From: Thomas Lamprecht <t.lamprecht@proxmox.com>
To: pve-devel@lists.proxmox.com
Subject: [PATCH cluster v3 03/38] pmxcfs: dfsm: add a callback that runs once all members are in sync
Date: Wed, 18 Nov 2026 05:37:15 +0100 [thread overview]
Message-ID: <20261118043817.1659212-4-t.lamprecht@proxmox.com> (raw)
In-Reply-To: <20261118043817.1659212-1-t.lamprecht@proxmox.com>
A service acting on shared state from the loop thread needs to know
when the local state matches that of all members. The existing synced
callback runs before queued messages are delivered. The sync leader
also enters that state before members needing updates have received
them, so their queued messages are still pending.
Add an optional callback after all members are marked in sync and the
queued messages have been delivered. Call it again on service timer
ticks while that condition holds, allowing failed or skipped actions
to be retried.
Other loop events can request the same check with dfsm_check_in_sync().
Use dfsm_nodeid_is_member() to check membership in the current group.
Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
changes v2 -> v3:
* comment: the condition is what this node has marked as synced, not an
acknowledgement of the other nodes
changes v1 -> v2:
* rebase onto the dfsm rework
* also reset the in-sync state when the connection gets finalized
* reword the comment of the callback
src/pmxcfs/dfsm.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++
src/pmxcfs/dfsm.h | 14 +++++++++++
2 files changed, 73 insertions(+)
diff --git a/src/pmxcfs/dfsm.c b/src/pmxcfs/dfsm.c
index c83cef7..b48ee13 100644
--- a/src/pmxcfs/dfsm.c
+++ b/src/pmxcfs/dfsm.c
@@ -124,6 +124,7 @@ struct dfsm {
uint32_t local_epoch_counter;
dfsm_sync_epoch_t sync_epoch;
uint32_t lowest_nodeid;
+ gboolean in_sync; /* see dfsm_in_sync_fn */
GSequence *msg_queue;
GList *sync_queue;
@@ -609,6 +610,27 @@ gboolean dfsm_restartable(dfsm_t *dfsm) {
void dfsm_set_errormode(dfsm_t *dfsm) { dfsm_set_mode(dfsm, DFSM_MODE_ERROR); }
+static void dfsm_notify_in_sync(dfsm_t *dfsm) {
+ g_return_if_fail(dfsm != NULL);
+ g_return_if_fail(dfsm->sync_info != NULL);
+
+ if (dfsm->in_sync || dfsm_get_mode(dfsm) != DFSM_MODE_SYNCED) {
+ return;
+ }
+
+ for (int i = 0; i < dfsm->sync_info->node_count; i++) {
+ if (!dfsm->sync_info->nodes[i].synced) {
+ return;
+ }
+ }
+
+ dfsm->in_sync = TRUE;
+
+ if (dfsm->dfsm_callbacks->dfsm_in_sync_fn) {
+ dfsm->dfsm_callbacks->dfsm_in_sync_fn(dfsm, dfsm->data);
+ }
+}
+
static void dfsm_release_sync_resources(
dfsm_t *dfsm, const struct cpg_address *member_list, size_t member_list_entries
) {
@@ -802,6 +824,8 @@ static void dfsm_cpg_deliver_callback(
goto leave;
}
+ dfsm_notify_in_sync(dfsm);
+
return;
} else if (base_header->type == DFSM_MESSAGE_VERIFY_REQUEST) {
@@ -990,6 +1014,8 @@ static void dfsm_cpg_deliver_callback(
goto leave;
}
+ dfsm_notify_in_sync(dfsm);
+
} else {
dfsm_set_mode(dfsm, DFSM_MODE_UPDATE);
@@ -1040,6 +1066,8 @@ static void dfsm_cpg_deliver_callback(
dfsm_release_sync_resources(dfsm, NULL, 0);
+ dfsm_notify_in_sync(dfsm);
+
return;
}
@@ -1212,6 +1240,7 @@ static void dfsm_cpg_confchg_callback(
dfsm->we_are_member = 0;
dfsm->state_sent = FALSE;
+ dfsm->in_sync = FALSE;
/* create new epoch */
dfsm->local_epoch_counter++;
@@ -1304,6 +1333,7 @@ static void dfsm_cpg_confchg_callback(
if (!dfsm_deliver_queue(dfsm)) {
goto leave;
}
+ dfsm_notify_in_sync(dfsm);
}
if (dfsm->dfsm_callbacks->dfsm_confchg_fn) {
@@ -1390,6 +1420,31 @@ gboolean dfsm_is_initialized(dfsm_t *dfsm) {
return (dfsm->cpg_handle != 0) ? TRUE : FALSE;
}
+void dfsm_check_in_sync(dfsm_t *dfsm) {
+ g_return_if_fail(dfsm != NULL);
+
+ if (dfsm->in_sync && dfsm_get_mode(dfsm) == DFSM_MODE_SYNCED &&
+ dfsm->dfsm_callbacks->dfsm_in_sync_fn) {
+ dfsm->dfsm_callbacks->dfsm_in_sync_fn(dfsm, dfsm->data);
+ }
+}
+
+gboolean dfsm_nodeid_is_member(dfsm_t *dfsm, uint32_t nodeid) {
+ g_return_val_if_fail(dfsm != NULL, FALSE);
+
+ if (!dfsm->sync_info) {
+ return FALSE;
+ }
+
+ for (int i = 0; i < dfsm->sync_info->node_count; i++) {
+ if (dfsm->sync_info->nodes[i].nodeid == nodeid) {
+ return TRUE;
+ }
+ }
+
+ return FALSE;
+}
+
gboolean dfsm_lowest_nodeid(dfsm_t *dfsm) {
g_return_val_if_fail(dfsm != NULL, FALSE);
@@ -1481,6 +1536,7 @@ cs_error_t dfsm_initialize(dfsm_t *dfsm, int *fd) {
dfsm->joined = FALSE;
g_mutex_unlock(&dfsm->cpg_mutex);
dfsm->we_are_member = 0;
+ dfsm->in_sync = FALSE;
dfsm_set_mode(dfsm, DFSM_MODE_START);
@@ -1608,6 +1664,7 @@ gboolean dfsm_finalize(dfsm_t *dfsm) {
dfsm->joined = FALSE;
g_mutex_unlock(&dfsm->cpg_mutex);
dfsm->we_are_member = 0;
+ dfsm->in_sync = FALSE;
}
return TRUE;
@@ -1759,6 +1816,8 @@ static void service_dfsm_timer(cfs_service_t *service, gpointer context) {
g_return_if_fail(dfsm != NULL);
dfsm_verify_request(dfsm);
+
+ dfsm_check_in_sync(dfsm);
}
static cfs_service_callbacks_t cfs_dfsm_callbacks = {
diff --git a/src/pmxcfs/dfsm.h b/src/pmxcfs/dfsm.h
index 5b193e8..6ec3eb1 100644
--- a/src/pmxcfs/dfsm.h
+++ b/src/pmxcfs/dfsm.h
@@ -79,6 +79,8 @@ typedef int (*dfsm_process_state_update_fn_t)(
typedef void (*dfsm_synced_fn_t)(dfsm_t *dfsm);
+typedef void (*dfsm_in_sync_fn_t)(dfsm_t *dfsm, gpointer data);
+
/* return values:
* res < 0 ... serious error, leave group
* res >= 0 ... OK
@@ -103,6 +105,12 @@ typedef struct {
dfsm_process_update_fn_t dfsm_process_update_fn;
dfsm_checksum_fn_t dfsm_checksum_fn;
dfsm_synced_fn_t dfsm_synced_fn;
+ /* Called whenever this node has marked all members as synced and delivered the messages queued
+ * meanwhile, so that the local state matches the one of all members: first right after a sync,
+ * then again on every service timer tick and dfsm_check_in_sync() call while that holds.
+ * dfsm_synced_fn runs earlier, when the local node enters the synced mode and before the queued
+ * messages are delivered. */
+ dfsm_in_sync_fn_t dfsm_in_sync_fn;
} dfsm_callbacks_t;
/* what became of a message sent with dfsm_send_message_sync */
@@ -168,6 +176,12 @@ cs_error_t dfsm_send_update_complete(dfsm_t *dfsm);
gboolean dfsm_lowest_nodeid(dfsm_t *dfsm);
+/* calls dfsm_in_sync_fn again if all members are still in sync, loop thread only */
+void dfsm_check_in_sync(dfsm_t *dfsm);
+
+/* whether a process of that node is a member of the current group, loop thread only */
+gboolean dfsm_nodeid_is_member(dfsm_t *dfsm, uint32_t nodeid);
+
gboolean dfsm_nodeid_is_local(dfsm_t *dfsm, uint32_t nodeid, uint32_t pid);
cs_error_t dfsm_verify_request(dfsm_t *dfsm);
--
2.47.3
next prev parent reply other threads:[~2026-11-18 4:38 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-18 4:37 [PATCH cluster/guest-common/qemu-server/container/manager/docs v3 00/38] fix #7846: guest identity (uid) and cluster ID Thomas Lamprecht
2026-11-18 4:37 ` [PATCH cluster v3 01/38] pmxcfs: reject changes to the cluster ID file from user space Thomas Lamprecht
2026-11-18 4:37 ` [PATCH cluster v3 02/38] pmxcfs: generate a cluster ID on standalone nodes Thomas Lamprecht
2026-11-18 4:37 ` Thomas Lamprecht [this message]
2026-11-18 4:37 ` [PATCH cluster v3 04/38] pmxcfs: quorum: pass the corosync membership to an optional listener Thomas Lamprecht
2026-11-18 4:37 ` [PATCH cluster v3 05/38] pmxcfs: confdb: call an optional listener when the nodes get published Thomas Lamprecht
2026-11-18 4:37 ` [PATCH cluster v3 06/38] pmxcfs: dcdb: generate the cluster ID once the cluster is in sync Thomas Lamprecht
2026-11-18 4:37 ` [PATCH cluster v3 07/38] cluster: add helper to read the cluster ID Thomas Lamprecht
2026-11-18 4:37 ` [PATCH cluster v3 08/38] pmxcfs: allow removing the cluster ID file in forced local mode Thomas Lamprecht
2026-11-18 4:37 ` [PATCH guest-common v3 09/38] guest identity: add helpers for the guest uid and registration time Thomas Lamprecht
2026-11-18 4:37 ` [PATCH guest-common v3 10/38] abstract config: assign a guest identity and keep it on config writes Thomas Lamprecht
2026-11-18 4:37 ` [PATCH guest-common v3 11/38] abstract config: let the VMID reservation return the previous state Thomas Lamprecht
2026-11-18 4:37 ` [PATCH guest-common v3 12/38] guest identity: allow taking over a uid that is unused in the cluster Thomas Lamprecht
2026-11-18 4:37 ` [PATCH guest-common v3 13/38] migrate: add shared helpers for the identity command of the migration tunnel Thomas Lamprecht
2026-11-18 4:37 ` [PATCH qemu-server v3 14/38] api: restore: release the VMID if a restore to an unused VMID fails Thomas Lamprecht
2026-11-18 4:37 ` [PATCH qemu-server v3 15/38] api: migrate, clone: refuse targets that would drop the guest identity Thomas Lamprecht
2026-11-18 4:37 ` [PATCH qemu-server v3 16/38] fix #7846: config: add a guest identity to the 'meta' property Thomas Lamprecht
2026-11-18 4:37 ` [PATCH qemu-server v3 17/38] restore: take over the guest uid from the backup where possible Thomas Lamprecht
2026-11-18 4:37 ` [PATCH qemu-server v3 18/38] api: remote migration: take over the guest uid from the source Thomas Lamprecht
2026-11-18 4:37 ` [PATCH qemu-server v3 19/38] api: status: return the guest uid Thomas Lamprecht
2026-11-18 4:37 ` [PATCH qemu-server v3 20/38] tests: remote migration: check a failed command and an early tunnel end Thomas Lamprecht
2026-11-18 4:37 ` [PATCH container v3 21/38] config: add read-only meta property with the creation time Thomas Lamprecht
2026-11-18 4:37 ` [PATCH container v3 22/38] fix #7846: config: add a guest identity to the 'meta' property Thomas Lamprecht
2026-11-18 4:37 ` [PATCH container v3 23/38] api: migrate, clone: refuse targets that would drop the guest identity Thomas Lamprecht
2026-11-18 4:37 ` [PATCH container v3 24/38] restore: take over the guest uid from the backup where possible Thomas Lamprecht
2026-11-18 4:37 ` [PATCH container v3 25/38] restore: refuse overwriting a container with another guest's backup Thomas Lamprecht
2026-11-18 4:37 ` [PATCH container v3 26/38] test: remote migration: check the cleanup of the target after failures Thomas Lamprecht
2026-11-18 4:37 ` [PATCH container v3 27/38] api: remote migration: take over the guest uid from the source Thomas Lamprecht
2026-11-18 4:37 ` [PATCH container v3 28/38] api: status: return the guest uid Thomas Lamprecht
2026-11-18 4:37 ` [PATCH manager v3 29/38] api: cluster resources: add guest uid and registration time Thomas Lamprecht
2026-11-18 4:37 ` [PATCH manager v3 30/38] api: cluster status: add cluster ID Thomas Lamprecht
2026-11-18 4:37 ` [PATCH manager v3 31/38] ui: restore: allow overwriting a guest with a backup of another guest Thomas Lamprecht
2026-11-18 4:37 ` [PATCH manager v3 32/38] ui: migrate: refuse target nodes that would drop the guest identity Thomas Lamprecht
2026-11-18 4:37 ` [PATCH manager v3 33/38] ui: guest summary: show " Thomas Lamprecht
2026-11-18 4:37 ` [PATCH manager v3 34/38] api: bulk migrate: refuse targets that would drop " Thomas Lamprecht
2026-11-18 4:37 ` [PATCH docs v3 35/38] vzdump: describe the guest identity of VMs and containers Thomas Lamprecht
2026-11-18 4:37 ` [PATCH docs v3 36/38] pvecm: document the cluster ID and how to get a new one Thomas Lamprecht
2026-11-18 4:37 ` [PATCH docs v3 37/38] qm: configuration: describe the read-only meta property Thomas Lamprecht
2026-11-18 4:37 ` [PATCH docs v3 38/38] pct: " Thomas Lamprecht
2026-11-18 13:49 ` [PATCH cluster/guest-common/qemu-server/container/manager/docs v3 00/38] fix #7846: guest identity (uid) and cluster ID Dominik Csapak
2026-11-18 14:13 ` Thomas Lamprecht
2026-11-19 10:38 ` superseded: " Thomas Lamprecht
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261118043817.1659212-4-t.lamprecht@proxmox.com \
--to=t.lamprecht@proxmox.com \
--cc=pve-devel@lists.proxmox.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox