This PR is a fallout from work on #7062.
# Changes
- Unify the freeze-and-flush and hard shutdown code paths into a single
method `Timeline::shutdown` that takes the shutdown mode as an argument.
- Replace `freeze_and_flush` bool arg in callers with that mode
argument, makes them more expressive.
- Switch timeline deletion to use `Timeline::shutdown` instead of its
own slightly-out-of-sync copy.
- Remove usage of `task_mgr::shutdown_watcher` /
`task_mgr::shutdown_token` where possible
# Future Work
Do we really need the freeze_and_flush?
If we could get rid of it, then there'd be no need for a specific
shutdown order.
Also, if you undo this patch's changes to the `eviction_task.rs` and
enable RUST_LOG=debug, it's easy to see that we do leave some task
hanging that logs under span `Connection{...}` at debug level. I think
it's a pre-existing issue; it's probably a broker client task.
## Problem
For reasons unrelated to this PR, I would like to make use of the tenant
conf in the `InMemoryLayer`. Previously, this was not possible without
copying and manually updating the copy to keep it in sync with updates.
## Summary of Changes:
Replace the `Arc<RwLock<AttachedTenantConf>>` with
`Arc<ArcSwap<AttachedTenantConf>>` (how many `Arc(s)` can one fit in a
type?). The most interesting part of this change is the updating of the
tenant config (`set_new_tenant_config` and
`set_new_location_config`). In theory, these two may race, although the
storage controller should prevent this via the tenant exclusive op lock.
Particular care has been taken to not "lose" a location config update by
using the read-copy-update approach when updating only the config.
## Problem
(Follows https://github.com/neondatabase/neon/pull/7237)
Some API users will query a tenant to wait for it to activate.
Currently, we return the current status of the tenant, whatever that may
be. Under heavy load, a pageserver starting up might take a long time to
activate such a tenant.
## Summary of changes
- In `tenant_status` handler, call wait_to_become_active on the tenant.
If the tenant is currently waiting for activation, this causes it to
skip the queue, similiar to other API handlers that require an active
tenant, like timeline creation. This avoids external services waiting a
long time for activation when polling GET /v1/tenant/<id>.
Tiered compaction hasn't scheduled the upload of image layers. In the
`test_gc_feedback.py` test this has caused warnings like with tiered
compaction:
```
INFO request[...] Deleting layer [...] not found in latest_files list, never uploaded?
```
Which caused errors like:
```
ERROR layer_delete[...] was unlinked but was not dangling
```
Fixes#7244
We want to move the code base away from task_mgr.
This PR refactors the walreceiver code such that it doesn't use
`task_mgr` anymore.
# Background
As a reminder, there are three tasks in a Timeline that's ingesting WAL.
`WalReceiverManager`, `WalReceiverConnectionHandler`, and
`WalReceiverConnectionPoller`.
See the documentation in `task_mgr.rs` for how they interact.
Before this PR, cancellation was requested through
task_mgr::shutdown_token() and `TaskHandle::shutdown`.
Wait-for-task-finish was implemented using a mixture of
`task_mgr::shutdown_tasks` and `TaskHandle::shutdown`.
This drawing might help:
<img width="300" alt="image"
src="https://github.com/neondatabase/neon/assets/956573/b6be7ad6-ecb3-41d0-b410-ec85cb8d6d20">
# Changes
For cancellation, the entire WalReceiver task tree now has a
`child_token()` of `Timeline::cancel`. The `TaskHandle` no longer is a
cancellation root.
This means that `Timeline::cancel.cancel()` is propagated.
For wait-for-task-finish, all three tasks in the task tree hold the
`Timeline::gate` open until they exit.
The downside of using the `Timeline::gate` is that we can no longer wait
for just the walreceiver to shut down, which is particularly relevant
for `Timeline::flush_and_shutdown`.
Effectively, it means that we might ingest more WAL while the
`freeze_and_flush()` call is ongoing.
Also, drive-by-fix the assertiosn around task kinds in `wait_lsn`. The
check for `WalReceiverConnectionHandler` was ineffective because that
never was a task_mgr task, but a TaskHandle task. Refine the assertion
to check whether we would wait, and only fail in that case.
# Alternatives
I contemplated (ab-)using the `Gate` by having a separate `Gate` for
`struct WalReceiver`.
All the child tasks would use _that_ gate instead of `Timeline::gate`.
And `struct WalReceiver` itself would hold an `Option<GateGuard>` of the
`Timeline::gate`.
Then we could have a `WalReceiver::stop` function that closes the
WalReceiver's gate, then drops the `WalReceiver::Option<GateGuard>`.
However, such design would mean sharing the WalReceiver's `Gate` in an
`Arc`, which seems awkward.
A proper abstraction would be to make gates hierarchical, analogous to
CancellationToken.
In the end, @jcsp and I talked it over and we determined that it's not
worth the effort at this time.
# Refs
part of #7062
The latest failures of test_secondary_downloads are spooky: layers are
missing on disk according to the test, but present according to the
pageserver logs:
- Make the pageserver assert that layers are really present on disk and
log the full path (debug mode only)
- Make the test dump a full listing on failure of the assert that failed
the last two times
Related: #6966
## Problem
The vectored read path holds the layer map lock while visiting a
timeline.
## Summary of changes
* Rework the fringe order to hold `Layer` on `Arc<InMemoryLayer>`
handles instead of descriptions that are resolved by the layer map at
the time of read. Note that previously `get_values_reconstruct_data` was
implemented for the layer description which already knew the lsn range
for the read. Now it is implemented on the new `ReadableLayer` handle
and needs to get the lsn range as an argument.
* Drop the layer map lock after updating the fringe.
Related https://github.com/neondatabase/neon/issues/6833
## Problem
Part of the legacy (but current) compaction algorithm is to find a stack
of overlapping delta layers which will be turned
into an image layer. This operation is exponential in terms of the
number of matching layers and we do it roughly every 20 seconds.
## Summary of changes
Only check if a new image layer is required if we've ingested a certain
amount of WAL since the last check.
The amount of wal is expressed in terms of multiples of checkpoint
distance, with the intuition being that
that there's little point doing the check if we only have two new L1
layers (not enough to create a new image).
## Problem
During this week's deployment we observed panics due to the blobs
for certain keys not fitting in the vectored read buffers. The likely
cause of this is a bloated AUX_FILE_KEY caused by logical replication.
## Summary of changes
This pr fixes the issue by allocating a buffer big enough to fit
the widest read. It also has the benefit of saving space if all keys
in the read have blobs smaller than the max vectored read size.
If the soft limit for the max size of a vectored read is violated,
we print a warning which includes the offending key and lsn.
A randomised (but deterministic) end to end test is also added for
vectored reads on the delta layer.
# Problem
As pointed out through doc-comments in this PR, `drop_old_connection` is
not cancellation-safe.
This means we can leave a `handle_walreceiver_connection` tokio task
dangling during Timeline shutdown.
More details described in the corresponding issue #7062.
# Solution
Don't cancel-by-drop the `connection_manager_loop_step` from the
`tokio::select!()` in the task_mgr task.
Instead, transform the code to use a `CancellationToken` ---
specifically, `task_mgr::shutdown_token()` --- and make code responsive
to it.
The `drop_old_connection()` is still not cancellation-safe and also
doesn't get a cancellation token, because there's no point inside the
function where we could return early if cancellation were requested
using a token.
We rely on the `handle_walreceiver_connection` to be sensitive to the
`TaskHandle`s cancellation token (argument name: `cancellation`).
Currently it checks for `cancellation` on each WAL message. It is
probably also sensitive to `Timeline::cancel` because ultimately all
that `handle_walreceiver_connection` does is interact with the
`Timeline`.
In summary, the above means that the following code (which is found in
`Timeline::shutdown`) now might **take longer**, but actually ensures
that all `handle_walreceiver_connection` tasks are finished:
```rust
task_mgr::shutdown_tasks(
Some(TaskKind::WalReceiverManager),
Some(self.tenant_shard_id),
Some(self.timeline_id)
)
```
# Refs
refs #7062
## Problem
This is a refactor.
This PR was a precursor to a much smaller change
e5bd602dc1,
where as I was writing it I found that we were not far from getting rid
of the last non-deprecated code paths that use `mgr::` scoped functions
to get at the TenantManager state.
We're almost done cleaning this up as per
https://github.com/neondatabase/neon/issues/5796. The only significant
remaining mgr:: item is `get_active_tenant_with_timeout`, which is
page_service's path for fetching tenants.
## Summary of changes
- Remove the bool argument to get_attached_tenant_shard: this was almost
always false from API use cases, and in cases when it was true, it was
readily replacable with an explicit check of the returned tenant's
status.
- Rather than letting the timeline eviction task query any tenant it
likes via `mgr::`, pass an `Arc<Tenant>` into the task. This is still an
ugly circular reference, but should eventually go away: either when we
switch to exclusively using disk usage eviction, or when we change
metadata storage to avoid the need to imitate layer accesses.
- Convert all the mgr::get_tenant call sites to use
TenantManager::get_attached_tenant_shard
- Move list_tenants into TenantManager.
## Problem
Follows: https://github.com/neondatabase/neon/pull/7182
- Sufficient concurrent writes could OOM a pageserver from the size of
indices on all the InMemoryLayer instances.
- Enforcement of checkpoint_period only happened if there were some
writes.
Closes: https://github.com/neondatabase/neon/issues/6916
## Summary of changes
- Add `ephemeral_bytes_per_memory_kb` config property. This controls the
ratio of ephemeral layer capacity to memory capacity. The weird unit is
to enable making the ratio less than 1:1 (set this property to 1024 to
use 1MB of ephemeral layers for every 1MB of RAM, set it smaller to get
a fraction).
- Implement background layer rolling checks in
Timeline::compaction_iteration -- this ensures we apply layer rolling
policy in the absence of writes.
- During background checks, if the total ephemeral layer size has
exceeded the limit, then roll layers whose size is greater than the mean
size of all ephemeral layers.
- Remove the tick() path from walreceiver: it isn't needed any more now
that we do equivalent checks from compaction_iteration.
- Add tests for the above.
---------
Co-authored-by: Arpad Müller <arpad-m@users.noreply.github.com>
## Problem
Currently, we return 409 (Conflict) in two cases:
- Temporary: Timeline creation cannot proceed because another timeline
with the same ID is being created
- Permanent: Timeline creation cannot proceed because another timeline
exists with different parameters but the same ID.
Callers which time out a request and retry should be able to distinguish
these cases.
Closes: #7208
## Summary of changes
- Expose `AlreadyCreating` errors as 429 instead of 409
## Problem
We currently hold the layer map read lock while doing IO on the read
path. This is not required for correctness.
## Summary of changes
Drop the layer map lock after figuring out which layer we wish to read
from.
Why is this correct:
* `Layer` models the lifecycle of an on disk layer. In the event the
layer is removed from local disk, it will be on demand downloaded
* `InMemoryLayer` holds the `EphemeralFile` which wraps the on disk
file. As long as the `InMemoryLayer` is in scope, it's safe to read from it.
Related https://github.com/neondatabase/neon/issues/6833
## Problem
Large quantities of ephemeral layer data can lead to excessive memory
consumption (https://github.com/neondatabase/neon/issues/6939). We
currently don't have a way to know how much ephemeral layer data is
present on a pageserver.
Before we can add new behaviors to proactively roll layers in response
to too much ephemeral data, we must calculate that total.
Related: https://github.com/neondatabase/neon/issues/6916
## Summary of changes
- Create GlobalResources and GlobalResourceUnits types, where timelines
carry a GlobalResourceUnits in their TimelineWriterState.
- Periodically update the size in GlobalResourceUnits:
- During tick()
- During layer roll
- During put() if the latest value has drifted more than 10MB since our
last update
- Expose the value of the global ephemeral layer bytes counter as a
prometheus metric.
- Extend the lifetime of TimelineWriterState:
- Instead of dropping it in TimelineWriter::drop, let it remain.
- Drop TimelineWriterState in roll_layer: this drops our guard on the
global byte count to reflect the fact that we're freezing the layer.
- Ensure the validity of the later in the writer state by clearing the
state in the same place we freeze layers, and asserting on the
write-ability of the layer in `writer()`
- Add a 'context' parameter to `get_open_layer_action` so that it can
skip the prev_lsn==lsn check when called in tick() -- this is needed
because now tick is called with a populated state, where
prev_lsn==Some(lsn) is true for an idle timeline.
- Extend layer rolling test to use this metric
Before this PR, each core had 3 executor threads from 3 different
runtimes. With this PR, we just have one runtime, with one thread per
core. Switching to a single tokio runtime should reduce that effective
over-commit of CPU and in theory help with tail latencies -- iff all
tokio tasks are well-behaved and yield to the runtime regularly.
Are All Tasks Well-Behaved? Are We Ready?
-----------------------------------------
Sadly there doesn't seem to be good out-of-the box tokio tooling to
answer this question.
We *believe* all tasks are well behaved in today's code base, as of the
switch to `virtual_file_io_engine = "tokio-epoll-uring"` in production
(https://github.com/neondatabase/aws/pull/1121).
The only remaining executor-thread-blocking code is walredo and some
filesystem namespace operations.
Filesystem namespace operations work is being tracked in #6663 and not
considered likely to actually block at this time.
Regarding walredo, it currently does a blocking `poll` for read/write to
the pipe file descriptors we use for IPC with the walredo process.
There is an ongoing experiment to make walredo async (#6628), but it
needs more time because there are surprisingly tricky trade-offs that
are articulated in that PR's description (which itself is still WIP).
What's relevant for *this* PR is that
1. walredo is always CPU-bound
2. production tail latencies for walredo request-response
(`pageserver_wal_redo_seconds_bucket`) are
- p90: with few exceptions, low hundreds of micro-seconds
- p95: except on very packed pageservers, below 1ms
- p99: all below 50ms, vast majority below 1ms
- p99.9: almost all around 50ms, rarely at >= 70ms
- [Dashboard
Link](https://neonprod.grafana.net/d/edgggcrmki3uof/2024-03-walredo-latency?orgId=1&var-ds=ZNX49CDVz&var-pXX_by_instance=0.9&var-pXX_by_instance=0.99&var-pXX_by_instance=0.95&var-adhoc=instance%7C%21%3D%7Cpageserver-30.us-west-2.aws.neon.tech&var-per_instance_pXX_max_seconds=0.0005&from=1711049688777&to=1711136088777)
The ones below 1ms are below our current threshold for when we start
thinking about yielding to the executor.
The tens of milliseconds stalls aren't great, but, not least because of
the implicit overcommit of CPU by the three runtimes, we can't be sure
whether these tens of milliseconds are inherently necessary to do the
walredo work or whether we could be faster if there was less contention
for CPU.
On the first item (walredo being always CPU-bound work): it means that
walredo processes will always compete with the executor threads.
We could yield, using async walredo, but then we hit the trade-offs
explained in that PR.
tl;dr: the risk of stalling executor threads through blocking walredo
seems low, and switching to one runtime cleans up one potential source
for higher-than-necessary stall times (explained in the previous
paragraphs).
Code Changes
------------
- Remove the 3 different runtime definitions.
- Add a new definition called `THE_RUNTIME`.
- Use it in all places that previously used one of the 3 removed
runtimes.
- Remove the argument from `task_mgr`.
- Fix failpoint usage where `pausable_failpoint!` should have been used.
We encountered some actual failures because of this, e.g., hung
`get_metric()` calls during test teardown that would client-timeout
after 300s.
As indicated by the comment above `THE_RUNTIME`, we could take this
clean-up further.
But before we create so much churn, let's first validate that there's no
perf regression.
Performance
-----------
We will test this in staging using the various nightly benchmark runs.
However, the worst-case impact of this change is likely compaction
(=>image layer creation) competing with compute requests.
Image layer creation work can't be easily generated & repeated quickly
by pagebench.
So, we'll simply watch getpage & basebackup tail latencies in staging.
Additionally, I have done manual benchmarking using pagebench.
Report:
https://neondatabase.notion.site/2024-03-23-oneruntime-change-benchmarking-22a399c411e24399a73311115fb703ec?pvs=4
Tail latencies and throughput are marginally better (no regression =
good).
Except in a workload with 128 clients against one tenant.
There, the p99.9 and p99.99 getpage latency is about 2x worse (at
slightly lower throughput).
A dip in throughput every 20s (compaction_period_ is clearly visible,
and probably responsible for that worse tail latency.
This has potential to improve with async walredo, and is an edge case
workload anyway.
Future Work
-----------
1. Once this change has shown satisfying results in production, change
the codebase to use the ambient runtime instead of explicitly
referencing `THE_RUNTIME`.
2. Have a mode where we run with a single-threaded runtime, so we
uncover executor stalls more quickly.
3. Switch or write our own failpoints library that is async-native:
https://github.com/neondatabase/neon/issues/7216
## Problem
The service that receives consumption metrics has lower availability
than S3. Writing metrics to S3 improves their availability.
Closes: https://github.com/neondatabase/cloud/issues/9824
## Summary of changes
- The same data as consumption metrics POST bodies is also compressed
and written to an S3 object with a timestamp-formatted path.
- Set `metric_collection_bucket` (same format as `remote_storage`
config) to configure the location to write to
A test was added which exercises secondary locations more, and there was
a location in the secondary downloader that warned on ephemeral files.
This was intended to be fixed in this faulty commit:
8cea866adf
Release notes: https://blog.rust-lang.org/2024/03/21/Rust-1.77.0.html
Thanks to #6886 the diff is reasonable, only for one new lint
`clippy::suspicious_open_options`. I added `truncate()` calls to the
places where it is obviously the right choice to me, and added allows
everywhere else, leaving it for followups.
I had to specify cargo install --locked because the build would fail otherwise.
This was also recommended by upstream.
This change improves the resilience of the system to unclean restarts.
Previously, re-attach responses only included attached tenants
- If the pageserver had local state for a secondary location, it would
remain, but with no guarantee that it was still _meant_ to be there.
After this change, the pageserver will only retain secondary locations
if the /re-attach response indicates that they should still be there.
- If the pageserver had local state for an attached location that was
omitted from a re-attach response, it would be entirely detached. This
is wasteful in a typical HA setup, where an offline node's tenants might
have been re-attached elsewhere before it restarts, but the offline
node's location should revert to a secondary location rather than being
wiped. Including secondary tenants in the re-attach response enables the
pageserver to avoid throwing away local state unnecessarily.
In this PR:
- The re-attach items are extended with a 'mode' field.
- Storage controller populates 'mode'
- Pageserver interprets it (default is attached if missing) to construct
either a SecondaryTenant or a Tenant.
- A new test exercises both cases.
## Problem
If a shutdown happens when a tenant is attaching, we were logging at
ERROR severity and with a backtrace. Yuck.
## Summary of changes
- Pass a flag into `make_broken` to enable quietening this non-scary
case.
Stacks on:
- https://github.com/neondatabase/neon/pull/7165
Fixes while working on background optimization of scheduling after a
split:
- When a tenant has secondary locations, we weren't detaching the parent
shards' secondary locations when doing a split
- When a reconciler detaches a location, it was feeding back a
locationconf with `Detached` mode in its `observed` object, whereas it
should omit that location. This could cause the background reconcile
task to keep kicking off no-op reconcilers forever (harmless but
annoying).
- During shard split, we were scheduling secondary locations for the
child shards, but no reconcile was run for these until the next time the
background reconcile task ran. Creating these ASAP is useful, because
they'll be used shortly after a shard split as the destination locations
for migrating the new shards to different nodes.
## Problem
Storage controller had basically no metrics.
## Summary of changes
1. Migrate the existing metrics to use Conrad's
[`measured`](https://docs.rs/measured/0.0.14/measured/) crate.
2. Add metrics for incoming http requests
3. Add metrics for outgoing http requests to the pageserver
4. Add metrics for outgoing pass through requests to the pageserver
5. Add metrics for database queries
Note that the metrics response for the attachment service does not use
chunked encoding like the rest of the metrics endpoints. Conrad has
kindly extended the crate such that it can now be done. Let's leave it
for a follow-up since the payload shouldn't be that big at this point.
Fixes https://github.com/neondatabase/neon/issues/6875
## Problem
The current implementation of struct Layer supports canceled read
requests, but those will leave the internal state such that a following
`Layer::keep_resident` call will need to repair the state. In
pathological cases seen during generation numbers resetting in staging
or with too many in-progress on-demand downloads, this repair activity
will need to wait for the download to complete, which stalls disk
usage-based eviction. Similar stalls have been observed in staging near
disk-full situations, where downloads failed because the disk was full.
Fixes#6028 or the "layer is present on filesystem but not evictable"
problems by:
1. not canceling pending evictions by a canceled
`LayerInner::get_or_maybe_download`
2. completing post-download initialization of the `LayerInner::inner`
from the download task
Not canceling evictions above case (1) and always initializing (2) lead
to plain `LayerInner::inner` always having the up-to-date information,
which leads to the old `Layer::keep_resident` never having to wait for
downloads to complete. Finally, the `Layer::keep_resident` is replaced
with `Layer::is_likely_resident`. These fix#7145.
## Summary of changes
- add a new test showing that a canceled get_or_maybe_download should
not cancel the eviction
- switch to using a `watch` internally rather than a `broadcast` to
avoid hanging eviction while a download is ongoing
- doc changes for new semantics and cleanup
- fix `Layer::keep_resident` to use just `self.0.inner.get()` as truth
as `Layer::is_likely_resident`
- remove `LayerInner::wanted_evicted` boolean as no longer needed
Builds upon: #7185. Cc: #5331.
Before this PR, cancellation for `LayerInner::get_or_maybe_download`
could occur so that we have downloaded the layer file in the filesystem,
but because of the cancellation chance, we have not set the internal
`LayerInner::inner` or initialized the state. With the detached init
support introduced in #7135 and in place in #7152, we can now initialize
the internal state after successfully downloading in the spawned task.
The next PR will fix the remaining problems that this PR leaves:
- `Layer::keep_resident` is still used because
- `Layer::get_or_maybe_download` always cancels an eviction, even when
canceled
Split off from #7030. Stacked on top of #7152. Cc: #5331.
- Enable debug logs for this test
- Add some debug logging detail in downloader.rs
- Add an info-level message in scheduler.rs that makes it obvious if a
command is waiting for an existing task rather than spawning a new one.
The second part of work towards fixing `Layer::keep_resident` so that it
does not need to repair the internal state. #7135 added a nicer API for
initialization. This PR uses it to remove a few indentation levels and
the loop construction. The next PR #7175 will use the refactorings done
in this PR, and always initialize the internal state after a download.
Cc: #5331
Since #6115 with more often used get_value_reconstruct_data and friends,
we should not have needless INFO level span creation near hot paths. In
our prod configuration, INFO spans are always created, but in practice,
very rarely anything at INFO level is logged underneath.
`ResidentLayer::load_keys` is only used during compaction so it is not
that hot, but this aligns the access paths and their span usage.
PR changes the span level to debug to align with others, and adds the
layer name to the error which was missing.
Split off from #7030.
Add shard_number to PageserverFeedback and parse it on the compute side.
When compute receives a new ps_feedback, it calculates min LSNs among
feedbacks from all shards, and uses those LSNs for backpressure.
Add `test_sharding_backpressure` to verify that backpressure slows down
compute to wait for the slowest shard.
Manual testing of the changes in #7160 revealed that, if the
thread-local destructor ever runs (it apparently doesn't in our test
suite runs, otherwise #7160 would not have auto-merged), we can
encounter an `abort()` due to a double-panic in the tracing code.
This github comment here contains the stack trace:
https://github.com/neondatabase/neon/pull/7160#issuecomment-2003778176
This PR reverts #7160 and uses a atomic counter to identify the
thread-local in log messages, instead of the memory address of the
thread local, which may be re-used.
with `immediate_gc` the span only covered the `gc_iteration`, make it
cover the whole needless spawned task, which also does waiting for layer
drops and stray logging in tests.
also clarify some comments while we are here.
Fixes: #6910
The PR #7141 added log message
```
ThreadLocalState is being dropped and id might be re-used in the future
```
which was supposed to be emitted when the thread-local is destroyed.
Instead, it was emitted on _each_ call to `thread_local_system()`,
ie.., on each tokio-epoll-uring operation.
Testing
-------
Reproduced the issue locally and verified that this PR fixes the issue.
## Problem
Followup to https://github.com/neondatabase/neon/pull/6725
In that PR, code for purging local files from a tenant shard was
duplicated.
## Summary of changes
- Refactor detach code into TenantManager
- `spawn_background_purge` method can now be common between detach and
split operations
refs https://github.com/neondatabase/neon/issues/7136
Problem
-------
Before this PR, we were using
`tokio_epoll_uring::thread_local_system()`,
which panics on tokio_epoll_uring::System::launch() failure
As we've learned in [the
past](https://github.com/neondatabase/neon/issues/6373#issuecomment-1905814391),
some older Linux kernels account io_uring instances as locked memory.
And while we've raised the limit in prod considerably, we did hit it
once on 2024-03-11 16:30 UTC.
That was after we enabled tokio-epoll-uring fleet-wide, but before
we had shipped release-5090 (c6ed86d3d0)
which did away with the last mass-creation of tokio-epoll-uring
instances as per
commit 3da410c8fe
Author: Christian Schwarz <christian@neon.tech>
Date: Tue Mar 5 10:03:54 2024 +0100
tokio-epoll-uring: use it on the layer-creating code paths (#6378)
Nonetheless, it highlighted that panicking in this situation is probably
not ideal, as it can leave the pageserver process in a semi-broken
state.
Further, due to low sampling rate of Prometheus metrics, we don't know
much about the circumstances of this failure instance.
Solution
--------
This PR implements a custom thread_local_system() that is
pageserver-aware
and will do the following on failure:
- dump relevant stats to `tracing!`, hopefully they will be useful to
understand the circumstances better
- if it's the locked memory failure (or any other ENOMEM): abort() the
process
- if it's ENOMEM, retry with exponential back-off, capped at 3s.
- add metric counters so we can create an alert
This makes sense in the production environment where we know that
_usually_, there's ample locked memory allowance available, and we know
the failure rate is rare.
## Problem
The existing secondary download API relied on the caller to wait as long
as it took to complete -- for large shards that could be a long time, so
typical clients that might have a baked-in ~30s timeout would have a
problem.
## Summary of changes
- Take a `wait_ms` query parameter to instruct the pageserver how long
to wait: if the download isn't complete in this duration, then 201 is
returned instead of 200.
- For both 200 and 201 responses, include response body describing
download progress, in terms of layers and bytes. This is sufficient for
the caller to track how much data is being transferred and log/present
that status.
- In storage controller live migrations, use this API to apply a much
longer outer timeout, with smaller individual per-request timeouts, and
log the progress of the downloads.
- Add a test that injects layer download delays to exercise the new
behavior
# Problem
On-demand downloads are still using `tokio::fs`, which we know is
inefficient.
# Changes
- Add `pagebench ondemand-download-churn` to quantify on-demand download
throughput
- Requires dumping layer map, which required making `history_buffer`
impl `Deserialize`
- Implement an equivalent of `tokio::io::copy_buf` for owned buffers =>
`owned_buffers_io` module and children.
- Make layer file download sensitive to `io_engine::get()`, using
VirtualFile + above copy loop
- For this, I had to move some code into the `retry_download`, e.g.,
`sync_all()` call.
Drive-by:
- fix missing escaping in `scripts/ps_ec2_setup_instance_store`
- if we failed in retry_download to create a file, we'd try to remove
it, encounter `NotFound`, and `abort()` the process using
`on_fatal_io_error`. This PR adds treats `NotFound` as a success.
# Testing
Functional
- The copy loop is generic & unit tested.
Performance
- Used the `ondemand-download-churn` benchmark to manually test against
real S3.
- Results (public Notion page):
https://neondatabase.notion.site/Benchmarking-tokio-epoll-uring-on-demand-downloads-2024-04-15-newer-code-03c0fdc475c54492b44d9627b6e4e710?pvs=4
- Performance is equivalent at low concurrency. Jumpier situation at
high concurrency, but, still less CPU / throughput with
tokio-epoll-uring.
- It’s a win.
# Future Work
Turn the manual performance testing described in the above results
document into a performance regression test:
https://github.com/neondatabase/neon/issues/7146
## Problem
Tenant deletion had a couple of TODOs where we weren't using proper
cancellation tokens that would have aborted the deletions during process
shutdown.
## Summary of changes
- Refactor enough that deletion/shutdown code has access to the
TenantManager's cancellation toke
- Use that cancellation token in tenant deletion instead of dummy
tokens.
fixes https://github.com/neondatabase/neon/issues/7116
Changes:
- refactor PageServerConfigBuilder: support not-set values
- implement runtime feature test
- use runtime feature test to determine `virtual_file_io_engine` if not
explicitly configured in the config
- log the effective engine at startup
- drive-by: improve assertion messages in `test_pageserver_init_node_id`
This needed a tiny bit of tokio-epoll-uring work, hence bumping it.
Changelog:
```
git log --no-decorate --oneline --reverse 868d2c42b5d54ca82fead6e8f2f233b69a540d3e..342ddd197a060a8354e8f11f4d12994419fff939
c7a74c6 Bump mio from 0.8.8 to 0.8.11
4df3466 Bump mio from 0.8.8 to 0.8.11 (#47)
342ddd1 lifecycle: expose `LaunchResult` enum (#49)
```
## Problem
See:
- https://github.com/neondatabase/neon/issues/6374
## Summary of changes
Whereas previously we calculated synthetic size from the gc_horizon or
the pitr_interval (whichever is the lower LSN), now we ignore gc_horizon
and exclusively start from the `pitr_interval`. This is a more generous
calculation for billing, where we do not charge users for data retained
due to gc_horizon.
Split off from #7030:
- each early exit is counted as canceled init, even though it most
likely was just `LayerInner::keep_resident` doing the no-download repair
check
- `downloaded_after` could had been accounted for multiple times, and
also when repairing to match on-disk state
Cc: #5331
Switched the order; doing https://github.com/neondatabase/neon/pull/6139
first then can remove uninit marker after.
## Problem
Previously, existence of a timeline directory was treated as evidence of
the timeline's logical existence. That is no longer the case since we
treat remote storage as the source of truth on each startup: we can
therefore do without this mark file.
The mark file had also been used as a pseudo-lock to guard against
concurrent creations of the same TimelineId -- now that persistence is
no longer required, this is a bit unwieldy.
In #6139 the `Tenant::timelines_creating` was added to protect against
concurrent creations on the same TimelineId, making the uninit mark file
entirely redundant.
## Summary of changes
- Code that writes & reads mark file is removed
- Some nearby `pub` definitions are amended to `pub(crate)`
- `test_duplicate_creation` is added to demonstrate that mutual
exclusion of creations still works.
## Problem
If a pageserver was offline when the storage controller started, there
was no mechanism to update the
storage controller state when the pageserver becomes active.
## Summary of changes
* Add a heartbeater module. The heartbeater must be driven by an
external loop.
* Integrate the heartbeater into the service.
- Extend the types used by the service and scheduler to keep track of a
nodes' utilisation score.
- Add a background loop to drive the heartbeater and update the state
based on the deltas it generated
- Do an initial round of heartbeats at start-up
