Merge #1800

1800: Cherry pick #1786 r=Abhinandan-Purkait a=Abhinandan-Purkait

Cherry pick #1786

Co-authored-by: Abhinandan Purkait <purkaitabhinandan@gmail.com>

Author: mayastor-bors

io-engine/src/bdev/nexus/nexus_persistence.rs

@@ -103,8 +103,9 @@ impl<'n> Nexus<'n> {
                     };
                     nexus_info.children.push(child_info);
                 });
-                // We started with this child because it was healthy in etcd, or isn't there at all.
-                // Being unhealthy here means it is undergoing a fault/retire before nexus is open.
+                // We started with this child because it was healthy in etcd, or
+                // isn't there at all. Being unhealthy here
+                // means it is undergoing a fault/retire before nexus is open.
                 if nexus_info.children.len() == 1 && !nexus_info.children[0].healthy {
                     warn!("{self:?} Not persisting: the only child went unhealthy during nexus creation");
                     return Err(Error::NexusCreate {
@@ -211,6 +212,7 @@ impl<'n> Nexus<'n> {
         };
 
         let mut retry = PersistentStore::retries();
+        let mut logged = false;
         loop {
             let Err(err) = PersistentStore::put(&key, &info.inner).await else {
                 trace!(?key, "{self:?}: the state was saved successfully");
@@ -225,10 +227,13 @@ impl<'n> Nexus<'n> {
                 });
             }
 
-            error!(
-                "{self:?}: failed to persist nexus information, \
-                will retry ({retry} left): {err}"
-            );
+            if !logged {
+                error!(
+                    "{self:?}: failed to persist nexus information, \
+                    will silently retry ({retry} left): {err}"
+                );
+                logged = true;
+            }
 
             // Allow some time for the connection to the persistent
             // store to be re-established before retrying the operation.

io-engine/src/core/env.rs

@@ -174,7 +174,7 @@ pub struct MayastorCliArgs {
     pub ps_timeout: Duration,
     #[clap(long = "ps-retries", default_value = "30")]
     /// Persistent store operation retries.
-    pub ps_retries: u8,
+    pub ps_retries: u16,
     #[clap(long = "bdev-pool-size", default_value = "65535")]
     /// Number of entries in memory pool for bdev I/O contexts
     pub bdev_io_ctx_pool_size: u64,
@@ -374,7 +374,7 @@ pub struct MayastorEnvironment {
     pub registration_endpoint: Option<Uri>,
     ps_endpoint: Option<String>,
     ps_timeout: Duration,
-    ps_retries: u8,
+    ps_retries: u16,
     mayastor_config: Option<String>,
     ptpl_dir: Option<String>,
     pool_config: Option<String>,

io-engine/src/persistent_store.rs

@@ -31,7 +31,7 @@ pub struct PersistentStoreBuilder {
     /// Operation timeout.
     timeout: Duration,
     /// Number of operation retries.
-    retries: u8,
+    retries: u16,
 }
 
 impl Default for PersistentStoreBuilder {
@@ -74,7 +74,7 @@ impl PersistentStoreBuilder {
     }
 
     /// Sets number of operation retries.
-    pub fn with_retries(mut self, retries: u8) -> Self {
+    pub fn with_retries(mut self, retries: u16) -> Self {
         self.retries = retries;
         self
     }
@@ -96,7 +96,7 @@ pub struct PersistentStore {
     /// Operation timeout.
     timeout: Duration,
     /// Number of operation retries.
-    retries: u8,
+    retries: u16,
 }
 
 /// Persistent store global instance.
@@ -311,7 +311,7 @@ impl PersistentStore {
     }
 
     /// Gets the number of operation retries.
-    pub fn retries() -> u8 {
+    pub fn retries() -> u16 {
         Self::instance().lock().retries
     }