Compare commits

...

3 Commits

Author SHA1 Message Date
Bojan Serafimov f6798d503a Skip sync safekeepers if possible 2023-06-27 10:35:25 -04:00
Shany Pozin d748615c1f RemoteTimelineClient::delete_all() to use s3::delete_objects (#4461)
## Problem
[#4325](https://github.com/neondatabase/neon/issues/4325)
## Summary of changes
Use delete_objects() method
2023-06-27 15:01:32 +03:00
Dmitry Rodionov 681c6910c2 Straighten the spec for timeline delete (#4538)
## Problem

Lets keep 500 for unusual stuff that is not considered normal. Came up
during one of the discussions around console logs now seeing this 500's.

## Summary of changes

- Return 409 Conflict instead of 500
- Remove 200 ok status because it is not used anymore
2023-06-27 13:56:32 +03:00
10 changed files with 75 additions and 24 deletions
+7 -3
View File
@@ -338,9 +338,13 @@ impl ComputeNode {
let lsn = match spec.mode {
ComputeMode::Primary => {
info!("starting safekeepers syncing");
let lsn = self
.sync_safekeepers(pspec.storage_auth_token.clone())
.with_context(|| "failed to sync safekeepers")?;
let lsn = if let Some(synced_lsn) = spec.skip_sync_safekeepers {
info!("no need to sync");
synced_lsn
} else {
self.sync_safekeepers(pspec.storage_auth_token.clone())
.with_context(|| "failed to sync safekeepers")?
};
info!("safekeepers synced at LSN {}", lsn);
lsn
}
+6
View File
@@ -68,6 +68,7 @@ pub struct EndpointConf {
http_port: u16,
pg_version: u32,
skip_pg_catalog_updates: bool,
skip_sync_safekeepers: Option<utils::lsn::Lsn>,
}
//
@@ -137,6 +138,7 @@ impl ComputeControlPlane {
tenant_id,
pg_version,
skip_pg_catalog_updates: false,
skip_sync_safekeepers: None,
});
ep.create_endpoint_dir()?;
@@ -151,6 +153,7 @@ impl ComputeControlPlane {
pg_port,
pg_version,
skip_pg_catalog_updates: false,
skip_sync_safekeepers: None,
})?,
)?;
std::fs::write(
@@ -189,6 +192,7 @@ pub struct Endpoint {
// Optimizations
skip_pg_catalog_updates: bool,
skip_sync_safekeepers: Option<utils::lsn::Lsn>,
}
impl Endpoint {
@@ -223,6 +227,7 @@ impl Endpoint {
tenant_id: conf.tenant_id,
pg_version: conf.pg_version,
skip_pg_catalog_updates: conf.skip_pg_catalog_updates,
skip_sync_safekeepers: conf.skip_sync_safekeepers,
})
}
@@ -457,6 +462,7 @@ impl Endpoint {
// Create spec file
let spec = ComputeSpec {
skip_sync_safekeepers: self.skip_sync_safekeepers,
skip_pg_catalog_updates: self.skip_pg_catalog_updates,
format_version: 1.0,
operation_uuid: None,
+9
View File
@@ -33,6 +33,15 @@ pub struct ComputeSpec {
#[serde(default)] // Default false
pub skip_pg_catalog_updates: bool,
/// An optinal hint that can be passed to speed up startup time if we know
/// that safekeepers have already been synced at the given LSN.
///
/// NOTE: If there's any possibility that the safekeepers could have advanced
/// (e.g. if we started compute, and it crashed) we should stay on the
/// safe side and provide None.
#[serde(default)]
pub skip_sync_safekeepers: Option<Lsn>,
// Information needed to connect to the storage layer.
//
// `tenant_id`, `timeline_id` and `pageserver_connstring` are always needed.
+15
View File
@@ -173,10 +173,15 @@ async fn s3_delete_objects_works(ctx: &mut MaybeEnabledS3) -> anyhow::Result<()>
let path2 = RemotePath::new(&PathBuf::from(format!("{}/path2", ctx.base_prefix,)))
.with_context(|| "RemotePath conversion")?;
let path3 = RemotePath::new(&PathBuf::from(format!("{}/path3", ctx.base_prefix,)))
.with_context(|| "RemotePath conversion")?;
let data1 = "remote blob data1".as_bytes();
let data1_len = data1.len();
let data2 = "remote blob data2".as_bytes();
let data2_len = data2.len();
let data3 = "remote blob data3".as_bytes();
let data3_len = data3.len();
ctx.client
.upload(std::io::Cursor::new(data1), data1_len, &path1, None)
.await?;
@@ -185,8 +190,18 @@ async fn s3_delete_objects_works(ctx: &mut MaybeEnabledS3) -> anyhow::Result<()>
.upload(std::io::Cursor::new(data2), data2_len, &path2, None)
.await?;
ctx.client
.upload(std::io::Cursor::new(data3), data3_len, &path3, None)
.await?;
ctx.client.delete_objects(&[path1, path2]).await?;
let prefixes = ctx.client.list_prefixes(None).await?;
assert_eq!(prefixes.len(), 1);
ctx.client.delete_objects(&[path3]).await?;
Ok(())
}
+7 -3
View File
@@ -186,10 +186,8 @@ paths:
schema:
$ref: "#/components/schemas/Error"
delete:
description: "Attempts to delete specified timeline. On 500 errors should be retried"
description: "Attempts to delete specified timeline. 500 and 409 errors should be retried"
responses:
"200":
description: Ok
"400":
description: Error when no tenant id found in path or no timeline id
content:
@@ -214,6 +212,12 @@ paths:
application/json:
schema:
$ref: "#/components/schemas/NotFoundError"
"409":
description: Deletion is already in progress, continue polling
content:
application/json:
schema:
$ref: "#/components/schemas/ConflictError"
"412":
description: Tenant is missing, or timeline has children
content:
+1
View File
@@ -187,6 +187,7 @@ impl From<crate::tenant::DeleteTimelineError> for ApiError {
format!("Cannot delete timeline which has child timelines: {children:?}")
.into_boxed_str(),
),
a @ AlreadyInProgress => ApiError::Conflict(a.to_string()),
Other(e) => ApiError::InternalServerError(e),
}
}
+10 -8
View File
@@ -440,8 +440,13 @@ pub enum GetTimelineError {
pub enum DeleteTimelineError {
#[error("NotFound")]
NotFound,
#[error("HasChildren")]
HasChildren(Vec<TimelineId>),
#[error("Timeline deletion is already in progress")]
AlreadyInProgress,
#[error(transparent)]
Other(#[from] anyhow::Error),
}
@@ -1755,14 +1760,11 @@ impl Tenant {
timeline = Arc::clone(timeline_entry.get());
// Prevent two tasks from trying to delete the timeline at the same time.
delete_lock_guard =
DeletionGuard(Arc::clone(&timeline.delete_lock).try_lock_owned().map_err(
|_| {
DeleteTimelineError::Other(anyhow::anyhow!(
"timeline deletion is already in progress"
))
},
)?);
delete_lock_guard = DeletionGuard(
Arc::clone(&timeline.delete_lock)
.try_lock_owned()
.map_err(|_| DeleteTimelineError::AlreadyInProgress)?,
);
// If another task finished the deletion just before we acquired the lock,
// return success.
@@ -862,10 +862,8 @@ impl RemoteTimelineClient {
"Found {} files not bound to index_file.json, proceeding with their deletion",
remaining.len()
);
for file in remaining {
warn!("Removing {}", file.object_name().unwrap_or_default());
self.storage_impl.delete(&file).await?;
}
warn!("About to remove {} files", remaining.len());
self.storage_impl.delete_objects(&remaining).await?;
}
let index_file_path = timeline_storage_path.join(Path::new(IndexPart::FILE_NAME));
+14 -2
View File
@@ -30,7 +30,18 @@ def test_startup_simple(neon_env_builder: NeonEnvBuilder, zenbenchmark: NeonBenc
neon_env_builder.num_safekeepers = 3
env = neon_env_builder.init_start()
env.neon_cli.create_branch("test_startup")
tenant_id = env.initial_tenant
timeline_id = env.neon_cli.create_branch("test_startup")
def get_synced_lsn():
"""Assert safekeepers are synced and get the LSN."""
commit_lsns = [
sk.http_client().timeline_status(tenant_id, timeline_id).commit_lsn
for sk in env.safekeepers
]
assert len(commit_lsns) == 3
assert len(set(commit_lsns)) == 1
return commit_lsns[0]
endpoint = None
@@ -63,7 +74,8 @@ def test_startup_simple(neon_env_builder: NeonEnvBuilder, zenbenchmark: NeonBenc
endpoint.stop()
# Imitate optimizations that console would do for the second start
endpoint.respec(skip_pg_catalog_updates=True)
lsn = get_synced_lsn()
endpoint.respec(skip_pg_catalog_updates=True, skip_sync_safekeepers=lsn.lsn_int)
# This test sometimes runs for longer than the global 5 minute timeout.
+4 -4
View File
@@ -463,10 +463,10 @@ def test_concurrent_timeline_delete_stuck_on(
# make the second call and assert behavior
log.info("second call start")
error_msg_re = "timeline deletion is already in progress"
error_msg_re = "Timeline deletion is already in progress"
with pytest.raises(PageserverApiException, match=error_msg_re) as second_call_err:
ps_http.timeline_delete(env.initial_tenant, child_timeline_id)
assert second_call_err.value.status_code == 500
assert second_call_err.value.status_code == 409
env.pageserver.allowed_errors.append(f".*{child_timeline_id}.*{error_msg_re}.*")
# the second call will try to transition the timeline into Stopping state as well
env.pageserver.allowed_errors.append(
@@ -518,9 +518,9 @@ def test_delete_timeline_client_hangup(neon_env_builder: NeonEnvBuilder):
ps_http.timeline_delete(env.initial_tenant, child_timeline_id, timeout=2)
env.pageserver.allowed_errors.append(
f".*{child_timeline_id}.*timeline deletion is already in progress.*"
f".*{child_timeline_id}.*Timeline deletion is already in progress.*"
)
with pytest.raises(PageserverApiException, match="timeline deletion is already in progress"):
with pytest.raises(PageserverApiException, match="Timeline deletion is already in progress"):
ps_http.timeline_delete(env.initial_tenant, child_timeline_id, timeout=2)
# make sure the timeout was due to the failpoint