# Problem
The timeout-based batching adds latency to unbatchable workloads.
We can choose a short batching timeout (e.g. 10us) but that requires
high-resolution timers, which tokio doesn't have.
I thoroughly explored options to use OS timers (see
[this](https://github.com/neondatabase/neon/pull/9822) abandoned PR).
In short, it's not an attractive option because any timer implementation
adds non-trivial overheads.
# Solution
The insight is that, in the steady state of a batchable workload, the
time we spend in `get_vectored` will be hundreds of microseconds anyway.
If we prepare the next batch concurrently to `get_vectored`, we will
have a sizeable batch ready once `get_vectored` of the current batch is
done and do not need an explicit timeout.
This can be reasonably described as **pipelining of the protocol
handler**.
# Implementation
We model the sub-protocol handler for pagestream requests
(`handle_pagrequests`) as two futures that form a pipeline:
2. Batching: read requests from the connection and fill the current
batch
3. Execution: `take` the current batch, execute it using `get_vectored`,
and send the response.
The Reading and Batching stage are connected through a new type of
channel called `spsc_fold`.
See the long comment in the `handle_pagerequests_pipelined` for details.
# Changes
- Refactor `handle_pagerequests`
- separate functions for
- reading one protocol message; produces a `BatchedFeMessage` with just
one page request in it
- batching; tried to merge an incoming `BatchedFeMessage` into an
existing `BatchedFeMessage`; returns `None` on success and returns back
the incoming message in case merging isn't possible
- execution of a batched message
- unify the timeline handle acquisition & request span construction; it
now happen in the function that reads the protocol message
- Implement serial and pipelined model
- serial: what we had before any of the batching changes
- read one protocol message
- execute protocol messages
- pipelined: the design described above
- optionality for execution of the pipeline: either via concurrent
futures vs tokio tasks
- Pageserver config
- remove batching timeout field
- add ability to configure pipelining mode
- add ability to limit max batch size for pipelined configurations
(required for the rollout, cf
https://github.com/neondatabase/cloud/issues/20620 )
- ability to configure execution mode
- Tests
- remove `batch_timeout` parametrization
- rename `test_getpage_merge_smoke` to `test_throughput`
- add parametrization to test different max batch sizes and execution
moes
- rename `test_timer_precision` to `test_latency`
- rename the test case file to `test_page_service_batching.py`
- better descriptions of what the tests actually do
## On the holding The `TimelineHandle` in the pending batch
While batching, we hold the `TimelineHandle` in the pending batch.
Therefore, the timeline will not finish shutting down while we're
batching.
This is not a problem in practice because the concurrently ongoing
`get_vectored` call will fail quickly with an error indicating that the
timeline is shutting down.
This results in the Execution stage returning a `QueryError::Shutdown`,
which causes the pipeline / entire page service connection to shut down.
This drops all references to the
`Arc<Mutex<Option<Box<BatchedFeMessage>>>>` object, thereby dropping the
contained `TimelineHandle`s.
- => fixes https://github.com/neondatabase/neon/issues/9850
# Performance
Local run of the benchmarks, results in [this empty
commit](1cf5b1463f)
in the PR branch.
Key take-aways:
* `concurrent-futures` and `tasks` deliver identical `batching_factor`
* tail latency impact unknown, cf
https://github.com/neondatabase/neon/issues/9837
* `concurrent-futures` has higher throughput than `tasks` in all
workloads (=lower `time` metric)
* In unbatchable workloads, `concurrent-futures` has 5% higher
`CPU-per-throughput` than that of `tasks`, and 15% higher than that of
`serial`.
* In batchable-32 workload, `concurrent-futures` has 8% lower
`CPU-per-throughput` than that of `tasks` (comparison to tput of
`serial` is irrelevant)
* in unbatchable workloads, mean and tail latencies of
`concurrent-futures` is practically identical to `serial`, whereas
`tasks` adds 20-30us of overhead
Overall, `concurrent-futures` seems like a slightly more attractive
choice.
# Rollout
This change is disabled-by-default.
Rollout plan:
- https://github.com/neondatabase/cloud/issues/20620
# Refs
- epic: https://github.com/neondatabase/neon/issues/9376
- this sub-task: https://github.com/neondatabase/neon/issues/9377
- the abandoned attempt to improve batching timeout resolution:
https://github.com/neondatabase/neon/pull/9820
- closes https://github.com/neondatabase/neon/issues/9850
- fixes https://github.com/neondatabase/neon/issues/9835
## Problem
For any given tenant shard, pageservers receive all of the tenant's WAL
from the safekeeper.
This soft-blocks us from using larger shard counts due to bandwidth
concerns and CPU overhead of filtering
out the records.
## Summary of changes
This PR lifts the decoding and interpretation of WAL from the pageserver
into the safekeeper.
A customised PG replication protocol is used where instead of sending
raw WAL, the safekeeper sends
filtered, interpreted records. The receiver drives the protocol
selection, so, on the pageserver side, usage
of the new protocol is gated by a new pageserver config:
`wal_receiver_protocol`.
More granularly the changes are:
1. Optionally inject the protocol and shard identity into the arguments
used for starting replication
2. On the safekeeper side, implement a new wal sending primitive which
decodes and interprets records
before sending them over
3. On the pageserver side, implement the ingestion of this new
replication message type. It's very similar
to what we already have for raw wal (minus decoding and interpreting).
## Notes
* This PR currently uses my [branch of
rust-postgres](https://github.com/neondatabase/rust-postgres/tree/vlad/interpreted-wal-record-replication-support)
which includes the deserialization logic for the new replication message
type. PR for that is open
[here](https://github.com/neondatabase/rust-postgres/pull/32).
* This PR contains changes for both pageservers and safekeepers. It's
safe to merge because the new protocol is disabled by default on the
pageserver side. We can gradually start enabling it in subsequent
releases.
* CI tests are running on https://github.com/neondatabase/neon/pull/9747
## Links
Related: https://github.com/neondatabase/neon/issues/9336
Epic: https://github.com/neondatabase/neon/issues/9329
Co-authored-by: Heikki Linnakangas <heikki@neon.tech>
Co-authored-by: Stas Kelvic <stas@neon.tech>
# Context
This PR contains PoC-level changes for a product feature that allows
onboarding large databases into Neon without going through the regular
data path.
# Changes
This internal RFC provides all the context
* https://github.com/neondatabase/cloud/pull/19799
In the language of the RFC, this PR covers
* the Importer code (`fast_import`)
* all the Pageserver changes (mgmt API changes, flow implementation,
etc)
* a basic test for the Pageserver changes
# Reviewing
As acknowledged in the RFC, the code added in this PR is not ready for
general availability.
Also, the **architecture is not to be discussed in this PR**, but in the
RFC and associated Slack channel instead.
Reviewers of this PR should take that into consideration.
The quality bar to apply during review depends on what area of the code
is being reviewed:
* Importer code (`fast_import`): practically anything goes
* Core flow (`flow.rs`):
* Malicious input data must be expected and the existing threat models
apply.
* The code must not be safe to execute on *dedicated* Pageserver
instances:
* This means in particular that tenants *on other* Pageserver instances
must not be affected negatively wrt data confidentiality, integrity or
availability.
* Other code: the usual quality bar
* Pay special attention to correct use of gate guards, timeline
cancellation in all places during shutdown & migration, etc.
* Consider the broader system impact; if you find potentially
problematic interactions with Storage features that were not covered in
the RFC, bring that up during the review.
I recommend submitting three separate reviews, for the three high-level
areas with different quality bars.
# References
(Internal-only)
* refs https://github.com/neondatabase/cloud/issues/17507
* refs https://github.com/neondatabase/company_projects/issues/293
* refs https://github.com/neondatabase/company_projects/issues/309
* refs https://github.com/neondatabase/cloud/issues/20646
---------
Co-authored-by: Stas Kelvich <stas.kelvich@gmail.com>
Co-authored-by: Heikki Linnakangas <heikki@neon.tech>
Co-authored-by: John Spray <john@neon.tech>
## Problem
We don't take advantage of queue depth generated by the compute
on the pageserver. We can process getpage requests more efficiently
by batching them.
## Summary of changes
Batch up incoming getpage requests that arrive within a configurable
time window (`server_side_batch_timeout`).
Then process the entire batch via one `get_vectored` timeline operation.
By default, no merging takes place.
## Testing
* **Functional**: https://github.com/neondatabase/neon/pull/9792
* **Performance**: will be done in staging/pre-prod
# Refs
* https://github.com/neondatabase/neon/issues/9377
* https://github.com/neondatabase/neon/issues/9376
Co-authored-by: Christian Schwarz <christian@neon.tech>
Right now, our environments create databases with the C locale, which is
really unfortunate for users who have data stored in other languages
that they want to analyze. For instance, show_trgm on Hebrew text
currently doesn't work in staging or production.
I don't envision this being the final solution. I think this is just a
way to set a known value so the pageserver doesn't use its parent
environment. The final solution to me is exposing initdb parameters to
users in the console. Then they could use a different locale or encoding
if they so chose.
Signed-off-by: Tristan Partin <tristan@neon.tech>
## Problem
In test environments, the `syncfs` that the pageserver does on startup
can take a long time, as other tests running concurrently might have
many gigabytes of dirty pages.
## Summary of changes
- Add a `no_sync` option to the pageserver's config.
- Skip syncfs on startup if this is set
- A subsequent PR (https://github.com/neondatabase/neon/pull/9678) will
enable this by default in tests. We need to wait until after the next
release to avoid breaking compat tests, which would fail if we set
no_sync & use an old pageserver binary.
Q: Why is this a different mechanism than safekeeper, which as a
--no-sync CLI?
A: Because the way we manage pageservers in neon_local depends on the
pageserver.toml containing the full configuration, whereas safekeepers
have a config file which is neon-local-specific and can drive a CLI
flag.
Q: Why is the option no_sync rather than sync?
A: For boolean configs with a dangerous value, it's preferable to make
"false" the safe option, so that any downstream future config tooling
that might have a "booleans are false by default" behavior (e.g. golang
structs) is safe by default.
Q: Why only skip the syncfs, and not all fsyncs?
A: Skipping all fsyncs would require more code changes, and the most
acute problem isn't fsyncs themselves (these just slow down a running
test), it's the syncfs (which makes a pageserver startup slow as a
result of _other_ tests)
Adds a configuration variable for timeline offloading support. The added
pageserver-global config option controls whether the pageserver
automatically offloads timelines during compaction.
Therefore, already offloaded timelines are not affected by this, nor is
the manual testing endpoint.
This allows the rollout of timeline offloading to be driven by the
storage team.
Part of #8088
## Problem
We need a way to incrementally switch to direct IO. During the rollout
we might want to switch to O_DIRECT on image and delta layer read path
first before others.
## Summary of changes
- Revisited and simplified direct io config in `PageserverConf`.
- We could add a fallback mode for open, but for read there isn't a
reasonable alternative (without creating another buffered virtual file).
- Added a wrapper around `VirtualFile`, current implementation become
`VirtualFileInner`
- Use `open_v2`, `create_v2`, `open_with_options_v2` when we want to use
the IO mode specified in PS config.
- Once we onboard all IO through VirtualFile using this new API, we will
delete the old code path.
- Make io mode live configurable for benchmarking.
- Only guaranteed for files opened after the config change, so do it
before the experiment.
As an example, we are using `open_v2` with
`virtual_file::IoMode::Direct` in
https://github.com/neondatabase/neon/pull/9169
We also remove `io_buffer_alignment` config in
a04cfd754b and use it as a compile time
constant. This way we don't have to carry the alignment around or make
frequent call to retrieve this information from the static variable.
Signed-off-by: Yuchen Liang <yuchen@neon.tech>
The DEFAULT_CONCURRENT_TENANT_SIZE_LOGICAL_SIZE_QUERIES constant was
unused, because we had just hardcoded it to 1 where the constant
should've been used.
Remove the ConfigurableSemaphore::Default implementation, since it was
unused.
There's some more code that still checks for uninit and delete
markers, see callers of is_delete_mark and is_uninit_mark, and github
issue #5718. But these functions were outright dead.
This adds preliminary PG17 support to Neon, based on RC1 / 2024-09-04
07b828e9d4
NOTICE: The data produced by the included version of the PostgreSQL fork
may not be compatible with the future full release of PostgreSQL 17 due to
expected or unexpected future changes in magic numbers and internals.
DO NOT EXPECT DATA IN V17-TENANTS TO BE COMPATIBLE WITH THE 17.0
RELEASE!
Co-authored-by: Anastasia Lubennikova <anastasia@neon.tech>
Co-authored-by: Alexander Bayandin <alexander@neon.tech>
Co-authored-by: Konstantin Knizhnik <knizhnik@neon.tech>
Co-authored-by: Heikki Linnakangas <heikki@neon.tech>
Addresses the 1.82 beta clippy lint `too_long_first_doc_paragraph` by
adding newlines to the first sentence if it is short enough, and making
a short first sentence if there is the need.
This PR simplifies the pageserver configuration parsing as follows:
* introduce the `pageserver_api::config::ConfigToml` type
* implement `Default` for `ConfigToml`
* use serde derive to do the brain-dead leg-work of processing the toml
document
* use `serde(default)` to fill in default values
* in `pageserver` crate:
* use `toml_edit` to deserialize the pageserver.toml string into a
`ConfigToml`
* `PageServerConfig::parse_and_validate` then
* consumes the `ConfigToml`
* destructures it exhaustively into its constituent fields
* constructs the `PageServerConfig`
The rules are:
* in `ConfigToml`, use `deny_unknown_fields` everywhere
* static default values go in `pageserver_api`
* if there cannot be a static default value (e.g. which default IO
engine to use, because it depends on the runtime), make the field in
`ConfigToml` an `Option`
* if runtime-augmentation of a value is needed, do that in
`parse_and_validate`
* a good example is `virtual_file_io_engine` or `l0_flush`, both of
which need to execute code to determine the effective value in
`PageServerConf`
The benefits:
* massive amount of brain-dead repetitive code can be deleted
* "unused variable" compile-time errors when removing a config value,
due to the exhaustive destructuring in `parse_and_validate`
* compile-time errors guide you when adding a new config field
Drawbacks:
* serde derive is sometimes a bit too magical
* `deny_unknown_fields` is easy to miss
Future Work / Benefits:
* make `neon_local` use `pageserver_api` to construct `ConfigToml` and
write it to `pageserver.toml`
* This provides more type safety / coompile-time errors than the current
approach.
### Refs
Fixes#3682
### Future Work
* `remote_storage` deser doesn't reject unknown fields
https://github.com/neondatabase/neon/issues/8915
* clean up `libs/pageserver_api/src/config.rs` further
* break up into multiple files, at least for tenant config
* move `models` as appropriate / refine distinction between config and
API models / be explicit about when it's the same
* use `pub(crate)` visibility on `mod defaults` to detect stale values
## Summary of changes
- Setting default io_buffer_alignment to 512 bytes.
- Fix places that assumed `DEFAULT_IO_BUFFER_ALIGNMENT=0`
- Adapt unit tests to handle merge with `chunk size <= 4096`.
## Testing and Performance
We have done sufficient performance de-risking.
Enabling it by default completes our correctness de-risking before the
next release.
Context: https://neondb.slack.com/archives/C07BZ38E6SD/p1725026845455259
Signed-off-by: Yuchen Liang <yuchen@neon.tech>
Co-authored-by: Christian Schwarz <christian@neon.tech>
Part of [Epic: Bypass PageCache for user data
blocks](https://github.com/neondatabase/neon/issues/7386).
# Problem
`InMemoryLayer` still uses the `PageCache` for all data stored in the
`VirtualFile` that underlies the `EphemeralFile`.
# Background
Before this PR, `EphemeralFile` is a fancy and (code-bloated) buffered
writer around a `VirtualFile` that supports `blob_io`.
The `InMemoryLayerInner::index` stores offsets into the `EphemeralFile`.
At those offset, we find a varint length followed by the serialized
`Value`.
Vectored reads (`get_values_reconstruct_data`) are not in fact vectored
- each `Value` that needs to be read is read sequentially.
The `will_init` bit of information which we use to early-exit the
`get_values_reconstruct_data` for a given key is stored in the
serialized `Value`, meaning we have to read & deserialize the `Value`
from the `EphemeralFile`.
The L0 flushing **also** needs to re-determine the `will_init` bit of
information, by deserializing each value during L0 flush.
# Changes
1. Store the value length and `will_init` information in the
`InMemoryLayer::index`. The `EphemeralFile` thus only needs to store the
values.
2. For `get_values_reconstruct_data`:
- Use the in-memory `index` figures out which values need to be read.
Having the `will_init` stored in the index enables us to do that.
- View the EphemeralFile as a byte array of "DIO chunks", each 512 bytes
in size (adjustable constant). A "DIO chunk" is the minimal unit that we
can read under direct IO.
- Figure out which chunks need to be read to retrieve the serialized
bytes for thes values we need to read.
- Coalesce chunk reads such that each DIO chunk is only read once to
serve all value reads that need data from that chunk.
- Merge adjacent chunk reads into larger
`EphemeralFile::read_exact_at_eof_ok` of up to 128k (adjustable
constant).
3. The new `EphemeralFile::read_exact_at_eof_ok` fills the IO buffer
from the underlying VirtualFile and/or its in-memory buffer.
4. The L0 flush code is changed to use the `index` directly, `blob_io`
5. We can remove the `ephemeral_file::page_caching` construct now.
The `get_values_reconstruct_data` changes seem like a bit overkill but
they are necessary so we issue the equivalent amount of read system
calls compared to before this PR where it was highly likely that even if
the first PageCache access was a miss, remaining reads within the same
`get_values_reconstruct_data` call from the same `EphemeralFile` page
were a hit.
The "DIO chunk" stuff is truly unnecessary for page cache bypass, but,
since we're working on [direct
IO](https://github.com/neondatabase/neon/issues/8130) and
https://github.com/neondatabase/neon/issues/8719 specifically, we need
to do _something_ like this anyways in the near future.
# Alternative Design
The original plan was to use the `vectored_blob_io` code it relies on
the invariant of Delta&Image layers that `index order == values order`.
Further, `vectored_blob_io` code's strategy for merging IOs is limited
to adjacent reads. However, with direct IO, there is another level of
merging that should be done, specifically, if multiple reads map to the
same "DIO chunk" (=alignment-requirement-sized and -aligned region of
the file), then it's "free" to read the chunk into an IO buffer and
serve the two reads from that buffer.
=> https://github.com/neondatabase/neon/issues/8719
# Testing / Performance
Correctness of the IO merging code is ensured by unit tests.
Additionally, minimal tests are added for the `EphemeralFile`
implementation and the bit-packed `InMemoryLayerIndexValue`.
Performance testing results are presented below.
All pref testing done on my M2 MacBook Pro, running a Linux VM.
It's a release build without `--features testing`.
We see definitive improvement in ingest performance microbenchmark and
an ad-hoc microbenchmark for getpage against InMemoryLayer.
```
baseline: commit 7c74112b2a origin/main
HEAD: ef1c55c52e
```
<details>
```
cargo bench --bench bench_ingest -- 'ingest 128MB/100b seq, no delta'
baseline
ingest-small-values/ingest 128MB/100b seq, no delta
time: [483.50 ms 498.73 ms 522.53 ms]
thrpt: [244.96 MiB/s 256.65 MiB/s 264.73 MiB/s]
HEAD
ingest-small-values/ingest 128MB/100b seq, no delta
time: [479.22 ms 482.92 ms 487.35 ms]
thrpt: [262.64 MiB/s 265.06 MiB/s 267.10 MiB/s]
```
</details>
We don't have a micro-benchmark for InMemoryLayer and it's quite
cumbersome to add one. So, I did manual testing in `neon_local`.
<details>
```
./target/release/neon_local stop
rm -rf .neon
./target/release/neon_local init
./target/release/neon_local start
./target/release/neon_local tenant create --set-default
./target/release/neon_local endpoint create foo
./target/release/neon_local endpoint start foo
psql 'postgresql://cloud_admin@127.0.0.1:55432/postgres'
psql (13.16 (Debian 13.16-0+deb11u1), server 15.7)
CREATE TABLE wal_test (
id SERIAL PRIMARY KEY,
data TEXT
);
DO $$
DECLARE
i INTEGER := 1;
BEGIN
WHILE i <= 500000 LOOP
INSERT INTO wal_test (data) VALUES ('data');
i := i + 1;
END LOOP;
END $$;
-- => result is one L0 from initdb and one 137M-sized ephemeral-2
DO $$
DECLARE
i INTEGER := 1;
random_id INTEGER;
random_record wal_test%ROWTYPE;
start_time TIMESTAMP := clock_timestamp();
selects_completed INTEGER := 0;
min_id INTEGER := 1; -- Minimum ID value
max_id INTEGER := 100000; -- Maximum ID value, based on your insert range
iters INTEGER := 100000000; -- Number of iterations to run
BEGIN
WHILE i <= iters LOOP
-- Generate a random ID within the known range
random_id := min_id + floor(random() * (max_id - min_id + 1))::int;
-- Select the row with the generated random ID
SELECT * INTO random_record
FROM wal_test
WHERE id = random_id;
-- Increment the select counter
selects_completed := selects_completed + 1;
-- Check if a second has passed
IF EXTRACT(EPOCH FROM clock_timestamp() - start_time) >= 1 THEN
-- Print the number of selects completed in the last second
RAISE NOTICE 'Selects completed in last second: %', selects_completed;
-- Reset counters for the next second
selects_completed := 0;
start_time := clock_timestamp();
END IF;
-- Increment the loop counter
i := i + 1;
END LOOP;
END $$;
./target/release/neon_local stop
baseline: commit 7c74112b2a origin/main
NOTICE: Selects completed in last second: 1864
NOTICE: Selects completed in last second: 1850
NOTICE: Selects completed in last second: 1851
NOTICE: Selects completed in last second: 1918
NOTICE: Selects completed in last second: 1911
NOTICE: Selects completed in last second: 1879
NOTICE: Selects completed in last second: 1858
NOTICE: Selects completed in last second: 1827
NOTICE: Selects completed in last second: 1933
ours
NOTICE: Selects completed in last second: 1915
NOTICE: Selects completed in last second: 1928
NOTICE: Selects completed in last second: 1913
NOTICE: Selects completed in last second: 1932
NOTICE: Selects completed in last second: 1846
NOTICE: Selects completed in last second: 1955
NOTICE: Selects completed in last second: 1991
NOTICE: Selects completed in last second: 1973
```
NB: the ephemeral file sizes differ by ca 1MiB, ours being 1MiB smaller.
</details>
# Rollout
This PR changes the code in-place and is not gated by a feature flag.
Part of #8130, closes#8719.
## Problem
Currently, vectored blob io only coalesce blocks if they are immediately
adjacent to each other. When we switch to Direct IO, we need a way to
coalesce blobs that are within the dio-aligned boundary but has gap
between them.
## Summary of changes
- Introduces a `VectoredReadCoalesceMode` for `VectoredReadPlanner` and
`StreamingVectoredReadPlanner` which has two modes:
- `AdjacentOnly` (current implementation)
- `Chunked(<alignment requirement>)`
- New `ChunkedVectorBuilder` that considers batching `dio-align`-sized
read, the start and end of the vectored read will respect
`stx_dio_offset_align` / `stx_dio_mem_align` (`vectored_read.start` and
`vectored_read.blobs_at.first().start_offset` will be two different
value).
- Since we break the assumption that blobs within single `VectoredRead`
are next to each other (implicit end offset), we start to store blob end
offsets in the `VectoredRead`.
- Adapted existing tests to run in both `VectoredReadCoalesceMode`.
- The io alignment can also be live configured at runtime.
Signed-off-by: Yuchen Liang <yuchen@neon.tech>
After the rollout has succeeded, we now set the default image
compression to be enabled.
We also remove its explicit mention from `neon_fixtures.py` added in
#8368 as it is now the default (and we switch to `zstd(1)` which is a
bit nicer on CPU time).
Part of https://github.com/neondatabase/neon/issues/5431
## Problem
Pageserver exposes some vectored get related configs which are not in
use.
## Summary of changes
Remove the following pageserver configs: get_impl, get_vectored_impl,
and `validate_get_vectored`.
They are not used in the pageserver since
https://github.com/neondatabase/neon/pull/8601.
Manual overrides have been removed from the aws repo in
https://github.com/neondatabase/aws/pull/1664.
Part of #8130, [RFC: Direct IO For Pageserver](https://github.com/neondatabase/neon/blob/problame/direct-io-rfc/docs/rfcs/034-direct-io-for-pageserver.md)
## Description
Add pageserver config for evaluating/enabling direct I/O.
- Disabled: current default, uses buffered io as is.
- Evaluate: still uses buffered io, but could do alignment checking and
perf simulation (pad latency by direct io RW to a fake file).
- Enabled: uses direct io, behavior on alignment error is configurable.
Signed-off-by: Yuchen Liang <yuchen@neon.tech>
part of https://github.com/neondatabase/neon/issues/8184
# Problem
We want to bypass PS PageCache for all data block reads, but
`compact_level0_phase1` currently uses `ValueRef::load` to load the WAL
records from delta layers.
Internally, that maps to `FileBlockReader:read_blk` which hits the
PageCache
[here](e78341e1c2/pageserver/src/tenant/block_io.rs (L229-L236)).
# Solution
This PR adds a mode for `compact_level0_phase1` that uses the
`MergeIterator` for reading the `Value`s from the delta layer files.
`MergeIterator` is a streaming k-merge that uses vectored blob_io under
the hood, which bypasses the PS PageCache for data blocks.
Other notable changes:
* change the `DiskBtreeReader::into_stream` to buffer the node, instead
of holding a `PageCache` `PageReadGuard`.
* Without this, we run out of page cache slots in
`test_pageserver_compaction_smoke`.
* Generally, `PageReadGuard`s aren't supposed to be held across await
points, so, this is a general bugfix.
# Testing / Validation / Performance
`MergeIterator` has not yet been used in production; it's being
developed as part of
* https://github.com/neondatabase/neon/issues/8002
Therefore, this PR adds a validation mode that compares the existing
approach's value iterator with the new approach's stream output, item by
item.
If they're not identical, we log a warning / fail the unit/regression
test.
To avoid flooding the logs, we apply a global rate limit of once per 10
seconds.
In any case, we use the existing approach's value.
Expected performance impact that will be monitored in staging / nightly
benchmarks / eventually pre-prod:
* with validation:
* increased CPU usage
* ~doubled VirtualFile read bytes/second metric
* no change in disk IO usage because the kernel page cache will likely
have the pages buffered on the second read
* without validation:
* slightly higher DRAM usage because each iterator participating in the
k-merge has a dedicated buffer (as opposed to before, where compactions
would rely on the PS PageCaceh as a shared evicting buffer)
* less disk IO if previously there were repeat PageCache misses (likely
case on a busy production Pageserver)
* lower CPU usage: PageCache out of the picture, fewer syscalls are made
(vectored blob io batches reads)
# Rollout
The new code is used with validation mode enabled-by-default.
This gets us validation everywhere by default, specifically in
- Rust unit tests
- Python tests
- Nightly pagebench (shouldn't really matter)
- Staging
Before the next release, I'll merge the following aws.git PR that
configures prod to continue using the existing behavior:
* https://github.com/neondatabase/aws/pull/1663
# Interactions With Other Features
This work & rollout should complete before Direct IO is enabled because
Direct IO would double the IOPS & latency for each compaction read
(#8240).
# Future Work
The streaming k-merge's memory usage is proportional to the amount of
memory per participating layer.
But `compact_level0_phase1` still loads all keys into memory for
`all_keys_iter`.
Thus, it continues to have active memory usage proportional to the
number of keys involved in the compaction.
Future work should replace `all_keys_iter` with a streaming keys
iterator.
This PR has a draft in its first commit, which I later reverted because
it's not necessary to achieve the goal of this PR / issue #8184.
Problem
-------
wait_lsn timeouts result in a user-facing errors like
```
$ /tmp/neon/pg_install/v16/bin/pgbench -s3424 -i -I dtGvp user=neondb_owner dbname=neondb host=ep-tiny-wave-w23owa37.eastus2.azure.neon.build sslmode=require options='-cstatement_timeout=0 '
dropping old tables...
NOTICE: table "pgbench_accounts" does not exist, skipping
NOTICE: table "pgbench_branches" does not exist, skipping
NOTICE: table "pgbench_history" does not exist, skipping
NOTICE: table "pgbench_tellers" does not exist, skipping
creating tables...
generating data (server-side)...
vacuuming...
pgbench: error: query failed: ERROR: [NEON_SMGR] [shard 0] could not read block 214338 in rel 1663/16389/16839.0 from page server at lsn C/E1C12828
DETAIL: page server returned error: LSN timeout: Timed out while waiting for WAL record at LSN C/E1418528 to arrive, last_record_lsn 6/999D9CA8 disk consistent LSN=6/999D9CA8, WalReceiver status: (update 2024-07-25 08:30:07): connecting to node 25, safekeeper candidates (id|update_time|commit_lsn): [(21|08:30:16|C/E1C129E0), (23|08:30:16|C/E1C129E0), (25|08:30:17|C/E1C129E0)]
CONTEXT: while scanning block 214338 of relation "public.pgbench_accounts"
pgbench: detail: Query was: vacuum analyze pgbench_accounts
```
Solution
--------
Its better to be slow than to fail the queries.
If the app has a deadline, it can use `statement_timeout`.
In the long term, we want to eliminate wait_lsn timeout.
In the short term (this PR), we bump the wait_lsn timeout to
a larger value to reduce the frequency at which these wait_lsn timeouts
occur.
We will observe SLOs and specifically
`pageserver_wait_lsn_seconds_bucket`
before we eliminate the timeout completely.
## Problem
Vectored get is already enabled in all prod regions without validation.
The pageserver defaults
are out of sync however.
## Summary of changes
Update the pageserver defaults to match the prod config. Also means that
when running tests locally,
people don't have to use the env vars to get the prod config.
## Problem
Deployed pageserver configurations are all like this:
```
disk_usage_based_eviction:
max_usage_pct: 85
min_avail_bytes: 0
period: "10s"
eviction_order:
type: "RelativeAccessed"
args:
highest_layer_count_loses_first: true
```
But we're maintaining this optional absolute order eviction, with test
cases etc.
## Summary of changes
- Remove absolute order eviction. Make the default eviction policy the
same as how we really deploy pageservers.
We're removing the usage of this long-meaningless config field in
https://github.com/neondatabase/aws/pull/1599
Once that PR has been deployed to staging and prod, we can merge this
PR.
`trace_read_requests` is a per `Tenant`-object option.
But the `handle_pagerequests` loop doesn't know which
`Tenant` object (i.e., which shard) the request is for.
The remaining use of the `Tenant` object is to check `tenant.cancel`.
That check is incorrect [if the pageserver hosts multiple
shards](https://github.com/neondatabase/neon/issues/7427#issuecomment-2220577518).
I'll fix that in a future PR where I completely eliminate the holding
of `Tenant/Timeline` objects across requests.
See [my code RFC](https://github.com/neondatabase/neon/pull/8286) for
the
high level idea.
Note that we can always bring the tracing functionality if we need it.
But since it's actually about logging the `page_service` wire bytes,
it should be a `page_service`-level config option, not per-Tenant.
And for enabling tracing on a single connection, we can implement
a `set pageserver_trace_connection;` option.
Removes the `ImageCompressionAlgorithm::DisabledNoDecompress` variant.
We now assume any blob with the specific bits set is actually a
compressed blob.
The `ImageCompressionAlgorithm::Disabled` variant still remains and is
the new default.
Reverts large parts of #8238 , as originally intended in that PR.
Part of #5431
part of https://github.com/neondatabase/neon/issues/7418
# Motivation
(reproducing #7418)
When we do an `InMemoryLayer::write_to_disk`, there is a tremendous
amount of random read I/O, as deltas from the ephemeral file (written in
LSN order) are written out to the delta layer in key order.
In benchmarks (https://github.com/neondatabase/neon/pull/7409) we can
see that this delta layer writing phase is substantially more expensive
than the initial ingest of data, and that within the delta layer write a
significant amount of the CPU time is spent traversing the page cache.
# High-Level Changes
Add a new mode for L0 flush that works as follows:
* Read the full ephemeral file into memory -- layers are much smaller
than total memory, so this is afforable
* Do all the random reads directly from this in memory buffer instead of
using blob IO/page cache/disk reads.
* Add a semaphore to limit how many timelines may concurrently do this
(limit peak memory).
* Make the semaphore configurable via PS config.
# Implementation Details
The new `BlobReaderRef::Slice` is a temporary hack until we can ditch
`blob_io` for `InMemoryLayer` => Plan for this is laid out in
https://github.com/neondatabase/neon/issues/8183
# Correctness
The correctness of this change is quite obvious to me: we do what we did
before (`blob_io`) but read from memory instead of going to disk.
The highest bug potential is in doing owned-buffers IO. I refactored the
API a bit in preliminary PR
https://github.com/neondatabase/neon/pull/8186 to make it less
error-prone, but still, careful review is requested.
# Performance
I manually measured single-client ingest performance from `pgbench -i
...`.
Full report:
https://neondatabase.notion.site/2024-06-28-benchmarking-l0-flush-performance-e98cff3807f94cb38f2054d8c818fe84?pvs=4
tl;dr:
* no speed improvements during ingest, but
* significantly lower pressure on PS PageCache (eviction rate drops to
1/3)
* (that's why I'm working on this)
* noticable but modestly lower CPU time
This is good enough for merging this PR because the changes require
opt-in.
We'll do more testing in staging & pre-prod.
# Stability / Monitoring
**memory consumption**: there's no _hard_ limit on max `InMemoryLayer`
size (aka "checkpoint distance") , hence there's no hard limit on the
memory allocation we do for flushing. In practice, we a) [log a
warning](23827c6b0d/pageserver/src/tenant/timeline.rs (L5741-L5743))
when we flush oversized layers, so we'd know which tenant is to blame
and b) if we were to put a hard limit in place, we would have to decide
what to do if there is an InMemoryLayer that exceeds the limit.
It seems like a better option to guarantee a max size for frozen layer,
dependent on `checkpoint_distance`. Then limit concurrency based on
that.
**metrics**: we do have the
[flush_time_histo](23827c6b0d/pageserver/src/tenant/timeline.rs (L3725-L3726)),
but that includes the wait time for the semaphore. We could add a
separate metric for the time spent after acquiring the semaphore, so one
can infer the wait time. Seems unnecessary at this point, though.
Add support for reading and writing zstd-compressed blobs for use in
image layer generation, but maybe one day useful also for delta layers.
The reading of them is unconditional while the writing is controlled by
the `image_compression` config variable allowing for experiments.
For the on-disk format, we re-use some of the bitpatterns we currently
keep reserved for blobs larger than 256 MiB. This assumes that we have
never ever written any such large blobs to image layers.
After the preparation in #7852, we now are unable to read blobs with a
size larger than 256 MiB (or write them).
A non-goal of this PR is to come up with good heuristics of when to
compress a bitpattern. This is left for future work.
Parts of the PR were inspired by #7091.
cc #7879
Part of #5431
Before this PR, `RemoteStorageConfig::from_toml` would support
deserializing an
empty `{}` TOML inline table to a `None`, otherwise try `Some()`.
We can instead let
* in proxy: let clap derive handle the Option
* in PS & SK: assume that if the field is specified, it must be a valid
RemtoeStorageConfig
(This PR started with a much simpler goal of factoring out the
`deserialize_item` function because I need that in another PR).
## Problem
In https://github.com/neondatabase/neon/pull/5299, the new config-v1
tenant config file was added to hold the LocationConf type. We left the
old config file in place for forward compat, and because running without
generations (therefore without LocationConf) as still useful before the
storage controller was ready for prime-time.
Closes: https://github.com/neondatabase/neon/issues/5388
## Summary of changes
- Remove code for reading and writing the legacy config file
- Remove Generation::Broken: it was unused.
- Treat missing config file on disk as an error loading a tenant, rather
than defaulting it. We can now remove LocationConf::default, and thereby
guarantee that we never construct a tenant with a None generation.
- Update some comments + add some assertions to clarify that
Generation::None is only used in layer metadata, not in the state of a
running tenant.
- Update docker compose test to create tenants with a generation
#8082 removed the legacy deletion path, but retained code for completing
deletions that were started before a pageserver restart. This PR cleans
up that remaining code, and removes all the pageserver code that dealt
with tenant deletion markers and resuming tenant deletions.
The release at https://github.com/neondatabase/neon/pull/8138 contains
https://github.com/neondatabase/neon/pull/8082, so we can now merge this
to `main`
Adds a `Deserialize` impl to `RemoteStorageConfig`. We thus achieve the
same as #7743 but with less repetitive code, by deriving `Deserialize`
impls on `S3Config`, `AzureConfig`, and `RemoteStorageConfig`. The
disadvantage is less useful error messages.
The git history of this PR contains a state where we go via an
intermediate representation, leveraging the `serde_json` crate,
without it ever being actual json though.
Also, the PR adds deserialization tests.
Alternative to #7743 .
## Problem
These APIs have be unused for some time. They were superseded by
/location_conf: the equivalent of ignoring a tenant is now to put it in
secondary mode.
## Summary of changes
- Remove APIs
- Remove tests & helpers that used them
- Remove error variants that are no longer needed.
refs https://github.com/neondatabase/neon/issues/7753
This PR is step (1) of removing sync walredo from Pageserver.
Changes:
* Remove the sync impl
* If sync is configured, warn! and use async instead
* Remove the metric that exposes `kind`
* Remove the tenant status API that exposes `kind`
Future Work
-----------
After we've released this change to prod and are sure we won't
roll back, we will
1. update the prod Ansible to remove the config flag from the prod
pageserver.toml.
2. remove the remaining `kind` code in pageserver
These two changes need no release inbetween.
See https://github.com/neondatabase/neon/issues/7753 for details.
This is the first step towards representing all of Pageserver
configuration as clean `serde::Serialize`able Rust structs in
`pageserver_api`.
The `neon_local` code will then use those structs instead of the crude
`toml_edit` / string concatenation that it does today.
refs https://github.com/neondatabase/neon/issues/7555
---------
Co-authored-by: Alex Chi Z <iskyzh@gmail.com>
## Problem
We are currently supporting two read paths. No bueno.
## Summary of changes
High level: use vectored read path to serve get page requests - gated by
`get_impl` config
Low level:
1. Add ps config, `get_impl` to specify which read path to use when
serving get page requests
2. Fix base cached image handling for the vectored read path. This was
subtly broken: previously we
would not mark keys that went past their cached lsn as complete. This is
a self standing change which
could be its own PR, but I've included it here because writing separate
tests for it is tricky.
3. Fork get page to use either the legacy or vectored implementation
4. Validate the use of vectored read path when serving get page requests
against the legacy implementation.
Controlled by `validate_vectored_get` ps config.
5. Use the vectored read path to serve get page requests in tests (with
validation).
## Note
Since the vectored read path does not go through the page cache to read
buffers, this change also amounts to a removal of the buffer page cache. Materialized page cache
is still used.
Currently we move data to the intended storage class via lifecycle
rules, but those are a daily batch job so data first spends up to a day
in standard storage.
Therefore, make it possible to specify the storage class used for
uploads to S3 so that the data doesn't have to be migrated
automatically.
The advantage of this is that it gives cleaner billing reports.
Part of https://github.com/neondatabase/cloud/issues/11348
Before this PR, the `nix::poll::poll` call would stall the executor.
This PR refactors the `walredo::process` module to allow for different
implementations, and adds a new `async` implementation which uses
`tokio::process::ChildStd{in,out}` for IPC.
The `sync` variant remains the default for now; we'll do more testing in
staging and gradual rollout to prod using the config variable.
Performance
-----------
I updated `bench_walredo.rs`, demonstrating that a single `async`-based
walredo manager used by N=1...128 tokio tasks has lower latency and
higher throughput.
I further did manual less-micro-benchmarking in the real pageserver
binary.
Methodology & results are published here:
https://neondatabase.notion.site/2024-04-08-async-walredo-benchmarking-8c0ed3cc8d364a44937c4cb50b6d7019?pvs=4
tl;dr:
- use pagebench against a pageserver patched to answer getpage request &
small-enough working set to fit into PS PageCache / kernel page cache.
- compare knee in the latency/throughput curve
- N tenants, each 1 pagebench clients
- sync better throughput at N < 30, async better at higher N
- async generally noticable but not much worse p99.X tail latencies
- eyeballing CPU efficiency in htop, `async` seems significantly more
CPU efficient at ca N=[0.5*ncpus, 1.5*ncpus], worse than `sync` outside
of that band
Mental Model For Walredo & Scheduler Interactions
-------------------------------------------------
Walredo is CPU-/DRAM-only work.
This means that as soon as the Pageserver writes to the pipe, the
walredo process becomes runnable.
To the Linux kernel scheduler, the `$ncpus` executor threads and the
walredo process thread are just `struct task_struct`, and it will divide
CPU time fairly among them.
In `sync` mode, there are always `$ncpus` runnable `struct task_struct`
because the executor thread blocks while `walredo` runs, and the
executor thread becomes runnable when the `walredo` process is done
handling the request.
In `async` mode, the executor threads remain runnable unless there are
no more runnable tokio tasks, which is unlikely in a production
pageserver.
The above means that in `sync` mode, there is an implicit concurrency
limit on concurrent walredo requests (`$num_runtimes *
$num_executor_threads_per_runtime`).
And executor threads do not compete in the Linux kernel scheduler for
CPU time, due to the blocked-runnable-ping-pong.
In `async` mode, there is no concurrency limit, and the walredo tasks
compete with the executor threads for CPU time in the kernel scheduler.
If we're not CPU-bound, `async` has a pipelining and hence throughput
advantage over `sync` because one executor thread can continue
processing requests while a walredo request is in flight.
If we're CPU-bound, under a fair CPU scheduler, the *fixed* number of
executor threads has to share CPU time with the aggregate of walredo
processes.
It's trivial to reason about this in `sync` mode due to the
blocked-runnable-ping-pong.
In `async` mode, at 100% CPU, the system arrives at some (potentially
sub-optiomal) equilibrium where the executor threads get just enough CPU
time to fill up the remaining CPU time with runnable walredo process.
Why `async` mode Doesn't Limit Walredo Concurrency
--------------------------------------------------
To control that equilibrium in `async` mode, one may add a tokio
semaphore to limit the number of in-flight walredo requests.
However, the placement of such a semaphore is non-trivial because it
means that tasks queuing up behind it hold on to their request-scoped
allocations.
In the case of walredo, that might be the entire reconstruct data.
We don't limit the number of total inflight Timeline::get (we only
throttle admission).
So, that queue might lead to an OOM.
The alternative is to acquire the semaphore permit *before* collecting
reconstruct data.
However, what if we need to on-demand download?
A combination of semaphores might help: one for reconstruct data, one
for walredo.
The reconstruct data semaphore permit is dropped after acquiring the
walredo semaphore permit.
This scheme effectively enables both a limit on in-flight reconstruct
data and walredo concurrency.
However, sizing the amount of permits for the semaphores is tricky:
- Reconstruct data retrieval is a mix of disk IO and CPU work.
- If we need to do on-demand downloads, it's network IO + disk IO + CPU
work.
- At this time, we have no good data on how the wall clock time is
distributed.
It turns out that, in my benchmarking, the system worked fine without a
semaphore. So, we're shipping async walredo without one for now.
Future Work
-----------
We will do more testing of `async` mode and gradual rollout to prod
using the config flag.
Once that is done, we'll remove `sync` mode to avoid the temporary code
duplication introduced by this PR.
The flag will be removed.
The `wait()` for the child process to exit is still synchronous; the
comment [here](
655d3b6468/pageserver/src/walredo.rs (L294-L306))
is still a valid argument in favor of that.
The `sync` mode had another implicit advantage: from tokio's
perspective, the calling task was using up coop budget.
But with `async` mode, that's no longer the case -- to tokio, the writes
to the child process pipe look like IO.
We could/should inform tokio about the CPU time budget consumed by the
task to achieve fairness similar to `sync`.
However, the [runtime function for this is
`tokio_unstable`](`https://docs.rs/tokio/latest/tokio/task/fn.consume_budget.html).
Refs
----
refs #6628
refs https://github.com/neondatabase/neon/issues/2975
## 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
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
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)
```
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
Currently we manually register nodes with the storage controller, and
use a script during deploy to register with the cloud control plane.
Rather than extend that script further, nodes should just register on
startup.
## Summary of changes
- Extend the re-attach request to include an optional
NodeRegisterRequest
- If the `register` field is set, handle it like a normal node
registration before executing the normal re-attach work.
- Update tests/neon_local that used to rely on doing an explicit
register step that could be enabled/disabled.
---------
Co-authored-by: Christian Schwarz <christian@neon.tech>
All of production is using it now as of
https://github.com/neondatabase/aws/pull/1121
The change in `flaky_tests.py` resets the flakiness detection logic.
The alternative would have been to repeat the choice of io engine in
each test name, which would junk up the various test reports too much.
---------
Co-authored-by: Alexander Bayandin <alexander@neon.tech>
