test results

34e69cfc93 18:04:59 - 18:31:15 => 05:01 + 21:15 = 26:16 duration

That's ca 5min slower than what we saw without tokio-epoll-uring
(scratches head)

libs/pageserver_api/src/models.rs

@@ -371,6 +371,8 @@ pub struct TenantInfo {
     /// If a layer is present in both local FS and S3, it counts only once.
     pub current_physical_size: Option<u64>, // physical size is only included in `tenant_status` endpoint
     pub attachment_status: TenantAttachmentStatus,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub generation: Option<u32>,
 }
 
 /// This represents the output of the "timeline_detail" and "timeline_list" API calls.
@@ -832,6 +834,7 @@ mod tests {
             state: TenantState::Active,
             current_physical_size: Some(42),
             attachment_status: TenantAttachmentStatus::Attached,
+            generation: None,
         };
         let expected_active = json!({
             "id": original_active.id.to_string(),
@@ -852,6 +855,7 @@ mod tests {
             },
             current_physical_size: Some(42),
             attachment_status: TenantAttachmentStatus::Attached,
+            generation: None,
         };
         let expected_broken = json!({
             "id": original_broken.id.to_string(),

pageserver/ctl/src/layers.rs

@@ -1,13 +1,15 @@
 use std::path::{Path, PathBuf};
 
 use anyhow::Result;
-use camino::Utf8Path;
+use camino::{Utf8Path, Utf8PathBuf};
 use clap::Subcommand;
 use pageserver::context::{DownloadBehavior, RequestContext};
 use pageserver::task_mgr::TaskKind;
 use pageserver::tenant::block_io::BlockCursor;
 use pageserver::tenant::disk_btree::DiskBtreeReader;
 use pageserver::tenant::storage_layer::delta_layer::{BlobRef, Summary};
+use pageserver::tenant::storage_layer::{delta_layer, image_layer};
+use pageserver::tenant::storage_layer::{DeltaLayer, ImageLayer};
 use pageserver::tenant::{TENANTS_SEGMENT_NAME, TIMELINES_SEGMENT_NAME};
 use pageserver::{page_cache, virtual_file};
 use pageserver::{
@@ -20,6 +22,7 @@ use pageserver::{
 };
 use std::fs;
 use utils::bin_ser::BeSer;
+use utils::id::{TenantId, TimelineId};
 
 use crate::layer_map_analyzer::parse_filename;
 
@@ -45,6 +48,13 @@ pub(crate) enum LayerCmd {
         /// The id from list-layer command
         id: usize,
     },
+    RewriteSummary {
+        layer_file_path: Utf8PathBuf,
+        #[clap(long)]
+        new_tenant_id: Option<TenantId>,
+        #[clap(long)]
+        new_timeline_id: Option<TimelineId>,
+    },
 }
 
 async fn read_delta_file(path: impl AsRef<Path>, ctx: &RequestContext) -> Result<()> {
@@ -100,6 +110,7 @@ pub(crate) async fn main(cmd: &LayerCmd) -> Result<()> {
                     println!("- timeline {}", timeline.file_name().to_string_lossy());
                 }
             }
+            Ok(())
         }
         LayerCmd::ListLayer {
             path,
@@ -128,6 +139,7 @@ pub(crate) async fn main(cmd: &LayerCmd) -> Result<()> {
                     idx += 1;
                 }
             }
+            Ok(())
         }
         LayerCmd::DumpLayer {
             path,
@@ -168,7 +180,63 @@ pub(crate) async fn main(cmd: &LayerCmd) -> Result<()> {
                     idx += 1;
                 }
             }
+            Ok(())
+        }
+        LayerCmd::RewriteSummary {
+            layer_file_path,
+            new_tenant_id,
+            new_timeline_id,
+        } => {
+            pageserver::virtual_file::init(10);
+            pageserver::page_cache::init(100);
+
+            let ctx = RequestContext::new(TaskKind::DebugTool, DownloadBehavior::Error);
+
+            macro_rules! rewrite_closure {
+                ($($summary_ty:tt)*) => {{
+                    |summary| $($summary_ty)* {
+                        tenant_id: new_tenant_id.unwrap_or(summary.tenant_id),
+                        timeline_id: new_timeline_id.unwrap_or(summary.timeline_id),
+                        ..summary
+                    }
+                }};
+            }
+
+            let res = ImageLayer::rewrite_summary(
+                layer_file_path,
+                rewrite_closure!(image_layer::Summary),
+                &ctx,
+            )
+            .await;
+            match res {
+                Ok(()) => {
+                    println!("Successfully rewrote summary of image layer {layer_file_path}");
+                    return Ok(());
+                }
+                Err(image_layer::RewriteSummaryError::MagicMismatch) => (), // fallthrough
+                Err(image_layer::RewriteSummaryError::Other(e)) => {
+                    return Err(e);
+                }
+            }
+
+            let res = DeltaLayer::rewrite_summary(
+                layer_file_path,
+                rewrite_closure!(delta_layer::Summary),
+                &ctx,
+            )
+            .await;
+            match res {
+                Ok(()) => {
+                    println!("Successfully rewrote summary of delta layer {layer_file_path}");
+                    return Ok(());
+                }
+                Err(delta_layer::RewriteSummaryError::MagicMismatch) => (), // fallthrough
+                Err(delta_layer::RewriteSummaryError::Other(e)) => {
+                    return Err(e);
+                }
+            }
+
+            anyhow::bail!("not an image or delta layer: {layer_file_path}");
         }
     }
-    Ok(())
 }

pageserver/src/bin/pageserver.rs

@@ -668,6 +668,31 @@ fn start_pageserver(
         );
     }
 
+    task_mgr::spawn(
+        BACKGROUND_RUNTIME.handle(),
+        TaskKind::BackgroundRuntimeTurnaroundMeasure,
+        None,
+        None,
+        "background runtime turnaround measure",
+        true,
+        async move {
+            let server = hyper::Server::try_bind(&"0.0.0.0:2342".parse().unwrap()).expect("bind");
+            let server = server
+                .serve(hyper::service::make_service_fn(|_| async move {
+                    Ok::<_, std::convert::Infallible>(hyper::service::service_fn(
+                        move |_: hyper::Request<hyper::Body>| async move {
+                            Ok::<_, std::convert::Infallible>(hyper::Response::new(
+                                hyper::Body::from(format!("alive")),
+                            ))
+                        },
+                    ))
+                }))
+                .with_graceful_shutdown(task_mgr::shutdown_watcher());
+            server.await?;
+            Ok(())
+        },
+    );
+
     let mut shutdown_pageserver = Some(shutdown_pageserver.drop_guard());
 
     // All started up! Now just sit and wait for shutdown signal.

pageserver/src/consumption_metrics.rs

@@ -269,7 +269,7 @@ async fn calculate_synthetic_size_worker(
             }
         };
 
-        for (tenant_id, tenant_state) in tenants {
+        for (tenant_id, tenant_state, _gen) in tenants {
             if tenant_state != TenantState::Active {
                 continue;
             }

pageserver/src/consumption_metrics/metrics.rs

@@ -197,7 +197,7 @@ pub(super) async fn collect_all_metrics(
         }
     };
 
-    let tenants = futures::stream::iter(tenants).filter_map(|(id, state)| async move {
+    let tenants = futures::stream::iter(tenants).filter_map(|(id, state, _)| async move {
         if state != TenantState::Active {
             None
         } else {

pageserver/src/disk_usage_eviction_task.rs

@@ -541,7 +541,7 @@ async fn collect_eviction_candidates(
 
     let mut candidates = Vec::new();
 
-    for (tenant_id, _state) in &tenants {
+    for (tenant_id, _state, _gen) in &tenants {
         if cancel.is_cancelled() {
             return Ok(EvictionCandidates::Cancelled);
         }

pageserver/src/http/routes.rs

@@ -768,11 +768,12 @@ async fn tenant_list_handler(
             ApiError::ResourceUnavailable("Tenant map is initializing or shutting down".into())
         })?
         .iter()
-        .map(|(id, state)| TenantInfo {
+        .map(|(id, state, gen)| TenantInfo {
             id: *id,
             state: state.clone(),
             current_physical_size: None,
             attachment_status: state.attachment_status(),
+            generation: (*gen).into(),
         })
         .collect::<Vec<TenantInfo>>();
 
@@ -801,6 +802,7 @@ async fn tenant_status(
             state: state.clone(),
             current_physical_size: Some(current_physical_size),
             attachment_status: state.attachment_status(),
+            generation: tenant.generation().into(),
         })
     }
     .instrument(info_span!("tenant_status_handler", %tenant_id))

pageserver/src/task_mgr.rs

@@ -293,6 +293,8 @@ pub enum TaskKind {
 
     DebugTool,
 
+    BackgroundRuntimeTurnaroundMeasure,
+
     #[cfg(test)]
     UnitTest,
 }

pageserver/src/tenant.rs

@@ -1714,6 +1714,10 @@ impl Tenant {
         self.current_state() == TenantState::Active
     }
 
+    pub fn generation(&self) -> Generation {
+        self.generation
+    }
+
     /// Changes tenant status to active, unless shutdown was already requested.
     ///
     /// `background_jobs_can_start` is an optional barrier set to a value during pageserver startup

pageserver/src/tenant/mgr.rs

@@ -1397,7 +1397,8 @@ pub(crate) enum TenantMapListError {
 ///
 /// Get list of tenants, for the mgmt API
 ///
-pub(crate) async fn list_tenants() -> Result<Vec<(TenantId, TenantState)>, TenantMapListError> {
+pub(crate) async fn list_tenants(
+) -> Result<Vec<(TenantId, TenantState, Generation)>, TenantMapListError> {
     let tenants = TENANTS.read().unwrap();
     let m = match &*tenants {
         TenantsMap::Initializing => return Err(TenantMapListError::Initializing),
@@ -1405,12 +1406,12 @@ pub(crate) async fn list_tenants() -> Result<Vec<(TenantId, TenantState)>, Tenan
     };
     Ok(m.iter()
         .filter_map(|(id, tenant)| match tenant {
-            TenantSlot::Attached(tenant) => Some((id, tenant.current_state())),
+            TenantSlot::Attached(tenant) => Some((id, tenant.current_state(), tenant.generation())),
             TenantSlot::Secondary => None,
             TenantSlot::InProgress(_) => None,
         })
         // TODO(sharding): make callers of this function shard-aware
-        .map(|(k, v)| (k.tenant_id, v))
+        .map(|(a, b, c)| (a.tenant_id, b, c))
         .collect())
 }
 

pageserver/src/tenant/storage_layer.rs

@@ -2,7 +2,7 @@
 
 pub mod delta_layer;
 mod filename;
-mod image_layer;
+pub mod image_layer;
 mod inmemory_layer;
 mod layer;
 mod layer_desc;

pageserver/src/tenant/storage_layer/delta_layer.rs

@@ -69,13 +69,13 @@ use super::{AsLayerDesc, LayerAccessStats, PersistentLayerDesc, ResidentLayer};
 #[derive(Debug, Serialize, Deserialize, PartialEq, Eq)]
 pub struct Summary {
     /// Magic value to identify this as a neon delta file. Always DELTA_FILE_MAGIC.
-    magic: u16,
-    format_version: u16,
+    pub magic: u16,
+    pub format_version: u16,
 
-    tenant_id: TenantId,
-    timeline_id: TimelineId,
-    key_range: Range<Key>,
-    lsn_range: Range<Lsn>,
+    pub tenant_id: TenantId,
+    pub timeline_id: TimelineId,
+    pub key_range: Range<Key>,
+    pub lsn_range: Range<Lsn>,
 
     /// Block number where the 'index' part of the file begins.
     pub index_start_blk: u32,
@@ -611,6 +611,61 @@ impl Drop for DeltaLayerWriter {
     }
 }
 
+#[derive(thiserror::Error, Debug)]
+pub enum RewriteSummaryError {
+    #[error("magic mismatch")]
+    MagicMismatch,
+    #[error(transparent)]
+    Other(#[from] anyhow::Error),
+}
+
+impl From<std::io::Error> for RewriteSummaryError {
+    fn from(e: std::io::Error) -> Self {
+        Self::Other(anyhow::anyhow!(e))
+    }
+}
+
+impl DeltaLayer {
+    pub async fn rewrite_summary<F>(
+        path: &Utf8Path,
+        rewrite: F,
+        ctx: &RequestContext,
+    ) -> Result<(), RewriteSummaryError>
+    where
+        F: Fn(Summary) -> Summary,
+    {
+        let file = VirtualFile::open_with_options(
+            path,
+            &*std::fs::OpenOptions::new().read(true).write(true),
+        )
+        .await
+        .with_context(|| format!("Failed to open file '{}'", path))?;
+        let file = FileBlockReader::new(file);
+        let summary_blk = file.read_blk(0, ctx).await?;
+        let actual_summary = Summary::des_prefix(summary_blk.as_ref()).context("deserialize")?;
+        let mut file = file.file;
+        if actual_summary.magic != DELTA_FILE_MAGIC {
+            return Err(RewriteSummaryError::MagicMismatch);
+        }
+
+        let new_summary = rewrite(actual_summary);
+
+        let mut buf = smallvec::SmallVec::<[u8; PAGE_SZ]>::new();
+        Summary::ser_into(&new_summary, &mut buf).context("serialize")?;
+        if buf.spilled() {
+            // The code in DeltaLayerWriterInner just warn!()s for this.
+            // It should probably error out as well.
+            return Err(RewriteSummaryError::Other(anyhow::anyhow!(
+                "Used more than one page size for summary buffer: {}",
+                buf.len()
+            )));
+        }
+        file.seek(SeekFrom::Start(0)).await?;
+        file.write_all(&buf).await?;
+        Ok(())
+    }
+}
+
 impl DeltaLayerInner {
     /// Returns nested result following Result<Result<_, OpErr>, Critical>:
     /// - inner has the success or transient failure
@@ -640,11 +695,11 @@ impl DeltaLayerInner {
             expected_summary.index_start_blk = actual_summary.index_start_blk;
             expected_summary.index_root_blk = actual_summary.index_root_blk;
             if actual_summary != expected_summary {
-                bail!(
-                    "in-file summary does not match expected summary. actual = {:?} expected = {:?}",
-                    actual_summary,
-                    expected_summary
-                );
+                // bail!(
+                //     "in-file summary does not match expected summary. actual = {:?} expected = {:?}",
+                //     actual_summary,
+                //     expected_summary
+                // );
             }
         }
 

pageserver/src/tenant/storage_layer/image_layer.rs

@@ -67,20 +67,20 @@ use super::{AsLayerDesc, Layer, PersistentLayerDesc, ResidentLayer};
 /// the 'index' starts at the block indicated by 'index_start_blk'
 ///
 #[derive(Debug, Serialize, Deserialize, PartialEq, Eq)]
-pub(super) struct Summary {
+pub struct Summary {
     /// Magic value to identify this as a neon image file. Always IMAGE_FILE_MAGIC.
-    magic: u16,
-    format_version: u16,
+    pub magic: u16,
+    pub format_version: u16,
 
-    tenant_id: TenantId,
-    timeline_id: TimelineId,
-    key_range: Range<Key>,
-    lsn: Lsn,
+    pub tenant_id: TenantId,
+    pub timeline_id: TimelineId,
+    pub key_range: Range<Key>,
+    pub lsn: Lsn,
 
     /// Block number where the 'index' part of the file begins.
-    index_start_blk: u32,
+    pub index_start_blk: u32,
     /// Block within the 'index', where the B-tree root page is stored
-    index_root_blk: u32,
+    pub index_root_blk: u32,
     // the 'values' part starts after the summary header, on block 1.
 }
 
@@ -296,6 +296,61 @@ impl ImageLayer {
     }
 }
 
+#[derive(thiserror::Error, Debug)]
+pub enum RewriteSummaryError {
+    #[error("magic mismatch")]
+    MagicMismatch,
+    #[error(transparent)]
+    Other(#[from] anyhow::Error),
+}
+
+impl From<std::io::Error> for RewriteSummaryError {
+    fn from(e: std::io::Error) -> Self {
+        Self::Other(anyhow::anyhow!(e))
+    }
+}
+
+impl ImageLayer {
+    pub async fn rewrite_summary<F>(
+        path: &Utf8Path,
+        rewrite: F,
+        ctx: &RequestContext,
+    ) -> Result<(), RewriteSummaryError>
+    where
+        F: Fn(Summary) -> Summary,
+    {
+        let file = VirtualFile::open_with_options(
+            path,
+            &*std::fs::OpenOptions::new().read(true).write(true),
+        )
+        .await
+        .with_context(|| format!("Failed to open file '{}'", path))?;
+        let file = FileBlockReader::new(file);
+        let summary_blk = file.read_blk(0, ctx).await?;
+        let actual_summary = Summary::des_prefix(summary_blk.as_ref()).context("deserialize")?;
+        let mut file = file.file;
+        if actual_summary.magic != IMAGE_FILE_MAGIC {
+            return Err(RewriteSummaryError::MagicMismatch);
+        }
+
+        let new_summary = rewrite(actual_summary);
+
+        let mut buf = smallvec::SmallVec::<[u8; PAGE_SZ]>::new();
+        Summary::ser_into(&new_summary, &mut buf).context("serialize")?;
+        if buf.spilled() {
+            // The code in ImageLayerWriterInner just warn!()s for this.
+            // It should probably error out as well.
+            return Err(RewriteSummaryError::Other(anyhow::anyhow!(
+                "Used more than one page size for summary buffer: {}",
+                buf.len()
+            )));
+        }
+        file.seek(SeekFrom::Start(0)).await?;
+        file.write_all(&buf).await?;
+        Ok(())
+    }
+}
+
 impl ImageLayerInner {
     /// Returns nested result following Result<Result<_, OpErr>, Critical>:
     /// - inner has the success or transient failure
@@ -329,11 +384,11 @@ impl ImageLayerInner {
             expected_summary.index_root_blk = actual_summary.index_root_blk;
 
             if actual_summary != expected_summary {
-                bail!(
-                    "in-file summary does not match expected summary. actual = {:?} expected = {:?}",
-                    actual_summary,
-                    expected_summary
-                );
+                // bail!(
+                //     "in-file summary does not match expected summary. actual = {:?} expected = {:?}",
+                //     actual_summary,
+                //     expected_summary
+                // );
             }
         }
 

test_runner/fixtures/neon_fixtures.py

@@ -1572,7 +1572,7 @@ class NeonAttachmentService:
             self.running = False
         return self
 
-    def attach_hook(self, tenant_id: TenantId, pageserver_id: int) -> int:
+    def attach_hook_issue(self, tenant_id: TenantId, pageserver_id: int) -> int:
         response = requests.post(
             f"{self.env.control_plane_api}/attach-hook",
             json={"tenant_id": str(tenant_id), "node_id": pageserver_id},
@@ -1582,6 +1582,13 @@ class NeonAttachmentService:
         assert isinstance(gen, int)
         return gen
 
+    def attach_hook_drop(self, tenant_id: TenantId):
+        response = requests.post(
+            f"{self.env.control_plane_api}/attach-hook",
+            json={"tenant_id": str(tenant_id), "node_id": None},
+        )
+        response.raise_for_status()
+
     def __enter__(self) -> "NeonAttachmentService":
         return self
 
@@ -1781,13 +1788,20 @@ class NeonPageserver(PgProtocol):
         to call into the pageserver HTTP client.
         """
         if self.env.attachment_service is not None:
-            generation = self.env.attachment_service.attach_hook(tenant_id, self.id)
+            generation = self.env.attachment_service.attach_hook_issue(tenant_id, self.id)
         else:
             generation = None
 
         client = self.http_client()
         return client.tenant_attach(tenant_id, config, config_null, generation=generation)
 
+    def tenant_detach(self, tenant_id: TenantId):
+        if self.env.attachment_service is not None:
+            self.env.attachment_service.attach_hook_drop(tenant_id)
+
+        client = self.http_client()
+        return client.tenant_detach(tenant_id)
+
 
 def append_pageserver_param_overrides(
     params_to_update: List[str],

test_runner/performance/test_pageserver_startup_many_tenants.py

@@ -0,0 +1,157 @@
+import queue
+import shutil
+import subprocess
+import threading
+from pathlib import Path
+from typing import List, Optional
+
+from fixtures.neon_fixtures import (
+    NeonEnv,
+    NeonEnvBuilder,
+    PgBin,
+    last_flush_lsn_upload,
+)
+from fixtures.pageserver.utils import wait_until_tenant_active
+from fixtures.remote_storage import LocalFsStorage, RemoteStorageKind
+from fixtures.types import TenantId
+
+
+def duplicate_tenant(
+    env: NeonEnv, remote_storage: LocalFsStorage, template_tenant: TenantId, new_tenant: TenantId
+):
+    src_timelines_dir: Path = remote_storage.tenant_path(template_tenant) / "timelines"
+    assert src_timelines_dir.is_dir(), f"{src_timelines_dir} is not a directory"
+
+    assert isinstance(remote_storage, LocalFsStorage)
+    dst_timelines_dir: Path = remote_storage.tenant_path(new_tenant) / "timelines"
+    dst_timelines_dir.parent.mkdir(parents=False, exist_ok=False)
+    dst_timelines_dir.mkdir(parents=False, exist_ok=False)
+
+    for tl in src_timelines_dir.iterdir():
+        src_tl_dir = src_timelines_dir / tl.name
+        assert src_tl_dir.is_dir(), f"{src_tl_dir} is not a directory"
+        dst_tl_dir = dst_timelines_dir / tl.name
+        dst_tl_dir.mkdir(parents=False, exist_ok=False)
+        for file in tl.iterdir():
+            shutil.copy2(file, dst_tl_dir)
+            if "__" in file.name:
+                cmd: List[str] = [
+                    str(
+                        env.neon_binpath / "pagectl"
+                    ),  # TODO: abstract this like the other binaries
+                    "layer",
+                    "rewrite-summary",
+                    str(dst_tl_dir / file.name),
+                    "--new-tenant-id",
+                    str(new_tenant),
+                ]
+                subprocess.run(cmd, check=True)
+            else:
+                # index_part etc need no patching
+                pass
+    return None
+
+
+def test_pageserver_startup_many_tenants(neon_env_builder: NeonEnvBuilder, pg_bin: PgBin):
+    """
+    Usage
+
+    TEST_OUTPUT=/mnt/many_tenants NEON_BIN=$PWD/target/release DEFAULT_PG_VERSION=15 ./scripts/pytest --preserve-database-files --timeout=0 ./test_runner/performance/test_pageserver_startup_many_tenants.py
+
+    Then
+
+    export NEON_REPO_DIR=/mnt/many_tenants/test_pageserver_startup_many_tenants/repo
+
+    # edit $NEON_REPO_DIR/pageserver_1/pageserver.toml to use metric collection,
+    # with intervals from prod:
+    #
+    # metric_collection_endpoint = "https://127.0.0.1:6666"
+    # metric_collection_interval: 10min
+    # cached_metric_collection_interval: 0s
+
+    # run a fake metric collection endpoint in some other terminal using
+    # python3 -m http.server 6666 > /dev/null 2>&1
+
+    # then start pageserver
+    ulimit -SH -n 100000
+    ./target/release/neon_local start
+
+
+
+    """
+    neon_env_builder.enable_pageserver_remote_storage(RemoteStorageKind.LOCAL_FS)
+    neon_env_builder.enable_generations = True
+
+    env = neon_env_builder.init_start()
+    remote_storage = env.pageserver_remote_storage
+    assert isinstance(remote_storage, LocalFsStorage)
+
+    # cleanup initial tenant
+    env.pageserver.tenant_detach(env.initial_tenant)
+
+    # create our template tenant
+    tenant_config_mgmt_api = {
+        "gc_period": "0s",
+        "checkpoint_timeout": "3650 day",
+        "compaction_period": "20 s",
+        "compaction_threshold": 10,
+        "compaction_target_size": 134217728,
+        "checkpoint_distance": 268435456,
+        "image_creation_threshold": 3,
+    }
+    tenant_config_cli = {k: str(v) for k, v in tenant_config_mgmt_api.items()}
+
+    ps_http = env.pageserver.http_client()
+
+    template_tenant, template_timeline = env.neon_cli.create_tenant(conf=tenant_config_cli)
+    ep = env.endpoints.create_start("main", tenant_id=template_tenant)
+    ep.safe_psql("create table foo(b text)")
+    for _i in range(0, 8):
+        ep.safe_psql("insert into foo(b) values ('some text')")
+        last_flush_lsn_upload(env, ep, template_tenant, template_timeline)
+    ep.stop_and_destroy()
+    env.pageserver.tenant_detach(template_tenant)
+
+    # duplicate the tenant in remote storage
+    def worker(queue: queue.Queue[Optional[TenantId]]):
+        while True:
+            tenant_id = queue.get()
+            if tenant_id is None:
+                return
+            assert isinstance(remote_storage, LocalFsStorage)
+            duplicate_tenant(env, remote_storage, template_tenant, tenant_id)
+
+    new_tenants: List[TenantId] = [TenantId.generate() for _ in range(0, 20_000)]
+    duplications: queue.Queue[Optional[TenantId]] = queue.Queue()
+    for t in new_tenants:
+        duplications.put(t)
+    workers = []
+    for _ in range(0, 8):
+        w = threading.Thread(target=worker, args=[duplications])
+        workers.append(w)
+        w.start()
+        duplications.put(None)
+    for w in workers:
+        w.join()
+
+    # for evaluation, use the same background loop periods as in prod
+    benchmark_tenant_config = {k: v for k, v in tenant_config_mgmt_api.items()}
+    del benchmark_tenant_config["compaction_period"]
+    del benchmark_tenant_config["gc_period"]
+    benchmark_tenant_config["eviction_policy"] = {
+        "kind": "LayerAccessThreshold",
+        "period": "10m",
+        # don't do evictions
+        "threshold": "1000d",
+    }
+
+    assert ps_http.tenant_list() == []
+    for tenant in new_tenants:
+        env.pageserver.tenant_attach(tenant, config=benchmark_tenant_config)
+    for tenant in new_tenants:
+        wait_until_tenant_active(ps_http, tenant)
+
+    # ensure all layers are resident for predictiable performance
+    # TODO: ensure all kinds of eviction are disabled (per-tenant, disk-usage-based)
+    for tenant in new_tenants:
+        ps_http.download_all_layers(tenant, template_timeline)

test_runner/regress/test_pageserver_generations.py

@@ -282,7 +282,7 @@ def test_deferred_deletion(neon_env_builder: NeonEnvBuilder):
 
     # Now advance the generation in the control plane: subsequent validations
     # from the running pageserver will fail.  No more deletions should happen.
-    env.attachment_service.attach_hook(env.initial_tenant, some_other_pageserver)
+    env.attachment_service.attach_hook_issue(env.initial_tenant, some_other_pageserver)
     generate_uploads_and_deletions(env, init=False)
 
     assert_deletion_queue(ps_http, lambda n: n > 0)
@@ -397,7 +397,7 @@ def test_deletion_queue_recovery(
     if keep_attachment == KeepAttachment.LOSE:
         some_other_pageserver = 101010
         assert env.attachment_service is not None
-        env.attachment_service.attach_hook(env.initial_tenant, some_other_pageserver)
+        env.attachment_service.attach_hook_issue(env.initial_tenant, some_other_pageserver)
 
     env.pageserver.start()