Set replicas to panic on disk errors, and optionally panic on replication errors (#10504)

* Till now, replicas that were unable to persist, would still execute the commands
  they got from the master, now they'll panic by default, and we add a new
  `replica-ignore-disk-errors` config to change that.
* Till now, when a command failed on a replica or AOF-loading, it only logged a
  warning and a stat, we add a new `propagation-error-behavior` config to allow
  panicking in that state (may become the default one day)

Note that commands that fail on the replica can either indicate a bug that could
cause data inconsistency between the replica and the master, or they could be
in some cases (specifically in previous versions), a result of a command (e.g. EVAL)
that failed on the master, but still had to be propagated to fail on the replica as well.

1 files changed, 13 insertions, 0 deletions

diff --git a/src/server.h b/src/server.h
index ef0215fe0..b26ec7b3b 100644
--- a/src/server.h
+++ b/src/server.h
@@ -1325,6 +1325,15 @@ struct redisMemOverhead {
     } *db;
 };
 
+/* Replication error behavior determines the replica behavior
+ * when it receives an error over the replication stream. In
+ * either case the error is logged. */
+enum {
+    PROPAGATION_ERR_BEHAVIOR_IGNORE = 0,
+    PROPAGATION_ERR_BEHAVIOR_PANIC,
+    PROPAGATION_ERR_BEHAVIOR_PANIC_ON_REPLICAS
+} replicationErrorBehavior;
+
 /* This structure can be optionally passed to RDB save/load functions in
  * order to implement additional functionalities, by storing and loading
  * metadata to the RDB file.
@@ -1772,6 +1781,10 @@ struct redisServer {
     int replica_announced;          /* If true, replica is announced by Sentinel */
     int slave_announce_port;        /* Give the master this listening port. */
     char *slave_announce_ip;        /* Give the master this ip address. */
+    int propagation_error_behavior; /* Configures the behavior of the replica
+                                     * when it receives an error on the replication stream */
+    int repl_ignore_disk_write_error;   /* Configures whether replicas panic when unable to
+                                         * persist writes to AOF. */
     /* The following two fields is where we store master PSYNC replid/offset
      * while the PSYNC is in progress. At the end we'll copy the fields into
      * the server->master client structure. */