feat(pageserver): add config items for gc-compaction auto trigger (#10455)

## Problem

part of https://github.com/neondatabase/neon/issues/9114

The automatic trigger is already implemented at
https://github.com/neondatabase/neon/pull/10221 but I need to write some
tests and finish my experiments in staging before I can merge it with
confidence. Given that I have some other patches that will modify the
config items, I'd like to get the config items merged first to reduce
conflicts.

## Summary of changes

* add `l2_lsn` to index_part.json -- below that LSN, data have been
processed by gc-compaction
* add a set of gc-compaction auto trigger control items into the config

---------

Signed-off-by: Alex Chi Z <chi@neon.tech>

control_plane/src/pageserver.rs

@@ -423,6 +423,21 @@ impl PageServerNode {
                 .map(|x| x.parse::<bool>())
                 .transpose()
                 .context("Failed to parse 'rel_size_v2_enabled' as bool")?,
+            gc_compaction_enabled: settings
+                .remove("gc_compaction_enabled")
+                .map(|x| x.parse::<bool>())
+                .transpose()
+                .context("Failed to parse 'gc_compaction_enabled' as bool")?,
+            gc_compaction_initial_threshold_kb: settings
+                .remove("gc_compaction_initial_threshold_kb")
+                .map(|x| x.parse::<u64>())
+                .transpose()
+                .context("Failed to parse 'gc_compaction_initial_threshold_kb' as integer")?,
+            gc_compaction_ratio_percent: settings
+                .remove("gc_compaction_ratio_percent")
+                .map(|x| x.parse::<u64>())
+                .transpose()
+                .context("Failed to parse 'gc_compaction_ratio_percent' as integer")?,
         };
         if !settings.is_empty() {
             bail!("Unrecognized tenant settings: {settings:?}")

libs/pageserver_api/src/config.rs

@@ -305,6 +305,16 @@ pub struct TenantConfigToml {
     /// Enable rel_size_v2 for this tenant. Once enabled, the tenant will persist this information into
     /// `index_part.json`, and it cannot be reversed.
     pub rel_size_v2_enabled: Option<bool>,
+
+    // gc-compaction related configs
+    /// Enable automatic gc-compaction trigger on this tenant.
+    pub gc_compaction_enabled: bool,
+    /// The initial threshold for gc-compaction in KB. Once the total size of layers below the gc-horizon is above this threshold,
+    /// gc-compaction will be triggered.
+    pub gc_compaction_initial_threshold_kb: u64,
+    /// The ratio that triggers the auto gc-compaction. If (the total size of layers between L2 LSN and gc-horizon) / (size below the L2 LSN)
+    /// is above this ratio, gc-compaction will be triggered.
+    pub gc_compaction_ratio_percent: u64,
 }
 
 pub mod defaults {
@@ -498,6 +508,9 @@ pub mod tenant_conf_defaults {
     // By default ingest enough WAL for two new L0 layers before checking if new image
     // image layers should be created.
     pub const DEFAULT_IMAGE_LAYER_CREATION_CHECK_THRESHOLD: u8 = 2;
+    pub const DEFAULT_GC_COMPACTION_ENABLED: bool = false;
+    pub const DEFAULT_GC_COMPACTION_INITIAL_THRESHOLD_KB: u64 = 10240000;
+    pub const DEFAULT_GC_COMPACTION_RATIO_PERCENT: u64 = 100;
 }
 
 impl Default for TenantConfigToml {
@@ -543,6 +556,9 @@ impl Default for TenantConfigToml {
             timeline_offloading: false,
             wal_receiver_protocol_override: None,
             rel_size_v2_enabled: None,
+            gc_compaction_enabled: DEFAULT_GC_COMPACTION_ENABLED,
+            gc_compaction_initial_threshold_kb: DEFAULT_GC_COMPACTION_INITIAL_THRESHOLD_KB,
+            gc_compaction_ratio_percent: DEFAULT_GC_COMPACTION_RATIO_PERCENT,
         }
     }
 }

libs/pageserver_api/src/models.rs

@@ -499,6 +499,12 @@ pub struct TenantConfigPatch {
     pub wal_receiver_protocol_override: FieldPatch<PostgresClientProtocol>,
     #[serde(skip_serializing_if = "FieldPatch::is_noop")]
     pub rel_size_v2_enabled: FieldPatch<bool>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub gc_compaction_enabled: FieldPatch<bool>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub gc_compaction_initial_threshold_kb: FieldPatch<u64>,
+    #[serde(skip_serializing_if = "FieldPatch::is_noop")]
+    pub gc_compaction_ratio_percent: FieldPatch<u64>,
 }
 
 /// An alternative representation of `pageserver::tenant::TenantConf` with
@@ -531,6 +537,9 @@ pub struct TenantConfig {
     pub timeline_offloading: Option<bool>,
     pub wal_receiver_protocol_override: Option<PostgresClientProtocol>,
     pub rel_size_v2_enabled: Option<bool>,
+    pub gc_compaction_enabled: Option<bool>,
+    pub gc_compaction_initial_threshold_kb: Option<u64>,
+    pub gc_compaction_ratio_percent: Option<u64>,
 }
 
 impl TenantConfig {
@@ -561,6 +570,9 @@ impl TenantConfig {
             mut timeline_offloading,
             mut wal_receiver_protocol_override,
             mut rel_size_v2_enabled,
+            mut gc_compaction_enabled,
+            mut gc_compaction_initial_threshold_kb,
+            mut gc_compaction_ratio_percent,
         } = self;
 
         patch.checkpoint_distance.apply(&mut checkpoint_distance);
@@ -606,6 +618,15 @@ impl TenantConfig {
             .wal_receiver_protocol_override
             .apply(&mut wal_receiver_protocol_override);
         patch.rel_size_v2_enabled.apply(&mut rel_size_v2_enabled);
+        patch
+            .gc_compaction_enabled
+            .apply(&mut gc_compaction_enabled);
+        patch
+            .gc_compaction_initial_threshold_kb
+            .apply(&mut gc_compaction_initial_threshold_kb);
+        patch
+            .gc_compaction_ratio_percent
+            .apply(&mut gc_compaction_ratio_percent);
 
         Self {
             checkpoint_distance,
@@ -633,6 +654,9 @@ impl TenantConfig {
             timeline_offloading,
             wal_receiver_protocol_override,
             rel_size_v2_enabled,
+            gc_compaction_enabled,
+            gc_compaction_initial_threshold_kb,
+            gc_compaction_ratio_percent,
         }
     }
 }

pageserver/src/tenant.rs

@@ -5476,6 +5476,11 @@ pub(crate) mod harness {
                 timeline_offloading: Some(tenant_conf.timeline_offloading),
                 wal_receiver_protocol_override: tenant_conf.wal_receiver_protocol_override,
                 rel_size_v2_enabled: tenant_conf.rel_size_v2_enabled,
+                gc_compaction_enabled: Some(tenant_conf.gc_compaction_enabled),
+                gc_compaction_initial_threshold_kb: Some(
+                    tenant_conf.gc_compaction_initial_threshold_kb,
+                ),
+                gc_compaction_ratio_percent: Some(tenant_conf.gc_compaction_ratio_percent),
             }
         }
     }

pageserver/src/tenant/config.rs

@@ -360,6 +360,15 @@ pub struct TenantConfOpt {
 
     #[serde(skip_serializing_if = "Option::is_none")]
     pub rel_size_v2_enabled: Option<bool>,
+
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub gc_compaction_enabled: Option<bool>,
+
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub gc_compaction_initial_threshold_kb: Option<u64>,
+
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub gc_compaction_ratio_percent: Option<u64>,
 }
 
 impl TenantConfOpt {
@@ -429,6 +438,15 @@ impl TenantConfOpt {
                 .wal_receiver_protocol_override
                 .or(global_conf.wal_receiver_protocol_override),
             rel_size_v2_enabled: self.rel_size_v2_enabled.or(global_conf.rel_size_v2_enabled),
+            gc_compaction_enabled: self
+                .gc_compaction_enabled
+                .unwrap_or(global_conf.gc_compaction_enabled),
+            gc_compaction_initial_threshold_kb: self
+                .gc_compaction_initial_threshold_kb
+                .unwrap_or(global_conf.gc_compaction_initial_threshold_kb),
+            gc_compaction_ratio_percent: self
+                .gc_compaction_ratio_percent
+                .unwrap_or(global_conf.gc_compaction_ratio_percent),
         }
     }
 
@@ -459,6 +477,9 @@ impl TenantConfOpt {
             mut timeline_offloading,
             mut wal_receiver_protocol_override,
             mut rel_size_v2_enabled,
+            mut gc_compaction_enabled,
+            mut gc_compaction_initial_threshold_kb,
+            mut gc_compaction_ratio_percent,
         } = self;
 
         patch.checkpoint_distance.apply(&mut checkpoint_distance);
@@ -528,6 +549,15 @@ impl TenantConfOpt {
             .wal_receiver_protocol_override
             .apply(&mut wal_receiver_protocol_override);
         patch.rel_size_v2_enabled.apply(&mut rel_size_v2_enabled);
+        patch
+            .gc_compaction_enabled
+            .apply(&mut gc_compaction_enabled);
+        patch
+            .gc_compaction_initial_threshold_kb
+            .apply(&mut gc_compaction_initial_threshold_kb);
+        patch
+            .gc_compaction_ratio_percent
+            .apply(&mut gc_compaction_ratio_percent);
 
         Ok(Self {
             checkpoint_distance,
@@ -555,6 +585,9 @@ impl TenantConfOpt {
             timeline_offloading,
             wal_receiver_protocol_override,
             rel_size_v2_enabled,
+            gc_compaction_enabled,
+            gc_compaction_initial_threshold_kb,
+            gc_compaction_ratio_percent,
         })
     }
 }
@@ -611,6 +644,9 @@ impl From<TenantConfOpt> for models::TenantConfig {
             timeline_offloading: value.timeline_offloading,
             wal_receiver_protocol_override: value.wal_receiver_protocol_override,
             rel_size_v2_enabled: value.rel_size_v2_enabled,
+            gc_compaction_enabled: value.gc_compaction_enabled,
+            gc_compaction_initial_threshold_kb: value.gc_compaction_initial_threshold_kb,
+            gc_compaction_ratio_percent: value.gc_compaction_ratio_percent,
         }
     }
 }

pageserver/src/tenant/remote_timeline_client/index.rs

@@ -77,11 +77,17 @@ pub struct IndexPart {
     ///
     /// None means no aux files have been written to the storage before the point
     /// when this flag is introduced.
+    ///
+    /// This flag is not used any more as all tenants have been transitioned to the new aux file policy.
     #[serde(skip_serializing_if = "Option::is_none", default)]
     pub(crate) last_aux_file_policy: Option<AuxFilePolicy>,
 
     #[serde(skip_serializing_if = "Option::is_none", default)]
     pub(crate) rel_size_migration: Option<RelSizeMigration>,
+
+    /// The LSN of gc-compaction horizon. Once gc-compaction is finished for all layer files below an LSN, this LSN will be updated.
+    #[serde(skip_serializing_if = "Option::is_none", default)]
+    pub(crate) l2_lsn: Option<Lsn>,
 }
 
 #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
@@ -116,10 +122,11 @@ impl IndexPart {
     /// - 9: +gc_blocking
     /// - 10: +import_pgdata
     /// - 11: +rel_size_migration
-    const LATEST_VERSION: usize = 11;
+    /// - 12: +l2_lsn
+    const LATEST_VERSION: usize = 12;
 
     // Versions we may see when reading from a bucket.
-    pub const KNOWN_VERSIONS: &'static [usize] = &[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11];
+    pub const KNOWN_VERSIONS: &'static [usize] = &[1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12];
 
     pub const FILE_NAME: &'static str = "index_part.json";
 
@@ -136,6 +143,7 @@ impl IndexPart {
             last_aux_file_policy: None,
             import_pgdata: None,
             rel_size_migration: None,
+            l2_lsn: None,
         }
     }
 
@@ -437,6 +445,7 @@ mod tests {
             last_aux_file_policy: None,
             import_pgdata: None,
             rel_size_migration: None,
+            l2_lsn: None,
         };
 
         let part = IndexPart::from_json_bytes(example.as_bytes()).unwrap();
@@ -483,6 +492,7 @@ mod tests {
             last_aux_file_policy: None,
             import_pgdata: None,
             rel_size_migration: None,
+            l2_lsn: None,
         };
 
         let part = IndexPart::from_json_bytes(example.as_bytes()).unwrap();
@@ -530,6 +540,7 @@ mod tests {
             last_aux_file_policy: None,
             import_pgdata: None,
             rel_size_migration: None,
+            l2_lsn: None,
         };
 
         let part = IndexPart::from_json_bytes(example.as_bytes()).unwrap();
@@ -580,6 +591,7 @@ mod tests {
             last_aux_file_policy: None,
             import_pgdata: None,
             rel_size_migration: None,
+            l2_lsn: None,
         };
 
         let empty_layers_parsed = IndexPart::from_json_bytes(empty_layers_json.as_bytes()).unwrap();
@@ -625,6 +637,7 @@ mod tests {
             last_aux_file_policy: None,
             import_pgdata: None,
             rel_size_migration: None,
+            l2_lsn: None,
         };
 
         let part = IndexPart::from_json_bytes(example.as_bytes()).unwrap();
@@ -673,6 +686,7 @@ mod tests {
             last_aux_file_policy: None,
             import_pgdata: None,
             rel_size_migration: None,
+            l2_lsn: None,
         };
 
         let part = IndexPart::from_json_bytes(example.as_bytes()).unwrap();
@@ -726,6 +740,7 @@ mod tests {
             last_aux_file_policy: Some(AuxFilePolicy::V2),
             import_pgdata: None,
             rel_size_migration: None,
+            l2_lsn: None,
         };
 
         let part = IndexPart::from_json_bytes(example.as_bytes()).unwrap();
@@ -784,6 +799,7 @@ mod tests {
             last_aux_file_policy: Default::default(),
             import_pgdata: None,
             rel_size_migration: None,
+            l2_lsn: None,
         };
 
         let part = IndexPart::from_json_bytes(example.as_bytes()).unwrap();
@@ -843,6 +859,7 @@ mod tests {
             last_aux_file_policy: Default::default(),
             import_pgdata: None,
             rel_size_migration: None,
+            l2_lsn: None,
         };
 
         let part = IndexPart::from_json_bytes(example.as_bytes()).unwrap();
@@ -907,6 +924,7 @@ mod tests {
             archived_at: None,
             import_pgdata: None,
             rel_size_migration: None,
+            l2_lsn: None,
         };
 
         let part = IndexPart::from_json_bytes(example.as_bytes()).unwrap();
@@ -984,6 +1002,7 @@ mod tests {
                 idempotency_key: import_pgdata::index_part_format::IdempotencyKey::new("specified-by-client-218a5213-5044-4562-a28d-d024c5f057f5".to_string()),
             }))),
             rel_size_migration: None,
+            l2_lsn: None,
         };
 
         let part = IndexPart::from_json_bytes(example.as_bytes()).unwrap();
@@ -1062,6 +1081,87 @@ mod tests {
                 idempotency_key: import_pgdata::index_part_format::IdempotencyKey::new("specified-by-client-218a5213-5044-4562-a28d-d024c5f057f5".to_string()),
             }))),
             rel_size_migration: Some(RelSizeMigration::Legacy),
+            l2_lsn: None,
+        };
+
+        let part = IndexPart::from_json_bytes(example.as_bytes()).unwrap();
+        assert_eq!(part, expected);
+    }
+
+    #[test]
+    fn v12_l2_lsn_is_parsed() {
+        let example = r#"{
+            "version": 12,
+            "layer_metadata":{
+                "000000000000000000000000000000000000-FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF__0000000001696070-00000000016960E9": { "file_size": 25600000 },
+                "000000000000000000000000000000000000-FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF__00000000016B59D8-00000000016B5A51": { "file_size": 9007199254741001 }
+            },
+            "disk_consistent_lsn":"0/16960E8",
+            "metadata": {
+                "disk_consistent_lsn": "0/16960E8",
+                "prev_record_lsn": "0/1696070",
+                "ancestor_timeline": "e45a7f37d3ee2ff17dc14bf4f4e3f52e",
+                "ancestor_lsn": "0/0",
+                "latest_gc_cutoff_lsn": "0/1696070",
+                "initdb_lsn": "0/1696070",
+                "pg_version": 14
+            },
+            "gc_blocking": {
+                "started_at": "2024-07-19T09:00:00.123",
+                "reasons": ["DetachAncestor"]
+            },
+            "import_pgdata": {
+                "V1": {
+                    "Done": {
+                        "idempotency_key": "specified-by-client-218a5213-5044-4562-a28d-d024c5f057f5",
+                        "started_at": "2024-11-13T09:23:42.123",
+                        "finished_at": "2024-11-13T09:42:23.123"
+                    }
+                }
+            },
+            "rel_size_migration": "legacy",
+            "l2_lsn": "0/16960E8"
+        }"#;
+
+        let expected = IndexPart {
+            version: 12,
+            layer_metadata: HashMap::from([
+                ("000000000000000000000000000000000000-FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF__0000000001696070-00000000016960E9".parse().unwrap(), LayerFileMetadata {
+                    file_size: 25600000,
+                    generation: Generation::none(),
+                    shard: ShardIndex::unsharded()
+                }),
+                ("000000000000000000000000000000000000-FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF__00000000016B59D8-00000000016B5A51".parse().unwrap(), LayerFileMetadata {
+                    file_size: 9007199254741001,
+                    generation: Generation::none(),
+                    shard: ShardIndex::unsharded()
+                })
+            ]),
+            disk_consistent_lsn: "0/16960E8".parse::<Lsn>().unwrap(),
+            metadata: TimelineMetadata::new(
+                Lsn::from_str("0/16960E8").unwrap(),
+                Some(Lsn::from_str("0/1696070").unwrap()),
+                Some(TimelineId::from_str("e45a7f37d3ee2ff17dc14bf4f4e3f52e").unwrap()),
+                Lsn::INVALID,
+                Lsn::from_str("0/1696070").unwrap(),
+                Lsn::from_str("0/1696070").unwrap(),
+                14,
+            ).with_recalculated_checksum().unwrap(),
+            deleted_at: None,
+            lineage: Default::default(),
+            gc_blocking: Some(GcBlocking {
+                started_at: parse_naive_datetime("2024-07-19T09:00:00.123000000"),
+                reasons: enumset::EnumSet::from_iter([GcBlockingReason::DetachAncestor]),
+            }),
+            last_aux_file_policy: Default::default(),
+            archived_at: None,
+            import_pgdata: Some(import_pgdata::index_part_format::Root::V1(import_pgdata::index_part_format::V1::Done(import_pgdata::index_part_format::Done{
+                started_at: parse_naive_datetime("2024-11-13T09:23:42.123000000"),
+                finished_at: parse_naive_datetime("2024-11-13T09:42:23.123000000"),
+                idempotency_key: import_pgdata::index_part_format::IdempotencyKey::new("specified-by-client-218a5213-5044-4562-a28d-d024c5f057f5".to_string()),
+            }))),
+            rel_size_migration: Some(RelSizeMigration::Legacy),
+            l2_lsn: Some("0/16960E8".parse::<Lsn>().unwrap()),
         };
 
         let part = IndexPart::from_json_bytes(example.as_bytes()).unwrap();

test_runner/regress/test_attach_tenant_config.py

@@ -177,6 +177,9 @@ def test_fully_custom_config(positive_env: NeonEnv):
             "args": {"format": "bincode", "compression": {"zstd": {"level": 1}}},
         },
         "rel_size_v2_enabled": True,
+        "gc_compaction_enabled": True,
+        "gc_compaction_initial_threshold_kb": 1024000,
+        "gc_compaction_ratio_percent": 200,
     }
 
     vps_http = env.storage_controller.pageserver_api()