[PATCH v3 manager 62/76] pvestatd: apply the multipath configuration and report the node status

[Thomas Lamprecht <t.lamprecht@proxmox.com>]

Use pvestatd's periodic loop to apply multipath configuration and
publish node health, including after reboots and storage changes. Run
this before node, guest, and storage status updates so a slow update
does not delay the first report of a path outage.

Nodes without multipath-tools send only a small report, resent once a
minute while unchanged. With the tools, daemon availability is checked
on every pass; without managed LUNs, a successful map listing is
reused for a minute. Log configuration errors when they first occur,
not on every pass.

Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
 PVE/Service/pvestatd.pm | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/PVE/Service/pvestatd.pm b/PVE/Service/pvestatd.pm
index f682c2f9d..4218db2e7 100755
--- a/PVE/Service/pvestatd.pm
+++ b/PVE/Service/pvestatd.pm
@@ -21,6 +21,8 @@ use PVE::NodeConfig;
 use PVE::Cluster qw(cfs_read_file);
 use PVE::Storage;
 use PVE::Storage::StatusCommand;
+use PVE::Multipath::Generator;
+use PVE::Multipath::Status;
 use PVE::QemuServer;
 use PVE::QemuServer::Monitor;
 use PVE::LXC;
@@ -808,6 +810,17 @@ my sub broadcast_version_info : prototype() {
     }
 }
 
+my $last_multipath_sync_error = '';
+my sub update_multipath_status : prototype() {
+    my $multipath = eval { PVE::Multipath::Generator::sync(); };
+    $multipath = { error => $@ } if $@;
+    my $sync_error = $multipath->{error} // '';
+    syslog('err', "multipath config sync error: $sync_error")
+        if $sync_error ne '' && $sync_error ne $last_multipath_sync_error;
+    $last_multipath_sync_error = $sync_error;
+    PVE::Multipath::Status::broadcast_status($multipath);
+}
+
 sub update_status {
     # update worker list. This is not really required, but we want to make sure that we also have a
     # correct list in case of an unexpected crash.
@@ -824,6 +837,12 @@ sub update_status {
 
     my $status_cfg = PVE::Cluster::cfs_read_file('status.cfg');
 
+    # apply the multipath configuration before the other updates: the storage status update can
+    # block in LVM while all paths of a LUN are lost
+    eval { update_multipath_status(); };
+    $err = $@;
+    syslog('err', "multipath status broadcast error: $err") if $err;
+
     eval { update_node_status($status_cfg, $pull_txn); };
     $err = $@;
     syslog('err', "node status update error: $err") if $err;
-- 
2.47.3