xml_set_id(request, "%lu", (unsigned long) nodeid);
|
||||
+ crm_xml_add_ll(request, XML_ATTR_ID, (unsigned long) nodeid);
|
||||
}
|
||||
|
||||
rc = send_controller_request(api, request, true);
|
||||
diff --git a/tools/crm_node.c b/tools/crm_node.c
|
||||
index 1e7ce6c..ad8c459 100644
|
||||
--- a/tools/crm_node.c
|
||||
+++ b/tools/crm_node.c
|
||||
@@ -552,7 +552,7 @@ remove_from_section(cib_t *cib, const char *element, const char *section,
|
||||
}
|
||||
crm_xml_add(xml, XML_ATTR_UNAME, node_name);
|
||||
if (node_id > 0) {
|
||||
- crm_xml_set_id(xml, "%ld", node_id);
|
||||
+ crm_xml_add_ll(xml, XML_ATTR_ID, node_id);
|
||||
}
|
||||
rc = cib->cmds->remove(cib, section, xml, cib_transaction);
|
||||
free_xml(xml);
|
||||
@@ -691,7 +691,7 @@ purge_node_from_fencer(const char *node_name, long node_id)
|
||||
cmd = create_request(CRM_OP_RM_NODE_CACHE, NULL, NULL, "stonith-ng",
|
||||
crm_system_name, NULL);
|
||||
if (node_id > 0) {
|
||||
- crm_xml_set_id(cmd, "%ld", node_id);
|
||||
+ crm_xml_add_ll(cmd, XML_ATTR_ID, node_id);
|
||||
}
|
||||
crm_xml_add(cmd, XML_ATTR_UNAME, node_name);
|
||||
|
@ -1,89 +0,0 @@
|
||||
From 22e093a5bff608c86d0ea68588078ca747a6d945 Mon Sep 17 00:00:00 2001
|
||||
From: Reid Wahl <nrwahl@protonmail.com>
|
||||
Date: Thu, 11 Jul 2024 12:29:34 -0700
|
||||
Subject: [PATCH] Fix: tools: crm_node -i must initialize nodeid before passing
|
||||
pointer
|
||||
|
||||
This is a regression introduced in 2.1.7 via a27f099.
|
||||
|
||||
Currently, crm_node -i passes a pointer to the uninitialized uint32_t
|
||||
nodeid variable, to pcmk__query_node_info(). Since the pointer is
|
||||
non-NULL, pcmk__query_node_info() dereferences it. Whatever garbage
|
||||
value resides there gets passed as the ID to query.
|
||||
|
||||
The controller parses the node ID from the request as an int. If the
|
||||
garbage value is greater than INT_MAX, it overflows to a negative int
|
||||
value, and the controller (in handle_node_info_request()) defaults it to
|
||||
0. In that case, there's no problem: we search for the local node name
|
||||
instead of the garbage node ID.
|
||||
|
||||
If the garbage value is less than or equal to INT_MAX, we search for it
|
||||
directly. We won't find a matching node unless one happens to exist with
|
||||
that garbage node ID. In the case of no match, crm_node -i outputs "Node
|
||||
is not known to cluster" instead of the local node's cluster-layer ID.
|
||||
|
||||
Thanks to Artur Novik for the report:
|
||||
https://lists.clusterlabs.org/pipermail/users/2024-July/036270.html
|
||||
|
||||
Fixes T847
|
||||
|
||||
Signed-off-by: Reid Wahl <nrwahl@protonmail.com>
|
||||
---
|
||||
lib/pacemaker/pcmk_cluster_queries.c | 22 +++++++++++-----------
|
||||
tools/crm_node.c | 2 +-
|
||||
2 files changed, 12 insertions(+), 12 deletions(-)
|
||||
|
||||
diff --git a/lib/pacemaker/pcmk_cluster_queries.c b/lib/pacemaker/pcmk_cluster_queries.c
|
||||
index 3229fae3eff..8404584580e 100644
|
||||
--- a/lib/pacemaker/pcmk_cluster_queries.c
|
||||
+++ b/lib/pacemaker/pcmk_cluster_queries.c
|
||||
@@ -586,25 +586,25 @@ pcmk_designated_controller(xmlNodePtr *xml, unsigned int message_timeout_ms)
|
||||
* the controller
|
||||
*
|
||||
* \param[in,out] out Output object
|
||||
- * \param[in,out] node_id ID of node whose name to get. If \p NULL
|
||||
- * or 0, get the local node name. If not
|
||||
- * \p NULL, store the true node ID here on
|
||||
+ * \param[in,out] node_id ID of node whose info to get. If \p NULL
|
||||
+ * or 0, get the local node's info. If not
|
||||
+ * \c NULL, store the true node ID here on
|
||||
* success.
|
||||
- * \param[out] node_name If not \p NULL, where to store the node
|
||||
+ * \param[out] node_name If not \c NULL, where to store the node
|
||||
* name
|
||||
- * \param[out] uuid If not \p NULL, where to store the node
|
||||
+ * \param[out] uuid If not \c NULL, where to store the node
|
||||
* UUID
|
||||
- * \param[out] state If not \p NULL, where to store the
|
||||
+ * \param[out] state If not \c NULL, where to store the
|
||||
* membership state
|
||||
- * \param[out] is_remote If not \p NULL, where to store whether the
|
||||
+ * \param[out] is_remote If not \c NULL, where to store whether the
|
||||
* node is a Pacemaker Remote node
|
||||
- * \param[out] have_quorum If not \p NULL, where to store whether the
|
||||
+ * \param[out] have_quorum If not \c NULL, where to store whether the
|
||||
* node has quorum
|
||||
* \param[in] show_output Whether to show the node info
|
||||
* \param[in] message_timeout_ms How long to wait for a reply from the
|
||||
- * \p pacemaker-controld API. If 0,
|
||||
- * \p pcmk_ipc_dispatch_sync will be used.
|
||||
- * Otherwise, \p pcmk_ipc_dispatch_poll will
|
||||
+ * \c pacemaker-controld API. If 0,
|
||||
+ * \c pcmk_ipc_dispatch_sync will be used.
|
||||
+ * Otherwise, \c pcmk_ipc_dispatch_poll will
|
||||
* be used.
|
||||
*
|
||||
* \return Standard Pacemaker return code
|
||||
diff --git a/tools/crm_node.c b/tools/crm_node.c
|
||||
index d4153605a69..8aa8d3d29c7 100644
|
||||
--- a/tools/crm_node.c
|
||||
+++ b/tools/crm_node.c
|
||||
@@ -434,7 +434,7 @@ run_controller_mainloop(void)
|
||||
static void
|
||||
print_node_id(void)
|
||||
{
|
||||
- uint32_t nodeid;
|
||||
+ uint32_t nodeid = 0;
|
||||
int rc = pcmk__query_node_info(out, &nodeid, NULL, NULL, NULL, NULL, NULL,
|
||||
false, 0);
|
||||
|
@ -1,387 +0,0 @@
|
||||
From 96bb1076281bfe46caab135f24ea24fc02ead388 Mon Sep 17 00:00:00 2001
|
||||
From: Chris Lumens <clumens@redhat.com>
|
||||
Date: Thu, 10 Jul 2025 11:15:20 -0400
|
||||
Subject: [PATCH 1/5] Refactor: scheduler: Fix formatting in pe_can_fence.
|
||||
|
||||
---
|
||||
lib/pengine/utils.c | 6 +++---
|
||||
1 file changed, 3 insertions(+), 3 deletions(-)
|
||||
|
||||
diff --git a/lib/pengine/utils.c b/lib/pengine/utils.c
|
||||
index 4055d6d..19cc5a2 100644
|
||||
--- a/lib/pengine/utils.c
|
||||
+++ b/lib/pengine/utils.c
|
||||
@@ -1,5 +1,5 @@
|
||||
/*
|
||||
- * Copyright 2004-2023 the Pacemaker project contributors
|
||||
+ * Copyright 2004-2025 the Pacemaker project contributors
|
||||
*
|
||||
* The version control history for this file may have further details.
|
||||
*
|
||||
@@ -63,10 +63,10 @@ pe_can_fence(const pcmk_scheduler_t *scheduler, const pcmk_node_t *node)
|
||||
} else if (scheduler->no_quorum_policy == pcmk_no_quorum_ignore) {
|
||||
return true;
|
||||
|
||||
- } else if(node == NULL) {
|
||||
+ } else if (node == NULL) {
|
||||
return false;
|
||||
|
||||
- } else if(node->details->online) {
|
||||
+ } else if (node->details->online) {
|
||||
crm_notice("We can fence %s without quorum because they're in our membership",
|
||||
pe__node_name(node));
|
||||
return true;
|
||||
--
|
||||
2.43.0
|
||||
|
||||
From a69d33bb78458e5bb19d07dacc91754856418649 Mon Sep 17 00:00:00 2001
|
||||
From: Chris Lumens <clumens@redhat.com>
|
||||
Date: Fri, 28 Mar 2025 15:08:56 -0400
|
||||
Subject: [PATCH 2/5] Med: scheduler: Don't always fence online remote nodes.
|
||||
|
||||
Let's assume you have a cluster configured as follows:
|
||||
|
||||
* Three nodes, plus one Pacemaker Remote node.
|
||||
* At least two NICs on each node.
|
||||
* Multiple layers of fencing, including fence_kdump.
|
||||
* The timeout for fence_kdump is set higher on the real nodes than it is
|
||||
on the remote node.
|
||||
* A resource is configured that can only be run on the remote node.
|
||||
|
||||
Now, let's assume that the node running the connection resource for the
|
||||
remote node is disconnect from the rest of the cluster. In testing,
|
||||
this disconnection was done by bringing one network interface down.
|
||||
|
||||
Due to the fence timeouts, the following things will occur:
|
||||
|
||||
* The node whose interface was brought down will split off into its own
|
||||
cluster partition without quorum, while the other two nodes maintain
|
||||
quorum.
|
||||
* The partition with quorum will restart the remote node resource on
|
||||
another real node in the partition.
|
||||
* The node by itself will be fenced. However, due to the long
|
||||
fence_kdump timeout, it will continue to make decisions regarding
|
||||
resources.
|
||||
* The node by itself will re-assign resources, including the remote
|
||||
connection resource. This resource will be assigned back to the same
|
||||
node again.
|
||||
* The node by itself will decide to fence the remote node, which will
|
||||
hit the "in our membership" clause of pe_can_fence. This is because
|
||||
remote nodes are marked as online when they are assigned, not when
|
||||
they are actually running.
|
||||
* When the fence_kdump timeout expires, the node by itself will fence
|
||||
the remote node. This succeeds because there is still a secondary
|
||||
network connection it can use. This fencing will succeed, causing the
|
||||
remote node to reboot and then causing a loss of service.
|
||||
* The node by itself will then be fenced.
|
||||
|
||||
The bug to me seems to be that the remote resource is marked as online
|
||||
when it isn't yet. I think with that changed, all the other remote
|
||||
fencing related code would then work as intended. However, it probably
|
||||
has to remain as-is in order to schedule resources on the remote node -
|
||||
resources probably can't be assigned to an offline node. Making changes
|
||||
in pe_can_fence seems like the least invasive way to deal with this
|
||||
problem.
|
||||
|
||||
I also think this probably has probably been here for a very long time -
|
||||
perhaps always - but we just haven't seen it due to the number of things
|
||||
that have to be configured before it can show up. In particular, the
|
||||
fencing timeouts and secondary network connection are what allow this
|
||||
behavior to happen.
|
||||
|
||||
I can't think of a good reason why a node without quorum would ever want
|
||||
to fence a remote node, especially if the connection resource has been
|
||||
moved to the quorate node.
|
||||
|
||||
My fix here therefore is just to test whether there is another node it
|
||||
could have been moved to and if so, don't fence it.
|
||||
|
||||
Fixes T978
|
||||
Fixes RHEL-84018
|
||||
---
|
||||
lib/pengine/utils.c | 33 +++++++++++++++++++++++++++++++++
|
||||
1 file changed, 33 insertions(+)
|
||||
|
||||
diff --git a/lib/pengine/utils.c b/lib/pengine/utils.c
|
||||
index 19cc5a2..402cecd 100644
|
||||
--- a/lib/pengine/utils.c
|
||||
+++ b/lib/pengine/utils.c
|
||||
@@ -67,6 +67,39 @@ pe_can_fence(const pcmk_scheduler_t *scheduler, const pcmk_node_t *node)
|
||||
return false;
|
||||
|
||||
} else if (node->details->online) {
|
||||
+ /* Remote nodes are marked online when we assign their resource to a
|
||||
+ * node, not when they are actually started (see remote_connection_assigned)
|
||||
+ * so the above test by itself isn't good enough.
|
||||
+ */
|
||||
+ if (pe__is_remote_node(node)) {
|
||||
+ /* If we're on a system without quorum, it's entirely possible that
|
||||
+ * the remote resource was automatically moved to a node on the
|
||||
+ * partition with quorum. We can't tell that from this node - the
|
||||
+ * best we can do is check if it's possible for the resource to run
|
||||
+ * on another node in the partition with quorum. If so, it has
|
||||
+ * likely been moved and we shouldn't fence it.
|
||||
+ *
|
||||
+ * NOTE: This condition appears to only come up in very limited
|
||||
+ * circumstances. It at least requires some very lengthy fencing
|
||||
+ * timeouts set, some way for fencing to still take place (a second
|
||||
+ * NIC is how I've reproduced it in testing, but fence_scsi or
|
||||
+ * sbd could work too), and a resource that runs on the remote node.
|
||||
+ */
|
||||
+ pcmk_resource_t *rsc = node->details->remote_rsc;
|
||||
+ pcmk_node_t *n = NULL;
|
||||
+ GHashTableIter iter;
|
||||
+
|
||||
+ g_hash_table_iter_init(&iter, rsc->allowed_nodes);
|
||||
+ while (g_hash_table_iter_next(&iter, NULL, (void **) &n)) {
|
||||
+ /* A node that's not online according to this non-quorum node
|
||||
+ * is a node that's in another partition.
|
||||
+ */
|
||||
+ if (!n->details->online) {
|
||||
+ return false;
|
||||
+ }
|
||||
+ }
|
||||
+ }
|
||||
+
|
||||
crm_notice("We can fence %s without quorum because they're in our membership",
|
||||
pe__node_name(node));
|
||||
return true;
|
||||
--
|
||||
2.43.0
|
||||
|
||||
From 7d503928c48b67da0bd06bccaa080f0309f7be90 Mon Sep 17 00:00:00 2001
|
||||
From: Chris Lumens <clumens@redhat.com>
|
||||
Date: Thu, 10 Jul 2025 11:25:05 -0400
|
||||
Subject: [PATCH 3/5] Med: scheduler: Require a cluster option for new remote
|
||||
fencing behavior.
|
||||
|
||||
We don't have a ton of confidence that the previous patch is the right
|
||||
thing to do for everyone, so we are going to hide it behind this
|
||||
undocumented cluster config option. By default, if the option is
|
||||
missing (or is set to "true"), the existing remote fencing behavior will
|
||||
be what happens. That is, a node without quorum will be allowed to
|
||||
fence remote nodes in the same partition even if they've been restarted
|
||||
elsewhere.
|
||||
|
||||
However, with fence-remote-without-quorum="false", we will check to see
|
||||
if the remote node could possibly have been started on another node and
|
||||
if so, it will not be fenced.
|
||||
---
|
||||
cts/cli/regression.daemons.exp | 5 +++++
|
||||
include/crm/common/options_internal.h | 5 ++++-
|
||||
include/crm/common/scheduler.h | 7 ++++++-
|
||||
lib/common/options.c | 13 ++++++++++++-
|
||||
lib/pengine/unpack.c | 12 +++++++++++-
|
||||
lib/pengine/utils.c | 6 +++++-
|
||||
6 files changed, 43 insertions(+), 5 deletions(-)
|
||||
|
||||
diff --git a/cts/cli/regression.daemons.exp b/cts/cli/regression.daemons.exp
|
||||
index 543d62f..678cb62 100644
|
||||
--- a/cts/cli/regression.daemons.exp
|
||||
+++ b/cts/cli/regression.daemons.exp
|
||||
@@ -292,6 +292,11 @@
|
||||
<shortdesc lang="en">Whether the cluster should check for active resources during start-up</shortdesc>
|
||||
<content type="boolean" default=""/>
|
||||
</parameter>
|
||||
+ <parameter name="fence-remote-without-quorum">
|
||||
+ <longdesc lang="en">By default, inquorate nodes can fence Pacemaker Remote nodes that are part of its partition regardless of whether the resource was successfully restarted elsewhere. If false, an additional check will be added to only fence remote nodes if the cluster thinks they were unable to be restarted.</longdesc>
|
||||
+ <shortdesc lang="en">*** Advanced Use Only *** Whether remote nodes can be fenced without quorum</shortdesc>
|
||||
+ <content type="boolean" default=""/>
|
||||
+ </parameter>
|
||||
<parameter name="stonith-enabled">
|
||||
<longdesc lang="en">If false, unresponsive nodes are immediately assumed to be harmless, and resources that were active on them may be recovered elsewhere. This can result in a "split-brain" situation, potentially leading to data loss and/or service unavailability.</longdesc>
|
||||
<shortdesc lang="en">*** Advanced Use Only *** Whether nodes may be fenced as part of recovery</shortdesc>
|
||||
diff --git a/include/crm/common/options_internal.h b/include/crm/common/options_internal.h
|
||||
index b727a58..95edc53 100644
|
||||
--- a/include/crm/common/options_internal.h
|
||||
+++ b/include/crm/common/options_internal.h
|
||||
@@ -1,5 +1,5 @@
|
||||
/*
|
||||
- * Copyright 2006-2023 the Pacemaker project contributors
|
||||
+ * Copyright 2006-2025 the Pacemaker project contributors
|
||||
*
|
||||
* The version control history for this file may have further details.
|
||||
*
|
||||
@@ -167,5 +167,8 @@ bool pcmk__valid_sbd_timeout(const char *value);
|
||||
#define PCMK__VALUE_RED "red"
|
||||
#define PCMK__VALUE_UNFENCING "unfencing"
|
||||
#define PCMK__VALUE_YELLOW "yellow"
|
||||
+
|
||||
+// Cluster options
|
||||
+#define PCMK__OPT_FENCE_REMOTE_WITHOUT_QUORUM "fence-remote-without-quorum"
|
||||
|
||||
#endif // PCMK__OPTIONS_INTERNAL__H
|
||||
diff --git a/include/crm/common/scheduler.h b/include/crm/common/scheduler.h
|
||||
index 96f9a62..259fa5b 100644
|
||||
--- a/include/crm/common/scheduler.h
|
||||
+++ b/include/crm/common/scheduler.h
|
||||
@@ -1,5 +1,5 @@
|
||||
/*
|
||||
- * Copyright 2004-2023 the Pacemaker project contributors
|
||||
+ * Copyright 2004-2025 the Pacemaker project contributors
|
||||
*
|
||||
* The version control history for this file may have further details.
|
||||
*
|
||||
@@ -184,6 +184,11 @@ struct pe_working_set_s {
|
||||
|
||||
int stonith_timeout; //!< Value of stonith-timeout property
|
||||
enum pe_quorum_policy no_quorum_policy; //!< Response to loss of quorum
|
||||
+
|
||||
+ // Can Pacemaker Remote nodes be fenced even from a node that doesn't
|
||||
+ // have quorum?
|
||||
+ bool fence_remote_without_quorum;
|
||||
+
|
||||
GHashTable *config_hash; //!< Cluster properties
|
||||
|
||||
//!< Ticket constraints unpacked from ticket state
|
||||
diff --git a/lib/common/options.c b/lib/common/options.c
|
||||
index 13d58e3..96f059c 100644
|
||||
--- a/lib/common/options.c
|
||||
+++ b/lib/common/options.c
|
||||
@@ -1,5 +1,5 @@
|
||||
/*
|
||||
- * Copyright 2004-2022 the Pacemaker project contributors
|
||||
+ * Copyright 2004-2025 the Pacemaker project contributors
|
||||
*
|
||||
* The version control history for this file may have further details.
|
||||
*
|
||||
@@ -232,6 +232,17 @@ static pcmk__cluster_option_t cluster_options[] = {
|
||||
},
|
||||
|
||||
// Fencing-related options
|
||||
+ { PCMK__OPT_FENCE_REMOTE_WITHOUT_QUORUM, NULL, "boolean", NULL,
|
||||
+ XML_BOOLEAN_TRUE, pcmk__valid_boolean,
|
||||
+ pcmk__opt_context_schedulerd,
|
||||
+ N_("*** Advanced Use Only *** "
|
||||
+ "Whether remote nodes can be fenced without quorum"),
|
||||
+ N_("By default, inquorate nodes can fence Pacemaker Remote nodes that "
|
||||
+ "are part of its partition regardless of whether the resource "
|
||||
+ "was successfully restarted elsewhere. If false, an additional "
|
||||
+ "check will be added to only fence remote nodes if the cluster "
|
||||
+ "thinks they were unable to be restarted.")
|
||||
+ },
|
||||
{
|
||||
"stonith-enabled", NULL, "boolean", NULL,
|
||||
XML_BOOLEAN_TRUE, pcmk__valid_boolean,
|
||||
diff --git a/lib/pengine/unpack.c b/lib/pengine/unpack.c
|
||||
index d484e93..e96b978 100644
|
||||
--- a/lib/pengine/unpack.c
|
||||
+++ b/lib/pengine/unpack.c
|
||||
@@ -1,5 +1,5 @@
|
||||
/*
|
||||
- * Copyright 2004-2023 the Pacemaker project contributors
|
||||
+ * Copyright 2004-2025 the Pacemaker project contributors
|
||||
*
|
||||
* The version control history for this file may have further details.
|
||||
*
|
||||
@@ -435,6 +435,16 @@ unpack_config(xmlNode *config, pcmk_scheduler_t *scheduler)
|
||||
* 1000));
|
||||
}
|
||||
|
||||
+ value = pcmk__cluster_option(config_hash,
|
||||
+ PCMK__OPT_FENCE_REMOTE_WITHOUT_QUORUM);
|
||||
+ if ((value != NULL) && !crm_is_true(value)) {
|
||||
+ crm_warn(PCMK__OPT_FENCE_REMOTE_WITHOUT_QUORUM " disabled - remote "
|
||||
+ "nodes may not be fenced in inquorate partition");
|
||||
+ scheduler->fence_remote_without_quorum = false;
|
||||
+ } else {
|
||||
+ scheduler->fence_remote_without_quorum = true;
|
||||
+ }
|
||||
+
|
||||
return TRUE;
|
||||
}
|
||||
|
||||
diff --git a/lib/pengine/utils.c b/lib/pengine/utils.c
|
||||
index 402cecd..f25717d 100644
|
||||
--- a/lib/pengine/utils.c
|
||||
+++ b/lib/pengine/utils.c
|
||||
@@ -70,8 +70,12 @@ pe_can_fence(const pcmk_scheduler_t *scheduler, const pcmk_node_t *node)
|
||||
/* Remote nodes are marked online when we assign their resource to a
|
||||
* node, not when they are actually started (see remote_connection_assigned)
|
||||
* so the above test by itself isn't good enough.
|
||||
+ *
|
||||
+ * This is experimental behavior, so the user has to opt into it by
|
||||
+ * adding fence-remote-without-quorum="false" to their CIB.
|
||||
*/
|
||||
- if (pe__is_remote_node(node)) {
|
||||
+ if (pe__is_remote_node(node)
|
||||
+ && !scheduler->fence_remote_without_quorum) {
|
||||
/* If we're on a system without quorum, it's entirely possible that
|
||||
* the remote resource was automatically moved to a node on the
|
||||
* partition with quorum. We can't tell that from this node - the
|
||||
--
|
||||
2.43.0
|
||||
|
||||
From 9ad7c0157cb0ac271ddf9b401e072a7d00de05de Mon Sep 17 00:00:00 2001
|
||||
From: "Gao,Yan" <ygao@suse.com>
|
||||
Date: Thu, 10 Apr 2025 12:51:57 +0200
|
||||
Subject: [PATCH 4/5] Refactor: libcrmcommon: move the new struct member to the
|
||||
end for backward compatibility
|
||||
|
||||
Commit f342b77561 broke backward compatibility by inserting the new
|
||||
member `fence_remote_without_quorum` into the middle of the
|
||||
`pe_working_set_s` struct.
|
||||
---
|
||||
include/crm/common/scheduler.h | 8 ++++----
|
||||
1 file changed, 4 insertions(+), 4 deletions(-)
|
||||
|
||||
diff --git a/include/crm/common/scheduler.h b/include/crm/common/scheduler.h
|
||||
index 259fa5b..4baee09 100644
|
||||
--- a/include/crm/common/scheduler.h
|
||||
+++ b/include/crm/common/scheduler.h
|
||||
@@ -185,10 +185,6 @@ struct pe_working_set_s {
|
||||
int stonith_timeout; //!< Value of stonith-timeout property
|
||||
enum pe_quorum_policy no_quorum_policy; //!< Response to loss of quorum
|
||||
|
||||
- // Can Pacemaker Remote nodes be fenced even from a node that doesn't
|
||||
- // have quorum?
|
||||
- bool fence_remote_without_quorum;
|
||||
-
|
||||
GHashTable *config_hash; //!< Cluster properties
|
||||
|
||||
//!< Ticket constraints unpacked from ticket state
|
||||
@@ -234,6 +230,10 @@ struct pe_working_set_s {
|
||||
void *priv; //!< For Pacemaker use only
|
||||
|
||||
guint node_pending_timeout; //!< Pending join times out after this (ms)
|
||||
+
|
||||
+ // Can Pacemaker Remote nodes be fenced even from a node that doesn't
|
||||
+ // have quorum?
|
||||
+ bool fence_remote_without_quorum;
|
||||
};
|
||||
|
||||
#ifdef __cplusplus
|
||||
--
|
||||
2.43.0
|
||||
|
||||
From 8159779e13da5ddd2a6ce77542e945abb4c2663d Mon Sep 17 00:00:00 2001
|
||||
From: Chris Lumens <clumens@redhat.com>
|
||||
Date: Tue, 29 Apr 2025 12:49:45 -0400
|
||||
Subject: [PATCH 5/5] Refactor: scheduler: Lower fencing log message to debug
|
||||
level.
|
||||
|
||||
Most other things in unpack_config are logged at debug or trace level.
|
||||
Having the fencing message at the warn level makes it come up quite
|
||||
often.
|
||||
---
|
||||
lib/pengine/unpack.c | 4 ++--
|
||||
1 file changed, 2 insertions(+), 2 deletions(-)
|
||||
|
||||
diff --git a/lib/pengine/unpack.c b/lib/pengine/unpack.c
|
||||
index e96b978..5d124a3 100644
|
||||
--- a/lib/pengine/unpack.c
|
||||
+++ b/lib/pengine/unpack.c
|
||||
@@ -438,8 +438,8 @@ unpack_config(xmlNode *config, pcmk_scheduler_t *scheduler)
|
||||
value = pcmk__cluster_option(config_hash,
|
||||
PCMK__OPT_FENCE_REMOTE_WITHOUT_QUORUM);
|
||||
if ((value != NULL) && !crm_is_true(value)) {
|
||||
- crm_warn(PCMK__OPT_FENCE_REMOTE_WITHOUT_QUORUM " disabled - remote "
|
||||
- "nodes may not be fenced in inquorate partition");
|
||||
+ crm_debug(PCMK__OPT_FENCE_REMOTE_WITHOUT_QUORUM " disabled - remote "
|
||||
+ "nodes may not be fenced in inquorate partition");
|
||||
scheduler->fence_remote_without_quorum = false;
|
||||
} else {
|
||||
scheduler->fence_remote_without_quorum = true;
|
||||
--
|
||||
2.43.0
|
||||
|
@ -36,7 +36,7 @@
|
||||
## can be incremented to build packages reliably considered "newer"
|
||||
## than previously built packages with the same pcmkversion)
|
||||
%global pcmkversion 2.1.7
|
||||
%global specversion 5
|
||||
%global specversion 4
|
||||
|
||||
## Upstream commit (full commit ID, abbreviated commit ID, or tag) to build
|
||||
%global commit 0f7f88312f7a1ccedee60bf768aba79ee13d41e0
|
||||
@ -244,7 +244,7 @@
|
||||
Name: pacemaker
|
||||
Summary: Scalable High-Availability cluster resource manager
|
||||
Version: %{pcmkversion}
|
||||
Release: %{pcmk_release}.3%{?dist}
|
||||
Release: %{pcmk_release}%{?dist}
|
||||
%if %{defined _unitdir}
|
||||
License: GPL-2.0-or-later AND LGPL-2.1-or-later
|
||||
%else
|
||||
@ -275,10 +275,6 @@ Patch007: 007-option-metadata.patch
|
||||
Patch008: 008-attrd-prep.patch
|
||||
Patch009: 009-attrd-cache-3.patch
|
||||
Patch010: 010-crm_attribute-free.patch
|
||||
Patch011: 011-attrd-memory-leak.patch
|
||||
Patch012: 012-dont-set-as-xml-id.patch
|
||||
Patch013: 013-crm_node-i-initialize.patch
|
||||
Patch014: 014-remote-fencing.patch
|
||||
|
||||
Requires: resource-agents
|
||||
Requires: %{pkgname_pcmk_libs}%{?_isa} = %{version}-%{release}
|
||||
@ -589,12 +585,6 @@ export LDFLAGS_HARDENED_EXE="%{?_hardening_ldflags}"
|
||||
export LDFLAGS_HARDENED_LIB="%{?_hardening_ldflags}"
|
||||
%endif
|
||||
|
||||
# DO NOT REMOVE THE FOLLOWING LINE!
|
||||
# This is necessary to ensure we use the git commit ID from the
|
||||
# pacemaker-abcd1234 directory name as the latest commit ID when
|
||||
# generating crm_config.h.
|
||||
rm -rf .git
|
||||
|
||||
./autogen.sh
|
||||
|
||||
%{configure} \
|
||||
@ -1030,22 +1020,6 @@ exit 0
|
||||
%license %{nagios_name}-%{nagios_hash}/COPYING
|
||||
|
||||
%changelog
|
||||
* Thu Jul 10 2025 Chris Lumens <clumens@redhat.com> - 2.1.7-5.3
|
||||
- Add option for controlling remote node fencing behavior
|
||||
- Resolves: RHEL-93220
|
||||
|
||||
* Wed Jul 24 2024 Chris Lumens <clumens@redhat.com> - 2.1.7-5.2
|
||||
- Fix an error in node ID handling in `crm_node -i`
|
||||
- Resolves: RHEL-49928
|
||||
|
||||
* Fri Jun 7 2024 Chris Lumens <clumens@redhat.com> - 2.1.7-5.1
|
||||
- Fix a memory leak in the attribute daemon
|
||||
- Resolves: RHEL-40145
|
||||
|
||||
* Thu Mar 21 2024 Chris Lumens <clumens@redhat.com> - 2.1.7-5
|
||||
- Fix upgrading to this package on multilib systems
|
||||
- Resolves: RHEL-29007
|
||||
|
||||
* Thu Feb 1 2024 Chris Lumens <clumens@redhat.com> - 2.1.7-4
|
||||
- Properly validate attribute set type in pacemaker-attrd
|
||||
- Fix `crm_attribute -t nodes --node localhost`
|
||||
|
Loading…
Reference in New Issue
Block a user