Merge branch 'main' into dap/planner-inventory

.envrc

@@ -5,3 +5,8 @@ PATH_add out/cockroachdb/bin
 PATH_add out/clickhouse
 PATH_add out/dendrite-stub/bin
 PATH_add out/mgd/root/opt/oxide/mgd/bin
+
+if nix flake show &> /dev/null
+then
+    use flake;
+fi

.github/buildomat/jobs/tuf-repo.sh

@@ -71,7 +71,7 @@ set -o errexit
 set -o pipefail
 set -o xtrace
 
-ALL_BOARDS=(gimlet-{c..e} psc-{b..c} sidecar-{b..c})
+ALL_BOARDS=(gimlet-{c..f} psc-{b..c} sidecar-{b..c})
 
 TOP=$PWD
 VERSION=$(< /input/package/work/version.txt)
@@ -278,8 +278,8 @@ EOF
     done
 }
 # usage:              SERIES           ROT_DIR      ROT_VERSION              BOARDS...
-add_hubris_artifacts  rot-staging-dev  staging/dev  cert-staging-dev-v1.0.4  "${ALL_BOARDS[@]}"
-add_hubris_artifacts  rot-prod-rel     prod/rel     cert-prod-rel-v1.0.4     "${ALL_BOARDS[@]}"
+add_hubris_artifacts  rot-staging-dev  staging/dev  cert-staging-dev-v1.0.5  "${ALL_BOARDS[@]}"
+add_hubris_artifacts  rot-prod-rel     prod/rel     cert-prod-rel-v1.0.5     "${ALL_BOARDS[@]}"
 
 for series in "${SERIES_LIST[@]}"; do
     /work/tufaceous assemble --no-generate-key /work/manifest-"$series".toml /work/repo-"$series".zip

.github/workflows/hakari.yml

@@ -24,7 +24,7 @@ jobs:
         with:
           toolchain: stable
       - name: Install cargo-hakari
-        uses: taiki-e/install-action@bee85d7ea77c01f7a403c22ac2c802b431b093df # v2
+        uses: taiki-e/install-action@7dcb31b8033f96afe112f0df83dcb01f9969d23b # v2
         with:
           tool: cargo-hakari
       - name: Check workspace-hack Cargo.toml is up-to-date

.gitignore

@@ -15,3 +15,4 @@ debug.out
 rusty-tags.vi
 *.sw*
 tags
+.direnv

Cargo.toml

@@ -208,6 +208,7 @@ gateway-client = { path = "clients/gateway-client" }
 gateway-messages = { git = "https://github.com/oxidecomputer/management-gateway-service", rev = "2739c18e80697aa6bc235c935176d14b4d757ee9", default-features = false, features = ["std"] }
 gateway-sp-comms = { git = "https://github.com/oxidecomputer/management-gateway-service", rev = "2739c18e80697aa6bc235c935176d14b4d757ee9" }
 gateway-test-utils = { path = "gateway-test-utils" }
+gethostname = "0.4.3"
 glob = "0.3.1"
 guppy = "0.17.4"
 headers = "0.3.9"
@@ -224,7 +225,7 @@ hyper = "0.14"
 hyper-rustls = "0.26.0"
 hyper-staticfile = "0.9.5"
 illumos-utils = { path = "illumos-utils" }
-indexmap = "2.1.0"
+indexmap = "2.2.2"
 indicatif = { version = "0.17.7", features = ["rayon"] }
 installinator = { path = "installinator" }
 installinator-artifactd = { path = "installinator-artifactd" }
@@ -408,7 +409,7 @@ wicket-common = { path = "wicket-common" }
 wicketd-client = { path = "clients/wicketd-client" }
 zeroize = { version = "1.7.0", features = ["zeroize_derive", "std"] }
 zip = { version = "0.6.6", default-features = false, features = ["deflate","bzip2"] }
-zone = { version = "0.3", default-features = false, features = ["async"] }
+zone = { version = "0.3", default-features = false, features = ["async", "sync"] }
 
 # NOTE: The test profile inherits from the dev profile, so settings under
 # profile.dev get inherited. AVOID setting anything under profile.test: that

common/src/nexus_config.rs

@@ -336,6 +336,8 @@ pub struct BackgroundTaskConfig {
     pub phantom_disks: PhantomDiskConfig,
     /// configuration for service zone nat sync task
     pub sync_service_zone_nat: SyncServiceZoneNatConfig,
+    /// configuration for the bfd manager task
+    pub bfd_manager: BfdManagerConfig,
 }
 
 #[serde_as]
@@ -378,6 +380,14 @@ pub struct NatCleanupConfig {
     pub period_secs: Duration,
 }
 
+#[serde_as]
+#[derive(Clone, Debug, Deserialize, Eq, PartialEq, Serialize)]
+pub struct BfdManagerConfig {
+    /// period (in seconds) for periodic activations of this background task
+    #[serde_as(as = "DurationSeconds<u64>")]
+    pub period_secs: Duration,
+}
+
 #[serde_as]
 #[derive(Clone, Debug, Deserialize, Eq, PartialEq, Serialize)]
 pub struct SyncServiceZoneNatConfig {
@@ -527,7 +537,7 @@ mod test {
     };
     use crate::address::{Ipv6Subnet, RACK_PREFIX};
     use crate::api::internal::shared::SwitchLocation;
-    use crate::nexus_config::SyncServiceZoneNatConfig;
+    use crate::nexus_config::{BfdManagerConfig, SyncServiceZoneNatConfig};
     use camino::{Utf8Path, Utf8PathBuf};
     use dropshot::ConfigDropshot;
     use dropshot::ConfigLogging;
@@ -672,6 +682,7 @@ mod test {
             dns_external.max_concurrent_server_updates = 8
             external_endpoints.period_secs = 9
             nat_cleanup.period_secs = 30
+            bfd_manager.period_secs = 30
             inventory.period_secs = 10
             inventory.nkeep = 11
             inventory.disable = false
@@ -773,6 +784,9 @@ mod test {
                         nat_cleanup: NatCleanupConfig {
                             period_secs: Duration::from_secs(30),
                         },
+                        bfd_manager: BfdManagerConfig {
+                            period_secs: Duration::from_secs(30),
+                        },
                         inventory: InventoryConfig {
                             period_secs: Duration::from_secs(10),
                             nkeep: 11,
@@ -838,6 +852,7 @@ mod test {
             dns_external.max_concurrent_server_updates = 8
             external_endpoints.period_secs = 9
             nat_cleanup.period_secs = 30
+            bfd_manager.period_secs = 30
             inventory.period_secs = 10
             inventory.nkeep = 3
             inventory.disable = false

dev-tools/omdb/src/bin/omdb/db.rs

@@ -2291,7 +2291,6 @@ async fn cmd_db_inventory(
                 opctx,
                 datastore,
                 id,
-                limit,
                 long_string_formatter,
             )
             .await
@@ -2496,16 +2495,12 @@ async fn cmd_db_inventory_collections_show(
     opctx: &OpContext,
     datastore: &DataStore,
     id: Uuid,
-    limit: NonZeroU32,
     long_string_formatter: LongStringFormatter,
 ) -> Result<(), anyhow::Error> {
-    let (collection, incomplete) = datastore
-        .inventory_collection_read_best_effort(opctx, id, limit)
+    let collection = datastore
+        .inventory_collection_read(opctx, id)
         .await
         .context("reading collection")?;
-    if incomplete {
-        limit_error(limit, || "loading collection");
-    }
 
     inv_collection_print(&collection).await?;
     let nerrors = inv_collection_print_errors(&collection).await?;

dev-tools/omdb/tests/env.out

@@ -23,6 +23,11 @@ EXECUTING COMMAND: omdb ["nexus", "--nexus-internal-url", "http://127.0.0.1:REDA
 termination: Exited(0)
 ---------------------------------------------
 stdout:
+task: "bfd_manager"
+    Manages bidirectional fowarding detection (BFD) configuration on rack
+    switches
+
+
 task: "dns_config_external"
     watches external DNS data stored in CockroachDB
 
@@ -96,6 +101,11 @@ EXECUTING COMMAND: omdb ["nexus", "background-tasks", "doc"]
 termination: Exited(0)
 ---------------------------------------------
 stdout:
+task: "bfd_manager"
+    Manages bidirectional fowarding detection (BFD) configuration on rack
+    switches
+
+
 task: "dns_config_external"
     watches external DNS data stored in CockroachDB
 
@@ -156,6 +166,11 @@ EXECUTING COMMAND: omdb ["--dns-server", "[::1]:REDACTED_PORT", "nexus", "backgr
 termination: Exited(0)
 ---------------------------------------------
 stdout:
+task: "bfd_manager"
+    Manages bidirectional fowarding detection (BFD) configuration on rack
+    switches
+
+
 task: "dns_config_external"
     watches external DNS data stored in CockroachDB
 

dev-tools/omdb/tests/successes.out

@@ -217,6 +217,11 @@ EXECUTING COMMAND: omdb ["nexus", "background-tasks", "doc"]
 termination: Exited(0)
 ---------------------------------------------
 stdout:
+task: "bfd_manager"
+    Manages bidirectional fowarding detection (BFD) configuration on rack
+    switches
+
+
 task: "dns_config_external"
     watches external DNS data stored in CockroachDB
 
@@ -339,6 +344,13 @@ task: "nat_v4_garbage_collector"
     started at <REDACTED     TIMESTAMP> (<REDACTED DURATION>s ago) and ran for <REDACTED DURATION>ms
 warning: unknown background task: "nat_v4_garbage_collector" (don't know how to interpret details: Null)
 
+task: "bfd_manager"
+  configured period: every 30s
+  currently executing: no
+  last completed activation: iter 2, triggered by an explicit signal
+    started at <REDACTED     TIMESTAMP> (<REDACTED DURATION>s ago) and ran for <REDACTED DURATION>ms
+warning: unknown background task: "bfd_manager" (don't know how to interpret details: Object {})
+
 task: "external_endpoints"
   configured period: every 1m
   currently executing: no