Follows #6123
Closes: https://github.com/neondatabase/neon/issues/5342
The approach here is to avoid using `Layer` from secondary tenants, and
instead make the eviction types (e.g. `EvictionCandidate`) have a
variant that carries a Layer for attached tenants, and a different
variant for secondary tenants.
Other changes:
- EvictionCandidate no longer carries a `Timeline`: this was only used
for providing a witness reference to remote timeline client.
- The types for returning eviction candidates are all in
disk_usage_eviction_task.rs now, whereas some of them were in
timeline.rs before.
- The EvictionCandidate type replaces LocalLayerInfoForDiskUsageEviction
type, which was basically the same thing.
## Problem
In #5980 the page service connection handler gets a simple piece of
logic for finding the right Timeline: at connection time, it picks an
arbitrary Timeline, and then when handling individual page requests it
checks if the original timeline is the correct shard, and if not looks
one up.
This is pretty slow in the case where we have to go look up the other
timeline, because we take the big tenants manager lock.
## Summary of changes
- Add a `shard_timelines` map of ShardIndex to Timeline on the page
service connection handler
- When looking up a Timeline for a particular ShardIndex, consult
`shard_timelines` to avoid hitting the TenantsManager unless we really
need to.
- Re-work the CancellationToken handling, because the handler now holds
gateguards on multiple timelines, and so must respect cancellation of
_any_ timeline it has in its cache, not just the timeline related to the
request it is currently servicing.
---------
Co-authored-by: Vlad Lazar <vlad@neon.tech>
The theme of the changes in this PR is that they're enablers for #6251
which are superficial struct/api changes.
This is a spinoff from #6251:
- Various APIs + clients thereof take TenantShardId rather than TenantId
- The creation API gets a ShardParameters member, which may be used to
configure shard count and stripe size. This enables the attachment
service to present a "virtual pageserver" creation endpoint that creates
multiple shards.
- The attachment service will use tenant size information to drive shard
splitting. Make a version of `TenantHistorySize` that is usable for
decoding these API responses.
- ComputeSpec includes a shard stripe size.
## Problem
Se.e
https://github.com/orgs/neondatabase/projects/49/views/13?pane=issue&itemId=48282912
## Summary of changes
Do not suspend compute if there are active auto vacuum workers
## Checklist before requesting a review
- [ ] I have performed a self-review of my code.
- [ ] If it is a core feature, I have added thorough tests.
- [ ] Do we need to implement analytics? if so did you add the relevant
metrics to the dashboard?
- [ ] If this PR requires public announcement, mark it with
/release-notes label and add several sentences in this section.
## Checklist before merging
- [ ] Do not forget to reformat commit message to not include the above
checklist
---------
Co-authored-by: Konstantin Knizhnik <knizhnik@neon.tech>
Fixes the race condition between timeline creation and tenant deletion
outlined in #6255.
Related: #5914, which is a similar race condition about the uninit
marker file.
Fixes#6255
Generally useful when debugging / troubleshooting.
I found this useful when manually duplicating a tenant from a script[^1]
where I can't use `neon_fixtures.Pageserver.tenant_attach`'s automatic
integration with the neon_local's attachment_service.
[^1]: https://github.com/neondatabase/neon/pull/6349
## Problem
Currently, activity monitor in `compute_ctl` has 500 ms polling
interval. It also looks on the list of current client backends looking
for an active one or one with the most recent state change. This means
we can miss short-living connections.
Yet, during testing this PR I realized that it's usually not a problem
with pooled connection, as pgbouncer maintains connections to Postgres
even though client connection are short-living. We can still miss direct
connections.
## Summary of changes
This commit introduces another way to detect user activity on the
compute. It polls a sum of `active_time` and sum of `sessions` from all
non-system databases in the `pg_stat_database` [1]. If user runs some
queries or just open a direct connection, it will rise; if user will
drop db, it can go down, but it's still a change and will be detected as
activity.
New statistic-based logic seems to be working fine. Yet, after having it
running for a couple of hours I've seen several odd cases with
connections via pgbouncer:
1. Sometimes, if you run just `psql pooler_connstr -c 'select 1;'`
`active_time` could be not updated immediately, and it may take a couple
of dozens of seconds. This doesn't seem critical, though.
2. Same query with pooler, `active_time` can be bumped a bit, then
pgbouncer keeps open connection to Postgres for ~10 minutes, then it
disconnects, and `active_time` *could be* bumped a bit again. 'Could be'
because I've seen it once, but it didn't reproduce for a second try.
I think this can create false-positives (hopefully rare), when we will
not suspend some computes because of lagged statistics update OR because
some non-user processes will try to connect to user databases.
Currently, we don't touch them outside of startup and
`postgres_exporter` is configured to do not discover other databases,
but this can change in the future.
New behavior is covered by feature flag `activity_monitor_experimental`,
which should be provided by control plane via neondatabase/cloud#9171
[1] https://www.postgresql.org/docs/current/monitoring-stats.html#MONITORING-PG-STAT-DATABASE-VIEW
Related to neondatabase/cloud#7966, neondatabase/cloud#7198
## Problem
When creating a timeline on a sharded tenant, we call into each shard.
We don't need to upload the initdb from every shard: only do it on shard
zero.
## Summary of changes
- Move the initdb upload into a function, and only call it on shard
zero.
## Problem
Occasional test failures with QueryError::Other errors saying
"cancelled" that get logged at error severity.
## Summary of changes
Avoid casting GetActiveTenantError::Cancelled into QueryError::Other --
it should be QueryError::Shutdown, which is not logged as an error.
Also shuts down `Broker`, which, before this PR, we did start in
`start()` but relied on the fixture to stop. Do it a bit earlier so
that, after `NeonEnv.stop()` returns, there are no child processes using
`repo_dir`.
Also, drive-by-fixes inverted logic around `ps_assert_metric_no_errors`,
missed during https://github.com/neondatabase/neon/pull/6295
---------
Co-authored-by: Alexander Bayandin <alexander@neon.tech>
safekeeper.rs is mostly about consensus, but state is wider. Also form
SafekeeperState which encapsulates persistent part + in memory layer with API
for atomic updates.
Moves remote_consistent_lsn back to SafekeeperMemState, fixes its absense from
memory dump.
Also renames SafekeeperState to TimelinePersistentState, as TimelineMemState and
TimelinePersistent state are created.
## Problem
Previously, `GET /v1/tenant/:tenant_id/timeline` and `GET
/v1/tenant/:tenant_id/timeline/:timeline_id`
would bump the priority of the background task which computes the
initial logical size by cancelling
the wait on the synchronisation semaphore. However, the request would
still return an approximate
logical size. It's undesirable to force background work for a status
request.
## Summary of changes
This PR updates the priority used by the timeline status request such
that they don't do priority boosting
by default anymore. An optional query parameter,
`force-await-initial-logical-size`, is added for both
mentioned endpoints. When set to true, it will skip the concurrency
limiting semaphore and wait
for the background task to complete before returning the exact logical
size.
In order to exercise this behaviour in a test I had to add an extra
failpoint. If you think it's too intrusive,
it can be removed.
Also fixeda small bug where the cancellation of a download is reported as an
opaque download failure upstream. This caused `test_location_conf_churn`
to fail at teardown due to a WARN log line.
Closes https://github.com/neondatabase/neon/issues/6168
## Problem
HTTP connection pool was not respecting the PitR options.
## Summary of changes
1. refactor neon_options a bit to allow easier access to cache_key
2. make HTTP not go through `StartupMessageParams`
3. expose SNI processing to replace what was removed in step 2.
Random find while looking at an idle 20k tenant pageserver where each
tenant
has 9 tiny L0 layers and compaction produces no new L1s / image layers.
The aggregate CPU cost of running this every 20s for 20k tenants is
actually substantial, due to the use of `spawn_blocking`.
This reverts commit ab1f37e908.
Thereby
fixes#5479
Updated Analysis
================
The problem with the original patch was that it, for the first time,
exposed the `VirtualFile` code to tokio task concurrency instead of just
thread-based concurrency. That caused the VirtualFile file descriptor
cache to start thrashing, effectively grinding the system to a halt.
Details
-------
At the time of the original patch, we had a _lot_ of runnable tasks in
the pageserver.
The symptom that prompted the revert (now being reverted in this PR) is
that our production systems fell into a valley of zero goodput, high
CPU, and zero disk IOPS shortly after PS restart.
We lay out the root cause for that behavior in this subsection.
At the time, there was no concurrency limit on the number of concurrent
initial logical size calculations.
Initial size calculation was initiated for all timelines within the
first 10 minutes as part of consumption metrics collection.
On a PS with 20k timelines, we'd thus have 20k runnable tasks.
Before the original patch, the `VirtualFile` code never returned
`Poll::Pending`.
That meant that once we entered it, the calling tokio task would not
yield to the tokio executor until we were done performing the
VirtualFile operation, i.e., doing a blocking IO system call.
The original patch switched the VirtualFile file descriptor cache's
synchronization primitives to those from `tokio::sync`.
It did not change that we were doing synchronous IO system calls.
And the cache had more slots than we have tokio executor threads.
So, these primitives never actually needed to return `Poll::Pending`.
But, the tokio scheduler makes tokio sync primitives return `Pending`
*artificially*, as a mechanism for the scheduler to get back into
control more often
([example](https://docs.rs/tokio/1.35.1/src/tokio/sync/batch_semaphore.rs.html#570)).
So, the new reality was that VirtualFile calls could now yield to the
tokio executor.
Tokio would pick one of the other 19999 runnable tasks to run.
These tasks were also using VirtualFile.
So, we now had a lot more concurrency in that area of the code.
The problem with more concurrency was that caches started thrashing,
most notably the VirtualFile file descriptor cache: each time a task
would be rescheduled, it would want to do its next VirtualFile
operation. For that, it would first need to evict another (task's)
VirtualFile fd from the cache to make room for its own fd. It would then
do one VirtualFile operation before hitting an await point and yielding
to the executor again. The executor would run the other 19999 tasks for
fairness before circling back to the first task, which would find its fd
evicted.
The other cache that would theoretically be impacted in a similar way is
the pageserver's `PageCache`.
However, for initial logical size calculation, it seems much less
relevant in experiments, likely because of the random access nature of
initial logical size calculation.
Fixes
=====
We fixed the above problems by
- raising VirtualFile cache sizes
- https://github.com/neondatabase/cloud/issues/8351
- changing code to ensure forward-progress once cache slots have been
acquired
- https://github.com/neondatabase/neon/pull/5480
- https://github.com/neondatabase/neon/pull/5482
- tbd: https://github.com/neondatabase/neon/issues/6065
- reducing the amount of runnable tokio tasks
- https://github.com/neondatabase/neon/pull/5578
- https://github.com/neondatabase/neon/pull/6000
- fix bugs that caused unnecessary concurrency induced by connection
handlers
- https://github.com/neondatabase/neon/issues/5993
I manually verified that this PR doesn't negatively affect startup
performance as follows:
create a pageserver in production configuration, with 20k
tenants/timelines, 9 tiny L0 layer files each; Start it, and observe
```
INFO Startup complete (368.009s since start) elapsed_ms=368009
```
I further verified in that same setup that, when using `pagebench`'s
getpage benchmark at as-fast-as-possible request rate against 5k of the
20k tenants, the achieved throughput is identical. The VirtualFile cache
isn't thrashing in that case.
Future Work
===========
We will still exposed to the cache thrashing risk from outside factors,
e.g., request concurrency is unbounded, and initial size calculation
skips the concurrency limiter when we establish a walreceiver
connection.
Once we start thrashing, we will degrade non-gracefully, i.e., encounter
a valley as was seen with the original patch.
However, we have sufficient means to deal with that unlikely situation:
1. we have dashboards & metrics to monitor & alert on cache thrashing
2. we can react by scaling the bottleneck resources (cache size) or by
manually shedding load through tenant relocation
Potential systematic solutions are future work:
* global concurrency limiting
* per-tenant rate limiting => #5899
* pageserver-initiated load shedding
Related Issues
==============
This PR unblocks the introduction of tokio-epoll-uring for asynchronous
disk IO ([Epic](#4744)).
Postgres can write multiline logs, and they are difficult to handle
after they are mixed with other logs. This PR combines multiline logs
from postgres into a single line, where previous line breaks are
replaced with unicode zero-width spaces. Then postgres logs are written
to stderr with `PG:` prefix.
It makes it easy to distinguish postgres logs from all other compute
logs with a simple grep, e.g. `|= "PG:"`
## Problem
Current cache doesn't support any updates from the cplane.
## Summary of changes
* Added redis notifier listner.
* Added cache which can be invalidated with the notifier. If the
notifier is not available, it's just a normal ttl cache.
* Updated cplane api.
The motivation behind this organization of the data is the following:
* In the Neon data model there are projects. Projects could have
multiple branches and each branch could have more than one endpoint.
* Also there is one special `main` branch.
* Password reset works per branch.
* Allowed IPs are the same for every branch in the project (except,
maybe, the main one).
* The main branch can be changed to the other branch.
* The endpoint can be moved between branches.
Every event described above requires some special processing on the
porxy (or cplane) side.
The idea of invalidating for the project is that whenever one of the
events above is happening with the project, proxy can invalidate all
entries for the entire project.
This approach also requires some additional API change (returning
project_id inside the auth info).
PR #6266 broke the getpage_latest_lsn benchmark.
Before this patch, we'd fail with
```
not implemented: split up range
```
because `r.start = rel size key` and `r.end = rel size key + 1`.
The filtering of the key ranges in that loop is a bit ugly, but,
I measured:
* setup with 180k layer files (20k tenants * 9 layers).
* total physical size is 463GiB
* 5k tenants, the range filtering takes `0.6 seconds` on an
i3en.3xlarge.
That's a tiny fraction of the overall time it takes for pagebench to get
ready to send requests. So, this is good enough for now / there are
other bottlenecks that are bigger.
## Problem
The code for tenant create and tenant attach was just a special case of
what upsert_location does.
## Summary of changes
- Use `upsert_location` for create and attach APIs
- Clean up error handling in upsert_location so that it can generate
appropriate HTTP response codes
- Update tests that asserted the old non-idempotent behavior of attach
- Rework the `test_ignore_while_attaching` test, and fix tenant shutdown
during activation, which this test was supposed to cover, but it was
actually just waiting for activation to complete.
This uses the [newly stable](https://blog.rust-lang.org/2023/12/21/async-fn-rpit-in-traits.html)
async trait feature for three internal traits. One requires `Send`
bounds to be present so uses `impl Future<...> + Send` instead.
Advantages:
* less macro usage
* no extra boxing
Disadvantages:
* impl syntax needed for `Send` bounds is a bit more verbose (but only
required in one place)
Part of #5771
Extracted from https://github.com/neondatabase/neon/pull/6214
This PR makes the test suite sensitive to the new env var
`NEON_ENV_BUILDER_FROM_REPO_DIR_USE_OVERLAYFS`.
If it is set, `NeonEnvBuilder.from_repo_dir` uses overlayfs
to duplicate the the snapshot repo dir contents.
Since mounting requires root privileges, we use sudo to perform
the mounts. That, and macOS support, is also why copytree remains
the default.
If we ever run on a filesystem with copy reflink support, we should
consider that as an alternative.
This PR can be tried on a Linux machine on the
`test_backward_compatiblity` test, which uses `from_repo_dir`.
During a previous incident, we noticed that this particular line can be
repeatedly logged every 100ms if the memory usage continues is
persistently high enough to warrant upscaling.
Per the added comment: Ideally we'd still like to include this log line,
because it's useful information, but the simple way to include it
produces far too many log lines, and the more complex ways to
deduplicate the log lines while still including the information are
probably not worth the effort right now.
This fixes the clippy lint firing on macOS on the conversion which
needed for portability. For some reason, the logic in
https://github.com/rust-lang/rust-clippy/pull/11669 to avoid an overlap
is not working.
## Summary of changes
### RequestMonitoring
We want to add an event stream with information on each request for
easier analysis than what we can do with diagnostic logs alone
(https://github.com/neondatabase/cloud/issues/8807). This
RequestMonitoring will keep a record of the final state of a request. On
drop it will be pushed into a queue to be uploaded.
Because this context is a bag of data, I don't want this information to
impact logic of request handling. I personally think that weakly typed
data (such as all these options) makes for spaghetti code. I will
however allow for this data to impact rate-limiting and blocking of
requests, as this does not _really_ change how a request is handled.
### Parquet
Each `RequestMonitoring` is flushed into a channel where it is converted
into `RequestData`, which is accumulated into parquet files. Each file
will have a certain number of rows per row group, and several row groups
will eventually fill up the file, which we then upload to S3.
We will also upload smaller files if they take too long to construct.
This is a lightweight change to keep the scrubber providing sensible
output when using sharding.
- The timeline count was wrong when using sharding
- When checking for tenant existence, we didn't re-use results between
different shards in the same tenant
Closes: https://github.com/neondatabase/neon/issues/5929
These functions don't need updating for sharding: it's fine for them to
remain shard-naive, as they're only used in the context of dumping a
layer file. The sharding metadata doesn't live in the layer file, it
lives in the index.
## Problem
Noticed while making other changes that there were `pub` items that were
unused.
## Summary of changes
- Make everything `pub(crate)` in metrics.rs, apart from items used from
`bin/`
- Fix the timelines eviction metric: it was never being incremented
- Remove an unused ephemeral_bytes counter.
## Problem
`black` is slow sometimes, we can replace it with `ruff format` (a new
feature in 0.1.2 [0]), which produces pretty similar to black style [1].
On my local machine (MacBook M1 Pro 16GB):
```
# `black` on main
$ hyperfine "BLACK_CACHE_DIR=/dev/null poetry run black ."
Benchmark 1: BLACK_CACHE_DIR=/dev/null poetry run black .
Time (mean ± σ): 3.131 s ± 0.090 s [User: 5.194 s, System: 0.859 s]
Range (min … max): 3.047 s … 3.354 s 10 runs
```
```
# `ruff format` on the current PR
$ hyperfine "RUFF_NO_CACHE=true poetry run ruff format"
Benchmark 1: RUFF_NO_CACHE=true poetry run ruff format
Time (mean ± σ): 300.7 ms ± 50.2 ms [User: 259.5 ms, System: 76.1 ms]
Range (min … max): 267.5 ms … 420.2 ms 10 runs
```
## Summary of changes
- Replace `black` with `ruff format` everywhere
- [0] https://docs.astral.sh/ruff/formatter/
- [1] https://docs.astral.sh/ruff/formatter/#black-compatibility
