[pull] main from MaterializeInc:main

LICENSE

@@ -13,7 +13,7 @@ Business Source License 1.1
 
 Licensor:                  Materialize, Inc.
 
-Licensed Work:             Materialize Version 20260911
+Licensed Work:             Materialize Version 20260912
                            The Licensed Work is © 2026 Materialize, Inc.
 
 Additional Use Grant:      Within a single installation of the Licensed Work,
@@ -39,7 +39,7 @@ Additional Use Grant:      Within a single installation of the Licensed Work,
                            whose definitions are controlled by such third
                            parties.
 
-Change Date:               September 11, 2030
+Change Date:               September 12, 2030
 
 Change License:            Apache License, Version 2.0
 

ci/mkpipeline.py

@@ -759,33 +759,47 @@ def permit_rerunning_successful_steps(pipeline: Any) -> None:
         )
 
 
+# Failures that are the infrastructure's fault rather than the step's, so every
+# step retries them regardless of what else it asks for.
+SHARED_AUTOMATIC_RETRIES = [
+    {
+        "exit_status": -1,
+        "signal_reason": "none",
+        "limit": 2,
+    },
+    {
+        "signal_reason": "agent_stop",  # Stopped by OS
+        "limit": 2,
+    },
+    {
+        "exit_status": 128,  # Temporary Github/GHCR/DockerHub connection issue
+        "limit": 2,
+    },
+    {
+        "exit_status": 199,  # Rust ICE https://github.com/rust-lang/rust/issues/148581
+        "limit": 2,
+    },
+]
+
+
 def set_retry_on_agent_lost(pipeline: Any) -> None:
     for step in steps(pipeline):
         if "trigger" in step or "wait" in step or "group" in step or "block" in step:
             continue
-        retry = step.setdefault("retry", {})
-        if "automatic" in retry:
+        automatic = step.setdefault("retry", {}).setdefault("automatic", [])
+        # A step retrying on every exit status already covers these.
+        if any(rule.get("exit_status") == "*" for rule in automatic):
             continue
-        retry.setdefault("automatic", []).extend(
-            [
-                {
-                    "exit_status": -1,
-                    "signal_reason": "none",
-                    "limit": 2,
-                },
-                {
-                    "signal_reason": "agent_stop",  # Stopped by OS
-                    "limit": 2,
-                },
-                {
-                    "exit_status": 128,  # Temporary Github/GHCR/DockerHub connection issue
-                    "limit": 2,
-                },
-                {
-                    "exit_status": 199,  # Rust ICE https://github.com/rust-lang/rust/issues/148581
-                    "limit": 2,
-                },
-            ]
+        # Merge rather than skip a step that declares its own rules: skipping
+        # lets a narrow override such as `exit_status: 1` drop every shared rule
+        # and hard-fail the step on the infrastructure classes they exist for.
+        # Nothing surfaces that, and the mzcompose plugin goes out of its way to
+        # propagate 128 and 199 so these rules can match.
+        declared = {(r.get("exit_status"), r.get("signal_reason")) for r in automatic}
+        automatic.extend(
+            dict(rule)
+            for rule in SHARED_AUTOMATIC_RETRIES
+            if (rule.get("exit_status"), rule.get("signal_reason")) not in declared
         )
 
 

doc/user/content/sql/system-catalog/mz_internal.md

@@ -227,6 +227,7 @@ usage.
 | `disk_bytes`        | [`uint8`]    | Approximate disk usage, in bytes.
 | `heap_bytes`        | [`uint8`]    | Approximate heap (RAM + swap) usage, in bytes.
 | `heap_limit`        | [`uint8`]    | Available heap (RAM + swap) space, in bytes.
+| `swap_bytes`        | [`uint8`]    | Approximate swap usage, in bytes.
 
 ## `mz_cluster_replica_metrics_history`
 
@@ -252,6 +253,7 @@ history is retained across restarts.
 | `occurred_at`    | [`timestamp with time zone`] | Wall-clock timestamp at which the event occurred.
 | `heap_bytes`     | [`uint8`] | Approximate heap (RAM + swap) usage, in bytes.
 | `heap_limit`     | [`uint8`] | Available heap (RAM + swap) space, in bytes.
+| `swap_bytes`     | [`uint8`] | Approximate swap usage, in bytes.
 
 ## `mz_cluster_replica_statuses`
 
@@ -298,6 +300,7 @@ At this time, we do not make any guarantees about the exactness or freshness of
 | `memory_percent` | [`double precision`] | Approximate RAM usage, in percent of the total allocation.
 | `disk_percent`   | [`double precision`] | Approximate disk usage, in percent of the total allocation.
 | `heap_percent`   | [`double precision`] | Approximate heap (RAM + swap) usage, in percent of the total allocation.
+| `swap_percent`   | [`double precision`] | Approximate swap usage, in percent of the total heap allocation.
 
 ## `mz_cluster_replica_utilization_history`
 
@@ -316,6 +319,7 @@ At this time, we do not make any guarantees about the exactness or freshness of
 | `memory_percent` | [`double precision`] | Approximate RAM usage, in percent of the total allocation.
 | `disk_percent`   | [`double precision`] | Approximate disk usage, in percent of the total allocation.
 | `heap_percent`   | [`double precision`] | Approximate heap (RAM + swap) usage, in percent of the total allocation.
+| `swap_percent`   | [`double precision`] | Approximate swap usage, in percent of the total heap allocation.
 | `occurred_at`    | [`timestamp with time zone`] | Wall-clock timestamp at which the event occurred.
 
 ## `mz_cluster_replica_history`

src/adapter/src/catalog/open/builtin_schema_migration.rs

@@ -462,6 +462,16 @@ static MIGRATIONS: LazyLock<Vec<MigrationStep>> = LazyLock::new(|| {
             MZ_INTERNAL_SCHEMA,
             "mz_object_dependencies",
         ),
+        // Adding the `swap_bytes` column to `mz_cluster_replica_metrics_history`
+        // is a backward-compatible append, so the shard schema can evolve in
+        // place. See the NOTE above: this version must stay at the workspace's
+        // current dev version until the change ships.
+        MigrationStep::evolution(
+            "26.43.0-dev.0",
+            CatalogItemType::Source,
+            MZ_INTERNAL_SCHEMA,
+            "mz_cluster_replica_metrics_history",
+        ),
     ]
 });
 

src/catalog/src/builtin/mz_internal.rs

@@ -2734,6 +2734,7 @@ pub static MZ_CLUSTER_REPLICA_METRICS_HISTORY: LazyLock<BuiltinSource> =
                 "Approximate heap (RAM + swap) usage, in bytes.",
             ),
             ("heap_limit", "Available heap (RAM + swap) space, in bytes."),
+            ("swap_bytes", "Approximate swap usage, in bytes."),
         ]),
         is_retained_metrics_object: false,
         access: vec![PUBLIC_SELECT],
@@ -2752,6 +2753,7 @@ pub static MZ_CLUSTER_REPLICA_METRICS: LazyLock<BuiltinView> = LazyLock::new(||
         .with_column("disk_bytes", SqlScalarType::UInt64.nullable(true))
         .with_column("heap_bytes", SqlScalarType::UInt64.nullable(true))
         .with_column("heap_limit", SqlScalarType::UInt64.nullable(true))
+        .with_column("swap_bytes", SqlScalarType::UInt64.nullable(true))
         .with_key(vec![0, 1])
         .finish(),
     column_comments: BTreeMap::from_iter([
@@ -2768,6 +2770,7 @@ pub static MZ_CLUSTER_REPLICA_METRICS: LazyLock<BuiltinView> = LazyLock::new(||
             "Approximate heap (RAM + swap) usage, in bytes.",
         ),
         ("heap_limit", "Available heap (RAM + swap) space, in bytes."),
+        ("swap_bytes", "Approximate swap usage, in bytes."),
     ]),
     sql: "
 SELECT
@@ -2778,7 +2781,8 @@ SELECT
     memory_bytes,
     disk_bytes,
     heap_bytes,
-    heap_limit
+    heap_limit,
+    swap_bytes
 FROM mz_internal.mz_cluster_replica_metrics_history
 JOIN mz_cluster_replicas r ON r.id = replica_id
 ORDER BY replica_id, process_id, occurred_at DESC",
@@ -2805,6 +2809,7 @@ ORDER BY replica_id, process_id, occurred_at DESC",
                 ("disk_bytes", SemanticType::ByteCount),
                 ("heap_bytes", SemanticType::ByteCount),
                 ("heap_limit", SemanticType::ByteCount),
+                ("swap_bytes", SemanticType::ByteCount),
             ]
         },
     }),
@@ -5421,6 +5426,7 @@ pub static MZ_CLUSTER_REPLICA_UTILIZATION: LazyLock<BuiltinView> = LazyLock::new
         .with_column("memory_percent", SqlScalarType::Float64.nullable(true))
         .with_column("disk_percent", SqlScalarType::Float64.nullable(true))
         .with_column("heap_percent", SqlScalarType::Float64.nullable(true))
+        .with_column("swap_percent", SqlScalarType::Float64.nullable(true))
         .finish(),
     column_comments: BTreeMap::from_iter([
         ("replica_id", "The ID of a cluster replica."),
@@ -5441,6 +5447,10 @@ pub static MZ_CLUSTER_REPLICA_UTILIZATION: LazyLock<BuiltinView> = LazyLock::new
             "heap_percent",
             "Approximate heap (RAM + swap) usage, in percent of the total allocation.",
         ),
+        (
+            "swap_percent",
+            "Approximate swap usage, in percent of the total heap allocation.",
+        ),
     ]),
     sql: "
 SELECT
@@ -5449,7 +5459,8 @@ SELECT
     m.cpu_nano_cores::float8 / NULLIF(s.cpu_nano_cores, 0) * 100 AS cpu_percent,
     m.memory_bytes::float8 / NULLIF(s.memory_bytes, 0) * 100 AS memory_percent,
     m.disk_bytes::float8 / NULLIF(s.disk_bytes, 0) * 100 AS disk_percent,
-    m.heap_bytes::float8 / NULLIF(m.heap_limit, 0) * 100 AS heap_percent
+    m.heap_bytes::float8 / NULLIF(m.heap_limit, 0) * 100 AS heap_percent,
+    m.swap_bytes::float8 / NULLIF(m.heap_limit, 0) * 100 AS swap_percent
 FROM
     mz_catalog.mz_cluster_replicas AS r
         JOIN mz_catalog.mz_cluster_replica_sizes AS s ON r.size = s.size
@@ -5486,6 +5497,7 @@ pub static MZ_CLUSTER_REPLICA_UTILIZATION_HISTORY: LazyLock<BuiltinView> =
             .with_column("memory_percent", SqlScalarType::Float64.nullable(true))
             .with_column("disk_percent", SqlScalarType::Float64.nullable(true))
             .with_column("heap_percent", SqlScalarType::Float64.nullable(true))
+            .with_column("swap_percent", SqlScalarType::Float64.nullable(true))
             .with_column(
                 "occurred_at",
                 SqlScalarType::TimestampTz { precision: None }.nullable(false),
@@ -5510,6 +5522,10 @@ pub static MZ_CLUSTER_REPLICA_UTILIZATION_HISTORY: LazyLock<BuiltinView> =
                 "heap_percent",
                 "Approximate heap (RAM + swap) usage, in percent of the total allocation.",
             ),
+            (
+                "swap_percent",
+                "Approximate swap usage, in percent of the total heap allocation.",
+            ),
             (
                 "occurred_at",
                 "Wall-clock timestamp at which the event occurred.",
@@ -5523,6 +5539,7 @@ SELECT
     m.memory_bytes::float8 / NULLIF(s.memory_bytes, 0) * 100 AS memory_percent,
     m.disk_bytes::float8 / NULLIF(s.disk_bytes, 0) * 100 AS disk_percent,
     m.heap_bytes::float8 / NULLIF(m.heap_limit, 0) * 100 AS heap_percent,
+    m.swap_bytes::float8 / NULLIF(m.heap_limit, 0) * 100 AS swap_percent,
     m.occurred_at
 FROM
     mz_catalog.mz_cluster_replicas AS r