rebase on main, fix test

Created using spr 1.3.6-beta.1
oxidecomputer · Aug 30, 2024 · 3fde731 · 3fde731
2 parents 318b00b + 61e1b38
commit 3fde731
Show file tree

Hide file tree

Showing 33 changed files with 843 additions and 145 deletions.
diff --git a/Cargo.lock b/Cargo.lock
diff --git a/Cargo.toml b/Cargo.toml
@@ -348,7 +348,7 @@ dyn-clone = "1.0.17"
 either = "1.13.0"
 expectorate = "1.1.0"
 fatfs = "0.3.6"
-filetime = "0.2.24"
+filetime = "0.2.25"
 flate2 = "1.0.31"
 float-ord = "0.3.2"
 flume = "0.11.0"

diff --git a/dev-tools/omdb/src/bin/omdb/nexus.rs b/dev-tools/omdb/src/bin/omdb/nexus.rs
@@ -34,6 +34,7 @@ use nexus_saga_recovery::LastPass;
 use nexus_types::deployment::Blueprint;
 use nexus_types::internal_api::background::LookupRegionPortStatus;
 use nexus_types::internal_api::background::RegionReplacementDriverStatus;
+use nexus_types::internal_api::background::RegionSnapshotReplacementFinishStatus;
 use nexus_types::internal_api::background::RegionSnapshotReplacementGarbageCollectStatus;
 use nexus_types::internal_api::background::RegionSnapshotReplacementStartStatus;
 use nexus_types::internal_api::background::RegionSnapshotReplacementStepStatus;
@@ -1661,6 +1662,30 @@ fn print_task_details(bgtask: &BackgroundTask, details: &serde_json::Value) {
                 println!("{}", table);
             }
         }
+    } else if name == "region_snapshot_replacement_finish" {
+        match serde_json::from_value::<RegionSnapshotReplacementFinishStatus>(
+            details.clone(),
+        ) {
+            Err(error) => eprintln!(
+                "warning: failed to interpret task details: {:?}: {:?}",
+                error, details
+            ),
+
+            Ok(status) => {
+                println!(
+                    "    total records transitioned to done: {}",
+                    status.records_set_to_done.len(),
+                );
+                for line in &status.records_set_to_done {
+                    println!("    > {line}");
+                }
+
+                println!("    errors: {}", status.errors.len());
+                for line in &status.errors {
+                    println!("    > {line}");
+                }
+            }
+        }
     } else {
         println!(
             "warning: unknown background task: {:?} \
@@ -1690,16 +1715,17 @@ fn bgtask_apply_kv_style(table: &mut tabled::Table) {
     );
 }
 
-// Extract and remove the event report. (If we don't do this, the `Debug`
-// output can be quite large.)
+/// Extract and remove the event report, returning None if it wasn't found and
+/// an error if something else went wrong. (If we don't do this, the `Debug`
+/// output can be quite large.)
 fn extract_event_buffer(
     value: &mut serde_json::Value,
-) -> anyhow::Result<EventBuffer<NestedSpec>> {
+) -> anyhow::Result<Option<EventBuffer<NestedSpec>>> {
     let Some(obj) = value.as_object_mut() else {
         bail!("expected value to be an object")
     };
     let Some(event_report) = obj.remove("event_report") else {
-        bail!("expected 'event_report' field in value")
+        return Ok(None);
     };
 
     // Try deserializing the event report generically. We could deserialize to
@@ -1714,19 +1740,22 @@ fn extract_event_buffer(
 
     let mut event_buffer = EventBuffer::default();
     event_buffer.add_event_report(event_report);
-    Ok(event_buffer)
+    Ok(Some(event_buffer))
 }
 
 // Make a short summary of the current state of an execution based on an event
 // buffer, and add it to the table.
 fn push_event_buffer_summary(
-    event_buffer: anyhow::Result<EventBuffer<NestedSpec>>,
+    event_buffer: anyhow::Result<Option<EventBuffer<NestedSpec>>>,
     builder: &mut tabled::builder::Builder,
 ) {
     match event_buffer {
-        Ok(buffer) => {
+        Ok(Some(buffer)) => {
             event_buffer_summary_impl(buffer, builder);
         }
+        Ok(None) => {
+            builder.push_record(["status:", "(no event report found)"]);
+        }
         Err(error) => {
             builder.push_record([
                 "event report error:".to_string(),

diff --git a/dev-tools/omdb/tests/env.out b/dev-tools/omdb/tests/env.out
@@ -127,6 +127,10 @@ task: "region_replacement_driver"
     drive region replacements forward to completion
 
 
+task: "region_snapshot_replacement_finish"
+    complete a region snapshot replacement if all the steps are done
+
+
 task: "region_snapshot_replacement_garbage_collection"
     clean up all region snapshot replacement step volumes
 
@@ -289,6 +293,10 @@ task: "region_replacement_driver"
     drive region replacements forward to completion
 
 
+task: "region_snapshot_replacement_finish"
+    complete a region snapshot replacement if all the steps are done
+
+
 task: "region_snapshot_replacement_garbage_collection"
     clean up all region snapshot replacement step volumes
 
@@ -438,6 +446,10 @@ task: "region_replacement_driver"
     drive region replacements forward to completion
 
 
+task: "region_snapshot_replacement_finish"
+    complete a region snapshot replacement if all the steps are done
+
+
 task: "region_snapshot_replacement_garbage_collection"
     clean up all region snapshot replacement step volumes
 

diff --git a/dev-tools/omdb/tests/successes.out b/dev-tools/omdb/tests/successes.out
@@ -343,6 +343,10 @@ task: "region_replacement_driver"
     drive region replacements forward to completion
 
 
+task: "region_snapshot_replacement_finish"
+    complete a region snapshot replacement if all the steps are done
+
+
 task: "region_snapshot_replacement_garbage_collection"
     clean up all region snapshot replacement step volumes
 
@@ -594,6 +598,14 @@ task: "region_replacement_driver"
     number of region replacement finish sagas started ok: 0
     number of errors: 0
 
+task: "region_snapshot_replacement_finish"
+  configured period: every <REDACTED_DURATION>s
+  currently executing: no
+  last completed activation: <REDACTED ITERATIONS>, triggered by a periodic timer firing
+    started at <REDACTED     TIMESTAMP> (<REDACTED DURATION>s ago) and ran for <REDACTED DURATION>ms
+    total records transitioned to done: 0
+    errors: 0
+
 task: "region_snapshot_replacement_garbage_collection"
   configured period: every <REDACTED_DURATION>s
   currently executing: no
@@ -1012,6 +1024,14 @@ task: "region_replacement_driver"
     number of region replacement finish sagas started ok: 0
     number of errors: 0
 
+task: "region_snapshot_replacement_finish"
+  configured period: every <REDACTED_DURATION>s
+  currently executing: no
+  last completed activation: <REDACTED ITERATIONS>, triggered by a periodic timer firing
+    started at <REDACTED     TIMESTAMP> (<REDACTED DURATION>s ago) and ran for <REDACTED DURATION>ms
+    total records transitioned to done: 0
+    errors: 0
+
 task: "region_snapshot_replacement_garbage_collection"
   configured period: every <REDACTED_DURATION>s
   currently executing: no

diff --git a/end-to-end-tests/src/bin/bootstrap.rs b/end-to-end-tests/src/bin/bootstrap.rs
@@ -8,8 +8,8 @@ use oxide_client::types::{
     NameOrId, SiloQuotasUpdate,
 };
 use oxide_client::{
-    ClientDisksExt, ClientHiddenExt, ClientProjectsExt,
-    ClientSystemNetworkingExt, ClientSystemSilosExt,
+    ClientDisksExt, ClientHiddenExt, ClientProjectsExt, ClientSystemIpPoolsExt,
+    ClientSystemSilosExt,
 };
 use serde::{de::DeserializeOwned, Deserialize};
 use std::time::Duration;

diff --git a/end-to-end-tests/src/bin/commtest.rs b/end-to-end-tests/src/bin/commtest.rs
@@ -9,7 +9,7 @@ use oxide_client::{
         UsernamePasswordCredentials,
     },
     ClientHiddenExt, ClientLoginExt, ClientProjectsExt,
-    ClientSystemHardwareExt, ClientSystemNetworkingExt, ClientSystemStatusExt,
+    ClientSystemHardwareExt, ClientSystemIpPoolsExt, ClientSystemStatusExt,
     ClientVpcsExt,
 };
 use std::{

diff --git a/nexus-config/src/nexus_config.rs b/nexus-config/src/nexus_config.rs
@@ -398,6 +398,9 @@ pub struct BackgroundTaskConfig {
         RegionSnapshotReplacementGarbageCollectionConfig,
     /// configuration for region snapshot replacement step task
     pub region_snapshot_replacement_step: RegionSnapshotReplacementStepConfig,
+    /// configuration for region snapshot replacement finisher task
+    pub region_snapshot_replacement_finish:
+        RegionSnapshotReplacementFinishConfig,
 }
 
 #[serde_as]
@@ -658,6 +661,14 @@ pub struct RegionSnapshotReplacementStepConfig {
     pub period_secs: Duration,
 }
 
+#[serde_as]
+#[derive(Clone, Debug, Deserialize, Eq, PartialEq, Serialize)]
+pub struct RegionSnapshotReplacementFinishConfig {
+    /// period (in seconds) for periodic activations of this background task
+    #[serde_as(as = "DurationSeconds<u64>")]
+    pub period_secs: Duration,
+}
+
 /// Configuration for a nexus server
 #[derive(Clone, Debug, Deserialize, PartialEq, Serialize)]
 pub struct PackageConfig {
@@ -908,6 +919,7 @@ mod test {
             region_snapshot_replacement_start.period_secs = 30
             region_snapshot_replacement_garbage_collection.period_secs = 30
             region_snapshot_replacement_step.period_secs = 30
+            region_snapshot_replacement_finish.period_secs = 30
             [default_region_allocation_strategy]
             type = "random"
             seed = 0
@@ -1082,6 +1094,10 @@ mod test {
                             RegionSnapshotReplacementStepConfig {
                                 period_secs: Duration::from_secs(30),
                             },
+                        region_snapshot_replacement_finish:
+                            RegionSnapshotReplacementFinishConfig {
+                                period_secs: Duration::from_secs(30),
+                            },
                     },
                     default_region_allocation_strategy:
                         crate::nexus_config::RegionAllocationStrategy::Random {
@@ -1161,6 +1177,7 @@ mod test {
             region_snapshot_replacement_start.period_secs = 30
             region_snapshot_replacement_garbage_collection.period_secs = 30
             region_snapshot_replacement_step.period_secs = 30
+            region_snapshot_replacement_finish.period_secs = 30
             [default_region_allocation_strategy]
             type = "random"
             "##,

diff --git a/nexus/examples/config-second.toml b/nexus/examples/config-second.toml
@@ -142,6 +142,7 @@ lookup_region_port.period_secs = 60
 region_snapshot_replacement_start.period_secs = 30
 region_snapshot_replacement_garbage_collection.period_secs = 30
 region_snapshot_replacement_step.period_secs = 30
+region_snapshot_replacement_finish.period_secs = 30
 
 [default_region_allocation_strategy]
 # allocate region on 3 random distinct zpools, on 3 random distinct sleds.

diff --git a/nexus/examples/config.toml b/nexus/examples/config.toml
@@ -128,6 +128,7 @@ lookup_region_port.period_secs = 60
 region_snapshot_replacement_start.period_secs = 30
 region_snapshot_replacement_garbage_collection.period_secs = 30
 region_snapshot_replacement_step.period_secs = 30
+region_snapshot_replacement_finish.period_secs = 30
 
 [default_region_allocation_strategy]
 # allocate region on 3 random distinct zpools, on 3 random distinct sleds.

diff --git a/nexus/external-api/output/nexus_tags.txt b/nexus/external-api/output/nexus_tags.txt
@@ -146,11 +146,7 @@ sled_view                                GET      /v1/system/hardware/sleds/{sle
 switch_list                              GET      /v1/system/hardware/switches
 switch_view                              GET      /v1/system/hardware/switches/{switch_id}
 
-API operations found with tag "system/metrics"
-OPERATION ID                             METHOD   URL PATH
-system_metric                            GET      /v1/system/metrics/{metric_name}
-
-API operations found with tag "system/networking"
+API operations found with tag "system/ip-pools"
 OPERATION ID                             METHOD   URL PATH
 ip_pool_create                           POST     /v1/system/ip-pools
 ip_pool_delete                           DELETE   /v1/system/ip-pools/{pool}
@@ -169,6 +165,13 @@ ip_pool_silo_update                      PUT      /v1/system/ip-pools/{pool}/sil
 ip_pool_update                           PUT      /v1/system/ip-pools/{pool}
 ip_pool_utilization_view                 GET      /v1/system/ip-pools/{pool}/utilization
 ip_pool_view                             GET      /v1/system/ip-pools/{pool}
+
+API operations found with tag "system/metrics"
+OPERATION ID                             METHOD   URL PATH
+system_metric                            GET      /v1/system/metrics/{metric_name}
+
+API operations found with tag "system/networking"
+OPERATION ID                             METHOD   URL PATH
 networking_address_lot_block_list        GET      /v1/system/networking/address-lot/{address_lot}/blocks
 networking_address_lot_create            POST     /v1/system/networking/address-lot
 networking_address_lot_delete            DELETE   /v1/system/networking/address-lot/{address_lot}