Compare commits

..

140 Commits

Author SHA1 Message Date
Folke Behrens
357795e0c5 VPC flow logs IaC 2025-04-06 13:14:40 +02:00
Folke Behrens
f105ddb778 aws lambda function for periodic collection of pod infomation 2025-04-06 13:14:40 +02:00
Alexander Bayandin
8e1b5a9727 Fix Postgres build on macOS (#11442)
## Problem
Postgres build fails with the following error on macOS:

```
/Users/bayandin/work/neon//vendor/postgres-v14/src/port/snprintf.c:424:27: error: 'strchrnul' is only available on macOS 15.4 or newer [-Werror,-Wunguarded-availability-new]
  424 |                         const char *next_pct = strchrnul(format + 1, '%');
      |                                                ^~~~~~~~~
/Users/bayandin/work/neon//vendor/postgres-v14/src/port/snprintf.c:376:14: note: 'strchrnul' has been marked as being introduced in macOS 15.4 here, but the deployment target is macOS 15.0.0
  376 | extern char *strchrnul(const char *s, int c);
      |              ^
/Users/bayandin/work/neon//vendor/postgres-v14/src/port/snprintf.c:424:27: note: enclose 'strchrnul' in a __builtin_available check to silence this warning
  424 |                         const char *next_pct = strchrnul(format + 1, '%');
      |                                                ^~~~~~~~~
  425 |
  426 |                         /* Dump literal data we just scanned over */
  427 |                         dostr(format, next_pct - format, target);
  428 |                         if (target->failed)
  429 |                                 break;
  430 |
  431 |                         if (*next_pct == '\0')
  432 |                                 break;
  433 |                         format = next_pct;
      |
1 error generated.
```

## Summary of changes
- Update Postgres fork to include changes from
6da2ba1d8a

Corresponding Postgres PRs:
- https://github.com/neondatabase/postgres/pull/608
- https://github.com/neondatabase/postgres/pull/609
- https://github.com/neondatabase/postgres/pull/610
- https://github.com/neondatabase/postgres/pull/611
2025-04-04 14:09:15 +00:00
Vlad Lazar
1ef4258f29 pageserver: add tenant level performance tracing sampling ratio (#11433)
## Problem

https://github.com/neondatabase/neon/pull/11140 introduces performance
tracing with OTEL
and a pageserver config which configures the sampling ratio of get page
requests.

Enabling a non-zero sampling ratio on a per region basis is too
aggressive and comes with perf
impact that isn't very well understood yet.

## Summary of changes

Add a `sampling_ratio` tenant level config which overrides the
pageserver level config.
Note that we do not cache the config and load it on every get page
request such that changes propagate
timely.

Note that I've had to remove the `SHARD_SELECTION` span to get this to
work. The tracing library doesn't
expose a neat way to drop a span if one realises it's not needed at
runtime.

Closes https://github.com/neondatabase/neon/issues/11392
2025-04-04 13:41:28 +00:00
Vlad Lazar
65e2aae6e4 pageserver/secondary: deregister IO metrics (#11283)
## Problem

IO metrics for secondary locations do not get deregistered when the
timeline is removed.

## Summary of changes

Stash the request context to be used for downloads in
`SecondaryTimelineDetail`. These objects match the lifetime of the
secondary timeline location pretty well.

When the timeline is removed, deregister the metrics too.

Closes https://github.com/neondatabase/neon/issues/11156
2025-04-04 10:52:59 +00:00
a-masterov
edc874e1b3 Use the same test image version as the computer one (#11448)
## Problem
Changes in compute can cause errors in tests if another version of
`neon-test-extensions` image is used.
## Summary of changes
Use the same version of `neon-test-extensions` image as `compute` one
for docker-compose based extension tests.
2025-04-04 10:13:00 +00:00
Dmitrii Kovalkov
181af302b5 storcon + safekeeper + scrubber: propagate root CA certs everywhere (#11418)
## Problem
There are some places in the code where we create `reqwest::Client`
without providing SSL CA certs from `ssl_ca_file`. These will break
after we enable TLS everywhere.
- Part of https://github.com/neondatabase/cloud/issues/22686

## Summary of changes
- Support `ssl_ca_file` in storage scrubber.
- Add `use_https_safekeeper_api` option to safekeeper to use https for
peer requests.
- Propagate SSL CA certs to storage_controller/client, storcon's
ComputeHook, PeerClient and maybe_forward.
2025-04-04 06:30:48 +00:00
Tristan Partin
497116b76d Download extension if it does not exist on the filesystem (#11315)
Previously we attempted to download all extensions in CREATE EXTENSION
statements. Extensions like pg_stat_statements and neon are not remote
extensions, but still we were requesting them when
skip_pg_catalog_updates was set to false.

Fixes: https://github.com/neondatabase/neon/issues/11127

Signed-off-by: Tristan Partin <tristan@neon.tech>
2025-04-04 01:06:22 +00:00
Arpad Müller
a917952b30 Add test_storcon_create_delete_sk_down and make it work (#11400)
Adds a test `test_storcon_create_delete_sk_down` which tests the
reconciler and pending op persistence if faced with a temporary
safekeeper downtime during timeline creation or deletion. This is in
contrast to `test_explicit_timeline_creation_storcon`, which tests the
happy path.

We also do some fixes:

* timeline and tenant deletion http requests didn't expect a body, but
`()` sent one.
* we got the tenant deletion http request's return type wrong: it's
supposed to be a hash map
* we add some logging to improve observability
* We fix `list_pending_ops` which had broken code meant to make it
possible to restrict oneself to a single pageserver. But diesel doesn't
support that sadly, or at least I couldn't figure out a way to make it
work. We don't need that functionality, so remove it.
* We add an info span to the heartbeater futures with the node id, so
that there is no context-free msgs like "Backoff: waiting 1.1 seconds
before processing with the task" in the storcon logs. we could also add
the full base url of the node but don't do it as most other log lines
contain that information already, and if we do duplication it should at
least not be verbose. One can always find out the base url from the node
id.

Successor of #11261
Part of #9011
2025-04-04 00:17:40 +00:00
Tristan Partin
e581b670f4 Improve nightly physical replication benchmark (#11389)
Log the created project and endpoint IDs and improve typing in the
source code to improve readability.

Signed-off-by: Tristan Partin <tristan@neon.tech>
2025-04-03 23:00:58 +00:00
Alexander Bayandin
8ed79ed773 build(deps): bump h2 to 4.2.0 (#11437)
## Problem

We switched `h2` from 4.1.0 to a git commit to fix stubgen (in
https://github.com/neondatabase/neon/pull/10491). `h2` 4.2.0 was
released soon after that, so we can switch back to a pinned version.

Expected no changes, as 4.2.0 is the right next commit after the commit
we currently use:
dacd614fed%5E

## Summary of changes
- Bump `h2` to 4.2.0
2025-04-03 21:42:34 +00:00
Alex Chi Z.
381f42519e fix(pageserver): skip gc-compaction over sparse keyspaces (#11404)
## Problem

Part of https://github.com/neondatabase/neon/issues/11318

It's not 100% safe for now to run gc-compaction over the sparse
keyspace. It might cause deleted file to re-appear if a specific
sequence of operations are done as in the issue, which in reality
doesn't happen due to how we split delta/image layers based on the key
range.

A long-term fix would be either having a separate gc-compaction code
path for metadata keys (as how we have a different code path for
metadata image layer generation), or let the compaction process aware of
the information of "there's an image layer that doesn't contain a key"
so that we can skip the keys.

## Summary of changes

* gc-compaction auto trigger only triggers compaction over the normal
data range.
* do not hold gc_block_guard across the full compaction job, only hold
it during each subcompaction.

---------

Signed-off-by: Alex Chi Z <chi@neon.tech>
2025-04-03 19:40:44 +00:00
Arpad Müller
375df517a0 storcon: return 503 instead of 500 if there is no new leader yet (#11417)
The leadership transfer protocol between storage controller instances is
as follows, listing the steps for the new pod:

The new pod does these things:

1. new pod comes online. looks in database if there is a leader. if
there is, it asks that leader to step down.
2. the new pod does some operations to come online. they should be
fairly short timed, but it's not zero.
3. the new pod updates the leader entry in the database.

The old pod, once it gets the step down request, changes its internal
state to stepped down. It treats all incoming requests specially now:
instead of processing, it wants to forward them to the new pod. The
forwarding however only works if the new pod is online already, so
before forwarding it reads from the db for a leader (also to get the
address to forward to in the first place).

If the new pod is not online yet, i.e. during step 2 above, the old pod
might legitimately land in the branch which this patch is editing: the
leader in the database is a stepped down instance.

Before, we've returned a `ApiError::InternalServerError`, but that would
print the full backtrace plus an error log. With this patch, we cut down
on the noise, as it's an expected situation to have a short storcon
downtime while we are cutting over to the new instance. A
`ResourceUnavailable` error is not just more fitting, it also doesn't
print a backtrace once encountered, and only prints on the INFO log
level (see `api_error_handler` function).

Fixes #11320
cc #8954
2025-04-03 18:43:16 +00:00
Vlad Lazar
9db63fea7a pageserver: optionally export perf traces in OTEL format (#11140)
Based on https://github.com/neondatabase/neon/pull/11139

## Problem

We want to export performance traces from the pageserver in OTEL format.
End goal is to see them in Grafana.

## Summary of changes

https://github.com/neondatabase/neon/pull/11139 introduces the
infrastructure required to run the otel collector alongside the
pageserver.

### Design

Requirements:
1. We'd like to avoid implementing our own performance tracing stack if
possible and use the `tracing` crate if possible.
2. Ideally, we'd like zero overhead of a sampling rate of zero and be a
be able to change the tracing config for a tenant on the fly.
3. We should leave the current span hierarchy intact. This includes
adding perf traces without modifying existing tracing.

To satisfy (3) (and (2) in part) a separate span hierarchy is used.
`RequestContext` gains an optional `perf_span` member
that's only set when the request was chosen by sampling. All perf span
related methods added to `RequestContext` are no-ops for requests that
are not sampled.

This on its own is not enough for (3), so performance spans use a
separate tracing subscriber. The `tracing` crate doesn't have great
support for this, so there's a fair amount of boilerplate to override
the subscriber at all points of the perf span lifecycle.

### Perf Impact

[Periodic
pagebench](https://neonprod.grafana.net/d/ddqtbfykfqfi8d/e904990?orgId=1&from=2025-02-08T14:15:59.362Z&to=2025-03-10T14:15:59.362Z&timezone=utc)
shows no statistically significant regression with a sample ratio of 0.
There's an annotation on the dashboard on 2025-03-06.

### Overview of changes:
1. Clean up the `RequestContext` API a bit. Namely, get rid of the
`RequestContext::extend` API and use the builder instead.
2. Add pageserver level configs for tracing: sampling ratio, otel
endpoint, etc.
3. Introduce some perf span tracking utilities and expose them via
`RequestContext`. We add a `tracing::Span` wrapper to be used for perf
spans and a `tracing::Instrumented` equivalent for it. See doc comments
for reason.
4. Set up OTEL tracing infra according to configuration. A separate
runtime is used for the collector.
5. Add perf traces to the read path.

## Refs

- epic https://github.com/neondatabase/neon/issues/9873

---------

Co-authored-by: Christian Schwarz <christian@neon.tech>
2025-04-03 17:56:51 +00:00
Alex Chi Z.
bfc767d60d fix(test): wait for shard split complete for test_lsn_lease_storcon (#11436)
## Problem

close https://github.com/neondatabase/neon/issues/11397
ref https://github.com/neondatabase/cloud/issues/23667

## Summary of changes

We need to wait until the shard split is complete, otherwise it will
print warning like waiting for shard split exclusive lock for 30s.

Signed-off-by: Alex Chi Z <chi@neon.tech>
2025-04-03 17:49:45 +00:00
Alex Chi Z.
109c54a300 fix(pageserver): avoid gc-compaction triggering circuit breaker (#11403)
## Problem

There are some cases where traditional gc might collect some layer files
causing gc-compaction cannot read the full history of the key. This
needs to be resolved in the long-term by improving the compaction
process. For now, let's simply avoid such errors triggering the circuit
breaker.

## Summary of changes

* Move the place where we trigger the circuit breaker. We only trigger
it during compactions other than L0 compactions. We added the trigger a
year ago due to file cleanup concerns in image layer compaction.
* For gc-compaction, only return errors to the upper
compaction_iteration if it's a shutdown error. Otherwise, just log it
and skip the compaction for a key range.

Signed-off-by: Alex Chi Z <chi@neon.tech>
Co-authored-by: Christian Schwarz <christian@neon.tech>
2025-04-03 17:18:37 +00:00
Vlad Lazar
74920d8cd8 storcon: notify compute if correct observed state was refreshed (#11342)
## Problem

Previously, if the observed state was refreshed and matching the intent,
we wouldn't send
a compute notification. This is unsafe. There's no guarantee that the
location landed on the
pageserver _and_ a compute notification for it was delivered.

See
https://github.com/neondatabase/neon/issues/11291#issuecomment-2743205411
for one such example.

## Summary of changes

Add a reproducer and notify the compute if the correct observed state
required a refresh.

Closes https://github.com/neondatabase/neon/issues/11291
2025-04-03 16:35:55 +00:00
Alex Chi Z.
131b32ef48 fix(pageserver): clean up aux files before detaching (#11299)
## Problem

Related to https://github.com/neondatabase/cloud/issues/26091 and
https://github.com/neondatabase/cloud/issues/25840

Close https://github.com/neondatabase/neon/issues/11297

Discussion on Slack:
https://neondb.slack.com/archives/C033RQ5SPDH/p1742320666313969

## Summary of changes

* When detaching, scan all aux files within
`sparse_non_inherited_keyspace` in the ancestor timeline and create an
image layer exactly at the ancestor LSN. All scanned keys will map to an
empty value, which is a delete tombstone.
- Note that end_lsn for rewritten delta layers = ancestor_lsn + 1, so
the image layer will have image_end_lsn=end_lsn. With the current
`select_layer` logic, the read path will always first read the image
layer.
* Add a test case.

---------

Signed-off-by: Alex Chi Z <chi@neon.tech>
Co-authored-by: Christian Schwarz <christian@neon.tech>
2025-04-03 15:55:22 +00:00
Suhas Thalanki
581bb5d7d5 removed pg_anon setup from compute dockerfile (#10960)
## Problem

Removing the `anon` v1 extension in postgres as described in
https://github.com/neondatabase/cloud/issues/22663. This extension is
not built for postgres v17 and is out of date when compared to the
upstream variant which is v2 (we have v1.4).

## Summary of changes

Removed the `anon` v1 extension from the compute docker image

Related to https://github.com/neondatabase/cloud/issues/22663
2025-04-03 15:26:35 +00:00
JC Grünhage
3c78133477 feat(ci): add 'released' tag to container images from release runs (#11425)
## Problem
We had a problem with https://github.com/neondatabase/neon/pull/11413
having e2e tests failing, because an e2e test
(8d271bed47)
depended on an unreleased pageserver fix
(0ee5bfa2fc).
This came up because neon release CI runs against the most recent
releases of the other components, but cloud e2e tests run against
latest, which is tagged from main.

## Summary of changes
Add an additional `released` tag for released versions.

## Alternative to consider
We could (and maybe should) instead switch to `latest` being used for
released versions and `main` being used where we use `latest` right now.
That'd also mean we don't have to adjust the CI in the cloud repo.
2025-04-03 14:57:44 +00:00
Suhas Thalanki
46e046e779 Exporting file_cache_used to calculate LFC utilization (#11384)
## Problem

Exporting `file_cache_used` which specifies the number of used chunks in
the LFC. This helps calculate LFC utilization as: `file_cache_used_pages
/ (file_cache_used * file_cache_chunk_size_pages)`

## Summary of changes

Exporting `file_cache_used`.

Related Issue: https://github.com/neondatabase/cloud/issues/26688
2025-04-03 14:54:45 +00:00
Arpad Müller
d8cee52637 Update rust to 1.86.0 (#11431)
We keep the practice of keeping the compiler up to date, pointing to the
latest release. This is done by many other projects in the Rust
ecosystem as well.

[Announcement blog
post](https://blog.rust-lang.org/2025/04/03/Rust-1.86.0.html).

Prior update was in #10914.
2025-04-03 14:53:28 +00:00
Dmitrii Kovalkov
2e11d129d0 tests: suppress mgm api timeout error in sotrcon (#11428)
## Problem
Since
0f367cb665
the timeout in `with_client_retries` is implemented via `tokio::timeout`
instead of `reqwest::ClientBuilder::timeout` (because we reuse the
client). It changed the error representation if the timeout is exceeded.
Such errors were suppressed in `allowed_errors.py`, but old regexps do
not match the new error.
Discussion:
https://neondb.slack.com/archives/C033RQ5SPDH/p1743533184736319

## Summary of changes
- Add new `Timeout` error to `allowed_errors.py`
2025-04-03 14:18:50 +00:00
Luís Tavares
43a7423f72 feat: bump pg_session_jwt extension to 0.3.0 (#11399)
## Problem

Bumps https://github.com/neondatabase/pg_session_jwt to the latest
release
[v0.3.0](https://github.com/neondatabase/pg_session_jwt/releases/tag/v0.3.0)
that introduces PostgREST fallback mechanisms.

## Summary of changes

Updates the extension download tar and the extension version in the
proxy constant.

## Subscribers
@mrl5
2025-04-03 13:01:18 +00:00
Arpad Müller
374736a4de Print remote_addr span for Failed to serve HTTP connection error (#11423)
I've encountered this error in #11422. Ideally we'd have the URL as well
to associate it with a tenant, but at this level we only have the remote
addr I guess. Better than nothing.
2025-04-03 11:58:12 +00:00
Alexander Bayandin
5e507776bc Compute: update plv8 patch (#11426)
## Problem

https://github.com/neondatabase/cloud/issues/26866

## Summary of changes
- Update plv8 patch

Co-authored-by: Alexey Kondratov <kondratov.aleksey@gmail.com>
2025-04-03 11:29:53 +00:00
Alexander Lakhin
4e8e0951be Increase timeout for test_pageserver_gc_compaction_smoke (#11410)
## Problem
The test_pageserver_gc_compaction_smoke fails rather often due to a
timeout on slow machines.
See https://github.com/neondatabase/neon/issues/11355.

## Summary of changes
Increase the timeout for the test.
2025-04-03 11:23:30 +00:00
JC Grünhage
64a8d0c2e6 impr(ci): retry container image pushing and send slack messages for failures (#11416)
## Problem
We've seen quite a few CI failures related to pushes to docker hub
failing with weird error messages that indicate maybe docker hub is just
not reliable.

## Summary of changes
Retry container image pushing up to 10 times, and send a slack message
if we had to retry, regardless of the job succeeding or not.
2025-04-03 08:59:42 +00:00
Tristan Partin
7602e6ffc0 Skip compute_ctl authorization checks in testing builds (#11186)
We will require authorization in production. We need to skip in testing
builds for now because regression tests would fail. See
https://github.com/neondatabase/neon/issues/11316 for more information.

Signed-off-by: Tristan Partin <tristan@neon.tech>

Signed-off-by: Tristan Partin <tristan@neon.tech>
2025-04-03 00:00:28 +00:00
Erik Grinaker
17193d6a33 test_runner: fix pagebench tenant configs (#11420)
## Problem

Pagebench creates a bunch of tenants by first creating a template tenant
and copying its remote storage, then attaching the copies to the
Pageserver.

These tenants had custom configurations to disable GC and compaction.
However, these configs were only picked up by the Pageserver on attach,
and not registered with the storage controller. This caused the storage
controller to replace the tenant configs with the default tenant config,
re-enabling GC and compaction which interferes with benchmark
performance.

Resolves #11381.

## Summary of changes

Register the copied tenants with the storage controller, instead of
directly attaching them to the Pageserver.
2025-04-02 20:11:39 +00:00
Erik Grinaker
03ae57236f docs: add compaction notes (#11415)
Lifted from
https://www.notion.so/neondatabase/Rough-Notes-on-Compaction-1baf189e004780859e65ef63b85cfa81?pvs=4.
2025-04-02 19:55:08 +00:00
Arpad Müller
e3d27b2f68 Start safekeeper node IDs with 0 and forbid 0 from registering (#11419)
Right now we start safekeeper node ids at 0. However, other code treats
0 as invalid (see #11407). We decided on latter. Therefore, make the
register python tests register safekeepers starting at node id 1 instead
of 0, and forbid safekeepers with id 0 from registering.

Context:
https://github.com/neondatabase/neon/pull/11407#discussion_r2024852328
2025-04-02 18:36:50 +00:00
Alex Chi Z.
dd1299f337 feat(storcon): passthrough mark invisible and add tests (#11401)
## Problem

close https://github.com/neondatabase/neon/issues/11279

## Summary of changes

* Allow passthrough of other methods in tenant timeline shard0
passthrough of storcon.
* Passthrough mark invisible API in storcon.

---------

Signed-off-by: Alex Chi Z <chi@neon.tech>
2025-04-02 17:11:49 +00:00
John Spray
cb19e4e05d pageserver: remove legacy TimelineInfo::latest_gc_cutoff field (2/2) (#11136)
## Problem

This field was retained for backward compat only in #10707.

Once https://github.com/neondatabase/cloud/pull/25233 is released,
nothing will be reading this field.

Related: https://github.com/neondatabase/cloud/issues/24250

## Summary of changes

- Remove TimelineInfo::latest_gc_cutoff_lsn
2025-04-02 15:21:58 +00:00
Erik Grinaker
9df230c837 storcon: improve autosplit defaults (#11332)
## Problem

In #11122, we changed the autosplit behavior to allow repeated and
initial splits. The defaults were set such that they retain the current
production settings (8 shards at 64 GB). However, these defaults don't
really make sense by themselves.

Once we deploy new settings to production, we should change the defaults
to something more reasonable.

## Summary of changes

Changes the following default settings:

* `max_split_shards`: 8 → 16
* `initial_split_threshold`: 64 GB → disabled
* `initial_split_shards`: 8 → 2
2025-04-02 15:11:52 +00:00
JC Grünhage
3c2bc5baba fix(ci): run checks on release PRs (#11375)
## Problem
Hotfix releases mean that sometimes changes in release PRs haven't been
tested and linted yet. Disabling tests and lints is therefore not
necessarily safe. In the future we will check whether tests have run on
the same git tree already to speed things up, but for now we need to
turn tests back on fully. This partially reverts:
https://github.com/neondatabase/neon/pull/11272

## Summary of changes
Run checks on `.*-rc-pr` runs.
2025-04-02 14:32:53 +00:00
Alexey Kondratov
6667810800 chore(compute_ctl): Minor code and comment fixes (#11411)
## Problem

In #11376 I mistakenly reworded one comment and also forgot to commit
one of the suggestions.

## Summary of changes

Fix it here.
2025-04-02 14:20:52 +00:00
Erik Grinaker
47f5bcf2bc pageserver: don't periodically flush layers for stale attachments (#11317)
## Problem

Tenants in attachment state `Stale` can't upload layers, and don't run
compaction, but still do periodic L0 layer flushes in the tenant
housekeeping loop. If the tenant remains stuck in stale mode, this
causes a large buildup of L0 layers, causing logging, metrics increases,
and possibly alerts.

Resolves #11245.

## Summary of changes

Don't perform periodic layer flushes in stale attachment state.
2025-04-02 12:55:15 +00:00
a-masterov
c179d098ef Increase the timeout for extensions upgrade tests (on schedule). (#11406)
## Problem
Sometimes the forced extension upgrade test fails (on schedule) due to a
timeout.
## Summary of changes
The timeout is increased to 60 mins.
2025-04-02 11:18:37 +00:00
Peter Bendel
4bc6dbdd5f use a prod-like shared_buffers size for some perf unit tests (#11373)
## Problem

In Neon DBaaS we adjust the shared_buffers to the size of the compute,
or better described we adjust the max number of connections to the
compute size and we adjust the shared_buffers size to the number of max
connections according to about the following sizes
`2 CU: 225mb; 4 CU: 450mb; 8 CU: 900mb`

[see](877e33b428/goapp/controlplane/internal/pkg/compute/computespec/pg_settings.go (L405))

## Summary of changes

We should run perf unit tests with settings that is realistic for a
paying customer and select 8 CU as the reference for those tests.
2025-04-02 10:43:05 +00:00
John Spray
7dc8370848 storcon: do graceful migrations from chaos injector (#11028)
## Problem

Followup to https://github.com/neondatabase/neon/pull/10913

Existing chaos injection just does simple cutovers to secondary
locations. Let's also exercise code for doing graceful migrations. This
should implicitly test how such migrations cope with overlapping with
service restarts.

## Summary of changes
2025-04-02 10:08:05 +00:00
Alex Chi Z.
c4fc602115 feat(pageserver): support synthetic size calculation for invisible branches (#11335)
## Problem

ref https://github.com/neondatabase/neon/issues/11279


Imagine we have a branch with 3 snapshots A, B, and C:
```
base---+---+---+---main
        \-A \-B \-C
base=100G, base-A=1G, A-B=1G, B-C=1G, C-main=1G
```
at this point, the synthetic size should be 100+1+1+1+1=104G.

after the deletion, the structure looks like:
```
base---+---+---+
       \-A \-B \-C
```
If we simply assume main never exists, the size will be calculated as
size(A) + size(B) + size(C)=300GB, which obviously is not what the user
would expect.

The correct way to do this is to assume part of main still exists, that
is to say, set C-main=1G:
```
base---+---+---+main
       \-A \-B \-C
```
And we will get the correct synthetic size of 100G+1+1+1=103G.


## Summary of changes

* Do not generate gc cutoff point for invisible branches.
* Use the same LSN as the last branchpoint for branch end.
* Remove test_api_handler for mark_invisible.

---------

Signed-off-by: Alex Chi Z <chi@neon.tech>
2025-04-01 18:50:58 +00:00
Konstantin Knizhnik
02936b82c5 Fix effective_lsn calculation for prefetch (#11219)
## Problem

See  https://neondb.slack.com/archives/C04DGM6SMTM/p1741594233757489

Consider the following scenario:

1. Backend A wants to prefetch some block B
2. Backend A checks that block B is not present in shared buffer
3. Backend A registers new prefetch request and calls
prefetch_do_request
4. prefetch_do_request calls neon_get_request_lsns
5. neon_get_request_lsns obtains LwLSN for block B
6. Backend B downloads B, updates and wallogs it (let say to Lsn1)
7. Block B is once again thrown from shared buffers, its LwLSN is set to
Lsn1
8. Backend A obtains current flush LSN, let's say that it is Lsn1
9. Backend A stores Lsn1 as effective_lsn in prefetch slot.
10. Backend A reads page B with LwLSN=Lsn1
11. Backend A finds in prefetch ring response for prefetch request for
block B with effective_lsn=Lsn1, so that it satisfies
neon_prefetch_response_usable condition
12. Backend A uses deteriorated version of the page!

## Summary of changes

Use `not_modified_since` as `effective_lsn`. 
It should not cause some degrade of performance because we store LwLSN
when it was not found in LwLSN hash, so if page is not changed till
prefetch response is arrived, then LwLSN should not be changed.

---------

Co-authored-by: Konstantin Knizhnik <knizhnik@neon.tech>
2025-04-01 15:48:02 +00:00
Arpad Müller
1fad1abb24 storcon: timeline deletion improvements and fixes (#11334)
This PR contains a bunch of smaller followups and fixes of the original
PR #11058. most of these implement suggestions from Arseny:

* remove `Queryable, Selectable` from `TimelinePersistence`: they are
not needed.
* no `Arc` around `CancellationToken`: it itself is an arc wrapper
* only schedule deletes instead of scheduling excludes and deletes
* persist and delete deletion ops
* delete rows in timelines table upon tenant and timeline deletion
* set `deleted_at` for timelines we are deleting before we start any
reconciles: this flag will help us later to recognize half-executed
deletions, or when we crashed before we could remove the timeline row
but after we removed the last pending op (handling these situations are
left for later).

Part of #9011
2025-04-01 15:16:33 +00:00
Arpad Müller
016068b966 API spec: add safekeepers field returned by storcon (#11385)
Add an optional `safekeepers` field to `TimelineInfo` which is returned
by the storcon upon timeline creation if the
`--timelines-onto-safekeepers` flag is enabled. It contains the list of
safekeepers chosen.

Other contexts where we return `TimelineInfo` do not contain the
`safekeepers` field, sadly I couldn't make this more type safe like done
in Rust via `TimelineCreateResponseStorcon`, as there is no way of
flattening or inheritance (and I don't that duplicating the entire type
for some minor type safety improvements is worth it).

The storcon side has been done in #11058.

Part of https://github.com/neondatabase/cloud/issues/16176
cc https://github.com/neondatabase/cloud/issues/16796
2025-04-01 12:39:10 +00:00
Erik Grinaker
80596feeaa pageserver: invert CompactFlags::NoYield as YieldForL0 (#11382)
## Problem

`CompactFlags::NoYield` was a bit inconvenient, since every caller
except for the background compaction loop should generally set it (e.g.
HTTP API calls, tests, etc). It was also inconsistent with
`CompactionOutcome::YieldForL0`.

## Summary of changes

Invert `CompactFlags::NoYield` as `CompactFlags::YieldForL0`. There
should be no behavioral changes.
2025-04-01 11:43:58 +00:00
Erik Grinaker
225cabd84d pageserver: update upload queue TODOs (#11377)
Update some upload queue TODOs, particularly to track
https://github.com/neondatabase/neon/issues/10283, which I won't get
around to.
2025-04-01 11:38:12 +00:00
Alexey Kondratov
557127550c feat(compute): Add compute_ctl_up metric (#11376)
## Problem

For computes running inside NeonVM, the actual compute image tag is
buried inside the NeonVM spec, and we cannot get it as part of standard
k8s container metrics (it's always an image and a tag of the NeonVM
runner container). The workaround we currently use is to extract the
running computes info from the control plane database with SQL. It has
several drawbacks: i) it's complicated, separate DB per region; ii) it's
slow; iii) it's still an indirect source of info, i.e. k8s state could
be different from what the control plane expects.

## Summary of changes

Add a new `compute_ctl_up` gauge metric with `build_tag` and `status`
labels. It will help us to both overview what are the tags/versions of
all running computes; and to break them down by current status (`empty`,
`running`, `failed`, etc.)

Later, we could introduce low cardinality (no endpoint or compute ids)
streaming aggregates for such metrics, so they will be blazingly fast
and usable for monitoring the fleet-wide state.
2025-04-01 08:51:17 +00:00
Konstantin Knizhnik
cfe3e6d4e1 Remove loop from pageserver_try_receive (#11387)
## Problem

Commit
3da70abfa5
cause noticeable performance regression (40% in update-with-prefetch in
test_bulk_update):
https://neondb.slack.com/archives/C04BLQ4LW7K/p1742633167580879

## Summary of changes

Remove loop from pageserver_try_receive to make it fetch not more than
one response. There is still loop in `pump_prefetch_state` which can
fetch as many responses as available.

Co-authored-by: Konstantin Knizhnik <knizhnik@neon.tech>
2025-03-31 19:49:32 +00:00
Alex Chi Z.
47d47000df fix(pageserver): passthrough lsn lease in storcon API (#11386)
## Problem

part of https://github.com/neondatabase/cloud/issues/23667

## Summary of changes

lsn_lease API can only be used on pageservers. This patch enables
storcon passthrough.

Signed-off-by: Alex Chi Z <chi@neon.tech>
2025-03-31 19:16:42 +00:00
Matthias van de Meent
e5b95bc9dc Neon LFC/prefetch: Improve page read handling (#11380)
Previously we had different meanings for the bitmask of vector IOps.
That has now been unified to "bit set = final result, no more
scribbling".

Furthermore, the LFC read path scribbled on pages that were already
read; that's probably not a good thing so that's been fixed too. In
passing, the read path of LFC has been updated to read only the
requested pages into the provided buffers, thus reducing the IO size of
vectorized IOs.

## Problem

## Summary of changes
2025-03-31 17:04:00 +00:00
Alex Chi Z.
0ee5bfa2fc fix(pageserver): allow sibling archived branch for detaching (#11383)
## Problem

close https://github.com/neondatabase/neon/issues/11379

## Summary of changes

Remove checks around archived branches for detach v2. I also updated the
comments `ancestor_retain_lsn`.

---------

Signed-off-by: Alex Chi Z <chi@neon.tech>
2025-03-31 16:32:55 +00:00
Fedor Dikarev
00bcafe82e chore(ci): upgrade stats action with docker images from ghcr.io (#11378)
## Problem
Current version of GitHub Workflow Stats action pull docker images from
DockerHub, that could be an issue with the new pull limits on DockerHub
side.

## Summary of changes
Switch to version `v0.2.2`, with docker images hosted on `ghcr.io`
2025-03-31 14:21:07 +00:00
Conrad Ludgate
ed117af73e chore(proxy/tokio-postgres): remove phf from sqlstate and switch to tracing (#11249)
In sqlstate, we have a manual `phf` construction, which is not
explicitly guaranteed to be stable - you're intended to use a build.rs
or the macro to make sure it's constructed correctly each time. This was
inherited from tokio-postgres upstream, which has the same issue
(https://github.com/rust-phf/rust-phf/pull/321#issuecomment-2724521193).

We don't need this encoding of sqlstate, so I've switched it to simply
parse 5 bytes
(https://www.postgresql.org/docs/current/errcodes-appendix.html).

While here, I switched out log for tracing.
2025-03-31 12:35:51 +00:00
Konstantin Knizhnik
21a891a06d Fix IS_LOCAL_REL macro (first class has oid=FirstNormalObjectId) (#11369)
## Problem

Macro IS_LOCAL_REL used for DEBUG_COMPARE_LOCAL mode use greater-than
rather than greater-or-equal comparison while first table really is
assigned FirstNormalObjectId.

## Summary of changes

Replace strict greater with greater-or-equal comparison.

Co-authored-by: Konstantin Knizhnik <knizhnik@neon.tech>
2025-03-31 11:16:35 +00:00
Alexander Bayandin
30a7dd630c ruff: enable TC — flake8-type-checking (#11368)
## Problem

`TYPE_CHECKING` is used inconsistently across Python tests.

## Summary of changes
- Update `ruff`: 0.7.0 -> 0.11.2
- Enable TC (flake8-type-checking):
https://docs.astral.sh/ruff/rules/#flake8-type-checking-tc
- (auto)fix all new issues
2025-03-30 18:58:33 +00:00
Erik Grinaker
db5384e1b0 pageserver: remove L0 flush upload wait (#11196)
## Problem

Previously, L0 flushes would wait for uploads, as a simple form of
backpressure. However, this prevented flush pipelining and upload
parallelism. It has since been disabled by default and replaced by L0
compaction backpressure.

Touches https://github.com/neondatabase/cloud/issues/24664.

## Summary of changes

This patch removes L0 flush upload waits, along with the
`l0_flush_wait_upload`. This can't be merged until the setting has been
removed across the fleet.
2025-03-30 13:14:04 +00:00
JC Grünhage
5cb6a4bc8b fix(ci): use the right sha in release PRs (#11365)
## Problem

`github.sha` contains a merge commit of `head` and `base` if we're in a
PR. In release PRs, this makes no sense, because we fast-forward the
`base` branch to contain the changes from `head`.

Even though we correctly use `${{ github.event.pull_request.head.sha ||
github.sha }}` to reference the git commit when building artifacts, we
don't use that when checking out code, because we want to test the merge
of head and base usually. In the case of release PRs, we definitely
always want to test on the head sha though, because we're going to
forward that, and it already has the base sha as a parent, so the merge
would end up with the same tree anyway.

As a side effect, not checking out `${{
github.event.pull_request.head.sha || github.sha }}` also caused
https://github.com/neondatabase/neon/actions/runs/13986389780/job/39173256184#step:6:49
to say `release-tag=release-compute-8187`, while
https://github.com/neondatabase/neon/actions/runs/14084613121/job/39445314780#step:6:48
is talking about `build-tag=release-compute-8186`

## Summary of changes
Run a few things on `github.event.pull_request.head.sha`, if we're in a
release PR.
2025-03-28 11:56:24 +00:00
Folke Behrens
1dbf40ee2c proxy: Update redis crate (#11372) 2025-03-28 11:43:52 +00:00
Fedor Dikarev
939354abea chore(ci): pin python base images to sha (#11367)
Similar to how we pin base `debian` images, also pin `python` base
images, so we better cache them and have reproducible builds.
2025-03-27 17:42:28 +00:00
Fedor Dikarev
1d5d168626 impr(ci): use hetzner buckets for cache (#11364)
## Problem
Occasionally getting data from GH cache could be slow, with less than
10MB/s and taking 5+ minutes to download cache:
```
Received 20971520 of 2987085791 (0.7%), 9.9 MBs/sec
Received 50331648 of 2987085791 (1.7%), 15.9 MBs/sec
...
Received 1065353216 of 2987085791 (35.7%), 4.8 MBs/sec
Received 1065353216 of 2987085791 (35.7%), 4.7 MBs/sec
...
```

https://github.com/neondatabase/neon/actions/runs/13956437454/job/39068664599#step:7:17

Resulting in getting cache even longer that build time.

## Summary of changes
Switch to the caches, that are closer to the runners, and they provided
stable throughput about 70-80MB/s
2025-03-27 11:11:45 +00:00
Folke Behrens
b40dd54732 compute-node: Add some debugging tools to image (#11352)
## Problem

Some useful debugging tools are missing from the compute image and
sometimes it's impossible to install them because memory is tightly
packed.

## Summary of changes

Add the following tools: iproute2, lsof, screen, tcpdump.
The other changes come from sorting the packages alphabetically.

```bash
$ docker image inspect ghcr.io/neondatabase/vm-compute-node-v16:7555 | jaq '.[0].Size'
1389759645
$ docker image inspect ghcr.io/neondatabase/vm-compute-node-v16:14083125313 | jaq '.[0].Size'
1396051101
$ echo $((1396051101 - 1389759645))
6291456
```
2025-03-27 11:09:27 +00:00
Folke Behrens
4bb7087d4d proxy: Fix some clippy warnings coming in next versions (#11359) 2025-03-26 10:50:16 +00:00
Arpad Müller
5f3551e405 Add "still waiting for task" for slow shutdowns (#11351)
To help with narrowing down
https://github.com/neondatabase/cloud/issues/26362, we make the case
more noisy where we are wait for the shutdown of a specific task (in the
case of that issue, the `gc_loop`).
2025-03-24 17:29:44 +00:00
Anastasia Lubennikova
3e5884ff01 Revert "feat(compute_ctl): allow to change audit_log_level for existi… (#11343)
…ng (#11308)"

This reverts commit e5aef3747c.

The logic of this commit was incorrect:
enabling audit requires a restart of the compute,
because audit extensions use shared_preload_libraries.
So it cannot be done in the configuration phase,
require endpoint restart instead.
2025-03-21 18:09:34 +00:00
Vlad Lazar
9fc7c22cc9 storcon: add use_local_compute_notifications flag (#11333)
## Problem

While working on bulk import, I want to use the `control-plane-url` flag
for a different request.
Currently, the local compute hook is used whenever no control plane is
specified in the config.
My test requires local compute notifications and a configured
`control-plane-url` which isn't supported.

## Summary of changes

Add a `use-local-compute-notifications` flag. When this is set, we use
the local flow regardless of other config values.
It's enabled by default in neon_local and disabled by default in all
other envs. I had to turn the flag off in tests
that wish to bypass the local flow, but that's expected.

---------

Co-authored-by: Arpad Müller <arpad-m@users.noreply.github.com>
2025-03-21 15:31:06 +00:00
Folke Behrens
23ad228310 pgxn: Increase the pageserver response timeout a bit (#11339)
Increase the PS response timeout slightly but noticeably,
so it does not coincide with the default TCP_RTO_MAX.
2025-03-21 14:21:53 +00:00
Dmitrii Kovalkov
aeb53fea94 storage: support multiple SSL CA certificates (#11341)
## Problem
- We need to support multiple SSL CA certificates for graceful root CA
certificate rotation.
- Closes: https://github.com/neondatabase/cloud/issues/25971

## Summary of changes
- Parses `ssl_ca_file` as a pem bundle, which may contain multiple
certificates. Single pem cert is a valid pem bundle, so the change is
backward compatible.
2025-03-21 13:43:38 +00:00
Dmitrii Kovalkov
0f367cb665 storcon: reuse reqwest http client (#11327)
## Problem

- Part of https://github.com/neondatabase/neon/issues/11113
- Building a new `reqwest::Client` for every request is expensive
because it parses CA certs under the hood. It's noticeable in storcon's
flamegraph.

## Summary of changes
- Reuse one `reqwest::Client` for all API calls to avoid parsing CA
certificates every time.
2025-03-21 11:48:22 +00:00
John Spray
76088c16d2 storcon: reproduce shard split issue (#11290)
## Problem

Issue https://github.com/neondatabase/neon/issues/11254 describes a case
where restart during a shard split can result in a bad end state in the
database.

## Summary of changes

- Add a reproducer for the issue
- Tighten an existing safety check around updated row counts in
complete_shard_split
2025-03-21 08:48:56 +00:00
John Spray
0d99609870 docs: storage controller retro-RFC (#11218)
## Problem

Various aspects of the controller's job are already described in RFCs,
but the overall service didn't have an RFC that records design tradeoffs
and the top level structure.

## Summary of changes

- Add a retrospective RFC that should be useful for anyone understanding
storage controller functionality
2025-03-21 08:32:11 +00:00
Alex Chi Z.
bae9b9acdc feat(pageserver): persist timeline invisible flag (#11331)
## Problem

part of https://github.com/neondatabase/neon/issues/11279

## Summary of changes

The invisible flag is used to exclude a timeline from synthetic size
calculation. For the first step, let's persist this flag. Most of the
code are following the `is_archived` modification flow.

Signed-off-by: Alex Chi Z <chi@neon.tech>
2025-03-20 18:39:08 +00:00
Nikita Kalyanov
53f54ba37a chore: expose detach_v2 (#11325)
we need this exposed in the spec to use it in cplane. extracted from
https://github.com/neondatabase/cloud/pull/26167

## Problem

## Summary of changes
2025-03-20 18:04:17 +00:00
Dmitrii Kovalkov
28fc051dcc storage: live ssl certificate reload (#11309)
## Problem
SSL certs are loaded only during start up. It doesn't allow the rotation
of short-lived certificates without server restart.

- Closes: https://github.com/neondatabase/cloud/issues/25525

## Summary of changes
- Implement `ReloadingCertificateResolver` which reloads certificates
from disk periodically.
2025-03-20 16:26:27 +00:00
Folke Behrens
d0102a473a pgxn: Include local port in no-response log messages (#11321)
## Problem

Now that stuck connections are quickly terminated it's not easy to
quickly find the right port from the pid to correlate the connection
with the one seen on pageserver side.

## Summary of changes

Call getsockname() and include the local port number in the
no-response-from-pageserver log messages.
2025-03-20 16:06:00 +00:00
Alex Chi Z.
78502798ae feat(compute_ctl): pass compute type to pageserver with pg_options (#11287)
## Problem

second try of https://github.com/neondatabase/neon/pull/11185, part of
https://github.com/neondatabase/cloud/issues/24706

## Summary of changes

Tristan reminded me of the `options` field of the pg wire protocol,
which can be used to pass configurations. This patch adds the parsing on
the pageserver side, and supplies `neon.endpoint_type` as part of the
`options`.

---------

Signed-off-by: Alex Chi Z <chi@neon.tech>
2025-03-20 15:48:40 +00:00
Erik Grinaker
65d690b21d storcon: add repeated auto-splits and initial splits (#11122)
## Problem

Currently, we only split tenants into 8 shards once, at the 64 GB split
threshold. For very large tenants, we need to keep splitting to avoid
huge shards. And we also want to eagerly split at a lower threshold to
improve throughput during initial ingestion.

See
https://github.com/neondatabase/cloud/issues/22532#issuecomment-2706215907
for details.

Touches https://github.com/neondatabase/cloud/issues/22532.
Requires #11157.

## Summary of changes

This adds parameters and logic to enable repeated splits when a tenant's
largest timeline divided by shard count exceeds `split_threshold`, as
well as eager initial splits at a lower threshold to speed up initial
ingestion. The default parameters are all set such that they retain the
current behavior in production (only split into 8 shards once, at 64
GB).

* `split_threshold` now specifies a maximum shard size. When a shard
exceeds it, all tenant shards are split by powers of 2 such that all
tenant shards fall below `split_threshold`. Disabled by default, like
today.
* Add `max_split_shards` to specify a max shard count for autosplits.
Defaults to 8 to retain current behavior.
* Add `initial_split_threshold` and `initial_split_shards` to specify a
threshold and target count for eager splits of unsharded tenants.
Defaults to 64 GB and 8 shards to retain current production behavior.

Because this PR sets `initial_split_threshold` to 64 GB by default, it
has the effect of enabling autosplits by default. This was not the case
previously, since `split_threshold` defaults to None, but it is already
enabled across production and staging. This is temporary until we
complete the production rollout.

For more details, see code comments.

This must wait until #11157 has been deployed to Pageservers.

Once this has been deployed to production, we plan to change the
parameters to:

* `split-threshold`: 256 GB
* `initial-split-threshold`: 16 GB
* `initial-split-shards`: 4
* `max-split-shards`: 16

The final split points will thus be:

* Start: 1 shard
* 16 GB: 4 shards
* 1 TB: 8 shards
* 2 TB: 16 shards

We will then change the default settings to be disabled by default.

---------

Co-authored-by: John Spray <john@neon.tech>
2025-03-20 15:43:57 +00:00
Arpad Müller
5dd60933d3 Mark min_readable_lsn as required in the pageserver API spec (#11324)
Fully applies the changes of
https://github.com/neondatabase/cloud/pull/25233 to neon.git. The field
is always present in the Rust struct definition, so it can be marked as
required.

cc #10707
2025-03-20 15:25:09 +00:00
Gleb Novikov
2065074559 fast_import: put job status to s3 (#11284)
## Problem

`fast_import` binary is being run inside neonvms, and they do not
support proper `kubectl describe logs` now, there are a bunch of other
caveats as well: https://github.com/neondatabase/autoscaling/issues/1320

Anyway, we needed a signal if job finished successfully or not, and if
not — at least some error message for the cplane operation. And after [a
short
discussion](https://neondb.slack.com/archives/C07PG8J1L0P/p1741954251813609),
that s3 object is the most convenient at the moment.

## Summary of changes

If `s3_prefix` was provided to `fast_import` call, any job run puts a
status object file into `{s3_prefix}/status/fast_import` with contents
`{"done": true}` or `{"done": false, "error": "..."}`. Added a test as
well
2025-03-20 15:23:35 +00:00
Konstantin Knizhnik
3da70abfa5 Fix pageserver_try_receive (#11096)
## Problem

See https://neondb.slack.com/archives/C04DGM6SMTM/p1741176713523469

The problem is that this function is using `PQgetCopyData(shard->conn,
&resp_buff.data, 1 /* async = true */)`
to try to fetch next message. But this function returns 0 if the whole
message is not present in the buffer.
And input buffer may contain only part of message so result is not
fetched.

## Summary of changes

Use `PQisBusy` + `WaitEventSetWait` to check if data is available and
`PQgetCopyData(shard->conn, &resp_buff.data, 0)` to read whole message
in this case.

---------

Co-authored-by: Konstantin Knizhnik <knizhnik@neon.tech>
2025-03-20 15:21:00 +00:00
Anastasia Lubennikova
e5aef3747c feat(compute_ctl): allow to change audit_log_level for existing (#11308)
projects.

Preserve the information about the current audit log level in compute
state, so that we don't relaunch rsyslog on every spec change

https://github.com/neondatabase/cloud/issues/25349

---------

Co-authored-by: Tristan Partin <tristan@neon.tech>
2025-03-20 11:23:20 +00:00
Arpad Müller
91dad2514f storcon: also support tenant deletion for safekeepers (#11289)
If a tenant gets deleted, delete also all of its timelines. We assume
that by the time a tenant is being deleted, no new timelines are being
created, so we don't need to worry about races with creation in this
situation.

Unlike #11233, which was very simple because it listed the timelines and
invoked timeline deletion, this PR obtains a list of safekeepers to
invoke the tenant deletion on, and then invokes tenant deletion on each
safekeeper that has one or multiple timelines.

Alternative to #11233
Builds on #11288
Part of #9011
2025-03-20 10:52:21 +00:00
Dmitrii Kovalkov
9bf59989db storcon: add https API (#11239)
## Problem

Pageservers use unencrypted HTTP requests for storage controller API.

- Closes: https://github.com/neondatabase/cloud/issues/25524

## Summary of changes

- Replace hyper0::server::Server with http_utils::server::Server in
storage controller.
- Add HTTPS handler for storage controller API.
- Support `ssl_ca_file` in pageserver.
2025-03-20 08:22:02 +00:00
Tristan Partin
c6f5a58d3b Remove potential for SQL injection (#11260)
Timeline IDs do not contain characters that may cause a SQL injection,
but best to always play it safe.

Signed-off-by: Tristan Partin <tristan@neon.tech>
2025-03-19 19:19:38 +00:00
Suhas Thalanki
5589efb6de moving LastWrittenLSNCache to Neon Extension (#11031)
## Problem

We currently have this code duplicated across different PG versions.
Moving this to an extension would reduce duplication and simplify
maintenance.

## Summary of changes

Moving the LastWrittenLSN code from PG versions to the Neon extension
and linking it with hooks.

Related Postgres PR: https://github.com/neondatabase/postgres/pull/590

Closes: https://github.com/neondatabase/neon/issues/10973

---------

Co-authored-by: Tristan Partin <tristan@neon.tech>
2025-03-19 17:29:40 +00:00
Folke Behrens
019a29748d proxy: Move release PR creation to Tuesday (#11306)
Move the creation of the proxy release PR to Tuesday mornings.
2025-03-19 16:45:29 +00:00
StepSecurity Bot
88ea855cff fix(ci): Fixing StepSecurity Flagged Issues (#11311)
This pull request is created by
[StepSecurity](https://app.stepsecurity.io/securerepo) at the request of
@areyou1or0.
 ## Summary

This pull request is created by
[StepSecurity](https://app.stepsecurity.io/securerepo) at the request of
@areyou1or0. Please merge the Pull Request to incorporate the requested
changes. Please tag @areyou1or0 on your message if you have any
questions related to the PR.
## Summary

This pull request is created by
[StepSecurity](https://app.stepsecurity.io/securerepo) at the request of
@areyou1or0. Please merge the Pull Request to incorporate the requested
changes. Please tag @areyou1or0 on your message if you have any
questions related to the PR.

## Security Fixes

### Least Privileged GitHub Actions Token Permissions

The GITHUB_TOKEN is an automatically generated secret to make
authenticated calls to the GitHub API. GitHub recommends setting minimum
token permissions for the GITHUB_TOKEN.

- [GitHub Security
Guide](https://docs.github.com/en/actions/security-guides/automatic-token-authentication#using-the-github_token-in-a-workflow)
- [The Open Source Security Foundation (OpenSSF) Security
Guide](https://github.com/ossf/scorecard/blob/main/docs/checks.md#token-permissions)
### Pinned Dependencies

GitHub Action tags and Docker tags are mutable. This poses a security
risk. GitHub's Security Hardening guide recommends pinning actions to
full length commit.

- [GitHub Security
Guide](https://docs.github.com/en/actions/security-guides/security-hardening-for-github-actions#using-third-party-actions)
- [The Open Source Security Foundation (OpenSSF) Security
Guide](https://github.com/ossf/scorecard/blob/main/docs/checks.md#pinned-dependencies)
### Harden Runner

[Harden-Runner](https://github.com/step-security/harden-runner) is an
open-source security agent for the GitHub-hosted runner to prevent
software supply chain attacks. It prevents exfiltration of credentials,
detects tampering of source code during build, and enables running jobs
without `sudo` access. See how popular open-source projects use
Harden-Runner
[here](https://docs.stepsecurity.io/whos-using-harden-runner).

<details>
<summary>Harden runner usage</summary>

You can find link to view insights and policy recommendation in the
build log

<img
src="https://github.com/step-security/harden-runner/blob/main/images/buildlog1.png?raw=true"
width="60%" height="60%">

Please refer to
[documentation](https://docs.stepsecurity.io/harden-runner) to find more
details.
</details>



will fix https://github.com/neondatabase/cloud/issues/26141
2025-03-19 16:44:22 +00:00
Vlad Lazar
9ce3704ab5 pageseserver: rename cplane api to storage controller api (#11310)
## Problem

The pageserver upcall api was designed to work with control plane or the
storage controller.
We have completed the transition period and now the upcall api only
targets the storage controller.

## Summary of changes

Rename types accordingly and tweak some comments.
2025-03-19 16:29:52 +00:00
Alexey Kondratov
518269ea6a feat(compute): Add perf test for compute startup time breakdown (#11198)
## Problem

We had a recent Postgres startup latency (`start_postgres_ms`)
degradation, but it was only caught with SLO alerts. There was actually
an existing test for the same purpose -- `start_postgres_ms`, but it's
doing only two starts, so it's a bit noisy.

## Summary of changes

Add new compute startup latency test that does 100 iterations and
reports p50, p90 and p99 latencies.

Part of https://github.com/neondatabase/cloud/issues/24882
2025-03-19 16:11:33 +00:00
a-masterov
cf9d817a21 Add tests for some extensions currently not covered by the regression tests (#11191)
## Problem
Some extensions do not contain tests, which can be easily run on top of
docker-compose or staging.

## Summary of changes
Added the pg_regress based tests for `pg_tiktoken`, `pgx_ulid`, `pg_rag`
Now they will be run on top of docker-compose, but I intend to adopt
them to be run on top staging in the next PRs
2025-03-19 15:38:33 +00:00
John Spray
55cb07f680 pageserver: improve debuggability of timeline creation failures during chaos testing (#11300)
## Problem

We're seeing timeline creation failures that look suspiciously like some
race with the cleanup-deletion of initdb temporary directories. I
couldn't spot the bug, but we can make it a bit easier to debug.

Related: https://github.com/neondatabase/neon/issues/11296

## Summary of changes

- Avoid surfacing distracting ENOENT failure to delete as a log error --
this is fine, and can happen if timeline is cancelled while doing
initdb, or if initdb itself has an error where it doesn't write the dir
(this error is surfaced separately)
- Log after purging initdb temp directories
2025-03-19 13:38:03 +00:00
Christian Schwarz
0f20dae3c3 impr: merge pageserver_api::models::TenantConfig and pageserver::tenant::config::TenantConfOpt (#11298)
The only difference between
- `pageserver_api::models::TenantConfig` and
- `pageserver::tenant::config::TenantConfOpt`

at this point is that `TenantConfOpt` serializes with
`skip_serializing_if = Option::is_none`.
That is an efficiency improvement for all the places that currently
serde `models::TenantConfig` because new serializations will no longer
write `$fieldname: null` for each field that is `None` at runtime.

This should be particularly beneficial for Storcon, which stores
JSON-serialized `models::TenantConfig` in its DB.

# Behavior Changes


This PR changes the serialization behavior: we omit `None` fields
instead of serializing `$fieldname: null`).

So it's a data format change (see section on compatibility below).

And it changes API responses from Storcon and Pageserver.

## API Response Compatibility

Storcon returns the location description.
Afaik it is passed through into
- storcon_cli output
- storcon UI in console admin UI

These outputs will no longer contain `$fieldname: null` values,
which de-bloats the output (good).
But in storcon UI, it also serves as an editor "default", which
will be eliminated after a storcon with this PR is released.


## Data Format Compatibility


Backwards compat: new software reading old serialized data will
deserialize to the same runtime value because all the field types
are exactly the same and `skip_serializing_if` does not affect
deserialization.

Forward compat: old software reading data serialized by new software
will map absence fields in the serialized form to runtime value
`Option::None`. This is serde default behavior, see this playground
to convince yourself:

https://play.rust-lang.org/?version=stable&mode=debug&edition=2024&gist=f7f4e1a169959a3085b6158c022a05eb

The `serde(with="humantime_serde")` however behaves strangely:
if used on an `Option<Duration>`, it still requires the field to be
present,
unlike the serde default behavior shown in the previous paragraph.
The workaround is to set `serde(default)`.
Previously it was set on each individual field, but, we do have the
container attribute, so, set it there.
This requires deriving a `Default` impl, which, because all fields are
`Option`,
is non-magic.
See my notes here:
https://gist.github.com/problame/eddbc225a5d12617e9f2c6413e0cf799

# Future Work

We should have separate types (& crates) for
- runtime types configuration (e.g. PageServerConf::tenant_config,
AttachedLocationConf)
- `config-v1` file pageserver local disk file format
- `mgmt API`
- `pageserver.toml`

Right now they all use the same, which is convenient but makes it hard
to reason about compatibility breakage.

# Refs

- corresponding docs.neon.build PR
https://github.com/neondatabase/docs/pull/470
2025-03-19 12:47:17 +00:00
JC Grünhage
aedeb37220 fix(ci): put the BUILD_TAG of the upcoming release into RC PR artifacts (#11304)
## Problem
#11061 changed how artifacts for releases are built, by
reusing/retagging the artifacts from release PRs. This resulted in the
BUILD_TAG that's baked into the images to not be as expected.
Context: https://neondb.slack.com/archives/C08JBTT3R1Q/p1742333300129069

## Summary of changes
Set BUILD_TAG to the release tag of the upcoming release when running
inside release PRs.
2025-03-19 09:34:28 +00:00
Anastasia Lubennikova
6af974548e feat(compute_ctl): Add basic audit logging for computes. (#11170)
if `audit_log_level` is set to Log, 
preload pgaudit extension and log DDL with masked parameters into
standard postgresql log
2025-03-19 00:13:36 +00:00
Christian Schwarz
9fb77d6cdd buffered writer: add cancellation sensitivity (#11052)
In
-
https://github.com/neondatabase/neon/pull/10993#issuecomment-2690428336

I added infinite retries for buffered writer flush IOs, primarily to
gracefully handle ENOSPC but more generally so that the buffered writer
is not left in a state where reads from the surrounding InMemoryLayer
cause panics.

However, I didn't add cancellation sensitivity, which is concerning
because then there is no way to detach a timeline/tenant that is
encountering the write IO errors.
That’s a legitimate scenario in the case of some edge case bug. 
See the #10993 description for details.


This PR
- first makes flush loop infallible, enabled by infinite retries
- then adds sensitivity to `Timeline::cancel` to the flush loop, thereby
making it fallible in one specific way again
- finally fixes the InMemoryLayer/EphemeralFile/BufferedWriter
amalgamate to remain read-available after flush loop is cancelled.

The support for read-availability after cancellation is necessary so
that reads from the InMemoryLayer that are already queued up behind the
RwLock that wraps the BufferedWriter won't panic because of the
`mutable=None` that we leave behind in case the flush loop gets
cancelled.

# Alternatives

One might think that we can only ship the change for read-availability
if flush encounters an error, without the infinite retrying and/or
cancellation sensitivity complexity.

The problem with that is that read-availability sounds good but is
really quite useless, because we cannot ingest new WAL without a
writable InMemoryLayer. Thus, very soon after we transition to read-only
mode, reads from compute are going to wait anyway, but on `wait_lsn`
instead of the RwLock, because ingest isn't progressing.

Thus, having the infinite flush retries still makes more sense because
they're just "slowness" to the user, whereas wait_lsn is hard errors.
2025-03-18 18:48:43 +00:00
JC Grünhage
99639c26b4 fix(ci): update build-tools image references (#11293)
## Problem
https://github.com/neondatabase/neon/pull/11210 migrated pushing images
to ghcr. Unfortunately, it was incomplete in using images from ghcr,
which resulted in a few places referencing the ghcr build-tools image,
while trying to use docker hub credentials.

## Summary of changes
Use build-tools image from ghcr consistently.
2025-03-18 15:21:22 +00:00
Ivan Efremov
86fe26c676 fix(proxy): Fix testodrome HTTP header handling in proxy (#11292)
Relates to #22486
2025-03-18 15:14:08 +00:00
JC Grünhage
eb6efda98b impr(ci): move some kinds of tests to PR runs only (#11272)
## Problem
The pipelines after release merges are slower than they need to be at
the moment. This is because some kinds of tests/checks run on all kinds
of pipelines, even though they only matter in some of those.

## Summary of changes
Run `check-codestyle-{rust,python,jsonnet}`, `build-and-test-locally`
and `trigger-e2e-tests` only on regular PRs, not release PR or pushes to
main or release branches.
2025-03-18 13:49:34 +00:00
Conrad Ludgate
fd41ab9bb6 chore: remove x509-parser (#11247)
Both crates seem well maintained. x509-cert is part of the high quality
RustCrypto project that we already make heavy use of, and I think it
makes sense to reduce the dependencies where possible.
2025-03-18 13:05:08 +00:00
JC Grünhage
2dfff6a2a3 impr(ci): use ghcr.io as the default container registry (#11210)
## Problem
Docker Hub has new rate limits coming up, and to avoid problems coming
with those we're switching to GHCR.

## Summary of changes
- Push images to GHCR initially and distribute them from there
- Use images from GHCR in docker-compose
2025-03-18 11:30:49 +00:00
Arpad Müller
2cf6ae76fc storcon: move safekeeper related stuff out of service.rs (#11288)
There is no functional change here. We move safekeeper related code from
`service.rs` to `service/safekeeper_service.rs`, so that safekeeper
related stuff is contained in a single file. This also helps with
preventing `service.rs` from growing even further.

Part of #9011.
2025-03-18 09:00:53 +00:00
Dmitrii Kovalkov
57d51e949d tests: suppress excessive pageserver errors in test_timeline_ancestor_detach_errors (#11277)
## Problem

The test is flaky because of the same reasons as described in
https://github.com/neondatabase/neon/issues/11177.
The test has already suppressed these `WARN` and `ERROR` log messages,
but the regexp didn't match all possible errors.

## Summary of changes
- Change regexp to suppress all possible allowed error log messages.
2025-03-18 07:10:11 +00:00
Arpad Müller
0d3d639ef3 storcon: remove timeouts for safekeeper heartbeating (#11232)
PRs #10891 and #10902 have time-bounded the safekeeper heartbeating of
the storage controller. Those timeouts were not meant to be permanent,
but temporary until we figured out the reasons for the safekeeper
heartbeating causing problems.

Now they are better understood and resolved. A comment is
[here](https://github.com/neondatabase/cloud/issues/24396#issuecomment-2679342929),
but most importantly, we've had:

* #10954 to send heartbeats concurrently (before the issue was we sent
them sequentially, so the total time time was number of nodes times time
for timeout to be hit, now the total time is the maximum of all things
we are heartbeating)
* work to actually make heartbeats work and not error, i.e. JWT rollout
for storcon, not sending heartbeats to decomissioned safekeepers,
removal of decomissioned safekeepers from the databases

Part of https://github.com/neondatabase/cloud/issues/25473
2025-03-18 03:37:45 +00:00
Alex Chi Z.
05ca27c981 fix(pagectl/benches): scope context with debug tools (#11285)
## Problem


7c462b3417
requires all contexts have scopes. pagectl/benches don't have such
scopes.

close https://github.com/neondatabase/neon/issues/11280

## Summary of changes

Adding scopes for the tools.

Signed-off-by: Alex Chi Z <chi@neon.tech>
2025-03-17 21:27:27 +00:00
Alex Chi Z.
bb64beffbb fix(pageserver): log compaction errors with timeline ids (#11231)
## Problem

Makes it easier to debug.

## Summary of changes

Log compaction errors with timeline ids.

Signed-off-by: Alex Chi Z <chi@neon.tech>
2025-03-17 19:42:02 +00:00
Konstantin Knizhnik
24f41bee5c Update LFC in case of unlogged build (#11262)
## Problem

Unlogged build is used for GIST/SPGIST/GIN/HNSW indexes.
In this mode we first change relation class to `RELPERSISTENCE_UNLOGGED`
and save them on local disk.
But we do not save unlogged relations in LFC.
It may cause fetching incorrect value from LFC if relfilenode is reused.

## Summary of changes

Save modified pages in LFC on second stage of unlogged build (when
modified pages are walloged).
There is no need to save pages in LFC at first phase because the will be
in any case overwritten with assigned LSN at second phase.

Co-authored-by: Konstantin Knizhnik <knizhnik@neon.tech>
2025-03-17 19:06:42 +00:00
Suhas Thalanki
a05c99f487 fix: removed anon pg extension (#10936)
## Problem

Removing the `anon` v1 extension in postgres as described in
https://github.com/neondatabase/cloud/issues/22663. This extension is
not built for postgres v17 and is out of date when compared to the
upstream variant which is v2 (we have v1.4).

## Summary of changes

Removed the `anon` v1 extension from being built or preloaded

Related to https://github.com/neondatabase/cloud/issues/22663
2025-03-17 18:23:32 +00:00
JC Grünhage
486ffeef6d fix(ci): don't have neon-test-extensions release tag push depend on compute-node-image build (#11281)
## Problem
Failures like
https://github.com/neondatabase/neon/actions/runs/13901493608/job/38896940612?pr=11272
are caused by the dependency on `compute-node-image`, which was wrong on
release jobs anyway.

## Summary of changes
Remove dependency on `compute-node-image` from the job
`add-release-tag-to-neon-test-extension-image`.
2025-03-17 16:31:49 +00:00
Arpad Müller
56149a046a Add test_explicit_timeline_creation_storcon and make it work (#11261)
Adds a basic test that makes the storcon issue explicit creation of a
timeline on safeekepers (main storcon PR in #11058). It was adapted from
`test_explicit_timeline_creation` from #11002.

Also, do a bunch of fixes needed to get the test work (the API
definitions weren't correct), and log more stuff when we can't create a
new timeline due to no safekeepers being active.

Part of #9011

---------

Co-authored-by: Arseny Sher <sher-ars@yandex.ru>
2025-03-17 16:28:21 +00:00
Roman Zaynetdinov
db30e1669c Add /configure_telemetry API endpoint (#11117)
Work on https://github.com/neondatabase/cloud/issues/23721 and
https://github.com/neondatabase/cloud/issues/23714

Depends on https://github.com/neondatabase/neon/pull/11111

- Add `/configure_telemetry` API endpoint
- Support second rsyslog configuration for Postgres logs export
- Enable logs export when compute feature is enabled and configure
Postgres to send logs to syslog

I have used `/configure_telemetry` name because in the future I see it
also being used for configuring a `pg_tracing` extension to export
traces. Let me know if you'd rather have these APIs separate. In this
case we can rename it to `/configure_rsyslog`.
2025-03-17 13:53:23 +00:00
JC Grünhage
fdf04d4d81 fix(ci): use correct branch ref for checking whether this is a release merge queue (#11270)
## Problem

https://github.com/neondatabase/neon/actions/runs/13894288475/job/38871819190
shows the "Add fast-fordward label to PR to trigger fast-forward merge"
job being skipped. This is due to not using the right variable for
checking which branch the merge queue is merging into.

## Summary of changes
Use the `branch` output of the `meta` task for checking the target
branch of a merge group.
2025-03-17 09:26:45 +00:00
Alexander Bayandin
136cae76c2 fix(ci): correct regex to detect release-compute RC PRs (#11269)
## Problem
The regex in `_meta.yml` workflow doesn't detect RC PRs for compute
releases:
https://neondb.slack.com/archives/C059ZC138NR/p1742164884669389

## Summary of changes
- Fix regex

---------

Co-authored-by: Peter Bendel <peterbendel@neon.tech>
2025-03-17 07:25:12 +00:00
Konstantin Knizhnik
15e63afe7d Support DEBUG_COMPARE_LOCAL mode for unloggedindex build (#11257)
## Problem

In unlogged index build (used fir GIST/SPGIST/GIN indexes) files is
created on disk and then removed at the end.
It contradicts to the logic of DEBUG_COMPARE_LOCAL mode.

## Summary of changes

Do not create and unlink files in unlogged build in DEBUG_COMPARE_LOCAL
mode.

Co-authored-by: Konstantin Knizhnik <knizhnik@neon.tech>
2025-03-17 06:07:24 +00:00
Alexey Kondratov
966abd3bd6 fix(compute_ctl): Dollar escaping helper fixes (#11263)
## Problem

In the previous PR #11045, one edge-case wasn't covered, when an ident
contains only one `$`, we were picking `$$` as a 'wrapper'. Yet, when
this `$` is at the beginning or at the end of the ident, then we end up
with `$$$` in a row which breaks the escaping.

## Summary of changes

Start from `x` tag instead of a blank string.

Slack:
https://neondb.slack.com/archives/C08HV951W2W/p1742076675079769?thread_ts=1742004205.461159&cid=C08HV951W2W
2025-03-16 18:39:54 +00:00
Alexey Kondratov
8566cad23b chore(docs): Refresh RFC guide to suggest using YYYY-MM-DD prefix (#11252)
## Problem

Serial/numeric IDs lead to collisions, which is not critical but looks
awkward.
Previous discussion:
https://neondb.slack.com/archives/C033A2WE6BZ/p1741891345869979

## Summary of changes

Suggest using the `YYYY-MM-DD` prefix, which i) has less chance of
collision; ii) provides out-of-the-box lexicographic sorting; iii) even
if it collides, it's not a big deal -- just two RFCs have been started
on the same day.

---------

Co-authored-by: Alexander Bayandin <alexander@neon.tech>
2025-03-16 17:17:58 +00:00
Peter Bendel
228bb75354 Extend large tenant OLTP workload ... (#11166)
... to better match the workload characteristics of real Neon customers

## Problem

We analyzed workloads of large Neon users and want to extend the oltp
workload to include characteristics seen in those workloads.

## Summary of changes

- for re-use branch delete inserted rows from last run
- adjust expected run-time (time-outs) in GitHub workflow
- add queries that exposes the prefetch getpages path
- add I/U/D transactions for another table (so far the workload was
insert/append-only)
- add an explicit vacuum analyze step and measure its time
- add reindex concurrently step and measure its time (and take care that
this step succeeds even if prior reindex runs have failed or were
canceled)
- create a second connection string for the pooled connection that
removes the `-pooler` suffix from the hostname because we want to run
long-running statements (database maintenance) and bypass the pooler
which doesn't support unlimited statement timeout

## Test run


https://github.com/neondatabase/neon/actions/runs/13851772887/job/38760172415
2025-03-16 14:04:48 +00:00
Cihan Demirci
a5b00b87ba CI(pre-merge-checks): use step-security/changed-files (#11265)
Use Step Security maintained version of `tj-actions/changed-files`.

https://www.stepsecurity.io/blog/harden-runner-detection-tj-actions-changed-files-action-is-compromised#use-the-stepsecurity-maintained-changed-files-action
2025-03-16 13:53:27 +00:00
John Spray
a674ed8caf storcon: safety check when completing shard split (#11256)
## Problem

There is a rare race between controller graceful deployment and shard
splitting where we may incorrectly both abort _and_ complete the split
(on different pods), and thereby leave no shards at all in the database.

Related: #11254

## Summary of changes

- In complete_shard_split, refuse to delete anything if child shards are
not found
2025-03-14 20:08:24 +00:00
Erik Grinaker
53d50c7ea5 pageserver: deflake compaction tests (#11246)
These need to set `NoYield`, otherwise they may be preempted by pending
L0 compaction.
2025-03-14 17:45:18 +00:00
Dmitrii Kovalkov
3168bd0e3a tests: suppress "Cancelled request finished with an error" in test_timeline_archive (#11241)
## Problem

Previous PR https://github.com/neondatabase/neon/pull/11190 didn't
suppress `Cancelled request finished with an error` messages, which are
also expected, so the test
https://github.com/neondatabase/neon/issues/11177 is still flaky.

## Summary of changes
- Suppress `Cancelled request finished with an error` in
`test_timeline_archive`
2025-03-14 17:42:09 +00:00
Alexander Bayandin
4a97cd0b7e test_runner: fix tests with jsonnet for Python 3.13 (#11240)
## Problem
Python's `jsonnet` 0.20.0 doesn't support Python 3.13, so we have a
couple of tests xfailed because of that.

## Summary of changes
- Bump `jsonnet` to `0.21.0rc2` which supports Python 3.13
- Unxfail `test_sql_exporter_metrics_e2e` and
`test_sql_exporter_metrics_smoke` on Python 3.13
2025-03-14 17:02:55 +00:00
Anastasia Lubennikova
b7c6738524 feat(compute_ctl): add pgaudt log gc to compute_ctl (#11169)
- add pgaudt_gc thread to compute_ctl
to cleanup old pgaudit logs if they exist.
pgaudit can rotate files, but it doesn't delete the old files
  
- Add AUDIT_LOG_DIR_SIZE metric to compute_ctl
to track the size of the audit log directory in bytes.

- Fix permissions for rsyslog state files directory
2025-03-14 14:08:16 +00:00
Conrad Ludgate
7fe5a689b4 feat(proxy): export ingress metrics (#11244)
## Problem

We exposed the direction tag in #10925 but didn't actually include the
ingress tag in the export to allow for an adaption period.

## Summary of changes

We now export the ingress direction
2025-03-14 13:54:57 +00:00
Dmitrii Kovalkov
b0922967e0 Bump humantime version and remove advisories.ignore (#11242)
## Problem

- Closes:
https://github.com/neondatabase/neon/issues/11179#issuecomment-2724222041

## Summary of changes
- Bump humantime version to `2.2`
- Remove `RUSTSEC-2025-0014` from `advisories.ignore`
2025-03-14 11:51:11 +00:00
Dmitrii Kovalkov
f68be2b5e2 safekeeper: https for management API (#11171)
## Problem

Storage controller uses unencrypted HTTP requests for safekeeper
management API.

- Closes: https://github.com/neondatabase/cloud/issues/24836

## Summary of changes

- Replace `hyper0::server::Server` with `http_utils::server::Server` in
safekeeper.
- Add HTTPS handler for safekeeper management API.
2025-03-14 11:41:22 +00:00
Christian Schwarz
04370b48b3 fix(storcon): optimization validation makes decisions based on wrong SecondaryProgress (#11229)
# Refs

- fixes https://github.com/neondatabase/neon/issues/11228

# Problem High-Level

When storcon validates whether a `ScheduleOptimizationAction` should be
applied, it retrieves the `tenant_secondary_status` to determine whether
a secondary is ready for the optimization.

When collecting results, it associates secondary statuses with the wrong
optimization actions in the batch of optimizations that we're
validating.

The result is that we make the decision for shard/location X based on
the SecondaryStatus of a random secondary location Y in the current
batch of optimizations.

A possible symptom is an early cutover, as seen in this engineering
investigation here:
- https://github.com/neondatabase/cloud/issues/25734

# Problem Code-Level

This code here in `optimize_all_validate`


97e2e27f68/storage_controller/src/service.rs (L7012-L7029)

zips the `want_secondary_status` with the Vec returned from
`tenant_for_shards_api` .

However, the Vec returned from `want_secondary_status` is not ordered
(it uses FuturesUnordered internally).

# Solution

Sort the Vec in input order before returning it.

`optimize_all_validate` was the only caller affected by this problem

While at it, also future-proof similar-looking function
`tenant_for_shards`.
None of its callers care about the order, but this type of function
signature is easy to use incorrectly.

# Future Work

Avoid the additional iteration, map, and allocation.

Change API to leverage AsyncFn (async closure).
And/or invert `tenant_for_shards_api` into a Future ext trait / iterator
adaptor thing.
2025-03-14 11:21:16 +00:00
Arpad Müller
5359cf717c storcon: add API definitions for exclude_timeline and term_bump (#11197)
Adds API definitions for the safekeeper API endpoints `exclude_timeline`
and `term_bump`. Also does a bugfix to return the correct type from
`delete_timeline`.

Part of #8614
2025-03-14 00:00:37 +00:00
Erik Grinaker
d6d78a050f pageserver: disable l0_flush_wait_upload by default (#11215)
## Problem

This is already disabled in production, as it is replaced by L0 flush
delays. It will be removed in a later PR, once the config option is no
longer specified in production.

## Summary of changes

Disable `l0_flush_wait_upload` by default.
2025-03-13 21:08:28 +00:00
Erik Grinaker
4ff000c042 pageserver: deflake test_metadata_image_creation (#11230)
## Problem

`test_metadata_image_creation ` became flaky with #11212, since image
compaction may yield to L0 compaction.

## Summary of changes

Set `NoYield` when compacting in tenant tests.
2025-03-13 20:46:21 +00:00
Conrad Ludgate
9a3020d2ce chore(proxy): pre-initialise metricvecs (#11226)
## Problem

We noticed that error metrics didn't show for some services with light
load. This is not great and can cause problems for dashboards/alerts

## Summary of changes

Pre-initialise some metricvecs.
2025-03-13 20:23:53 +00:00
Alex Chi Z.
23b713900e feat(storcon): passthrough ancestor detach behavior (#11199)
## Problem

https://github.com/neondatabase/neon/issues/10310
https://github.com/neondatabase/neon/pull/11158

## Summary of changes

We need to passthrough the new detach behavior through the storcon API.

Signed-off-by: Alex Chi Z <chi@neon.tech>
2025-03-13 20:21:23 +00:00
Arpad Müller
b1a1be6a4c switch pytests and neon_local to control_plane_hooks_api (#11195)
We want to switch away from and deprecate the `--compute-hook-url` param
for the storcon in favour of `--control-plane-url` because it allows us
to construct urls with `notify-safekeepers`.

This PR switches the pytests and neon_local from a
`control_plane_compute_hook_api` to a new param named
`control_plane_hooks_api` which is supposed to point to the parent of
the `notify-attach` URL.

We still support reading the old url from disk to not be too disruptive
with existing deployments, but we just ignore it.

Also add docs for the `notify-safekeepers` upcall API.

Follow-up of #11173
Part of https://github.com/neondatabase/neon/issues/11163
2025-03-13 19:50:52 +00:00
Erik Grinaker
8afae9d03c pageserver: enable l0_flush_delay_threshold by default (#11214)
## Problem

`l0_flush_delay_threshold` has already been set to 30 in production for
a couple of weeks. Let's harmonize the default.

## Summary of changes

Update `DEFAULT_L0_FLUSH_DELAY_FACTOR` to 3 such that the default
`l0_flush_delay_threshold` is `3 * compaction_threshold`.

This differs from the production setting, which is hardcoded to 30 (with
`compaction_threshold` at 10), and is more appropriate for any tenants
that have custom `compaction_threshold` overrides.
2025-03-13 19:15:22 +00:00
JC Grünhage
066b0a1be9 fix(ci): correctly push neon-test-extensions in releases and to ghcr (#11225)
## Problem
ef0d4a48a adjusted how we build container images and how we push them,
and the neon-test-extensions image was overlooked. Additionally, is was
also missed in 1f0dea9a1, which pushed our container images to GHCR.

## Summary of changes
Push neon-test-extensions to GHCR and also push release tags for it.
2025-03-13 18:18:55 +00:00
Konstantin Knizhnik
398d2794eb Handle DEBUG_COMPARE_LOCAL mode in neon_zeroextend (#11220)
## Problem

DEBUG_COMPARE_LOCAL is not supported in neon_zeroextend added in PG16

## Summary of changes

Add support of DEBUG_COMPARE_LOCAL in neon_zeroextend

Co-authored-by: Konstantin Knizhnik <knizhnik@neon.tech>
2025-03-13 16:30:32 +00:00
Erik Grinaker
3c3b9dc919 pageserver: enable image_creation_preempt_threshold by default (#11216)
## Problem

This is already set in production, we should harmonize the default.

## Summary of changes

Default `image_creation_preempt_threshold` to 3.
2025-03-13 16:28:21 +00:00
Christian Schwarz
ed31dd2a3c pageserver: better observability for slow wait_lsn (#11176)
# Problem

We leave too few observability breadcrumbs in the case where wait_lsn is
exceptionally slow.

# Changes

- refactor: extract the monitoring logic out of `log_slow` into
`monitor_slow_future`
- add global + per-timeline counter for time spent waiting for wait_lsn
- It is updated while we're still waiting, similar to what we do for
page_service response flush.
- add per-timeline counterpair for started & finished wait_lsn count
- add slow-logging to leave breadcrumbs in logs, not just metrics

For the slow-logging, we need to consider not flooding the logs during a
broker or network outage/blip.
The solution is a "log-streak-level" concurrency limit per timeline.
At any given time, there is at most one slow wait_lsn that is logging
the "still running" and "completed" sequence of logs.
Other concurrent slow wait_lsn's don't log at all.
This leaves at least one breadcrumb in each timeline's logs if some
wait_lsn was exceptionally slow during a given period.
The full degree of slowness can then be determined by looking at the
per-timeline metric.

# Performance

Reran the `bench_log_slow` benchmark, no difference, so, existing call
sites are fine.

We do use a Semaphore, but only try_acquire it _after_ things have
already been determined to be slow. So, no baseline overhead
anticipated.

# Refs

-
https://github.com/neondatabase/cloud/issues/23486#issuecomment-2711587222
2025-03-13 15:03:53 +00:00
Conrad Ludgate
3dec117572 feat(compute_ctl): use TLS if configured (#10972)
Closes: https://github.com/neondatabase/cloud/issues/22998

If control-plane reports that TLS should be used, load the certificates
(and watch for updates), make sure postgres use them, and detects
updates.

Procedure:
1. Load certificates
2. Reconfigure postgres/pgbouncer
3. Loop on a timer until certificates have loaded
4. Go to 1

Notes:
1. We only run this procedure if requested on startup by control plane.
2. We needed to compile pgbouncer with openssl enabled
3. Postgres doesn't allow tls keys to be globally accessible - must be
read only to the postgres user. I couldn't convince the autoscaling team
to let me put this logic into the VM settings, so instead compute_ctl
will copy the keys to be read-only by postgres.
4. To mitigate a race condition, we also verify that the key matches the
cert.
2025-03-13 15:03:22 +00:00
Alex Chi Z.
b2286f5bcb fix(pageserver): don't panic if gc-compaction find no keys (#11200)
## Problem

There was a panic on staging that compaction didn't find any keys. This
is possible if all layers selected for compaction does not contain any
keys within the current shard.

## Summary of changes

Make panic an error. In the future, we can try creating an empty image
layer so that GC can clean up those layers. Otherwise, for now, we can
only rely on shard ancestor compaction to remove these data.

Signed-off-by: Alex Chi Z <chi@neon.tech>
2025-03-13 14:38:45 +00:00
Erik Grinaker
c036fec065 pageserver: enable compaction_l0_first by default (#11212)
## Problem

`compaction_l0_first` has already been enabled in production for a
couple of weeks.

## Summary of changes

Enable `compaction_l0_first` by default.

Also set `CompactFlags::NoYield` in `timeline_checkpoint_handler`, to
ensure explicitly requested compaction runs to completion. This endpoint
is mainly used in tests, and caused some flakiness where tests expected
compaction to complete.
2025-03-13 14:28:42 +00:00
490 changed files with 16018 additions and 6918 deletions

View File

@@ -8,6 +8,7 @@ self-hosted-runner:
- small-arm64
- us-east-2
config-variables:
- AWS_ECR_REGION
- AZURE_DEV_CLIENT_ID
- AZURE_DEV_REGISTRY_NAME
- AZURE_DEV_SUBSCRIPTION_ID
@@ -15,23 +16,25 @@ config-variables:
- AZURE_PROD_REGISTRY_NAME
- AZURE_PROD_SUBSCRIPTION_ID
- AZURE_TENANT_ID
- BENCHMARK_INGEST_TARGET_PROJECTID
- BENCHMARK_LARGE_OLTP_PROJECTID
- BENCHMARK_PROJECT_ID_PUB
- BENCHMARK_PROJECT_ID_SUB
- REMOTE_STORAGE_AZURE_CONTAINER
- REMOTE_STORAGE_AZURE_REGION
- SLACK_UPCOMING_RELEASE_CHANNEL_ID
- DEV_AWS_OIDC_ROLE_ARN
- BENCHMARK_INGEST_TARGET_PROJECTID
- PGREGRESS_PG16_PROJECT_ID
- PGREGRESS_PG17_PROJECT_ID
- SLACK_ON_CALL_QA_STAGING_STREAM
- DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN
- SLACK_ON_CALL_STORAGE_STAGING_STREAM
- SLACK_CICD_CHANNEL_ID
- SLACK_STORAGE_CHANNEL_ID
- HETZNER_CACHE_BUCKET
- HETZNER_CACHE_ENDPOINT
- HETZNER_CACHE_REGION
- NEON_DEV_AWS_ACCOUNT_ID
- NEON_PROD_AWS_ACCOUNT_ID
- AWS_ECR_REGION
- BENCHMARK_LARGE_OLTP_PROJECTID
- PGREGRESS_PG16_PROJECT_ID
- PGREGRESS_PG17_PROJECT_ID
- REMOTE_STORAGE_AZURE_CONTAINER
- REMOTE_STORAGE_AZURE_REGION
- SLACK_CICD_CHANNEL_ID
- SLACK_ON_CALL_DEVPROD_STREAM
- SLACK_ON_CALL_QA_STAGING_STREAM
- SLACK_ON_CALL_STORAGE_STAGING_STREAM
- SLACK_RUST_CHANNEL_ID
- SLACK_STORAGE_CHANNEL_ID
- SLACK_UPCOMING_RELEASE_CHANNEL_ID

View File

@@ -39,20 +39,26 @@ registries = {
],
}
release_branches = ["release", "release-proxy", "release-compute"]
outputs: dict[str, dict[str, list[str]]] = {}
target_tags = [target_tag, "latest"] if branch == "main" else [target_tag]
target_stages = (
["dev", "prod"] if branch in ["release", "release-proxy", "release-compute"] else ["dev"]
target_tags = (
[target_tag, "latest"]
if branch == "main"
else [target_tag, "released"]
if branch in release_branches
else [target_tag]
)
target_stages = ["dev", "prod"] if branch in release_branches else ["dev"]
for component_name, component_images in components.items():
for stage in target_stages:
outputs[f"{component_name}-{stage}"] = {
f"docker.io/neondatabase/{component_image}:{source_tag}": [
f"ghcr.io/neondatabase/{component_image}:{source_tag}": [
f"{registry}/{component_image}:{tag}"
for registry, tag in itertools.product(registries[stage], target_tags)
if not (registry == "docker.io/neondatabase" and tag == source_tag)
if not (registry == "ghcr.io/neondatabase" and tag == source_tag)
]
for component_image in component_images
}

View File

@@ -11,12 +11,27 @@ try:
except json.JSONDecodeError as e:
raise ValueError("Failed to parse IMAGE_MAP as JSON") from e
for source, targets in parsed_image_map.items():
for target in targets:
cmd = ["docker", "buildx", "imagetools", "create", "-t", target, source]
print(f"Running: {' '.join(cmd)}")
result = subprocess.run(cmd, text=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
failures = []
if result.returncode != 0:
print(f"Error: {result.stdout}")
raise RuntimeError(f"Command failed: {' '.join(cmd)}")
pending = [(source, target) for source, targets in parsed_image_map.items() for target in targets]
while len(pending) > 0:
if len(failures) > 10:
print("Error: more than 10 failures!")
for failure in failures:
print(f'"{failure[0]}" failed with the following output:')
print(failure[1])
raise RuntimeError("Retry limit reached.")
source, target = pending.pop(0)
cmd = ["docker", "buildx", "imagetools", "create", "-t", target, source]
print(f"Running: {' '.join(cmd)}")
result = subprocess.run(cmd, text=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
if result.returncode != 0:
failures.append((" ".join(cmd), result.stdout))
pending.append((source, target))
if len(failures) > 0 and (github_output := os.getenv("GITHUB_OUTPUT")):
with open(github_output, "a") as f:
f.write("slack_notify=true\n")

View File

@@ -8,6 +8,9 @@ defaults:
run:
shell: bash -euxo pipefail {0}
permissions:
contents: read
jobs:
setup-databases:
permissions:
@@ -27,13 +30,18 @@ jobs:
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Set up Connection String
id: set-up-prep-connstr
run: |
@@ -58,10 +66,10 @@ jobs:
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
- uses: actions/checkout@v4
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}

View File

@@ -37,17 +37,20 @@ env:
RUST_BACKTRACE: 1
COPT: '-Werror'
permissions:
contents: read
jobs:
build-neon:
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large')) }}
runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large')) }}
permissions:
id-token: write # aws-actions/configure-aws-credentials
contents: read
container:
image: ${{ inputs.build-tools-image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
# Raise locked memory limit for tokio-epoll-uring.
# On 5.10 LTS kernels < 5.10.162 (and generally mainline kernels < 5.12),
# io_uring will account the memory of the CQ and SQ as locked.
@@ -59,7 +62,12 @@ jobs:
BUILD_TAG: ${{ inputs.build-tag }}
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
@@ -120,29 +128,49 @@ jobs:
- name: Cache postgres v14 build
id: cache_pg_14
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v14
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v14_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
- name: Cache postgres v15 build
id: cache_pg_15
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v15
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v15_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
- name: Cache postgres v16 build
id: cache_pg_16
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v16
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v16_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
- name: Cache postgres v17 build
id: cache_pg_17
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ inputs.build-type }}-pg-${{ steps.pg_v17_rev.outputs.pg_rev }}-bookworm-${{ hashFiles('Makefile', 'build-tools.Dockerfile') }}
@@ -221,7 +249,7 @@ jobs:
fi
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
@@ -318,19 +346,24 @@ jobs:
contents: read
statuses: write
needs: [ build-neon ]
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large')) }}
runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', inputs.arch == 'arm64' && 'large-arm64' || 'large')) }}
container:
image: ${{ inputs.build-tools-image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
# for changed limits, see comments on `options:` earlier in this file
options: --init --shm-size=512mb --ulimit memlock=67108864:67108864
strategy:
fail-fast: false
matrix: ${{ fromJSON(format('{{"include":{0}}}', inputs.test-cfg)) }}
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true

View File

@@ -12,21 +12,39 @@ defaults:
run:
shell: bash -euxo pipefail {0}
permissions:
contents: read
jobs:
check-codestyle-python:
runs-on: [ self-hosted, small ]
permissions:
packages: read
container:
image: ${{ inputs.build-tools-image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- uses: actions/checkout@v4
- uses: actions/cache@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Cache poetry deps
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}

View File

@@ -23,25 +23,38 @@ jobs:
check-codestyle-rust:
strategy:
matrix:
arch: ${{ fromJson(inputs.archs) }}
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'small-arm64' || 'small')) }}
arch: ${{ fromJSON(inputs.archs) }}
runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'small-arm64' || 'small')) }}
permissions:
packages: read
container:
image: ${{ inputs.build-tools-image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
- name: Cache cargo deps
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: |
~/.cargo/registry
!~/.cargo/registry/src

View File

@@ -20,6 +20,9 @@ defaults:
run:
shell: bash -euo pipefail {0}
permissions:
contents: read
jobs:
create-release-branch:
runs-on: ubuntu-22.04
@@ -28,7 +31,12 @@ jobs:
contents: write # for `git push`
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ inputs.source-branch }}
fetch-depth: 0

View File

@@ -5,10 +5,16 @@ on:
github-event-name:
type: string
required: true
github-event-json:
type: string
required: true
outputs:
build-tag:
description: "Tag for the current workflow run"
value: ${{ jobs.tags.outputs.build-tag }}
release-tag:
description: "Tag for the release if this is an RC PR run"
value: ${{ jobs.tags.outputs.release-tag }}
previous-storage-release:
description: "Tag of the last storage release"
value: ${{ jobs.tags.outputs.storage }}
@@ -24,6 +30,9 @@ on:
release-pr-run-id:
description: "Only available if `run-kind in [storage-release, proxy-release, compute-release]`. Contains the run ID of the `Build and Test` workflow, assuming one with the current commit can be found."
value: ${{ jobs.tags.outputs.release-pr-run-id }}
sha:
description: "github.event.pull_request.head.sha on release PRs, github.sha otherwise"
value: ${{ jobs.tags.outputs.sha }}
permissions: {}
@@ -35,19 +44,22 @@ jobs:
tags:
runs-on: ubuntu-22.04
outputs:
build-tag: ${{ steps.build-tag.outputs.tag }}
build-tag: ${{ steps.build-tag.outputs.build-tag }}
release-tag: ${{ steps.build-tag.outputs.release-tag }}
compute: ${{ steps.previous-releases.outputs.compute }}
proxy: ${{ steps.previous-releases.outputs.proxy }}
storage: ${{ steps.previous-releases.outputs.storage }}
run-kind: ${{ steps.run-kind.outputs.run-kind }}
release-pr-run-id: ${{ steps.release-pr-run-id.outputs.release-pr-run-id }}
sha: ${{ steps.sha.outputs.sha }}
permissions:
contents: read
steps:
# Need `fetch-depth: 0` to count the number of commits in the branch
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
fetch-depth: 0
egress-policy: audit
- name: Get run kind
id: run-kind
@@ -69,6 +81,23 @@ jobs:
run: |
echo "run-kind=$RUN_KIND" | tee -a $GITHUB_OUTPUT
- name: Get the right SHA
id: sha
env:
SHA: >
${{
contains(fromJSON('["storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), steps.run-kind.outputs.run-kind)
&& fromJSON(inputs.github-event-json).pull_request.head.sha
|| github.sha
}}
run: |
echo "sha=$SHA" | tee -a $GITHUB_OUTPUT
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
ref: ${{ steps.sha.outputs.sha }}
- name: Get build tag
id: build-tag
env:
@@ -79,16 +108,16 @@ jobs:
run: |
case $RUN_KIND in
push-main)
echo "tag=$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
echo "build-tag=$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
storage-release)
echo "tag=release-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
echo "build-tag=release-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
proxy-release)
echo "tag=release-proxy-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
echo "build-tag=release-proxy-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
compute-release)
echo "tag=release-compute-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
echo "build-tag=release-compute-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
pr|storage-rc-pr|compute-rc-pr|proxy-rc-pr)
BUILD_AND_TEST_RUN_ID=$(gh api --paginate \
@@ -96,10 +125,21 @@ jobs:
-H "X-GitHub-Api-Version: 2022-11-28" \
"/repos/${GITHUB_REPOSITORY}/actions/runs?head_sha=${CURRENT_SHA}&branch=${CURRENT_BRANCH}" \
| jq '[.workflow_runs[] | select(.name == "Build and Test")][0].id // ("Error: No matching workflow run found." | halt_error(1))')
echo "tag=$BUILD_AND_TEST_RUN_ID" | tee -a $GITHUB_OUTPUT
echo "build-tag=$BUILD_AND_TEST_RUN_ID" | tee -a $GITHUB_OUTPUT
case $RUN_KIND in
storage-rc-pr)
echo "release-tag=release-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
proxy-rc-pr)
echo "release-tag=release-proxy-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
compute-rc-pr)
echo "release-tag=release-compute-$(git rev-list --count HEAD)" | tee -a $GITHUB_OUTPUT
;;
esac
;;
workflow-dispatch)
echo "tag=$GITHUB_RUN_ID" | tee -a $GITHUB_OUTPUT
echo "build-tag=$GITHUB_RUN_ID" | tee -a $GITHUB_OUTPUT
;;
*)
echo "Unexpected RUN_KIND ('${RUN_KIND}'), failing to assign build-tag!"
@@ -120,10 +160,10 @@ jobs:
- name: Get the release PR run ID
id: release-pr-run-id
if: ${{ contains(fromJson('["storage-release", "compute-release", "proxy-release"]'), steps.run-kind.outputs.run-kind) }}
if: ${{ contains(fromJSON('["storage-release", "compute-release", "proxy-release"]'), steps.run-kind.outputs.run-kind) }}
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
CURRENT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
CURRENT_SHA: ${{ github.sha }}
run: |
RELEASE_PR_RUN_ID=$(gh api "/repos/${GITHUB_REPOSITORY}/actions/runs?head_sha=$CURRENT_SHA" | jq '[.workflow_runs[] | select(.name == "Build and Test") | select(.head_branch | test("^rc/release(-(proxy)|(compute))?/[0-9]{4}-[0-9]{2}-[0-9]{2}$"; "s"))] | first | .id // ("Faied to find Build and Test run from RC PR!" | halt_error(1))')
RELEASE_PR_RUN_ID=$(gh api "/repos/${GITHUB_REPOSITORY}/actions/runs?head_sha=$CURRENT_SHA" | jq '[.workflow_runs[] | select(.name == "Build and Test") | select(.head_branch | test("^rc/release(-(proxy|compute))?/[0-9]{4}-[0-9]{2}-[0-9]{2}$"; "s"))] | first | .id // ("Failed to find Build and Test run from RC PR!" | halt_error(1))')
echo "release-pr-run-id=$RELEASE_PR_RUN_ID" | tee -a $GITHUB_OUTPUT

View File

@@ -49,7 +49,12 @@ jobs:
id-token: write # Required for aws/azure login
packages: write # required for pushing to GHCR
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
sparse-checkout: .github/scripts/push_with_image_map.py
sparse-checkout-cone-mode: false
@@ -59,7 +64,7 @@ jobs:
- name: Configure AWS credentials
if: contains(inputs.image-map, 'amazonaws.com/')
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: "${{ inputs.aws-region }}"
role-to-assume: "arn:aws:iam::${{ inputs.aws-account-id }}:role/${{ inputs.aws-role-to-assume }}"
@@ -67,7 +72,7 @@ jobs:
- name: Login to ECR
if: contains(inputs.image-map, 'amazonaws.com/')
uses: aws-actions/amazon-ecr-login@v2
uses: aws-actions/amazon-ecr-login@062b18b96a7aff071d4dc91bc00c4c1a7945b076 # v2.0.1
with:
registries: "${{ inputs.aws-account-id }}"
@@ -86,19 +91,31 @@ jobs:
- name: Login to GHCR
if: contains(inputs.image-map, 'ghcr.io/')
uses: docker/login-action@v3
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.repository_owner }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Log in to Docker Hub
uses: docker/login-action@v3
uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- name: Copy docker images to target registries
id: push
run: python3 .github/scripts/push_with_image_map.py
env:
IMAGE_MAP: ${{ inputs.image-map }}
- name: Notify Slack if container image pushing fails
if: steps.push.outputs.slack_notify == 'true' || failure()
uses: slackapi/slack-github-action@485a9d42d3a73031f12ec201c457e2162c45d02d # v2.0.0
with:
method: chat.postMessage
token: ${{ secrets.SLACK_BOT_TOKEN }}
payload: |
channel: ${{ vars.SLACK_ON_CALL_DEVPROD_STREAM }}
text: |
Pushing container images failed in <${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}|GitHub Run>

View File

@@ -26,8 +26,13 @@ jobs:
needs: [ check-permissions ]
runs-on: ubuntu-22.04
steps:
- uses: actions/checkout@v4
- uses: reviewdog/action-actionlint@v1
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: reviewdog/action-actionlint@a5524e1c19e62881d79c1f1b9b6f09f16356e281 # v1.65.2
env:
# SC2046 - Quote this to prevent word splitting. - https://www.shellcheck.net/wiki/SC2046
# SC2086 - Double quote to prevent globbing and word splitting. - https://www.shellcheck.net/wiki/SC2086

View File

@@ -47,6 +47,11 @@ jobs:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- run: gh pr --repo "${GITHUB_REPOSITORY}" edit "${PR_NUMBER}" --remove-label "approved-for-ci-run"
create-or-update-pr-for-ci-run:
@@ -63,9 +68,14 @@ jobs:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- run: gh pr --repo "${GITHUB_REPOSITORY}" edit "${PR_NUMBER}" --remove-label "approved-for-ci-run"
- uses: actions/checkout@v4
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ github.event.pull_request.head.sha }}
token: ${{ secrets.CI_ACCESS_TOKEN }}
@@ -153,6 +163,11 @@ jobs:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Close PR and delete `ci-run/pr-${{ env.PR_NUMBER }}` branch
run: |
CLOSED="$(gh pr --repo ${GITHUB_REPOSITORY} list --head ${BRANCH} --json 'closed' --jq '.[].closed')"

View File

@@ -87,17 +87,22 @@ jobs:
runs-on: ${{ matrix.RUNNER }}
container:
image: neondatabase/build-tools:pinned-bookworm
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials # necessary on Azure runners
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
@@ -164,7 +169,7 @@ jobs:
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: |
@@ -190,17 +195,22 @@ jobs:
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
@@ -245,17 +255,22 @@ jobs:
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
@@ -314,7 +329,7 @@ jobs:
# Post both success and failure to the Slack channel
- name: Post to a Slack channel
if: ${{ github.event.schedule && !cancelled() }}
uses: slackapi/slack-github-action@v1
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: "C06T9AMNDQQ" # on-call-compute-staging-stream
slack-message: |
@@ -346,13 +361,18 @@ jobs:
tpch-compare-matrix: ${{ steps.tpch-compare-matrix.outputs.matrix }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Generate matrix for pgbench benchmark
id: pgbench-compare-matrix
run: |
region_id_default=${{ env.DEFAULT_REGION_ID }}
runner_default='["self-hosted", "us-east-2", "x64"]'
runner_azure='["self-hosted", "eastus2", "x64"]'
image_default="neondatabase/build-tools:pinned-bookworm"
image_default="ghcr.io/neondatabase/build-tools:pinned-bookworm"
matrix='{
"pg_version" : [
16
@@ -368,18 +388,18 @@ jobs:
"db_size": [ "10gb" ],
"runner": ['"$runner_default"'],
"image": [ "'"$image_default"'" ],
"include": [{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new-many-tables","db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "azure-eastus2", "platform": "neonvm-azure-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_azure"', "image": "neondatabase/build-tools:pinned-bookworm" },
{ "pg_version": 16, "region_id": "azure-eastus2", "platform": "neonvm-azure-captest-new", "db_size": "10gb","runner": '"$runner_azure"', "image": "neondatabase/build-tools:pinned-bookworm" },
{ "pg_version": 16, "region_id": "azure-eastus2", "platform": "neonvm-azure-captest-new", "db_size": "50gb","runner": '"$runner_azure"', "image": "neondatabase/build-tools:pinned-bookworm" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-sharding-reuse", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new-many-tables","db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" }]
"include": [{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new-many-tables","db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 16, "region_id": "azure-eastus2", "platform": "neonvm-azure-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_azure"', "image": "ghcr.io/neondatabase/build-tools:pinned-bookworm" },
{ "pg_version": 16, "region_id": "azure-eastus2", "platform": "neonvm-azure-captest-new", "db_size": "10gb","runner": '"$runner_azure"', "image": "ghcr.io/neondatabase/build-tools:pinned-bookworm" },
{ "pg_version": 16, "region_id": "azure-eastus2", "platform": "neonvm-azure-captest-new", "db_size": "50gb","runner": '"$runner_azure"', "image": "ghcr.io/neondatabase/build-tools:pinned-bookworm" },
{ "pg_version": 16, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-sharding-reuse", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-freetier", "db_size": "3gb" ,"runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new-many-tables","db_size": "10gb","runner": '"$runner_default"', "image": "'"$image_default"'" },
{ "pg_version": 17, "region_id": "'"$region_id_default"'", "platform": "neonvm-captest-new", "db_size": "50gb","runner": '"$runner_default"', "image": "'"$image_default"'" }]
}'
if [ "$(date +%A)" = "Saturday" ] || [ ${RUN_AWS_RDS_AND_AURORA} = "true" ]; then
@@ -441,7 +461,7 @@ jobs:
strategy:
fail-fast: false
matrix: ${{fromJson(needs.generate-matrices.outputs.pgbench-compare-matrix)}}
matrix: ${{fromJSON(needs.generate-matrices.outputs.pgbench-compare-matrix)}}
env:
TEST_PG_BENCH_DURATIONS_MATRIX: "60m"
@@ -457,18 +477,23 @@ jobs:
container:
image: ${{ matrix.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
# Increase timeout to 8h, default timeout is 6h
timeout-minutes: 480
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
@@ -483,7 +508,7 @@ jobs:
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
- name: Create Neon Project
if: contains(fromJson('["neonvm-captest-new", "neonvm-captest-new-many-tables", "neonvm-captest-freetier", "neonvm-azure-captest-freetier", "neonvm-azure-captest-new"]'), matrix.platform)
if: contains(fromJSON('["neonvm-captest-new", "neonvm-captest-new-many-tables", "neonvm-captest-freetier", "neonvm-azure-captest-freetier", "neonvm-azure-captest-new"]'), matrix.platform)
id: create-neon-project
uses: ./.github/actions/neon-project-create
with:
@@ -523,7 +548,7 @@ jobs:
# without (neonvm-captest-new)
# and with (neonvm-captest-new-many-tables) many relations in the database
- name: Create many relations before the run
if: contains(fromJson('["neonvm-captest-new-many-tables"]'), matrix.platform)
if: contains(fromJSON('["neonvm-captest-new-many-tables"]'), matrix.platform)
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
@@ -600,7 +625,7 @@ jobs:
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: |
@@ -642,17 +667,22 @@ jobs:
runs-on: ${{ matrix.RUNNER }}
container:
image: neondatabase/build-tools:pinned-bookworm
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
@@ -726,7 +756,7 @@ jobs:
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: |
@@ -753,7 +783,7 @@ jobs:
strategy:
fail-fast: false
matrix: ${{ fromJson(needs.generate-matrices.outputs.olap-compare-matrix) }}
matrix: ${{ fromJSON(needs.generate-matrices.outputs.olap-compare-matrix) }}
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
@@ -767,10 +797,10 @@ jobs:
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
# Increase timeout to 12h, default timeout is 6h
@@ -778,10 +808,15 @@ jobs:
timeout-minutes: 720
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
@@ -854,7 +889,7 @@ jobs:
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: |
@@ -880,7 +915,7 @@ jobs:
strategy:
fail-fast: false
matrix: ${{ fromJson(needs.generate-matrices.outputs.tpch-compare-matrix) }}
matrix: ${{ fromJSON(needs.generate-matrices.outputs.tpch-compare-matrix) }}
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
@@ -892,17 +927,22 @@ jobs:
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
@@ -979,7 +1019,7 @@ jobs:
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: |
@@ -999,7 +1039,7 @@ jobs:
strategy:
fail-fast: false
matrix: ${{ fromJson(needs.generate-matrices.outputs.olap-compare-matrix) }}
matrix: ${{ fromJSON(needs.generate-matrices.outputs.olap-compare-matrix) }}
env:
POSTGRES_DISTRIB_DIR: /tmp/neon/pg_install
@@ -1011,17 +1051,22 @@ jobs:
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
@@ -1091,7 +1136,7 @@ jobs:
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: |

View File

@@ -19,7 +19,7 @@ on:
value: ${{ jobs.check-image.outputs.tag }}
image:
description: "build-tools image"
value: neondatabase/build-tools:${{ jobs.check-image.outputs.tag }}
value: ghcr.io/neondatabase/build-tools:${{ jobs.check-image.outputs.tag }}
defaults:
run:
@@ -49,8 +49,22 @@ jobs:
everything: ${{ steps.set-more-variables.outputs.everything }}
found: ${{ steps.set-more-variables.outputs.found }}
permissions:
packages: read
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Set variables
id: set-variables
@@ -70,12 +84,12 @@ jobs:
env:
IMAGE_TAG: ${{ steps.set-variables.outputs.image-tag }}
EVERYTHING: |
${{ contains(fromJson(steps.set-variables.outputs.archs), 'x64') &&
contains(fromJson(steps.set-variables.outputs.archs), 'arm64') &&
contains(fromJson(steps.set-variables.outputs.debians), 'bullseye') &&
contains(fromJson(steps.set-variables.outputs.debians), 'bookworm') }}
${{ contains(fromJSON(steps.set-variables.outputs.archs), 'x64') &&
contains(fromJSON(steps.set-variables.outputs.archs), 'arm64') &&
contains(fromJSON(steps.set-variables.outputs.debians), 'bullseye') &&
contains(fromJSON(steps.set-variables.outputs.debians), 'bookworm') }}
run: |
if docker manifest inspect neondatabase/build-tools:${IMAGE_TAG}; then
if docker manifest inspect ghcr.io/neondatabase/build-tools:${IMAGE_TAG}; then
found=true
else
found=false
@@ -90,31 +104,45 @@ jobs:
strategy:
matrix:
arch: ${{ fromJson(needs.check-image.outputs.archs) }}
debian: ${{ fromJson(needs.check-image.outputs.debians) }}
arch: ${{ fromJSON(needs.check-image.outputs.archs) }}
debian: ${{ fromJSON(needs.check-image.outputs.debians) }}
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
permissions:
packages: write
runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: docker/setup-buildx-action@v3
- uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
with:
cache-binary: false
- uses: docker/login-action@v3
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- uses: docker/login-action@v3
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: cache.neon.build
username: ${{ secrets.NEON_CI_DOCKERCACHE_USERNAME }}
password: ${{ secrets.NEON_CI_DOCKERCACHE_PASSWORD }}
- uses: docker/build-push-action@v6
- uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
file: build-tools.Dockerfile
context: .
@@ -126,35 +154,49 @@ jobs:
cache-from: type=registry,ref=cache.neon.build/build-tools:cache-${{ matrix.debian }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/build-tools:cache-{0}-{1},mode=max', matrix.debian, matrix.arch) || '' }}
tags: |
neondatabase/build-tools:${{ needs.check-image.outputs.tag }}-${{ matrix.debian }}-${{ matrix.arch }}
ghcr.io/neondatabase/build-tools:${{ needs.check-image.outputs.tag }}-${{ matrix.debian }}-${{ matrix.arch }}
merge-images:
needs: [ check-image, build-image ]
runs-on: ubuntu-22.04
permissions:
packages: write
steps:
- uses: docker/login-action@v3
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Create multi-arch image
env:
DEFAULT_DEBIAN_VERSION: bookworm
ARCHS: ${{ join(fromJson(needs.check-image.outputs.archs), ' ') }}
DEBIANS: ${{ join(fromJson(needs.check-image.outputs.debians), ' ') }}
ARCHS: ${{ join(fromJSON(needs.check-image.outputs.archs), ' ') }}
DEBIANS: ${{ join(fromJSON(needs.check-image.outputs.debians), ' ') }}
EVERYTHING: ${{ needs.check-image.outputs.everything }}
IMAGE_TAG: ${{ needs.check-image.outputs.tag }}
run: |
for debian in ${DEBIANS}; do
tags=("-t" "neondatabase/build-tools:${IMAGE_TAG}-${debian}")
tags=("-t" "ghcr.io/neondatabase/build-tools:${IMAGE_TAG}-${debian}")
if [ "${EVERYTHING}" == "true" ] && [ "${debian}" == "${DEFAULT_DEBIAN_VERSION}" ]; then
tags+=("-t" "neondatabase/build-tools:${IMAGE_TAG}")
tags+=("-t" "ghcr.io/neondatabase/build-tools:${IMAGE_TAG}")
fi
for arch in ${ARCHS}; do
tags+=("neondatabase/build-tools:${IMAGE_TAG}-${debian}-${arch}")
tags+=("ghcr.io/neondatabase/build-tools:${IMAGE_TAG}-${debian}-${arch}")
done
docker buildx imagetools create "${tags[@]}"

View File

@@ -28,6 +28,9 @@ env:
# - You can connect up to four levels of workflows
# - You can call a maximum of 20 unique reusable workflows from a single workflow file.
# https://docs.github.com/en/actions/sharing-automations/reusing-workflows#limitations
permissions:
contents: read
jobs:
build-pgxn:
if: |
@@ -40,14 +43,19 @@ jobs:
runs-on: macos-15
strategy:
matrix:
postgres-version: ${{ inputs.rebuild_everything && fromJson('["v14", "v15", "v16", "v17"]') || fromJSON(inputs.pg_versions) }}
postgres-version: ${{ inputs.rebuild_everything && fromJSON('["v14", "v15", "v16", "v17"]') || fromJSON(inputs.pg_versions) }}
env:
# Use release build only, to have less debug info around
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout main repo
uses: actions/checkout@v4
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set pg ${{ matrix.postgres-version }} for caching
id: pg_rev
@@ -55,8 +63,13 @@ jobs:
- name: Cache postgres ${{ matrix.postgres-version }} build
id: cache_pg
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/${{ matrix.postgres-version }}
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-${{ matrix.postgres-version }}-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
@@ -107,8 +120,13 @@ jobs:
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout main repo
uses: actions/checkout@v4
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Set pg v17 for caching
id: pg_rev
@@ -116,15 +134,25 @@ jobs:
- name: Cache postgres v17 build
id: cache_pg
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v17-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache walproposer-lib
id: cache_walproposer_lib
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/build/walproposer-lib
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-walproposer_lib-v17-${{ steps.pg_rev.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
@@ -165,8 +193,13 @@ jobs:
# Hence keeping target/ (and general cache size) smaller
BUILD_TYPE: release
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout main repo
uses: actions/checkout@v4
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
@@ -185,32 +218,57 @@ jobs:
- name: Cache postgres v14 build
id: cache_pg
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v14
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v14-${{ steps.pg_rev_v14.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v15 build
id: cache_pg_v15
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v15
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v15-${{ steps.pg_rev_v15.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v16 build
id: cache_pg_v16
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v16
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v16-${{ steps.pg_rev_v16.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache postgres v17 build
id: cache_pg_v17
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/v17
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-pg-v17-${{ steps.pg_rev_v17.outputs.pg_rev }}-${{ hashFiles('Makefile') }}
- name: Cache cargo deps (only for v17)
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: |
~/.cargo/registry
!~/.cargo/registry/src
@@ -220,8 +278,13 @@ jobs:
- name: Cache walproposer-lib
id: cache_walproposer_lib
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: pg_install/build/walproposer-lib
key: v1-${{ runner.os }}-${{ runner.arch }}-${{ env.BUILD_TYPE }}-walproposer_lib-v17-${{ steps.pg_rev_v17.outputs.pg_rev }}-${{ hashFiles('Makefile') }}

View File

@@ -37,6 +37,11 @@ jobs:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Cancel previous e2e-tests runs for this PR
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
@@ -53,8 +58,13 @@ jobs:
check-rust-dependencies: ${{ steps.files-changed.outputs.rust_dependencies }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
@@ -70,6 +80,7 @@ jobs:
uses: ./.github/workflows/_meta.yml
with:
github-event-name: ${{ github.event_name }}
github-event-json: ${{ toJSON(github.event) }}
build-build-tools-image:
needs: [ check-permissions ]
@@ -77,25 +88,34 @@ jobs:
secrets: inherit
check-codestyle-python:
needs: [ check-permissions, build-build-tools-image ]
needs: [ meta, check-permissions, build-build-tools-image ]
# No need to run on `main` because we this in the merge queue. We do need to run this in `.*-rc-pr` because of hotfixes.
if: ${{ contains(fromJSON('["pr", "storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
uses: ./.github/workflows/_check-codestyle-python.yml
with:
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
secrets: inherit
check-codestyle-jsonnet:
needs: [ check-permissions, build-build-tools-image ]
needs: [ meta, check-permissions, build-build-tools-image ]
# We do need to run this in `.*-rc-pr` because of hotfixes.
if: ${{ contains(fromJSON('["pr", "push-main", "storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
runs-on: [ self-hosted, small ]
container:
image: ${{ needs.build-build-tools-image.outputs.image }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Check Jsonnet code formatting
run: |
@@ -107,12 +127,17 @@ jobs:
needs: [ check-permissions ]
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
- uses: dorny/paths-filter@v3
- uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36 # v3.0.2
id: check-if-submodules-changed
with:
filters: |
@@ -121,7 +146,7 @@ jobs:
- name: Check vendor/postgres-v14 submodule reference
if: steps.check-if-submodules-changed.outputs.vendor == 'true'
uses: jtmullen/submodule-branch-check-action@v1
uses: jtmullen/submodule-branch-check-action@ab0d3a69278e3fa0a2d4f3be3199d2514b676e13 # v1.3.0
with:
path: "vendor/postgres-v14"
fetch_depth: "50"
@@ -130,7 +155,7 @@ jobs:
- name: Check vendor/postgres-v15 submodule reference
if: steps.check-if-submodules-changed.outputs.vendor == 'true'
uses: jtmullen/submodule-branch-check-action@v1
uses: jtmullen/submodule-branch-check-action@ab0d3a69278e3fa0a2d4f3be3199d2514b676e13 # v1.3.0
with:
path: "vendor/postgres-v15"
fetch_depth: "50"
@@ -139,7 +164,7 @@ jobs:
- name: Check vendor/postgres-v16 submodule reference
if: steps.check-if-submodules-changed.outputs.vendor == 'true'
uses: jtmullen/submodule-branch-check-action@v1
uses: jtmullen/submodule-branch-check-action@ab0d3a69278e3fa0a2d4f3be3199d2514b676e13 # v1.3.0
with:
path: "vendor/postgres-v16"
fetch_depth: "50"
@@ -148,7 +173,7 @@ jobs:
- name: Check vendor/postgres-v17 submodule reference
if: steps.check-if-submodules-changed.outputs.vendor == 'true'
uses: jtmullen/submodule-branch-check-action@v1
uses: jtmullen/submodule-branch-check-action@ab0d3a69278e3fa0a2d4f3be3199d2514b676e13 # v1.3.0
with:
path: "vendor/postgres-v17"
fetch_depth: "50"
@@ -156,7 +181,9 @@ jobs:
pass_if_unchanged: true
check-codestyle-rust:
needs: [ check-permissions, build-build-tools-image ]
needs: [ meta, check-permissions, build-build-tools-image ]
# No need to run on `main` because we this in the merge queue. We do need to run this in `.*-rc-pr` because of hotfixes.
if: ${{ contains(fromJSON('["pr", "storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
uses: ./.github/workflows/_check-codestyle-rust.yml
with:
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
@@ -164,8 +191,9 @@ jobs:
secrets: inherit
check-dependencies-rust:
needs: [ files-changed, build-build-tools-image ]
if: ${{ needs.files-changed.outputs.check-rust-dependencies == 'true' }}
needs: [ meta, files-changed, build-build-tools-image ]
# No need to run on `main` because we this in the merge queue. We do need to run this in `.*-rc-pr` because of hotfixes.
if: ${{ needs.files-changed.outputs.check-rust-dependencies == 'true' && contains(fromJSON('["pr", "storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
uses: ./.github/workflows/cargo-deny.yml
with:
build-tools-image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
@@ -173,12 +201,14 @@ jobs:
build-and-test-locally:
needs: [ meta, build-build-tools-image ]
# We do need to run this in `.*-rc-pr` because of hotfixes.
if: ${{ contains(fromJSON('["pr", "push-main", "storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
strategy:
fail-fast: false
matrix:
arch: [ x64, arm64 ]
# Do not build or run tests in debug for release branches
build-type: ${{ fromJson((startsWith(github.ref_name, 'release') && github.event_name == 'push') && '["release"]' || '["debug", "release"]') }}
build-type: ${{ fromJSON((startsWith(github.ref_name, 'release') && github.event_name == 'push') && '["release"]' || '["debug", "release"]') }}
include:
- build-type: release
arch: arm64
@@ -209,16 +239,26 @@ jobs:
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Cache poetry deps
uses: actions/cache@v4
uses: tespkg/actions-cache@b7bf5fcc2f98a52ac6080eb0fd282c2f752074b1 # v1.8.0
with:
endpoint: ${{ vars.HETZNER_CACHE_REGION }}.${{ vars.HETZNER_CACHE_ENDPOINT }}
bucket: ${{ vars.HETZNER_CACHE_BUCKET }}
accessKey: ${{ secrets.HETZNER_CACHE_ACCESS_KEY }}
secretKey: ${{ secrets.HETZNER_CACHE_SECRET_KEY }}
use-fallback: false
path: ~/.cache/pypoetry/virtualenvs
key: v2-${{ runner.os }}-${{ runner.arch }}-python-deps-bookworm-${{ hashFiles('poetry.lock') }}
@@ -248,8 +288,8 @@ jobs:
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
# for changed limits, see comments on `options:` earlier in this file
options: --init --shm-size=512mb --ulimit memlock=67108864:67108864
strategy:
@@ -259,8 +299,13 @@ jobs:
pytest_split_group: [ 1, 2, 3, 4, 5 ]
build_type: [ release ]
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Pytest benchmarks
uses: ./.github/actions/run-python-test-set
@@ -288,7 +333,12 @@ jobs:
runs-on: ubuntu-22.04
steps:
- uses: slackapi/slack-github-action@v2
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: slackapi/slack-github-action@485a9d42d3a73031f12ec201c457e2162c45d02d # v2.0.0
with:
method: chat.postMessage
token: ${{ secrets.SLACK_BOT_TOKEN }}
@@ -314,12 +364,17 @@ jobs:
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Create Allure report
if: ${{ !cancelled() }}
@@ -331,7 +386,7 @@ jobs:
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
- uses: actions/github-script@v7
- uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
if: ${{ !cancelled() }}
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
@@ -367,8 +422,8 @@ jobs:
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
strategy:
fail-fast: false
@@ -379,7 +434,12 @@ jobs:
coverage-json: ${{ steps.upload-coverage-report-new.outputs.summary-json }}
steps:
# Need `fetch-depth: 0` for differential coverage (to get diff between two commits)
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
fetch-depth: 0
@@ -450,7 +510,7 @@ jobs:
REPORT_URL=https://${BUCKET}.s3.amazonaws.com/code-coverage/${COMMIT_SHA}/lcov/summary.json
echo "summary-json=${REPORT_URL}" >> $GITHUB_OUTPUT
- uses: actions/github-script@v7
- uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
env:
REPORT_URL_NEW: ${{ steps.upload-coverage-report-new.outputs.report-url }}
COMMIT_SHA: ${{ github.event.pull_request.head.sha || github.sha }}
@@ -470,19 +530,26 @@ jobs:
})
trigger-e2e-tests:
# Depends on jobs that can get skipped
# !failure() && !cancelled() because it depends on jobs that can get skipped
if: >-
${{
(
!github.event.pull_request.draft
|| contains( github.event.pull_request.labels.*.name, 'run-e2e-tests-in-draft')
|| needs.meta.outputs.run-kind == 'push-main'
) && !failure() && !cancelled()
(
needs.meta.outputs.run-kind == 'pr'
&& (
!github.event.pull_request.draft
|| contains(github.event.pull_request.labels.*.name, 'run-e2e-tests-in-draft')
)
)
|| contains(fromJSON('["push-main", "storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind)
)
&& !failure() && !cancelled()
}}
needs: [ check-permissions, push-neon-image-dev, push-compute-image-dev, meta ]
uses: ./.github/workflows/trigger-e2e-tests.yml
with:
github-event-name: ${{ github.event_name }}
github-event-json: ${{ toJSON(github.event) }}
secrets: inherit
neon-image-arch:
@@ -492,30 +559,45 @@ jobs:
matrix:
arch: [ x64, arm64 ]
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
permissions:
packages: write
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
ref: ${{ needs.meta.outputs.sha }}
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: docker/setup-buildx-action@v3
- uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
with:
cache-binary: false
- uses: docker/login-action@v3
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- uses: docker/login-action@v3
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: cache.neon.build
username: ${{ secrets.NEON_CI_DOCKERCACHE_USERNAME }}
password: ${{ secrets.NEON_CI_DOCKERCACHE_PASSWORD }}
- uses: docker/build-push-action@v6
- uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
context: .
# ARM-specific flags are recommended for Graviton ≥ 2, these flags are also supported by Ampere Altra (Azure)
@@ -523,7 +605,7 @@ jobs:
build-args: |
ADDITIONAL_RUSTFLAGS=${{ matrix.arch == 'arm64' && '-Ctarget-feature=+lse -Ctarget-cpu=neoverse-n1' || '' }}
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
BUILD_TAG=${{ needs.meta.outputs.build-tag }}
BUILD_TAG=${{ needs.meta.outputs.release-tag || needs.meta.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-bookworm
DEBIAN_VERSION=bookworm
provenance: false
@@ -533,7 +615,7 @@ jobs:
cache-from: type=registry,ref=cache.neon.build/neon:cache-bookworm-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/neon:cache-{0}-{1},mode=max', 'bookworm', matrix.arch) || '' }}
tags: |
neondatabase/neon:${{ needs.meta.outputs.build-tag }}-bookworm-${{ matrix.arch }}
ghcr.io/neondatabase/neon:${{ needs.meta.outputs.build-tag }}-bookworm-${{ matrix.arch }}
neon-image:
needs: [ neon-image-arch, meta ]
@@ -543,19 +625,26 @@ jobs:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
packages: write
steps:
- uses: docker/login-action@v3
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
egress-policy: audit
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Create multi-arch image
run: |
docker buildx imagetools create -t neondatabase/neon:${{ needs.meta.outputs.build-tag }} \
-t neondatabase/neon:${{ needs.meta.outputs.build-tag }}-bookworm \
neondatabase/neon:${{ needs.meta.outputs.build-tag }}-bookworm-x64 \
neondatabase/neon:${{ needs.meta.outputs.build-tag }}-bookworm-arm64
docker buildx imagetools create -t ghcr.io/neondatabase/neon:${{ needs.meta.outputs.build-tag }} \
-t ghcr.io/neondatabase/neon:${{ needs.meta.outputs.build-tag }}-bookworm \
ghcr.io/neondatabase/neon:${{ needs.meta.outputs.build-tag }}-bookworm-x64 \
ghcr.io/neondatabase/neon:${{ needs.meta.outputs.build-tag }}-bookworm-arm64
compute-node-image-arch:
needs: [ check-permissions, build-build-tools-image, meta ]
@@ -564,6 +653,7 @@ jobs:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
packages: write
strategy:
fail-fast: false
matrix:
@@ -582,15 +672,21 @@ jobs:
debian: bookworm
arch: [ x64, arm64 ]
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
ref: ${{ needs.meta.outputs.sha }}
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: docker/setup-buildx-action@v3
- uses: docker/setup-buildx-action@b5ca514318bd6ebac0fb2aedd5d36ec1b5c232a2 # v3.10.0
with:
cache-binary: false
# Disable parallelism for docker buildkit.
@@ -599,25 +695,31 @@ jobs:
[worker.oci]
max-parallelism = 1
- uses: docker/login-action@v3
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
- uses: docker/login-action@v3
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: cache.neon.build
username: ${{ secrets.NEON_CI_DOCKERCACHE_USERNAME }}
password: ${{ secrets.NEON_CI_DOCKERCACHE_PASSWORD }}
- name: Build compute-node image
uses: docker/build-push-action@v6
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
context: .
build-args: |
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
PG_VERSION=${{ matrix.version.pg }}
BUILD_TAG=${{ needs.meta.outputs.build-tag }}
BUILD_TAG=${{ needs.meta.outputs.release-tag || needs.meta.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
DEBIAN_VERSION=${{ matrix.version.debian }}
provenance: false
@@ -627,17 +729,17 @@ jobs:
cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
cache-to: ${{ github.ref_name == 'main' && format('type=registry,ref=cache.neon.build/compute-node-{0}:cache-{1}-{2},mode=max', matrix.version.pg, matrix.version.debian, matrix.arch) || '' }}
tags: |
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }}-${{ matrix.arch }}
ghcr.io/neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }}-${{ matrix.arch }}
- name: Build neon extensions test image
if: matrix.version.pg >= 'v16'
uses: docker/build-push-action@v6
uses: docker/build-push-action@471d1dc4e07e5cdedd4c2171150001c434f0b7a4 # v6.15.0
with:
context: .
build-args: |
GIT_VERSION=${{ github.event.pull_request.head.sha || github.sha }}
PG_VERSION=${{ matrix.version.pg }}
BUILD_TAG=${{ needs.meta.outputs.build-tag }}
BUILD_TAG=${{ needs.meta.outputs.release-tag || needs.meta.outputs.build-tag }}
TAG=${{ needs.build-build-tools-image.outputs.image-tag }}-${{ matrix.version.debian }}
DEBIAN_VERSION=${{ matrix.version.debian }}
provenance: false
@@ -647,7 +749,7 @@ jobs:
target: extension-tests
cache-from: type=registry,ref=cache.neon.build/compute-node-${{ matrix.version.pg }}:cache-${{ matrix.version.debian }}-${{ matrix.arch }}
tags: |
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{needs.meta.outputs.build-tag}}-${{ matrix.version.debian }}-${{ matrix.arch }}
ghcr.io/neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{needs.meta.outputs.build-tag}}-${{ matrix.version.debian }}-${{ matrix.arch }}
compute-node-image:
needs: [ compute-node-image-arch, meta ]
@@ -656,6 +758,7 @@ jobs:
id-token: write # aws-actions/configure-aws-credentials
statuses: write
contents: read
packages: write
runs-on: ubuntu-22.04
strategy:
@@ -672,30 +775,39 @@ jobs:
debian: bookworm
steps:
- uses: docker/login-action@v3
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
egress-policy: audit
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Create multi-arch compute-node image
run: |
docker buildx imagetools create -t neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }} \
-t neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }} \
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
docker buildx imagetools create -t ghcr.io/neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }} \
-t ghcr.io/neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }} \
ghcr.io/neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
ghcr.io/neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
- name: Create multi-arch neon-test-extensions image
if: matrix.version.pg >= 'v16'
run: |
docker buildx imagetools create -t neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }} \
-t neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }} \
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
docker buildx imagetools create -t ghcr.io/neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }} \
-t ghcr.io/neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }} \
ghcr.io/neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }}-x64 \
ghcr.io/neondatabase/neon-test-extensions-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.version.debian }}-arm64
vm-compute-node-image-arch:
needs: [ check-permissions, meta, compute-node-image ]
if: ${{ contains(fromJSON('["push-main", "pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'large-arm64' || 'large')) }}
permissions:
contents: read
packages: write
strategy:
fail-fast: false
matrix:
@@ -713,7 +825,12 @@ jobs:
VM_BUILDER_VERSION: v0.42.2
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Downloading vm-builder
run: |
@@ -721,33 +838,36 @@ jobs:
chmod +x vm-builder
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: docker/login-action@v3
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
# Note: we need a separate pull step here because otherwise vm-builder will try to pull, and
# it won't have the proper authentication (written at v0.6.0)
- name: Pulling compute-node image
run: |
docker pull neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}
docker pull ghcr.io/neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}
- name: Build vm image
run: |
./vm-builder \
-size=2G \
-spec=compute/vm-image-spec-${{ matrix.version.debian }}.yaml \
-src=neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }} \
-dst=neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.arch }} \
-src=ghcr.io/neondatabase/compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }} \
-dst=ghcr.io/neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.arch }} \
-target-arch=linux/${{ matrix.arch }}
- name: Pushing vm-compute-node image
run: |
docker push neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.arch }}
docker push ghcr.io/neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-${{ matrix.arch }}
vm-compute-node-image:
needs: [ vm-compute-node-image-arch, meta ]
if: ${{ contains(fromJSON('["push-main", "pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
permissions:
packages: write
runs-on: ubuntu-22.04
strategy:
matrix:
@@ -758,16 +878,22 @@ jobs:
- pg: v16
- pg: v17
steps:
- uses: docker/login-action@v3
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
egress-policy: audit
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Create multi-arch compute-node image
run: |
docker buildx imagetools create -t neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }} \
neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-amd64 \
neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-arm64
docker buildx imagetools create -t ghcr.io/neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }} \
ghcr.io/neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-amd64 \
ghcr.io/neondatabase/vm-compute-node-${{ matrix.version.pg }}:${{ needs.meta.outputs.build-tag }}-arm64
test-images:
@@ -785,18 +911,33 @@ jobs:
arch: [ x64, arm64 ]
pg_version: [v16, v17]
runs-on: ${{ fromJson(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'small-arm64' || 'small')) }}
permissions:
packages: read
runs-on: ${{ fromJSON(format('["self-hosted", "{0}"]', matrix.arch == 'arm64' && 'small-arm64' || 'small')) }}
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: neondatabase/dev-actions/set-docker-config-dir@6094485bf440001c94a94a3f9e221e81ff6b6193
- uses: docker/login-action@v3
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
# `neondatabase/neon` contains multiple binaries, all of them use the same input for the version into the same version formatting library.
- uses: docker/login-action@74a5d142397b4f367a81961eba4e8cd7edddf772 # v3.4.0
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
# `ghcr.io/neondatabase/neon` contains multiple binaries, all of them use the same input for the version into the same version formatting library.
# Pick pageserver as currently the only binary with extra "version" features printed in the string to verify.
# Regular pageserver version string looks like
# Neon page server git-env:32d14403bd6ab4f4520a94cbfd81a6acef7a526c failpoints: true, features: []
@@ -807,7 +948,7 @@ jobs:
shell: bash # ensure no set -e for better error messages
if: ${{ contains(fromJSON('["push-main", "pr", "storage-rc-pr", "proxy-rc-pr"]'), needs.meta.outputs.run-kind) }}
run: |
pageserver_version=$(docker run --rm neondatabase/neon:${{ needs.meta.outputs.build-tag }} "/bin/sh" "-c" "/usr/local/bin/pageserver --version")
pageserver_version=$(docker run --rm ghcr.io/neondatabase/neon:${{ needs.meta.outputs.build-tag }} "/bin/sh" "-c" "/usr/local/bin/pageserver --version")
echo "Pageserver version string: $pageserver_version"
@@ -839,7 +980,7 @@ jobs:
TEST_EXTENSIONS_TAG: >-
${{
contains(fromJSON('["storage-rc-pr", "proxy-rc-pr"]'), needs.meta.outputs.run-kind)
&& 'latest'
&& needs.meta.outputs.previous-compute-release
|| needs.meta.outputs.build-tag
}}
TEST_VERSION_ONLY: ${{ matrix.pg_version }}
@@ -881,7 +1022,12 @@ jobs:
compute-dev: ${{ steps.generate.outputs.compute-dev }}
compute-prod: ${{ steps.generate.outputs.compute-prod }}
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
sparse-checkout: .github/scripts/generate_image_maps.py
sparse-checkout-cone-mode: false
@@ -892,7 +1038,7 @@ jobs:
env:
SOURCE_TAG: >-
${{
contains(fromJson('["storage-release", "compute-release", "proxy-release"]'), needs.meta.outputs.run-kind)
contains(fromJSON('["storage-release", "compute-release", "proxy-release"]'), needs.meta.outputs.run-kind)
&& needs.meta.outputs.release-pr-run-id
|| needs.meta.outputs.build-tag
}}
@@ -978,16 +1124,64 @@ jobs:
acr-registry-name: ${{ vars.AZURE_PROD_REGISTRY_NAME }}
secrets: inherit
# This is a bit of a special case so we're not using a generated image map.
add-latest-tag-to-neon-extensions-test-image:
if: github.ref_name == 'main'
push-neon-test-extensions-image-dockerhub:
if: ${{ contains(fromJSON('["push-main", "pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind) }}
needs: [ meta, compute-node-image ]
uses: ./.github/workflows/_push-to-container-registry.yml
permissions:
packages: write
id-token: write
with:
image-map: |
{
"docker.io/neondatabase/neon-test-extensions-v16:${{ needs.meta.outputs.build-tag }}": ["docker.io/neondatabase/neon-test-extensions-v16:latest"],
"docker.io/neondatabase/neon-test-extensions-v17:${{ needs.meta.outputs.build-tag }}": ["docker.io/neondatabase/neon-test-extensions-v17:latest"]
"ghcr.io/neondatabase/neon-test-extensions-v16:${{ needs.meta.outputs.build-tag }}": [
"docker.io/neondatabase/neon-test-extensions-v16:${{ needs.meta.outputs.build-tag }}"
],
"ghcr.io/neondatabase/neon-test-extensions-v17:${{ needs.meta.outputs.build-tag }}": [
"docker.io/neondatabase/neon-test-extensions-v17:${{ needs.meta.outputs.build-tag }}"
]
}
secrets: inherit
add-latest-tag-to-neon-test-extensions-image:
if: ${{ needs.meta.outputs.run-kind == 'push-main' }}
needs: [ meta, compute-node-image ]
uses: ./.github/workflows/_push-to-container-registry.yml
permissions:
packages: write
id-token: write
with:
image-map: |
{
"ghcr.io/neondatabase/neon-test-extensions-v16:${{ needs.meta.outputs.build-tag }}": [
"docker.io/neondatabase/neon-test-extensions-v16:latest",
"ghcr.io/neondatabase/neon-test-extensions-v16:latest"
],
"ghcr.io/neondatabase/neon-test-extensions-v17:${{ needs.meta.outputs.build-tag }}": [
"docker.io/neondatabase/neon-test-extensions-v17:latest",
"ghcr.io/neondatabase/neon-test-extensions-v17:latest"
]
}
secrets: inherit
add-release-tag-to-neon-test-extensions-image:
if: ${{ needs.meta.outputs.run-kind == 'compute-release' }}
needs: [ meta ]
uses: ./.github/workflows/_push-to-container-registry.yml
permissions:
packages: write
id-token: write
with:
image-map: |
{
"ghcr.io/neondatabase/neon-test-extensions-v16:${{ needs.meta.outputs.release-pr-run-id }}": [
"docker.io/neondatabase/neon-test-extensions-v16:${{ needs.meta.outputs.build-tag }}",
"ghcr.io/neondatabase/neon-test-extensions-v16:${{ needs.meta.outputs.build-tag }}"
],
"ghcr.io/neondatabase/neon-test-extensions-v17:${{ needs.meta.outputs.release-pr-run-id }}": [
"docker.io/neondatabase/neon-test-extensions-v17:${{ needs.meta.outputs.build-tag }}",
"ghcr.io/neondatabase/neon-test-extensions-v17:${{ needs.meta.outputs.build-tag }}"
]
}
secrets: inherit
@@ -1001,6 +1195,11 @@ jobs:
contents: write
pull-requests: write
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Set PR's status to pending and request a remote CI test
run: |
COMMIT_SHA=${{ github.event.pull_request.head.sha || github.sha }}
@@ -1082,11 +1281,16 @@ jobs:
runs-on: [ self-hosted, small ]
container: ${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/ansible:latest
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Create git tag and GitHub release
if: ${{ contains(fromJSON('["storage-release", "proxy-release", "compute-release"]'), needs.meta.outputs.run-kind) }}
uses: actions/github-script@v7
uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
env:
TAG: "${{ needs.meta.outputs.build-tag }}"
BRANCH: "${{ github.ref_name }}"
@@ -1234,8 +1438,13 @@ jobs:
if: github.ref_name == 'release' && needs.deploy.result != 'success' && always()
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Post release-deploy failure to team-storage slack channel
uses: slackapi/slack-github-action@v2
uses: slackapi/slack-github-action@485a9d42d3a73031f12ec201c457e2162c45d02d # v2.0.0
with:
method: chat.postMessage
token: ${{ secrets.SLACK_BOT_TOKEN }}
@@ -1256,7 +1465,12 @@ jobs:
runs-on: ubuntu-22.04
steps:
- uses: aws-actions/configure-aws-credentials@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
@@ -1344,15 +1558,20 @@ jobs:
steps:
# The list of possible results:
# https://docs.github.com/en/actions/learn-github-actions/contexts#needs-context
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Fail the job if any of the dependencies do not succeed
run: exit 1
if: |
contains(needs.*.result, 'failure')
|| contains(needs.*.result, 'cancelled')
|| (needs.check-dependencies-rust.result == 'skipped' && needs.files-changed.outputs.check-rust-dependencies == 'true')
|| needs.build-and-test-locally.result == 'skipped'
|| needs.check-codestyle-python.result == 'skipped'
|| needs.check-codestyle-rust.result == 'skipped'
|| (needs.check-dependencies-rust.result == 'skipped' && needs.files-changed.outputs.check-rust-dependencies == 'true' && contains(fromJSON('["pr", "storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind))
|| (needs.build-and-test-locally.result == 'skipped' && contains(fromJSON('["pr", "push-main", "storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind))
|| (needs.check-codestyle-python.result == 'skipped' && contains(fromJSON('["pr", "storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind))
|| (needs.check-codestyle-rust.result == 'skipped' && contains(fromJSON('["pr", "storage-rc-pr", "proxy-rc-pr", "compute-rc-pr"]'), needs.meta.outputs.run-kind))
|| needs.files-changed.result == 'skipped'
|| (needs.push-compute-image-dev.result == 'skipped' && contains(fromJSON('["push-main", "pr", "compute-release", "compute-rc-pr"]'), needs.meta.outputs.run-kind))
|| (needs.push-neon-image-dev.result == 'skipped' && contains(fromJSON('["push-main", "pr", "storage-release", "storage-rc-pr", "proxy-release", "proxy-rc-pr"]'), needs.meta.outputs.run-kind))

View File

@@ -33,7 +33,12 @@ jobs:
steps:
# Need `fetch-depth: 0` to count the number of commits in the branch
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0
@@ -94,12 +99,17 @@ jobs:
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Create Allure report
if: ${{ !cancelled() }}
@@ -111,7 +121,7 @@ jobs:
env:
REGRESS_TEST_RESULT_CONNSTR_NEW: ${{ secrets.REGRESS_TEST_RESULT_CONNSTR_NEW }}
- uses: actions/github-script@v7
- uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
if: ${{ !cancelled() }}
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries

View File

@@ -9,6 +9,9 @@ on:
schedule:
- cron: '0 10 * * *'
permissions:
contents: read
jobs:
cargo-deny:
strategy:
@@ -24,16 +27,24 @@ jobs:
runs-on: [self-hosted, small]
permissions:
packages: read
container:
image: ${{ inputs.build-tools-image || 'neondatabase/build-tools:pinned' }}
image: ${{ inputs.build-tools-image || 'ghcr.io/neondatabase/build-tools:pinned' }}
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ matrix.ref }}
@@ -45,7 +56,7 @@ jobs:
- name: Post to a Slack channel
if: ${{ github.event_name == 'schedule' && failure() }}
uses: slackapi/slack-github-action@v2
uses: slackapi/slack-github-action@485a9d42d3a73031f12ec201c457e2162c45d02d # v2.0.0
with:
method: chat.postMessage
token: ${{ secrets.SLACK_BOT_TOKEN }}

View File

@@ -18,6 +18,11 @@ jobs:
check-permissions:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@v2
with:
egress-policy: audit
- name: Disallow CI runs on PRs from forks
if: |
inputs.github-event-name == 'pull_request' &&

View File

@@ -11,6 +11,11 @@ jobs:
cleanup:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@v2
with:
egress-policy: audit
- name: Cleanup
run: |
gh extension install actions/gh-actions-cache

View File

@@ -37,14 +37,19 @@ jobs:
runs-on: us-east-2
container:
image: neondatabase/build-tools:pinned-bookworm
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
@@ -121,7 +126,7 @@ jobs:
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: ${{ vars.SLACK_ON_CALL_QA_STAGING_STREAM }}
slack-message: |

View File

@@ -13,6 +13,11 @@ jobs:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@v2
with:
egress-policy: audit
- name: Remove fast-forward label to PR
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}

View File

@@ -34,7 +34,12 @@ jobs:
runs-on: small
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: false
@@ -50,7 +55,7 @@ jobs:
echo tag=${tag} >> ${GITHUB_OUTPUT}
- name: Test extension upgrade
timeout-minutes: 20
timeout-minutes: 60
env:
NEW_COMPUTE_TAG: latest
OLD_COMPUTE_TAG: ${{ steps.get-last-compute-release-tag.outputs.tag }}
@@ -67,7 +72,7 @@ jobs:
- name: Post to the Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: ${{ vars.SLACK_ON_CALL_QA_STAGING_STREAM }}
slack-message: |

View File

@@ -23,6 +23,9 @@ concurrency:
group: ingest-bench-workflow
cancel-in-progress: true
permissions:
contents: read
jobs:
ingest:
strategy:
@@ -67,18 +70,23 @@ jobs:
PGCOPYDB_LIB_PATH: /pgcopydb/lib
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
timeout-minutes: 1440
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials # necessary to download artefacts
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}

View File

@@ -27,6 +27,11 @@ jobs:
is-member: ${{ steps.check-user.outputs.is-member }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@v2
with:
egress-policy: audit
- name: Check whether `${{ github.actor }}` is a member of `${{ github.repository_owner }}`
id: check-user
env:
@@ -69,6 +74,11 @@ jobs:
issues: write # for `gh issue edit`
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@v2
with:
egress-policy: audit
- name: Add `${{ env.LABEL }}` label
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

View File

@@ -2,8 +2,8 @@ name: large oltp benchmark
on:
# uncomment to run on push for debugging your PR
push:
branches: [ bodobolero/synthetic_oltp_workload ]
#push:
# branches: [ bodobolero/synthetic_oltp_workload ]
schedule:
# * is a special character in YAML so you have to quote this string
@@ -12,7 +12,7 @@ on:
# │ │ ┌───────────── day of the month (1 - 31)
# │ │ │ ┌───────────── month (1 - 12 or JAN-DEC)
# │ │ │ │ ┌───────────── day of the week (0 - 6 or SUN-SAT)
- cron: '0 15 * * *' # run once a day, timezone is utc, avoid conflict with other benchmarks
- cron: '0 15 * * 0,2,4' # run on Sunday, Tuesday, Thursday at 3 PM UTC
workflow_dispatch: # adds ability to run this manually
defaults:
@@ -22,7 +22,10 @@ defaults:
concurrency:
# Allow only one workflow globally because we need dedicated resources which only exist once
group: large-oltp-bench-workflow
cancel-in-progress: true
cancel-in-progress: false
permissions:
contents: read
jobs:
oltp:
@@ -31,9 +34,9 @@ jobs:
matrix:
include:
- target: new_branch
custom_scripts: insert_webhooks.sql@2 select_any_webhook_with_skew.sql@4 select_recent_webhook.sql@4
custom_scripts: insert_webhooks.sql@200 select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3 IUD_one_transaction.sql@100
- target: reuse_branch
custom_scripts: insert_webhooks.sql@2 select_any_webhook_with_skew.sql@4 select_recent_webhook.sql@4
custom_scripts: insert_webhooks.sql@200 select_any_webhook_with_skew.sql@300 select_recent_webhook.sql@397 select_prefetch_webhook.sql@3 IUD_one_transaction.sql@100
max-parallel: 1 # we want to run each stripe size sequentially to be able to compare the results
permissions:
contents: write
@@ -46,25 +49,31 @@ jobs:
PG_VERSION: 16 # pre-determined by pre-determined project
TEST_OUTPUT: /tmp/test_output
BUILD_TYPE: remote
SAVE_PERF_REPORT: ${{ github.ref_name == 'main' }}
PLATFORM: ${{ matrix.target }}
runs-on: [ self-hosted, us-east-2, x64 ]
container:
image: neondatabase/build-tools:pinned-bookworm
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
# Increase timeout to 8h, default timeout is 6h
timeout-minutes: 480
# Increase timeout to 2 days, default timeout is 6h - database maintenance can take a long time
# (normally 1h pgbench, 3h vacuum analyze 3.5h re-index) x 2 = 15h, leave some buffer for regressions
# in one run vacuum didn't finish within 12 hours
timeout-minutes: 2880
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Configure AWS credentials # necessary to download artefacts
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
@@ -89,29 +98,45 @@ jobs:
- name: Set up Connection String
id: set-up-connstr
run: |
case "${{ matrix.target }}" in
new_branch)
CONNSTR=${{ steps.create-neon-branch-oltp-target.outputs.dsn }}
;;
reuse_branch)
CONNSTR=${{ secrets.BENCHMARK_LARGE_OLTP_REUSE_CONNSTR }}
;;
*)
echo >&2 "Unknown target=${{ matrix.target }}"
exit 1
;;
esac
case "${{ matrix.target }}" in
new_branch)
CONNSTR=${{ steps.create-neon-branch-oltp-target.outputs.dsn }}
;;
reuse_branch)
CONNSTR=${{ secrets.BENCHMARK_LARGE_OLTP_REUSE_CONNSTR }}
;;
*)
echo >&2 "Unknown target=${{ matrix.target }}"
exit 1
;;
esac
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
CONNSTR_WITHOUT_POOLER="${CONNSTR//-pooler/}"
- name: Benchmark pgbench with custom-scripts
echo "connstr=${CONNSTR}" >> $GITHUB_OUTPUT
echo "connstr_without_pooler=${CONNSTR_WITHOUT_POOLER}" >> $GITHUB_OUTPUT
- name: Delete rows from prior runs in reuse branch
if: ${{ matrix.target == 'reuse_branch' }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr_without_pooler }}
PG_CONFIG: /tmp/neon/pg_install/v16/bin/pg_config
PSQL: /tmp/neon/pg_install/v16/bin/psql
PG_16_LIB_PATH: /tmp/neon/pg_install/v16/lib
run: |
echo "$(date '+%Y-%m-%d %H:%M:%S') - Deleting rows in table webhook.incoming_webhooks from prior runs"
export LD_LIBRARY_PATH=${PG_16_LIB_PATH}
${PSQL} "${BENCHMARK_CONNSTR}" -c "SET statement_timeout = 0; DELETE FROM webhook.incoming_webhooks WHERE created_at > '2025-02-27 23:59:59+00';"
echo "$(date '+%Y-%m-%d %H:%M:%S') - Finished deleting rows in table webhook.incoming_webhooks from prior runs"
- name: Benchmark pgbench with custom-scripts
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance
run_in_parallel: false
save_perf_report: ${{ env.SAVE_PERF_REPORT }}
extra_params: -m remote_cluster --timeout 21600 -k test_perf_oltp_large_tenant
save_perf_report: true
extra_params: -m remote_cluster --timeout 7200 -k test_perf_oltp_large_tenant_pgbench
pg_version: ${{ env.PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
@@ -119,6 +144,21 @@ jobs:
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
- name: Benchmark database maintenance
uses: ./.github/actions/run-python-test-set
with:
build_type: ${{ env.BUILD_TYPE }}
test_selection: performance
run_in_parallel: false
save_perf_report: true
extra_params: -m remote_cluster --timeout 172800 -k test_perf_oltp_large_tenant_maintenance
pg_version: ${{ env.PG_VERSION }}
aws-oicd-role-arn: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
env:
BENCHMARK_CONNSTR: ${{ steps.set-up-connstr.outputs.connstr_without_pooler }}
VIP_VAP_ACCESS_TOKEN: "${{ secrets.VIP_VAP_ACCESS_TOKEN }}"
PERF_TEST_RESULT_CONNSTR: "${{ secrets.PERF_TEST_RESULT_CONNSTR }}"
- name: Delete Neon Branch for large tenant
if: ${{ always() && matrix.target == 'new_branch' }}
uses: ./.github/actions/neon-branch-delete
@@ -127,6 +167,13 @@ jobs:
branch_id: ${{ steps.create-neon-branch-oltp-target.outputs.branch_id }}
api_key: ${{ secrets.NEON_STAGING_API_KEY }}
- name: Configure AWS credentials # again because prior steps could have exceeded 5 hours
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
role-duration-seconds: 18000 # 5 hours
- name: Create Allure report
id: create-allure-report
if: ${{ !cancelled() }}
@@ -136,7 +183,7 @@ jobs:
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: |

View File

@@ -7,12 +7,20 @@ on:
- release-proxy
- release-compute
permissions:
contents: read
jobs:
lint-release-pr:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout PR branch
uses: actions/checkout@v4
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
fetch-depth: 0 # Fetch full history for git operations
ref: ${{ github.event.pull_request.head.ref }}

View File

@@ -42,8 +42,13 @@ jobs:
rebuild_everything: ${{ steps.files_changed.outputs.rebuild_neon_extra || steps.files_changed.outputs.rebuild_macos }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
@@ -71,8 +76,8 @@ jobs:
uses: ./.github/workflows/build-macos.yml
with:
pg_versions: ${{ needs.files-changed.outputs.postgres_changes }}
rebuild_rust_code: ${{ fromJson(needs.files-changed.outputs.rebuild_rust_code) }}
rebuild_everything: ${{ fromJson(needs.files-changed.outputs.rebuild_everything) }}
rebuild_rust_code: ${{ fromJSON(needs.files-changed.outputs.rebuild_rust_code) }}
rebuild_everything: ${{ fromJSON(needs.files-changed.outputs.rebuild_everything) }}
gather-rust-build-stats:
needs: [ check-permissions, build-build-tools-image, files-changed ]
@@ -90,8 +95,8 @@ jobs:
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
env:
@@ -101,8 +106,13 @@ jobs:
CARGO_INCREMENTAL: 0
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Checkout
uses: actions/checkout@v4
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
submodules: true
@@ -117,7 +127,7 @@ jobs:
run: cargo build --all --release --timings -j$(nproc)
- name: Configure AWS credentials
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_ARN }}
@@ -134,7 +144,7 @@ jobs:
echo "report-url=${REPORT_URL}" >> $GITHUB_OUTPUT
- name: Publish build stats report
uses: actions/github-script@v7
uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
env:
REPORT_URL: ${{ steps.upload-stats.outputs.report-url }}
SHA: ${{ github.event.pull_request.head.sha || github.sha }}

View File

@@ -25,6 +25,9 @@ concurrency:
group: ${{ github.workflow }}
cancel-in-progress: false
permissions:
contents: read
jobs:
trigger_bench_on_ec2_machine_in_eu_central_1:
permissions:
@@ -34,10 +37,10 @@ jobs:
pull-requests: write
runs-on: [ self-hosted, small ]
container:
image: neondatabase/build-tools:pinned-bookworm
image: ghcr.io/neondatabase/build-tools:pinned-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init
timeout-minutes: 360 # Set the timeout to 6 hours
env:
@@ -48,13 +51,18 @@ jobs:
steps:
# we don't need the neon source code because we run everything remotely
# however we still need the local github actions to run the allure step below
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Show my own (github runner) external IP address - usefull for IP allowlisting
run: curl https://ifconfig.me
- name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}
@@ -143,7 +151,7 @@ jobs:
- name: Post to a Slack channel
if: ${{ github.event.schedule && failure() }}
uses: slackapi/slack-github-action@v1
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: "Periodic pagebench testing on dedicated hardware: ${{ job.status }}\n${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}"
@@ -161,7 +169,7 @@ jobs:
- name: Assume AWS OIDC role that allows to manage (start/stop/describe... EC machine)
if: always() && steps.poll_step.outputs.too_many_runs != 'true'
uses: aws-actions/configure-aws-credentials@v4
uses: aws-actions/configure-aws-credentials@e3dd6a429d7300a6a4c196c26e071d42e0343502 # v4.0.2
with:
aws-region: eu-central-1
role-to-assume: ${{ vars.DEV_AWS_OIDC_ROLE_MANAGE_BENCHMARK_EC2_VMS_ARN }}

View File

@@ -53,8 +53,8 @@ jobs:
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init --user root
services:
clickhouse:
@@ -88,7 +88,12 @@ jobs:
ports:
- 8083:8083
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Download Neon artifact
uses: ./.github/actions/download
@@ -138,7 +143,7 @@ jobs:
- name: Post to a Slack channel
if: github.event.schedule && failure()
uses: slackapi/slack-github-action@v1
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: |
@@ -153,12 +158,17 @@ jobs:
container:
image: ${{ needs.build-build-tools-image.outputs.image }}-bookworm
credentials:
username: ${{ secrets.NEON_DOCKERHUB_USERNAME }}
password: ${{ secrets.NEON_DOCKERHUB_PASSWORD }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
options: --init --user root
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Download Neon artifact
uses: ./.github/actions/download
@@ -206,7 +216,7 @@ jobs:
- name: Post to a Slack channel
if: github.event.schedule && failure()
uses: slackapi/slack-github-action@v1
uses: slackapi/slack-github-action@fcfb566f8b0aab22203f066d80ca1d7e4b5d05b3 # v1.27.1
with:
channel-id: "C06KHQVQ7U3" # on-call-qa-staging-stream
slack-message: |

View File

@@ -40,14 +40,19 @@ jobs:
skip: ${{ steps.check-manifests.outputs.skip }}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@v2
with:
egress-policy: audit
- name: Check if we really need to pin the image
id: check-manifests
env:
FROM_TAG: ${{ inputs.from-tag }}
TO_TAG: pinned
run: |
docker manifest inspect "docker.io/neondatabase/build-tools:${FROM_TAG}" > "${FROM_TAG}.json"
docker manifest inspect "docker.io/neondatabase/build-tools:${TO_TAG}" > "${TO_TAG}.json"
docker manifest inspect "ghcr.io/neondatabase/build-tools:${FROM_TAG}" > "${FROM_TAG}.json"
docker manifest inspect "ghcr.io/neondatabase/build-tools:${TO_TAG}" > "${TO_TAG}.json"
if diff "${FROM_TAG}.json" "${TO_TAG}.json"; then
skip=true
@@ -71,13 +76,13 @@ jobs:
with:
image-map: |
{
"docker.io/neondatabase/build-tools:${{ inputs.from-tag }}-bullseye": [
"ghcr.io/neondatabase/build-tools:${{ inputs.from-tag }}-bullseye": [
"docker.io/neondatabase/build-tools:pinned-bullseye",
"ghcr.io/neondatabase/build-tools:pinned-bullseye",
"${{ vars.NEON_DEV_AWS_ACCOUNT_ID }}.dkr.ecr.${{ vars.AWS_ECR_REGION }}.amazonaws.com/build-tools:pinned-bullseye",
"${{ vars.AZURE_DEV_REGISTRY_NAME }}.azurecr.io/neondatabase/build-tools:pinned-bullseye"
],
"docker.io/neondatabase/build-tools:${{ inputs.from-tag }}-bookworm": [
"ghcr.io/neondatabase/build-tools:${{ inputs.from-tag }}-bookworm": [
"docker.io/neondatabase/build-tools:pinned-bookworm",
"docker.io/neondatabase/build-tools:pinned",
"ghcr.io/neondatabase/build-tools:pinned-bookworm",

View File

@@ -19,15 +19,22 @@ permissions: {}
jobs:
meta:
runs-on: ubuntu-22.04
permissions:
contents: read
outputs:
python-changed: ${{ steps.python-src.outputs.any_changed }}
rust-changed: ${{ steps.rust-src.outputs.any_changed }}
branch: ${{ steps.group-metadata.outputs.branch }}
pr-number: ${{ steps.group-metadata.outputs.pr-number }}
steps:
- uses: actions/checkout@v4
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: tj-actions/changed-files@4edd678ac3f81e2dc578756871e4d00c19191daf # v45.0.4
- uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- uses: step-security/changed-files@3dbe17c78367e7d60f00d78ae6781a35be47b4a1 # v45.0.1
id: python-src
with:
files: |
@@ -38,7 +45,7 @@ jobs:
poetry.lock
pyproject.toml
- uses: tj-actions/changed-files@4edd678ac3f81e2dc578756871e4d00c19191daf # v45.0.4
- uses: step-security/changed-files@3dbe17c78367e7d60f00d78ae6781a35be47b4a1 # v45.0.1
id: rust-src
with:
files: |
@@ -72,6 +79,9 @@ jobs:
|| needs.meta.outputs.python-changed == 'true'
|| needs.meta.outputs.rust-changed == 'true'
needs: [ meta ]
permissions:
contents: read
packages: write
uses: ./.github/workflows/build-build-tools-image.yml
with:
# Build only one combination to save time
@@ -82,6 +92,9 @@ jobs:
check-codestyle-python:
if: needs.meta.outputs.python-changed == 'true'
needs: [ meta, build-build-tools-image ]
permissions:
contents: read
packages: read
uses: ./.github/workflows/_check-codestyle-python.yml
with:
# `-bookworm-x64` suffix should match the combination in `build-build-tools-image`
@@ -91,6 +104,9 @@ jobs:
check-codestyle-rust:
if: needs.meta.outputs.rust-changed == 'true'
needs: [ meta, build-build-tools-image ]
permissions:
contents: read
packages: read
uses: ./.github/workflows/_check-codestyle-rust.yml
with:
# `-bookworm-x64` suffix should match the combination in `build-build-tools-image`
@@ -114,8 +130,13 @@ jobs:
- check-codestyle-rust
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Create fake `neon-cloud-e2e` check
uses: actions/github-script@v7
uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
with:
# Retry script for 5XX server errors: https://github.com/actions/github-script#retries
retries: 5
@@ -148,7 +169,7 @@ jobs:
${{
always()
&& github.event_name == 'merge_group'
&& contains(fromJson('["release", "release-proxy", "release-compute"]'), github.base_ref)
&& contains(fromJSON('["release", "release-proxy", "release-compute"]'), needs.meta.outputs.branch)
}}
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}

View File

@@ -23,8 +23,13 @@ jobs:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Add comment
uses: thollander/actions-comment-pull-request@v3
uses: thollander/actions-comment-pull-request@65f9e5c9a1f2cd378bd74b2e057c9736982a8e74 # v3
with:
comment-tag: ${{ github.job }}
pr-number: ${{ github.event.number }}

View File

@@ -22,7 +22,12 @@ jobs:
runs-on: ubuntu-22.04
steps:
- uses: neondatabase/dev-actions/release-pr-notify@main
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- uses: neondatabase/dev-actions/release-pr-notify@483a843f2a8bcfbdc4c69d27630528a3ddc4e14b # main
with:
slack-token: ${{ secrets.SLACK_BOT_TOKEN }}
slack-channel-id: ${{ vars.SLACK_UPCOMING_RELEASE_CHANNEL_ID || 'C05QQ9J1BRC' }} # if not set, then `#test-release-notifications`

View File

@@ -3,7 +3,7 @@ name: Create Release Branch
on:
schedule:
# It should be kept in sync with if-condition in jobs
- cron: '0 6 * * THU' # Proxy release
- cron: '0 6 * * TUE' # Proxy release
- cron: '0 6 * * FRI' # Storage release
- cron: '0 7 * * FRI' # Compute release
workflow_dispatch:
@@ -43,7 +43,7 @@ jobs:
ci-access-token: ${{ secrets.CI_ACCESS_TOKEN }}
create-proxy-release-branch:
if: ${{ github.event.schedule == '0 6 * * THU' || inputs.create-proxy-release-branch }}
if: ${{ github.event.schedule == '0 6 * * TUE' || inputs.create-proxy-release-branch }}
permissions:
contents: write

View File

@@ -6,6 +6,9 @@ on:
- cron: '25 0 * * *'
- cron: '25 1 * * 6'
permissions:
contents: read
jobs:
gh-workflow-stats-batch-2h:
name: GitHub Workflow Stats Batch 2 hours
@@ -14,8 +17,13 @@ jobs:
permissions:
actions: read
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Export Workflow Run for the past 2 hours
uses: neondatabase/gh-workflow-stats-action@v0.2.1
uses: neondatabase/gh-workflow-stats-action@701b1f202666d0b82e67b4d387e909af2b920127 # v0.2.2
with:
db_uri: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
db_table: "gh_workflow_stats_neon"
@@ -29,8 +37,13 @@ jobs:
permissions:
actions: read
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Export Workflow Run for the past 48 hours
uses: neondatabase/gh-workflow-stats-action@v0.2.1
uses: neondatabase/gh-workflow-stats-action@701b1f202666d0b82e67b4d387e909af2b920127 # v0.2.2
with:
db_uri: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
db_table: "gh_workflow_stats_neon"
@@ -44,8 +57,13 @@ jobs:
permissions:
actions: read
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@4d991eb9b905ef189e4c376166672c3f2f230481 # v2.11.0
with:
egress-policy: audit
- name: Export Workflow Run for the past 30 days
uses: neondatabase/gh-workflow-stats-action@v0.2.1
uses: neondatabase/gh-workflow-stats-action@701b1f202666d0b82e67b4d387e909af2b920127 # v0.2.2
with:
db_uri: ${{ secrets.GH_REPORT_STATS_DB_RW_CONNSTR }}
db_table: "gh_workflow_stats_neon"

View File

@@ -9,6 +9,9 @@ on:
github-event-name:
type: string
required: true
github-event-json:
type: string
required: true
defaults:
run:
@@ -31,6 +34,11 @@ jobs:
runs-on: ubuntu-22.04
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@v2
with:
egress-policy: audit
- name: Cancel previous e2e-tests runs for this PR
env:
GH_TOKEN: ${{ secrets.CI_ACCESS_TOKEN }}
@@ -43,6 +51,7 @@ jobs:
uses: ./.github/workflows/_meta.yml
with:
github-event-name: ${{ inputs.github-event-name || github.event_name }}
github-event-json: ${{ inputs.github-event-json || toJSON(github.event) }}
trigger-e2e-tests:
needs: [ meta ]
@@ -63,6 +72,11 @@ jobs:
|| needs.meta.outputs.build-tag
}}
steps:
- name: Harden the runner (Audit all outbound calls)
uses: step-security/harden-runner@v2
with:
egress-policy: audit
- name: Wait for `push-{neon,compute}-image-dev` job to finish
# It's important to have a timeout here, the script in the step can run infinitely
timeout-minutes: 60

1284
Cargo.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -40,6 +40,8 @@ members = [
"libs/proxy/postgres-protocol2",
"libs/proxy/postgres-types2",
"libs/proxy/tokio-postgres2",
"lambda/aztraffic",
"lambda/pod_info_dumper",
]
[workspace.package]
@@ -50,7 +52,7 @@ license = "Apache-2.0"
[workspace.dependencies]
ahash = "0.8"
anyhow = { version = "1.0", features = ["backtrace"] }
arc-swap = "1.6"
arc-swap = "1.7"
async-compression = { version = "0.4.0", features = ["tokio", "gzip", "zstd"] }
atomic-take = "1.1.0"
flate2 = "1.0.26"
@@ -106,13 +108,13 @@ hostname = "0.4"
http = {version = "1.1.0", features = ["std"]}
http-types = { version = "2", default-features = false }
http-body-util = "0.1.2"
humantime = "2.1"
humantime = "2.2"
humantime-serde = "1.1.1"
hyper0 = { package = "hyper", version = "0.14" }
hyper = "1.4"
hyper-util = "0.1"
tokio-tungstenite = "0.21.0"
indexmap = "2"
indexmap = { version = "2", features = ["serde"] }
indoc = "2"
ipnet = "2.10.0"
itertools = "0.10"
@@ -130,7 +132,7 @@ nix = { version = "0.27", features = ["dir", "fs", "process", "socket", "signal"
# on compute startup metrics (start_postgres_ms), >= 25% degradation.
notify = "6.0.0"
num_cpus = "1.15"
num-traits = "0.2.15"
num-traits = "0.2.19"
once_cell = "1.13"
opentelemetry = "0.27"
opentelemetry_sdk = "0.27"
@@ -146,7 +148,7 @@ procfs = "0.16"
prometheus = {version = "0.13", default-features=false, features = ["process"]} # removes protobuf dependency
prost = "0.13"
rand = "0.8"
redis = { version = "0.25.2", features = ["tokio-rustls-comp", "keep-alive"] }
redis = { version = "0.29.2", features = ["tokio-rustls-comp", "keep-alive"] }
regex = "1.10.2"
reqwest = { version = "0.12", default-features = false, features = ["rustls-tls"] }
reqwest-tracing = { version = "0.5", features = ["opentelemetry_0_27"] }
@@ -215,10 +217,10 @@ urlencoding = "2.1"
uuid = { version = "1.6.1", features = ["v4", "v7", "serde"] }
walkdir = "2.3.2"
rustls-native-certs = "0.8"
x509-parser = "0.16"
whoami = "1.5.1"
zerocopy = { version = "0.7", features = ["derive"] }
json-structural-diff = { version = "0.2.0" }
x509-cert = { version = "0.2.5" }
## TODO replace this with tracing
env_logger = "0.11"
@@ -342,3 +344,12 @@ inherits = "release"
debug = false # true = 2 = all symbols, 1 = line only
opt-level = "z"
lto = true
[profile.release-lambda-function]
inherits = "release"
lto = true
opt-level = "z"
codegen-units = 1
panic = "abort"
debug = false
strip = true

View File

@@ -2,7 +2,7 @@
### The image itself is mainly used as a container for the binaries and for starting e2e tests with custom parameters.
### By default, the binaries inside the image have some mock parameters and can start, but are not intended to be used
### inside this image in the real deployments.
ARG REPOSITORY=neondatabase
ARG REPOSITORY=ghcr.io/neondatabase
ARG IMAGE=build-tools
ARG TAG=pinned
ARG DEFAULT_PG_VERSION=17

View File

@@ -292,7 +292,7 @@ WORKDIR /home/nonroot
# Rust
# Please keep the version of llvm (installed above) in sync with rust llvm (`rustc --version --verbose | grep LLVM`)
ENV RUSTC_VERSION=1.85.0
ENV RUSTC_VERSION=1.86.0
ENV RUSTUP_HOME="/home/nonroot/.rustup"
ENV PATH="/home/nonroot/.cargo/bin:${PATH}"
ARG RUSTFILT_VERSION=0.2.1

View File

@@ -77,7 +77,7 @@
# build_and_test.yml github workflow for how that's done.
ARG PG_VERSION
ARG REPOSITORY=neondatabase
ARG REPOSITORY=ghcr.io/neondatabase
ARG IMAGE=build-tools
ARG TAG=pinned
ARG BUILD_TAG
@@ -369,7 +369,7 @@ FROM build-deps AS plv8-src
ARG PG_VERSION
WORKDIR /ext-src
COPY compute/patches/plv8-3.1.10.patch .
COPY compute/patches/plv8* .
# plv8 3.2.3 supports v17
# last release v3.2.3 - Sep 7, 2024
@@ -393,7 +393,7 @@ RUN case "${PG_VERSION:?}" in \
git clone --recurse-submodules --depth 1 --branch ${PLV8_TAG} https://github.com/plv8/plv8.git plv8-src && \
tar -czf plv8.tar.gz --exclude .git plv8-src && \
cd plv8-src && \
if [[ "${PG_VERSION:?}" < "v17" ]]; then patch -p1 < /ext-src/plv8-3.1.10.patch; fi
if [[ "${PG_VERSION:?}" < "v17" ]]; then patch -p1 < /ext-src/plv8_v3.1.10.patch; else patch -p1 < /ext-src/plv8_v3.2.3.patch; fi
# Step 1: Build the vendored V8 engine. It doesn't depend on PostgreSQL, so use
# 'build-deps' as the base. This enables caching and avoids unnecessary rebuilds.
@@ -1338,8 +1338,8 @@ ARG PG_VERSION
# Do not update without approve from proxy team
# Make sure the version is reflected in proxy/src/serverless/local_conn_pool.rs
WORKDIR /ext-src
RUN wget https://github.com/neondatabase/pg_session_jwt/archive/refs/tags/v0.2.0.tar.gz -O pg_session_jwt.tar.gz && \
echo "5ace028e591f2e000ca10afa5b1ca62203ebff014c2907c0ec3b29c36f28a1bb pg_session_jwt.tar.gz" | sha256sum --check && \
RUN wget https://github.com/neondatabase/pg_session_jwt/archive/refs/tags/v0.3.0.tar.gz -O pg_session_jwt.tar.gz && \
echo "19be2dc0b3834d643706ed430af998bb4c2cdf24b3c45e7b102bb3a550e8660c pg_session_jwt.tar.gz" | sha256sum --check && \
mkdir pg_session_jwt-src && cd pg_session_jwt-src && tar xzf ../pg_session_jwt.tar.gz --strip-components=1 -C . && \
sed -i 's/pgrx = "0.12.6"/pgrx = { version = "0.12.9", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
sed -i 's/version = "0.12.6"/version = "0.12.9"/g' pgrx-tests/Cargo.toml && \
@@ -1352,27 +1352,6 @@ COPY --from=pg_session_jwt-src /ext-src/ /ext-src/
WORKDIR /ext-src/pg_session_jwt-src
RUN cargo pgrx install --release
#########################################################################################
#
# Layer "pg-anon-pg-build"
# compile anon extension
#
#########################################################################################
FROM rust-extensions-build-pgrx12 AS pg-anon-pg-build
ARG PG_VERSION
COPY --from=pg-build /usr/local/pgsql/ /usr/local/pgsql/
# This is an experimental extension, never got to real production.
# !Do not remove! It can be present in shared_preload_libraries and compute will fail to start if library is not found.
ENV PATH="/usr/local/pgsql/bin/:$PATH"
RUN wget https://gitlab.com/dalibo/postgresql_anonymizer/-/archive/latest/postgresql_anonymizer-latest.tar.gz -O pg_anon.tar.gz && \
mkdir pg_anon-src && cd pg_anon-src && tar xzf ../pg_anon.tar.gz --strip-components=1 -C . && \
find /usr/local/pgsql -type f | sed 's|^/usr/local/pgsql/||' > /before.txt && \
sed -i 's/pgrx = "0.12.9"/pgrx = { version = "=0.12.9", features = [ "unsafe-postgres" ] }/g' Cargo.toml && \
make -j $(getconf _NPROCESSORS_ONLN) extension PG_CONFIG=/usr/local/pgsql/bin/pg_config PGVER=pg$(echo "$PG_VERSION" | sed 's/^v//') && \
make -j $(getconf _NPROCESSORS_ONLN) install PG_CONFIG=/usr/local/pgsql/bin/pg_config PGVER=pg$(echo "$PG_VERSION" | sed 's/^v//') && \
echo 'trusted = true' >> /usr/local/pgsql/share/extension/anon.control
#########################################################################################
#
# Layer "wal2json-build"
@@ -1727,6 +1706,8 @@ RUN set -e \
libevent-dev \
libtool \
pkg-config \
libcurl4-openssl-dev \
libssl-dev \
&& apt clean && rm -rf /var/lib/apt/lists/*
# Use `dist_man_MANS=` to skip manpage generation (which requires python3/pandoc)
@@ -1735,7 +1716,7 @@ RUN set -e \
&& git clone --recurse-submodules --depth 1 --branch ${PGBOUNCER_TAG} https://github.com/pgbouncer/pgbouncer.git pgbouncer \
&& cd pgbouncer \
&& ./autogen.sh \
&& ./configure --prefix=/usr/local/pgbouncer --without-openssl \
&& ./configure --prefix=/usr/local/pgbouncer \
&& make -j $(nproc) dist_man_MANS= \
&& make install dist_man_MANS=
@@ -1906,26 +1887,30 @@ RUN apt update && \
;; \
esac && \
apt install --no-install-recommends -y \
ca-certificates \
gdb \
liblz4-1 \
libreadline8 \
iproute2 \
libboost-iostreams1.74.0 \
libboost-regex1.74.0 \
libboost-serialization1.74.0 \
libboost-system1.74.0 \
libossp-uuid16 \
libcurl4 \
libevent-2.1-7 \
libgeos-c1v5 \
liblz4-1 \
libossp-uuid16 \
libprotobuf-c1 \
libreadline8 \
libsfcgal1 \
libxml2 \
libxslt1.1 \
libzstd1 \
libcurl4 \
libevent-2.1-7 \
locales \
lsof \
procps \
ca-certificates \
rsyslog \
screen \
tcpdump \
$VERSION_INSTALLS && \
apt clean && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* && \
localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8

View File

@@ -33,6 +33,7 @@
import 'sql_exporter/lfc_hits.libsonnet',
import 'sql_exporter/lfc_misses.libsonnet',
import 'sql_exporter/lfc_used.libsonnet',
import 'sql_exporter/lfc_used_pages.libsonnet',
import 'sql_exporter/lfc_writes.libsonnet',
import 'sql_exporter/logical_slot_restart_lsn.libsonnet',
import 'sql_exporter/max_cluster_size.libsonnet',

View File

@@ -0,0 +1,10 @@
{
metric_name: 'lfc_used_pages',
type: 'gauge',
help: 'LFC pages used',
key_labels: null,
values: [
'lfc_used_pages',
],
query: importstr 'sql_exporter/lfc_used_pages.sql',
}

View File

@@ -0,0 +1 @@
SELECT lfc_value AS lfc_used_pages FROM neon.neon_lfc_stats WHERE lfc_key = 'file_cache_used_pages';

View File

@@ -2,23 +2,6 @@ diff --git a/expected/ut-A.out b/expected/ut-A.out
index da723b8..5328114 100644
--- a/expected/ut-A.out
+++ b/expected/ut-A.out
@@ -9,13 +9,16 @@ SET search_path TO public;
----
-- No.A-1-1-3
CREATE EXTENSION pg_hint_plan;
+LOG: Sending request to compute_ctl: http://localhost:3081/extension_server/pg_hint_plan
-- No.A-1-2-3
DROP EXTENSION pg_hint_plan;
-- No.A-1-1-4
CREATE SCHEMA other_schema;
CREATE EXTENSION pg_hint_plan SCHEMA other_schema;
+LOG: Sending request to compute_ctl: http://localhost:3081/extension_server/pg_hint_plan
ERROR: extension "pg_hint_plan" must be installed in schema "hint_plan"
CREATE EXTENSION pg_hint_plan;
+LOG: Sending request to compute_ctl: http://localhost:3081/extension_server/pg_hint_plan
DROP SCHEMA other_schema;
----
---- No. A-5-1 comment pattern
@@ -3175,6 +3178,7 @@ SELECT s.query, s.calls
FROM public.pg_stat_statements s
JOIN pg_catalog.pg_database d
@@ -27,18 +10,6 @@ index da723b8..5328114 100644
ORDER BY 1;
query | calls
--------------------------------------+-------
diff --git a/expected/ut-fdw.out b/expected/ut-fdw.out
index d372459..6282afe 100644
--- a/expected/ut-fdw.out
+++ b/expected/ut-fdw.out
@@ -7,6 +7,7 @@ SET pg_hint_plan.debug_print TO on;
SET client_min_messages TO LOG;
SET pg_hint_plan.enable_hint TO on;
CREATE EXTENSION file_fdw;
+LOG: Sending request to compute_ctl: http://localhost:3081/extension_server/file_fdw
CREATE SERVER file_server FOREIGN DATA WRAPPER file_fdw;
CREATE USER MAPPING FOR PUBLIC SERVER file_server;
CREATE FOREIGN TABLE ft1 (id int, val int) SERVER file_server OPTIONS (format 'csv', filename :'filename');
diff --git a/sql/ut-A.sql b/sql/ut-A.sql
index 7c7d58a..4fd1a07 100644
--- a/sql/ut-A.sql

View File

@@ -1,24 +1,3 @@
diff --git a/expected/ut-A.out b/expected/ut-A.out
index e7d68a1..65a056c 100644
--- a/expected/ut-A.out
+++ b/expected/ut-A.out
@@ -9,13 +9,16 @@ SET search_path TO public;
----
-- No.A-1-1-3
CREATE EXTENSION pg_hint_plan;
+LOG: Sending request to compute_ctl: http://localhost:3081/extension_server/pg_hint_plan
-- No.A-1-2-3
DROP EXTENSION pg_hint_plan;
-- No.A-1-1-4
CREATE SCHEMA other_schema;
CREATE EXTENSION pg_hint_plan SCHEMA other_schema;
+LOG: Sending request to compute_ctl: http://localhost:3081/extension_server/pg_hint_plan
ERROR: extension "pg_hint_plan" must be installed in schema "hint_plan"
CREATE EXTENSION pg_hint_plan;
+LOG: Sending request to compute_ctl: http://localhost:3081/extension_server/pg_hint_plan
DROP SCHEMA other_schema;
----
---- No. A-5-1 comment pattern
diff --git a/expected/ut-J.out b/expected/ut-J.out
index 2fa3c70..314e929 100644
--- a/expected/ut-J.out
@@ -160,15 +139,3 @@ index a09bd34..0ad227c 100644
error hint:
explain_filter
diff --git a/expected/ut-fdw.out b/expected/ut-fdw.out
index 017fa4b..98d989b 100644
--- a/expected/ut-fdw.out
+++ b/expected/ut-fdw.out
@@ -7,6 +7,7 @@ SET pg_hint_plan.debug_print TO on;
SET client_min_messages TO LOG;
SET pg_hint_plan.enable_hint TO on;
CREATE EXTENSION file_fdw;
+LOG: Sending request to compute_ctl: http://localhost:3081/extension_server/file_fdw
CREATE SERVER file_server FOREIGN DATA WRAPPER file_fdw;
CREATE USER MAPPING FOR PUBLIC SERVER file_server;
CREATE FOREIGN TABLE ft1 (id int, val int) SERVER file_server OPTIONS (format 'csv', filename :'filename');

View File

@@ -15,7 +15,7 @@ index 7a4b88c..56678af 100644
HEADERS = src/halfvec.h src/sparsevec.h src/vector.h
diff --git a/src/hnswbuild.c b/src/hnswbuild.c
index b667478..fc1897c 100644
index b667478..dc95d89 100644
--- a/src/hnswbuild.c
+++ b/src/hnswbuild.c
@@ -843,9 +843,17 @@ HnswParallelBuildMain(dsm_segment *seg, shm_toc *toc)
@@ -36,7 +36,7 @@ index b667478..fc1897c 100644
/* Close relations within worker */
index_close(indexRel, indexLockmode);
table_close(heapRel, heapLockmode);
@@ -1100,12 +1108,38 @@ BuildIndex(Relation heap, Relation index, IndexInfo *indexInfo,
@@ -1100,12 +1108,39 @@ BuildIndex(Relation heap, Relation index, IndexInfo *indexInfo,
SeedRandom(42);
#endif
@@ -62,10 +62,11 @@ index b667478..fc1897c 100644
+#else
+ RelFileNode rlocator = RelationGetSmgr(index)->smgr_rnode.node;
+#endif
+
+ SetLastWrittenLSNForBlockRange(XactLastRecEnd, rlocator,
+ MAIN_FORKNUM, 0, RelationGetNumberOfBlocks(index));
+ SetLastWrittenLSNForRelation(XactLastRecEnd, rlocator, MAIN_FORKNUM);
+ if (set_lwlsn_block_range_hook)
+ set_lwlsn_block_range_hook(XactLastRecEnd, rlocator,
+ MAIN_FORKNUM, 0, RelationGetNumberOfBlocks(index));
+ if (set_lwlsn_relation_hook)
+ set_lwlsn_relation_hook(XactLastRecEnd, rlocator, MAIN_FORKNUM);
+ }
+#endif
+ }

View File

@@ -1,12 +1,6 @@
commit 46b38d3e46f9cd6c70d9b189dd6ff4abaa17cf5e
Author: Alexander Bayandin <alexander@neon.tech>
Date: Sat Nov 30 18:29:32 2024 +0000
Fix v8 9.7.37 compilation on Debian 12
diff --git a/patches/code/84cf3230a9680aac3b73c410c2b758760b6d3066.patch b/patches/code/84cf3230a9680aac3b73c410c2b758760b6d3066.patch
new file mode 100644
index 0000000..f0a5dc7
index 0000000..fae1cb3
--- /dev/null
+++ b/patches/code/84cf3230a9680aac3b73c410c2b758760b6d3066.patch
@@ -0,0 +1,30 @@
@@ -35,8 +29,21 @@ index 0000000..f0a5dc7
+@@ -5,6 +5,7 @@
+ #ifndef V8_HEAP_CPPGC_PREFINALIZER_HANDLER_H_
+ #define V8_HEAP_CPPGC_PREFINALIZER_HANDLER_H_
+
+
++#include <utility>
+ #include <vector>
+
+
+ #include "include/cppgc/prefinalizer.h"
diff --git a/plv8.cc b/plv8.cc
index c1ce883..6e47e94 100644
--- a/plv8.cc
+++ b/plv8.cc
@@ -379,7 +379,7 @@ _PG_init(void)
NULL,
&plv8_v8_flags,
NULL,
- PGC_USERSET, 0,
+ PGC_SUSET, 0,
#if PG_VERSION_NUM >= 90100
NULL,
#endif

View File

@@ -0,0 +1,13 @@
diff --git a/plv8.cc b/plv8.cc
index edfa2aa..623e7f2 100644
--- a/plv8.cc
+++ b/plv8.cc
@@ -385,7 +385,7 @@ _PG_init(void)
NULL,
&plv8_v8_flags,
NULL,
- PGC_USERSET, 0,
+ PGC_SUSET, 0,
#if PG_VERSION_NUM >= 90100
NULL,
#endif

View File

@@ -1,11 +1,5 @@
commit 68f3b3b0d594f08aacc4a082ee210749ed5677eb
Author: Anastasia Lubennikova <anastasia@neon.tech>
Date: Mon Jul 15 12:31:56 2024 +0100
Neon: fix unlogged index build patch
diff --git a/src/ruminsert.c b/src/ruminsert.c
index e8b209d..e89bf2a 100644
index 255e616..7a2240f 100644
--- a/src/ruminsert.c
+++ b/src/ruminsert.c
@@ -628,6 +628,10 @@ rumbuild(Relation heap, Relation index, struct IndexInfo *indexInfo)
@@ -30,7 +24,7 @@ index e8b209d..e89bf2a 100644
/*
* Write index to xlog
*/
@@ -713,6 +721,21 @@ rumbuild(Relation heap, Relation index, struct IndexInfo *indexInfo)
@@ -713,6 +721,22 @@ rumbuild(Relation heap, Relation index, struct IndexInfo *indexInfo)
UnlockReleaseBuffer(buffer);
}
@@ -41,9 +35,10 @@ index e8b209d..e89bf2a 100644
+#else
+ RelFileNode rlocator = RelationGetSmgr(index)->smgr_rnode.node;
+#endif
+
+ SetLastWrittenLSNForBlockRange(XactLastRecEnd, rlocator, MAIN_FORKNUM, 0, RelationGetNumberOfBlocks(index));
+ SetLastWrittenLSNForRelation(XactLastRecEnd, rlocator, MAIN_FORKNUM);
+ if (set_lwlsn_block_range_hook)
+ set_lwlsn_block_range_hook(XactLastRecEnd, rlocator, MAIN_FORKNUM, 0, RelationGetNumberOfBlocks(index));
+ if (set_lwlsn_relation_hook)
+ set_lwlsn_relation_hook(XactLastRecEnd, rlocator, MAIN_FORKNUM);
+
+ smgr_end_unlogged_build(index->rd_smgr);
+ }

View File

@@ -39,6 +39,13 @@ commands:
user: nobody
sysvInitAction: respawn
shell: '/bin/sql_exporter -config.file=/etc/sql_exporter_autoscaling.yml -web.listen-address=:9499'
# Rsyslog by default creates a unix socket under /dev/log . That's where Postgres sends logs also.
# We run syslog with postgres user so it can't create /dev/log. Instead we configure rsyslog to
# use a different path for the socket. The symlink actually points to our custom path.
- name: rsyslogd-socket-symlink
user: root
sysvInitAction: sysinit
shell: "ln -s /var/db/postgres/rsyslogpipe /dev/log"
- name: rsyslogd
user: postgres
sysvInitAction: respawn
@@ -77,6 +84,9 @@ files:
# compute_ctl will rewrite this file with the actual configuration, if needed.
- filename: compute_rsyslog.conf
content: |
# Syslock.Name specifies a non-default pipe location that is writeable for the postgres user.
module(load="imuxsock" SysSock.Name="/var/db/postgres/rsyslogpipe") # provides support for local system logging
*.* /dev/null
$IncludeConfig /etc/rsyslog.d/*.conf
build: |
@@ -145,7 +155,7 @@ merge: |
COPY compute_rsyslog.conf /etc/compute_rsyslog.conf
RUN chmod 0666 /etc/compute_rsyslog.conf
RUN chmod 0666 /var/log/
RUN mkdir /var/log/rsyslog && chown -R postgres /var/log/rsyslog
COPY --from=libcgroup-builder /libcgroup-install/bin/* /usr/bin/

View File

@@ -39,6 +39,13 @@ commands:
user: nobody
sysvInitAction: respawn
shell: '/bin/sql_exporter -config.file=/etc/sql_exporter_autoscaling.yml -web.listen-address=:9499'
# Rsyslog by default creates a unix socket under /dev/log . That's where Postgres sends logs also.
# We run syslog with postgres user so it can't create /dev/log. Instead we configure rsyslog to
# use a different path for the socket. The symlink actually points to our custom path.
- name: rsyslogd-socket-symlink
user: root
sysvInitAction: sysinit
shell: "ln -s /var/db/postgres/rsyslogpipe /dev/log"
- name: rsyslogd
user: postgres
sysvInitAction: respawn
@@ -77,6 +84,9 @@ files:
# compute_ctl will rewrite this file with the actual configuration, if needed.
- filename: compute_rsyslog.conf
content: |
# Syslock.Name specifies a non-default pipe location that is writeable for the postgres user.
module(load="imuxsock" SysSock.Name="/var/db/postgres/rsyslogpipe") # provides support for local system logging
*.* /dev/null
$IncludeConfig /etc/rsyslog.d/*.conf
build: |
@@ -140,7 +150,7 @@ merge: |
COPY compute_rsyslog.conf /etc/compute_rsyslog.conf
RUN chmod 0666 /etc/compute_rsyslog.conf
RUN chmod 0666 /var/log/
RUN mkdir /var/log/rsyslog && chown -R postgres /var/log/rsyslog
COPY --from=libcgroup-builder /libcgroup-install/bin/* /usr/bin/

View File

@@ -26,6 +26,7 @@ fail.workspace = true
flate2.workspace = true
futures.workspace = true
http.workspace = true
indexmap.workspace = true
jsonwebtoken.workspace = true
metrics.workspace = true
nix.workspace = true
@@ -34,16 +35,19 @@ num_cpus.workspace = true
once_cell.workspace = true
opentelemetry.workspace = true
opentelemetry_sdk.workspace = true
p256 = { version = "0.13", features = ["pem"] }
postgres.workspace = true
regex.workspace = true
reqwest = { workspace = true, features = ["json"] }
ring = "0.17"
serde.workspace = true
serde_with.workspace = true
serde_json.workspace = true
signal-hook.workspace = true
spki = { version = "0.7.3", features = ["std"] }
tar.workspace = true
tower.workspace = true
tower-http.workspace = true
reqwest = { workspace = true, features = ["json"] }
tokio = { workspace = true, features = ["rt", "rt-multi-thread"] }
tokio-postgres.workspace = true
tokio-util.workspace = true
@@ -57,6 +61,7 @@ thiserror.workspace = true
url.workspace = true
uuid.workspace = true
walkdir.workspace = true
x509-cert.workspace = true
postgres_initdb.workspace = true
compute_api.workspace = true

View File

@@ -45,7 +45,9 @@ use anyhow::{Context, Result};
use clap::Parser;
use compute_api::responses::ComputeCtlConfig;
use compute_api::spec::ComputeSpec;
use compute_tools::compute::{ComputeNode, ComputeNodeParams, forward_termination_signal};
use compute_tools::compute::{
BUILD_TAG, ComputeNode, ComputeNodeParams, forward_termination_signal,
};
use compute_tools::extension_server::get_pg_version_string;
use compute_tools::logger::*;
use compute_tools::params::*;
@@ -57,10 +59,6 @@ use tracing::{error, info};
use url::Url;
use utils::failpoint_support;
// this is an arbitrary build tag. Fine as a default / for testing purposes
// in-case of not-set environment var
const BUILD_TAG_DEFAULT: &str = "latest";
// Compatibility hack: if the control plane specified any remote-ext-config
// use the default value for extension storage proxy gateway.
// Remove this once the control plane is updated to pass the gateway URL
@@ -147,7 +145,7 @@ fn main() -> Result<()> {
.build()?;
let _rt_guard = runtime.enter();
let build_tag = runtime.block_on(init())?;
runtime.block_on(init())?;
// enable core dumping for all child processes
setrlimit(Resource::CORE, rlimit::INFINITY, rlimit::INFINITY)?;
@@ -174,8 +172,6 @@ fn main() -> Result<()> {
cgroup: cli.cgroup,
#[cfg(target_os = "linux")]
vm_monitor_addr: cli.vm_monitor_addr,
build_tag,
live_config_allowed: cli_spec.live_config_allowed,
},
cli_spec.spec,
@@ -189,7 +185,7 @@ fn main() -> Result<()> {
deinit_and_exit(exit_code);
}
async fn init() -> Result<String> {
async fn init() -> Result<()> {
init_tracing_and_logging(DEFAULT_LOG_LEVEL).await?;
let mut signals = Signals::new([SIGINT, SIGTERM, SIGQUIT])?;
@@ -199,12 +195,9 @@ async fn init() -> Result<String> {
}
});
let build_tag = option_env!("BUILD_TAG")
.unwrap_or(BUILD_TAG_DEFAULT)
.to_string();
info!("build_tag: {build_tag}");
info!("compute build_tag: {}", &BUILD_TAG.to_string());
Ok(build_tag)
Ok(())
}
fn try_spec_from_cli(cli: &Cli) -> Result<CliSpecParams> {

View File

@@ -31,6 +31,7 @@ use camino::{Utf8Path, Utf8PathBuf};
use clap::{Parser, Subcommand};
use compute_tools::extension_server::{PostgresMajorVersion, get_pg_version};
use nix::unistd::Pid;
use std::ops::Not;
use tracing::{Instrument, error, info, info_span, warn};
use utils::fs_ext::is_directory_empty;
@@ -44,7 +45,7 @@ mod s3_uri;
const PG_WAIT_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(600);
const PG_WAIT_RETRY_INTERVAL: std::time::Duration = std::time::Duration::from_millis(300);
#[derive(Subcommand, Debug)]
#[derive(Subcommand, Debug, Clone, serde::Serialize)]
enum Command {
/// Runs local postgres (neon binary), restores into it,
/// uploads pgdata to s3 to be consumed by pageservers
@@ -84,6 +85,15 @@ enum Command {
},
}
impl Command {
fn as_str(&self) -> &'static str {
match self {
Command::Pgdata { .. } => "pgdata",
Command::DumpRestore { .. } => "dump-restore",
}
}
}
#[derive(clap::Parser)]
struct Args {
#[clap(long, env = "NEON_IMPORTER_WORKDIR")]
@@ -437,7 +447,7 @@ async fn run_dump_restore(
#[allow(clippy::too_many_arguments)]
async fn cmd_pgdata(
s3_client: Option<aws_sdk_s3::Client>,
s3_client: Option<&aws_sdk_s3::Client>,
kms_client: Option<aws_sdk_kms::Client>,
maybe_s3_prefix: Option<s3_uri::S3Uri>,
maybe_spec: Option<Spec>,
@@ -506,14 +516,14 @@ async fn cmd_pgdata(
if let Some(s3_prefix) = maybe_s3_prefix {
info!("upload pgdata");
aws_s3_sync::upload_dir_recursive(
s3_client.as_ref().unwrap(),
s3_client.unwrap(),
Utf8Path::new(&pgdata_dir),
&s3_prefix.append("/pgdata/"),
)
.await
.context("sync dump directory to destination")?;
info!("write status");
info!("write pgdata status to s3");
{
let status_dir = workdir.join("status");
std::fs::create_dir(&status_dir).context("create status directory")?;
@@ -550,13 +560,15 @@ async fn cmd_dumprestore(
&key_id,
spec.source_connstring_ciphertext_base64,
)
.await?;
.await
.context("decrypt source connection string")?;
let dest = if let Some(dest_ciphertext) =
spec.destination_connstring_ciphertext_base64
{
decode_connstring(kms_client.as_ref().unwrap(), &key_id, dest_ciphertext)
.await?
.await
.context("decrypt destination connection string")?
} else {
bail!(
"destination connection string must be provided in spec for dump_restore command"
@@ -601,7 +613,18 @@ pub(crate) async fn main() -> anyhow::Result<()> {
// Initialize AWS clients only if s3_prefix is specified
let (s3_client, kms_client) = if args.s3_prefix.is_some() {
let config = aws_config::load_defaults(BehaviorVersion::v2024_03_28()).await;
// Create AWS config with enhanced retry settings
let config = aws_config::defaults(BehaviorVersion::v2024_03_28())
.retry_config(
aws_config::retry::RetryConfig::standard()
.with_max_attempts(5) // Retry up to 5 times
.with_initial_backoff(std::time::Duration::from_millis(200)) // Start with 200ms delay
.with_max_backoff(std::time::Duration::from_secs(5)), // Cap at 5 seconds
)
.load()
.await;
// Create clients from the config with enhanced retry settings
let s3_client = aws_sdk_s3::Client::new(&config);
let kms = aws_sdk_kms::Client::new(&config);
(Some(s3_client), Some(kms))
@@ -609,79 +632,108 @@ pub(crate) async fn main() -> anyhow::Result<()> {
(None, None)
};
let spec: Option<Spec> = if let Some(s3_prefix) = &args.s3_prefix {
let spec_key = s3_prefix.append("/spec.json");
let object = s3_client
.as_ref()
.unwrap()
.get_object()
.bucket(&spec_key.bucket)
.key(spec_key.key)
.send()
.await
.context("get spec from s3")?
.body
.collect()
.await
.context("download spec body")?;
serde_json::from_slice(&object.into_bytes()).context("parse spec as json")?
} else {
None
};
match tokio::fs::create_dir(&args.working_directory).await {
Ok(()) => {}
Err(e) if e.kind() == std::io::ErrorKind::AlreadyExists => {
if !is_directory_empty(&args.working_directory)
// Capture everything from spec assignment onwards to handle errors
let res = async {
let spec: Option<Spec> = if let Some(s3_prefix) = &args.s3_prefix {
let spec_key = s3_prefix.append("/spec.json");
let object = s3_client
.as_ref()
.unwrap()
.get_object()
.bucket(&spec_key.bucket)
.key(spec_key.key)
.send()
.await
.context("check if working directory is empty")?
{
bail!("working directory is not empty");
} else {
// ok
}
}
Err(e) => return Err(anyhow::Error::new(e).context("create working directory")),
}
.context("get spec from s3")?
.body
.collect()
.await
.context("download spec body")?;
serde_json::from_slice(&object.into_bytes()).context("parse spec as json")?
} else {
None
};
match args.command {
Command::Pgdata {
source_connection_string,
interactive,
pg_port,
num_cpus,
memory_mb,
} => {
cmd_pgdata(
s3_client,
kms_client,
args.s3_prefix,
spec,
match tokio::fs::create_dir(&args.working_directory).await {
Ok(()) => {}
Err(e) if e.kind() == std::io::ErrorKind::AlreadyExists => {
if !is_directory_empty(&args.working_directory)
.await
.context("check if working directory is empty")?
{
bail!("working directory is not empty");
} else {
// ok
}
}
Err(e) => return Err(anyhow::Error::new(e).context("create working directory")),
}
match args.command.clone() {
Command::Pgdata {
source_connection_string,
interactive,
pg_port,
args.working_directory,
args.pg_bin_dir,
args.pg_lib_dir,
num_cpus,
memory_mb,
)
.await?;
}
Command::DumpRestore {
source_connection_string,
destination_connection_string,
} => {
cmd_dumprestore(
kms_client,
spec,
} => {
cmd_pgdata(
s3_client.as_ref(),
kms_client,
args.s3_prefix.clone(),
spec,
source_connection_string,
interactive,
pg_port,
args.working_directory.clone(),
args.pg_bin_dir,
args.pg_lib_dir,
num_cpus,
memory_mb,
)
.await
}
Command::DumpRestore {
source_connection_string,
destination_connection_string,
args.working_directory,
args.pg_bin_dir,
args.pg_lib_dir,
} => {
cmd_dumprestore(
kms_client,
spec,
source_connection_string,
destination_connection_string,
args.working_directory.clone(),
args.pg_bin_dir,
args.pg_lib_dir,
)
.await
}
}
}
.await;
if let Some(s3_prefix) = args.s3_prefix {
info!("write job status to s3");
{
let status_dir = args.working_directory.join("status");
if std::fs::exists(&status_dir)?.not() {
std::fs::create_dir(&status_dir).context("create status directory")?;
}
let status_file = status_dir.join("fast_import");
let res_obj = match res {
Ok(_) => serde_json::json!({"command": args.command.as_str(), "done": true}),
Err(err) => {
serde_json::json!({"command": args.command.as_str(), "done": false, "error": err.to_string()})
}
};
std::fs::write(&status_file, res_obj.to_string()).context("write status file")?;
aws_s3_sync::upload_dir_recursive(
s3_client.as_ref().unwrap(),
&status_dir,
&s3_prefix.append("/status/"),
)
.await?;
.await
.context("sync status directory to destination")?;
}
}

View File

@@ -20,6 +20,7 @@ use futures::future::join_all;
use futures::stream::FuturesUnordered;
use nix::sys::signal::{Signal, kill};
use nix::unistd::Pid;
use once_cell::sync::Lazy;
use postgres;
use postgres::NoTls;
use postgres::error::SqlState;
@@ -35,16 +36,32 @@ use crate::disk_quota::set_disk_quota;
use crate::installed_extensions::get_installed_extensions;
use crate::logger::startup_context_from_env;
use crate::lsn_lease::launch_lsn_lease_bg_task_for_static;
use crate::metrics::COMPUTE_CTL_UP;
use crate::monitor::launch_monitor;
use crate::pg_helpers::*;
use crate::rsyslog::configure_audit_rsyslog;
use crate::rsyslog::{
PostgresLogsRsyslogConfig, configure_audit_rsyslog, configure_postgres_logs_export,
launch_pgaudit_gc,
};
use crate::spec::*;
use crate::swap::resize_swap;
use crate::sync_sk::{check_if_synced, ping_safekeeper};
use crate::tls::watch_cert_for_changes;
use crate::{config, extension_server, local_proxy};
pub static SYNC_SAFEKEEPERS_PID: AtomicU32 = AtomicU32::new(0);
pub static PG_PID: AtomicU32 = AtomicU32::new(0);
// This is an arbitrary build tag. Fine as a default / for testing purposes
// in-case of not-set environment var
const BUILD_TAG_DEFAULT: &str = "latest";
/// Build tag/version of the compute node binaries/image. It's tricky and ugly
/// to pass it everywhere as a part of `ComputeNodeParams`, so we use a
/// global static variable.
pub static BUILD_TAG: Lazy<String> = Lazy::new(|| {
option_env!("BUILD_TAG")
.unwrap_or(BUILD_TAG_DEFAULT)
.to_string()
});
/// Static configuration params that don't change after startup. These mostly
/// come from the CLI args, or are derived from them.
@@ -68,7 +85,6 @@ pub struct ComputeNodeParams {
pub pgdata: String,
pub pgbin: String,
pub pgversion: String,
pub build_tag: String,
/// The port that the compute's external HTTP server listens on
pub external_http_port: u16,
@@ -112,6 +128,7 @@ pub struct ComputeNode {
// key: ext_archive_name, value: started download time, download_completed?
pub ext_download_progress: RwLock<HashMap<String, (DateTime<Utc>, bool)>>,
pub compute_ctl_config: ComputeCtlConfig,
}
// store some metrics about download size that might impact startup time
@@ -135,8 +152,6 @@ pub struct ComputeState {
/// passed by the control plane with a /configure HTTP request.
pub pspec: Option<ParsedSpec>,
pub compute_ctl_config: ComputeCtlConfig,
/// If the spec is passed by a /configure request, 'startup_span' is the
/// /configure request's tracing span. The main thread enters it when it
/// processes the compute startup, so that the compute startup is considered
@@ -160,7 +175,6 @@ impl ComputeState {
last_active: None,
error: None,
pspec: None,
compute_ctl_config: ComputeCtlConfig::default(),
startup_span: None,
metrics: ComputeMetrics::default(),
}
@@ -171,6 +185,11 @@ impl ComputeState {
info!("Changing compute status from {} to {}", prev, status);
self.status = status;
state_changed.notify_all();
COMPUTE_CTL_UP.reset();
COMPUTE_CTL_UP
.with_label_values(&[&BUILD_TAG, status.to_string().as_str()])
.set(1);
}
pub fn set_failed_status(&mut self, err: anyhow::Error, state_changed: &Condvar) {
@@ -314,7 +333,6 @@ impl ComputeNode {
let pspec = ParsedSpec::try_from(cli_spec).map_err(|msg| anyhow::anyhow!(msg))?;
new_state.pspec = Some(pspec);
}
new_state.compute_ctl_config = compute_ctl_config;
Ok(ComputeNode {
params,
@@ -323,6 +341,7 @@ impl ComputeNode {
state: Mutex::new(new_state),
state_changed: Condvar::new(),
ext_download_progress: RwLock::new(HashMap::new()),
compute_ctl_config,
})
}
@@ -341,11 +360,19 @@ impl ComputeNode {
this.prewarm_postgres()?;
}
// Set the up metric with Empty status before starting the HTTP server.
// That way on the first metric scrape, an external observer will see us
// as 'up' and 'empty' (unless the compute was started with a spec or
// already configured by control plane).
COMPUTE_CTL_UP
.with_label_values(&[&BUILD_TAG, ComputeStatus::Empty.to_string().as_str()])
.set(1);
// Launch the external HTTP server first, so that we can serve control plane
// requests while configuration is still in progress.
crate::http::server::Server::External {
port: this.params.external_http_port,
jwks: this.state.lock().unwrap().compute_ctl_config.jwks.clone(),
config: this.compute_ctl_config.clone(),
compute_id: this.params.compute_id.clone(),
}
.launch(&this);
@@ -524,6 +551,16 @@ impl ComputeNode {
// Collect all the tasks that must finish here
let mut pre_tasks = tokio::task::JoinSet::new();
// Make sure TLS certificates are properly loaded and in the right place.
if self.compute_ctl_config.tls.is_some() {
let this = self.clone();
pre_tasks.spawn(async move {
this.watch_cert_for_changes().await;
Ok::<(), anyhow::Error>(())
});
}
// If there are any remote extensions in shared_preload_libraries, start downloading them
if pspec.spec.remote_extensions.is_some() {
let (this, spec) = (self.clone(), pspec.spec.clone());
@@ -579,11 +616,13 @@ impl ComputeNode {
if let Some(pgbouncer_settings) = &pspec.spec.pgbouncer_settings {
info!("tuning pgbouncer");
let pgbouncer_settings = pgbouncer_settings.clone();
let tls_config = self.compute_ctl_config.tls.clone();
// Spawn a background task to do the tuning,
// so that we don't block the main thread that starts Postgres.
let pgbouncer_settings = pgbouncer_settings.clone();
let _handle = tokio::spawn(async move {
let res = tune_pgbouncer(pgbouncer_settings).await;
let res = tune_pgbouncer(pgbouncer_settings, tls_config).await;
if let Err(err) = res {
error!("error while tuning pgbouncer: {err:?}");
// Continue with the startup anyway
@@ -606,7 +645,7 @@ impl ComputeNode {
});
}
// Configure and start rsyslog if necessary
// Configure and start rsyslog for HIPAA if necessary
if let ComputeAudit::Hipaa = pspec.spec.audit_log_level {
let remote_endpoint = std::env::var("AUDIT_LOGGING_ENDPOINT").unwrap_or("".to_string());
if remote_endpoint.is_empty() {
@@ -614,13 +653,22 @@ impl ComputeNode {
}
let log_directory_path = Path::new(&self.params.pgdata).join("log");
// TODO: make this more robust
// now rsyslog starts once and there is no monitoring or restart if it fails
configure_audit_rsyslog(
log_directory_path.to_str().unwrap(),
"hipaa",
&remote_endpoint,
)?;
let log_directory_path = log_directory_path.to_string_lossy().to_string();
configure_audit_rsyslog(log_directory_path.clone(), "hipaa", &remote_endpoint)?;
// Launch a background task to clean up the audit logs
launch_pgaudit_gc(log_directory_path);
}
// Configure and start rsyslog for Postgres logs export
if self.has_feature(ComputeFeature::PostgresLogsExport) {
if let Some(ref project_id) = pspec.spec.cluster.cluster_id {
let host = PostgresLogsRsyslogConfig::default_host(project_id);
let conf = PostgresLogsRsyslogConfig::new(Some(&host));
configure_postgres_logs_export(conf)?;
} else {
warn!("not configuring rsyslog for Postgres logs export: project ID is missing")
}
}
// Launch remaining service threads
@@ -855,6 +903,14 @@ impl ComputeNode {
info!("Storage auth token not set");
}
config.application_name("compute_ctl");
if let Some(spec) = &compute_state.pspec {
config.options(&format!(
"-c neon.compute_mode={}",
spec.spec.mode.to_type_str()
));
}
// Connect to pageserver
let mut client = config.connect(NoTls)?;
let pageserver_connect_micros = start_time.elapsed().as_micros() as u64;
@@ -1105,9 +1161,10 @@ impl ComputeNode {
// Remove/create an empty pgdata directory and put configuration there.
self.create_pgdata()?;
config::write_postgres_conf(
&pgdata_path.join("postgresql.conf"),
pgdata_path,
&pspec.spec,
self.params.internal_http_port,
&self.compute_ctl_config.tls,
)?;
// Syncing safekeepers is only safe with primary nodes: if a primary
@@ -1489,11 +1546,13 @@ impl ComputeNode {
if let Some(ref pgbouncer_settings) = spec.pgbouncer_settings {
info!("tuning pgbouncer");
let pgbouncer_settings = pgbouncer_settings.clone();
let tls_config = self.compute_ctl_config.tls.clone();
// Spawn a background task to do the tuning,
// so that we don't block the main thread that starts Postgres.
let pgbouncer_settings = pgbouncer_settings.clone();
tokio::spawn(async move {
let res = tune_pgbouncer(pgbouncer_settings).await;
let res = tune_pgbouncer(pgbouncer_settings, tls_config).await;
if let Err(err) = res {
error!("error while tuning pgbouncer: {err:?}");
}
@@ -1505,7 +1564,8 @@ impl ComputeNode {
// Spawn a background task to do the configuration,
// so that we don't block the main thread that starts Postgres.
let local_proxy = local_proxy.clone();
let mut local_proxy = local_proxy.clone();
local_proxy.tls = self.compute_ctl_config.tls.clone();
tokio::spawn(async move {
if let Err(err) = local_proxy::configure(&local_proxy) {
error!("error while configuring local_proxy: {err:?}");
@@ -1515,8 +1575,12 @@ impl ComputeNode {
// Write new config
let pgdata_path = Path::new(&self.params.pgdata);
let postgresql_conf_path = pgdata_path.join("postgresql.conf");
config::write_postgres_conf(&postgresql_conf_path, &spec, self.params.internal_http_port)?;
config::write_postgres_conf(
pgdata_path,
&spec,
self.params.internal_http_port,
&self.compute_ctl_config.tls,
)?;
if !spec.skip_pg_catalog_updates {
let max_concurrent_connections = spec.reconfigure_concurrency;
@@ -1587,6 +1651,56 @@ impl ComputeNode {
Ok(())
}
pub async fn watch_cert_for_changes(self: Arc<Self>) {
// update status on cert renewal
if let Some(tls_config) = &self.compute_ctl_config.tls {
let tls_config = tls_config.clone();
// wait until the cert exists.
let mut cert_watch = watch_cert_for_changes(tls_config.cert_path.clone()).await;
tokio::task::spawn_blocking(move || {
let handle = tokio::runtime::Handle::current();
'cert_update: loop {
// let postgres/pgbouncer/local_proxy know the new cert/key exists.
// we need to wait until it's configurable first.
let mut state = self.state.lock().unwrap();
'status_update: loop {
match state.status {
// let's update the state to config pending
ComputeStatus::ConfigurationPending | ComputeStatus::Running => {
state.set_status(
ComputeStatus::ConfigurationPending,
&self.state_changed,
);
break 'status_update;
}
// exit loop
ComputeStatus::Failed
| ComputeStatus::TerminationPending
| ComputeStatus::Terminated => break 'cert_update,
// wait
ComputeStatus::Init
| ComputeStatus::Configuration
| ComputeStatus::Empty => {
state = self.state_changed.wait(state).unwrap();
}
}
}
drop(state);
// wait for a new certificate update
if handle.block_on(cert_watch.changed()).is_err() {
break;
}
}
});
}
}
/// Update the `last_active` in the shared state, but ensure that it's a more recent one.
pub fn update_last_active(&self, last_active: Option<DateTime<Utc>>) {
let mut state = self.state.lock().unwrap();
@@ -1943,12 +2057,8 @@ LIMIT 100",
let mut download_tasks = Vec::new();
for library in &libs_vec {
let (ext_name, ext_path) = remote_extensions.get_ext(
library,
true,
&self.params.build_tag,
&self.params.pgversion,
)?;
let (ext_name, ext_path) =
remote_extensions.get_ext(library, true, &BUILD_TAG, &self.params.pgversion)?;
download_tasks.push(self.download_extension(ext_name, ext_path));
}
let results = join_all(download_tasks).await;

View File

@@ -6,11 +6,13 @@ use std::io::Write;
use std::io::prelude::*;
use std::path::Path;
use compute_api::spec::{ComputeAudit, ComputeMode, ComputeSpec, GenericOption};
use compute_api::responses::TlsConfig;
use compute_api::spec::{ComputeAudit, ComputeFeature, ComputeMode, ComputeSpec, GenericOption};
use crate::pg_helpers::{
GenericOptionExt, GenericOptionsSearch, PgOptionsSerialize, escape_conf_value,
};
use crate::tls::{self, SERVER_CRT, SERVER_KEY};
/// Check that `line` is inside a text file and put it there if it is not.
/// Create file if it doesn't exist.
@@ -38,10 +40,12 @@ pub fn line_in_file(path: &Path, line: &str) -> Result<bool> {
/// Create or completely rewrite configuration file specified by `path`
pub fn write_postgres_conf(
path: &Path,
pgdata_path: &Path,
spec: &ComputeSpec,
extension_server_port: u16,
tls_config: &Option<TlsConfig>,
) -> Result<()> {
let path = pgdata_path.join("postgresql.conf");
// File::create() destroys the file content if it exists.
let mut file = File::create(path)?;
@@ -86,6 +90,20 @@ pub fn write_postgres_conf(
)?;
}
// tls
if let Some(tls_config) = tls_config {
writeln!(file, "ssl = on")?;
// postgres requires the keyfile to be in a secure file,
// currently too complicated to ensure that at the VM level,
// so we just copy them to another file instead. :shrug:
tls::update_key_path_blocking(pgdata_path, tls_config);
// these are the default, but good to be explicit.
writeln!(file, "ssl_cert_file = '{}'", SERVER_CRT)?;
writeln!(file, "ssl_key_file = '{}'", SERVER_KEY)?;
}
// Locales
if cfg!(target_os = "macos") {
writeln!(file, "lc_messages='C'")?;
@@ -99,6 +117,7 @@ pub fn write_postgres_conf(
writeln!(file, "lc_numeric='C.UTF-8'")?;
}
writeln!(file, "neon.compute_mode={}", spec.mode.to_type_str())?;
match spec.mode {
ComputeMode::Primary => {}
ComputeMode::Static(lsn) => {
@@ -140,52 +159,89 @@ pub fn write_postgres_conf(
writeln!(file, "# Managed by compute_ctl: end")?;
}
// If audit logging is enabled, configure pgaudit.
// If base audit logging is enabled, configure it.
// In this setup, the audit log will be written to the standard postgresql log.
//
// If compliance audit logging is enabled, configure pgaudit.
//
// Note, that this is called after the settings from spec are written.
// This way we always override the settings from the spec
// and don't allow the user or the control plane admin to change them.
if let ComputeAudit::Hipaa = spec.audit_log_level {
writeln!(file, "# Managed by compute_ctl audit settings: begin")?;
// This log level is very verbose
// but this is necessary for HIPAA compliance.
writeln!(file, "pgaudit.log='all'")?;
writeln!(file, "pgaudit.log_parameter=on")?;
// Disable logging of catalog queries
// The catalog doesn't contain sensitive data, so we don't need to audit it.
writeln!(file, "pgaudit.log_catalog=off")?;
// Set log rotation to 5 minutes
// TODO: tune this after performance testing
writeln!(file, "pgaudit.log_rotation_age=5")?;
match spec.audit_log_level {
ComputeAudit::Disabled => {}
ComputeAudit::Log => {
writeln!(file, "# Managed by compute_ctl base audit settings: start")?;
writeln!(file, "pgaudit.log='ddl,role'")?;
// Disable logging of catalog queries to reduce the noise
writeln!(file, "pgaudit.log_catalog=off")?;
// Add audit shared_preload_libraries, if they are not present.
//
// The caller who sets the flag is responsible for ensuring that the necessary
// shared_preload_libraries are present in the compute image,
// otherwise the compute start will fail.
if let Some(libs) = spec.cluster.settings.find("shared_preload_libraries") {
let mut extra_shared_preload_libraries = String::new();
if !libs.contains("pgaudit") {
extra_shared_preload_libraries.push_str(",pgaudit");
}
if !libs.contains("pgauditlogtofile") {
extra_shared_preload_libraries.push_str(",pgauditlogtofile");
if let Some(libs) = spec.cluster.settings.find("shared_preload_libraries") {
let mut extra_shared_preload_libraries = String::new();
if !libs.contains("pgaudit") {
extra_shared_preload_libraries.push_str(",pgaudit");
}
writeln!(
file,
"shared_preload_libraries='{}{}'",
libs, extra_shared_preload_libraries
)?;
} else {
// Typically, this should be unreacheable,
// because we always set at least some shared_preload_libraries in the spec
// but let's handle it explicitly anyway.
writeln!(file, "shared_preload_libraries='neon,pgaudit'")?;
}
writeln!(file, "# Managed by compute_ctl base audit settings: end")?;
}
ComputeAudit::Hipaa => {
writeln!(
file,
"shared_preload_libraries='{}{}'",
libs, extra_shared_preload_libraries
"# Managed by compute_ctl compliance audit settings: begin"
)?;
} else {
// Typically, this should be unreacheable,
// because we always set at least some shared_preload_libraries in the spec
// but let's handle it explicitly anyway.
// This log level is very verbose
// but this is necessary for HIPAA compliance.
// Exclude 'misc' category, because it doesn't contain anythig relevant.
writeln!(file, "pgaudit.log='all, -misc'")?;
writeln!(file, "pgaudit.log_parameter=on")?;
// Disable logging of catalog queries
// The catalog doesn't contain sensitive data, so we don't need to audit it.
writeln!(file, "pgaudit.log_catalog=off")?;
// Set log rotation to 5 minutes
// TODO: tune this after performance testing
writeln!(file, "pgaudit.log_rotation_age=5")?;
// Add audit shared_preload_libraries, if they are not present.
//
// The caller who sets the flag is responsible for ensuring that the necessary
// shared_preload_libraries are present in the compute image,
// otherwise the compute start will fail.
if let Some(libs) = spec.cluster.settings.find("shared_preload_libraries") {
let mut extra_shared_preload_libraries = String::new();
if !libs.contains("pgaudit") {
extra_shared_preload_libraries.push_str(",pgaudit");
}
if !libs.contains("pgauditlogtofile") {
extra_shared_preload_libraries.push_str(",pgauditlogtofile");
}
writeln!(
file,
"shared_preload_libraries='{}{}'",
libs, extra_shared_preload_libraries
)?;
} else {
// Typically, this should be unreacheable,
// because we always set at least some shared_preload_libraries in the spec
// but let's handle it explicitly anyway.
writeln!(
file,
"shared_preload_libraries='neon,pgaudit,pgauditlogtofile'"
)?;
}
writeln!(
file,
"shared_preload_libraries='neon,pgaudit,pgauditlogtofile'"
"# Managed by compute_ctl compliance audit settings: end"
)?;
}
writeln!(file, "# Managed by compute_ctl audit settings: end")?;
}
writeln!(file, "neon.extension_server_port={}", extension_server_port)?;
@@ -197,6 +253,12 @@ pub fn write_postgres_conf(
writeln!(file, "neon.disable_logical_replication_subscribers=false")?;
}
// We need Postgres to send logs to rsyslog so that we can forward them
// further to customers' log aggregation systems.
if spec.features.contains(&ComputeFeature::PostgresLogsExport) {
writeln!(file, "log_destination='stderr,syslog'")?;
}
// This is essential to keep this line at the end of the file,
// because it is intended to override any settings above.
writeln!(file, "include_if_exists = 'compute_ctl_temp_override.conf'")?;

View File

@@ -4,7 +4,8 @@ module(load="imfile")
# Input configuration for log files in the specified directory
# Replace {log_directory} with the directory containing the log files
input(type="imfile" File="{log_directory}/*.log" Tag="{tag}" Severity="info" Facility="local0")
global(workDirectory="/var/log")
# the directory to store rsyslog state files
global(workDirectory="/var/log/rsyslog")
# Forward logs to remote syslog server
*.* @@{remote_endpoint}
*.* @@{remote_endpoint}

View File

@@ -0,0 +1,10 @@
# Program name comes from postgres' syslog_facility configuration: https://www.postgresql.org/docs/current/runtime-config-logging.html#GUC-SYSLOG-IDENT
# Default value is 'postgres'.
if $programname == 'postgres' then {{
# Forward Postgres logs to telemetry otel collector
action(type="omfwd" target="{logs_export_target}" port="{logs_export_port}" protocol="tcp"
template="RSYSLOG_SyslogProtocol23Format"
action.resumeRetryCount="3"
queue.type="linkedList" queue.size="1000")
stop
}}

View File

@@ -59,9 +59,12 @@ impl AsyncAuthorizeRequest<Body> for Authorize {
Box::pin(async move {
let request_id = request.extract_parts::<RequestId>().await.unwrap();
// TODO: Remove this check after a successful rollout
if jwks.keys.is_empty() {
warn!(%request_id, "Authorization has not been configured");
// TODO: Remove this stanza after teaching neon_local and the
// regression tests to use a JWT + JWKS.
//
// https://github.com/neondatabase/neon/issues/11316
if cfg!(feature = "testing") {
warn!(%request_id, "Skipping compute_ctl authorization check");
return Ok(request);
}
@@ -110,8 +113,6 @@ impl AsyncAuthorizeRequest<Body> for Authorize {
impl Authorize {
/// Verify the token using the JSON Web Key set and return the token data.
fn verify(jwks: &JwkSet, token: &str, validation: &Validation) -> Result<TokenData<Claims>> {
debug_assert!(!jwks.keys.is_empty());
for jwk in jwks.keys.iter() {
let decoding_key = match DecodingKey::from_jwk(jwk) {
Ok(key) => key,

View File

@@ -306,6 +306,36 @@ paths:
schema:
$ref: "#/components/schemas/GenericError"
/configure_telemetry:
post:
tags:
- Configure
summary: Configure rsyslog
description: |
This API endpoint configures rsyslog to forward Postgres logs
to a specified otel collector.
operationId: configureTelemetry
requestBody:
required: true
content:
application/json:
schema:
type: object
properties:
logs_export_host:
type: string
description: |
Hostname and the port of the otel collector. Leave empty to disable logs forwarding.
Example: config-shy-breeze-123-collector-monitoring.neon-telemetry.svc.cluster.local:54526
responses:
204:
description: "Telemetry configured successfully"
500:
content:
application/json:
schema:
$ref: "#/components/schemas/GenericError"
components:
securitySchemes:
JWT:

View File

@@ -1,9 +1,11 @@
use std::sync::Arc;
use axum::body::Body;
use axum::extract::State;
use axum::response::Response;
use compute_api::requests::ConfigurationRequest;
use compute_api::requests::{ConfigurationRequest, ConfigureTelemetryRequest};
use compute_api::responses::{ComputeStatus, ComputeStatusResponse};
use compute_api::spec::ComputeFeature;
use http::StatusCode;
use tokio::task;
use tracing::info;
@@ -11,6 +13,7 @@ use tracing::info;
use crate::compute::{ComputeNode, ParsedSpec};
use crate::http::JsonResponse;
use crate::http::extract::Json;
use crate::rsyslog::{PostgresLogsRsyslogConfig, configure_postgres_logs_export};
// Accept spec in JSON format and request compute configuration. If anything
// goes wrong after we set the compute status to `ConfigurationPending` and
@@ -92,3 +95,25 @@ pub(in crate::http) async fn configure(
JsonResponse::success(StatusCode::OK, body)
}
pub(in crate::http) async fn configure_telemetry(
State(compute): State<Arc<ComputeNode>>,
request: Json<ConfigureTelemetryRequest>,
) -> Response {
if !compute.has_feature(ComputeFeature::PostgresLogsExport) {
return JsonResponse::error(
StatusCode::PRECONDITION_FAILED,
"Postgres logs export feature is not enabled".to_string(),
);
}
let conf = PostgresLogsRsyslogConfig::new(request.logs_export_host.as_deref());
if let Err(err) = configure_postgres_logs_export(conf) {
return JsonResponse::error(StatusCode::INTERNAL_SERVER_ERROR, err.to_string());
}
Response::builder()
.status(StatusCode::NO_CONTENT)
.body(Body::from(""))
.unwrap()
}

View File

@@ -5,7 +5,7 @@ use axum::response::{IntoResponse, Response};
use http::StatusCode;
use serde::Deserialize;
use crate::compute::ComputeNode;
use crate::compute::{BUILD_TAG, ComputeNode};
use crate::http::JsonResponse;
use crate::http::extract::{Path, Query};
@@ -47,7 +47,7 @@ pub(in crate::http) async fn download_extension(
remote_extensions.get_ext(
&filename,
ext_server_params.is_library,
&compute.params.build_tag,
&BUILD_TAG,
&compute.params.pgversion,
)
};

View File

@@ -8,8 +8,8 @@ use axum::Router;
use axum::middleware::{self};
use axum::response::IntoResponse;
use axum::routing::{get, post};
use compute_api::responses::ComputeCtlConfig;
use http::StatusCode;
use jsonwebtoken::jwk::JwkSet;
use tokio::net::TcpListener;
use tower::ServiceBuilder;
use tower_http::{
@@ -41,7 +41,7 @@ pub enum Server {
},
External {
port: u16,
jwks: JwkSet,
config: ComputeCtlConfig,
compute_id: String,
},
}
@@ -79,7 +79,7 @@ impl From<&Server> for Router<Arc<ComputeNode>> {
router
}
Server::External {
jwks, compute_id, ..
config, compute_id, ..
} => {
let unauthenticated_router =
Router::<Arc<ComputeNode>>::new().route("/metrics", get(metrics::get_metrics));
@@ -87,6 +87,7 @@ impl From<&Server> for Router<Arc<ComputeNode>> {
let authenticated_router = Router::<Arc<ComputeNode>>::new()
.route("/check_writability", post(check_writability::is_writable))
.route("/configure", post(configure::configure))
.route("/configure_telemetry", post(configure::configure_telemetry))
.route("/database_schema", get(database_schema::get_schema_dump))
.route("/dbs_and_roles", get(dbs_and_roles::get_catalog_objects))
.route("/insights", get(insights::get_insights))
@@ -95,7 +96,7 @@ impl From<&Server> for Router<Arc<ComputeNode>> {
.route("/terminate", post(terminate::terminate))
.layer(AsyncRequireAuthorizationLayer::new(Authorize::new(
compute_id.clone(),
jwks.clone(),
config.jwks.clone(),
)));
router

View File

@@ -26,3 +26,4 @@ pub mod spec;
mod spec_apply;
pub mod swap;
pub mod sync_sk;
pub mod tls;

View File

@@ -1,6 +1,9 @@
use metrics::core::Collector;
use metrics::core::{AtomicF64, Collector, GenericGauge};
use metrics::proto::MetricFamily;
use metrics::{IntCounterVec, UIntGaugeVec, register_int_counter_vec, register_uint_gauge_vec};
use metrics::{
IntCounterVec, IntGaugeVec, UIntGaugeVec, register_gauge, register_int_counter_vec,
register_int_gauge_vec, register_uint_gauge_vec,
};
use once_cell::sync::Lazy;
pub(crate) static INSTALLED_EXTENSIONS: Lazy<UIntGaugeVec> = Lazy::new(|| {
@@ -59,10 +62,31 @@ pub(crate) static REMOTE_EXT_REQUESTS_TOTAL: Lazy<IntCounterVec> = Lazy::new(||
.expect("failed to define a metric")
});
// Size of audit log directory in bytes
pub(crate) static AUDIT_LOG_DIR_SIZE: Lazy<GenericGauge<AtomicF64>> = Lazy::new(|| {
register_gauge!(
"compute_audit_log_dir_size",
"Size of audit log directory in bytes",
)
.expect("failed to define a metric")
});
// Report that `compute_ctl` is up and what's the current compute status.
pub(crate) static COMPUTE_CTL_UP: Lazy<IntGaugeVec> = Lazy::new(|| {
register_int_gauge_vec!(
"compute_ctl_up",
"Whether compute_ctl is running",
&["build_tag", "status"]
)
.expect("failed to define a metric")
});
pub fn collect() -> Vec<MetricFamily> {
let mut metrics = INSTALLED_EXTENSIONS.collect();
let mut metrics = COMPUTE_CTL_UP.collect();
metrics.extend(INSTALLED_EXTENSIONS.collect());
metrics.extend(CPLANE_REQUESTS_TOTAL.collect());
metrics.extend(REMOTE_EXT_REQUESTS_TOTAL.collect());
metrics.extend(DB_MIGRATION_FAILED.collect());
metrics.extend(AUDIT_LOG_DIR_SIZE.collect());
metrics
}

View File

@@ -10,8 +10,10 @@ use std::str::FromStr;
use std::time::{Duration, Instant};
use anyhow::{Result, bail};
use compute_api::responses::TlsConfig;
use compute_api::spec::{Database, GenericOption, GenericOptions, PgIdent, Role};
use futures::StreamExt;
use indexmap::IndexMap;
use ini::Ini;
use notify::{RecursiveMode, Watcher};
use postgres::config::Config;
@@ -206,8 +208,8 @@ impl Escaping for PgIdent {
/// Here we somewhat mimic the logic of Postgres' `pg_get_functiondef()`,
/// <https://github.com/postgres/postgres/blob/8b49392b270b4ac0b9f5c210e2a503546841e832/src/backend/utils/adt/ruleutils.c#L2924>
fn pg_quote_dollar(&self) -> (String, String) {
let mut tag: String = "".to_string();
let mut outer_tag = "x".to_string();
let mut tag: String = "x".to_string();
let mut outer_tag = "xx".to_string();
// Find the first suitable tag that is not present in the string.
// Postgres' max role/DB name length is 63 bytes, so even in the
@@ -406,7 +408,7 @@ pub fn create_pgdata(pgdata: &str) -> Result<()> {
/// Update pgbouncer.ini with provided options
fn update_pgbouncer_ini(
pgbouncer_config: HashMap<String, String>,
pgbouncer_config: IndexMap<String, String>,
pgbouncer_ini_path: &str,
) -> Result<()> {
let mut conf = Ini::load_from_file(pgbouncer_ini_path)?;
@@ -427,7 +429,10 @@ fn update_pgbouncer_ini(
/// Tune pgbouncer.
/// 1. Apply new config using pgbouncer admin console
/// 2. Add new values to pgbouncer.ini to preserve them after restart
pub async fn tune_pgbouncer(pgbouncer_config: HashMap<String, String>) -> Result<()> {
pub async fn tune_pgbouncer(
mut pgbouncer_config: IndexMap<String, String>,
tls_config: Option<TlsConfig>,
) -> Result<()> {
let pgbouncer_connstr = if std::env::var_os("AUTOSCALING").is_some() {
// for VMs use pgbouncer specific way to connect to
// pgbouncer admin console without password
@@ -473,19 +478,21 @@ pub async fn tune_pgbouncer(pgbouncer_config: HashMap<String, String>) -> Result
}
};
// Apply new config
for (option_name, value) in pgbouncer_config.iter() {
let query = format!("SET {}={}", option_name, value);
// keep this log line for debugging purposes
info!("Applying pgbouncer setting change: {}", query);
if let Some(tls_config) = tls_config {
// pgbouncer starts in a half-ok state if it cannot find these files.
// It will default to client_tls_sslmode=deny, which causes proxy to error.
// There is a small window at startup where these files don't yet exist in the VM.
// Best to wait until it exists.
loop {
if let Ok(true) = tokio::fs::try_exists(&tls_config.key_path).await {
break;
}
tokio::time::sleep(Duration::from_millis(500)).await
}
if let Err(err) = client.simple_query(&query).await {
// Don't fail on error, just print it into log
error!(
"Failed to apply pgbouncer setting change: {}, {}",
query, err
);
};
pgbouncer_config.insert("client_tls_cert_file".to_string(), tls_config.cert_path);
pgbouncer_config.insert("client_tls_key_file".to_string(), tls_config.key_path);
pgbouncer_config.insert("client_tls_sslmode".to_string(), "allow".to_string());
}
// save values to pgbouncer.ini
@@ -501,6 +508,13 @@ pub async fn tune_pgbouncer(pgbouncer_config: HashMap<String, String>) -> Result
};
update_pgbouncer_ini(pgbouncer_config, &pgbouncer_ini_path)?;
info!("Applying pgbouncer setting change");
if let Err(err) = client.simple_query("RELOAD").await {
// Don't fail on error, just print it into log
error!("Failed to apply pgbouncer setting change, {err}",);
};
Ok(())
}

View File

@@ -1,8 +1,14 @@
use std::fs;
use std::io::ErrorKind;
use std::path::Path;
use std::process::Command;
use std::time::Duration;
use std::{fs::OpenOptions, io::Write};
use anyhow::{Context, Result};
use tracing::info;
use anyhow::{Context, Result, anyhow};
use tracing::{error, info, instrument, warn};
const POSTGRES_LOGS_CONF_PATH: &str = "/etc/rsyslog.d/postgres_logs.conf";
fn get_rsyslog_pid() -> Option<String> {
let output = Command::new("pgrep")
@@ -43,7 +49,7 @@ fn restart_rsyslog() -> Result<()> {
}
pub fn configure_audit_rsyslog(
log_directory: &str,
log_directory: String,
tag: &str,
remote_endpoint: &str,
) -> Result<()> {
@@ -75,3 +81,196 @@ pub fn configure_audit_rsyslog(
Ok(())
}
/// Configuration for enabling Postgres logs forwarding from rsyslogd
pub struct PostgresLogsRsyslogConfig<'a> {
pub host: Option<&'a str>,
}
impl<'a> PostgresLogsRsyslogConfig<'a> {
pub fn new(host: Option<&'a str>) -> Self {
Self { host }
}
pub fn build(&self) -> Result<String> {
match self.host {
Some(host) => {
if let Some((target, port)) = host.split_once(":") {
Ok(format!(
include_str!(
"config_template/compute_rsyslog_postgres_export_template.conf"
),
logs_export_target = target,
logs_export_port = port,
))
} else {
Err(anyhow!("Invalid host format for Postgres logs export"))
}
}
None => Ok("".to_string()),
}
}
fn current_config() -> Result<String> {
let config_content = match std::fs::read_to_string(POSTGRES_LOGS_CONF_PATH) {
Ok(c) => c,
Err(err) if err.kind() == ErrorKind::NotFound => String::new(),
Err(err) => return Err(err.into()),
};
Ok(config_content)
}
/// Returns the default host for otel collector that receives Postgres logs
pub fn default_host(project_id: &str) -> String {
format!(
"config-{}-collector.neon-telemetry.svc.cluster.local:10514",
project_id
)
}
}
pub fn configure_postgres_logs_export(conf: PostgresLogsRsyslogConfig) -> Result<()> {
let new_config = conf.build()?;
let current_config = PostgresLogsRsyslogConfig::current_config()?;
if new_config == current_config {
info!("postgres logs rsyslog configuration is up-to-date");
return Ok(());
}
// When new config is empty we can simply remove the configuration file.
if new_config.is_empty() {
info!("removing rsyslog config file: {}", POSTGRES_LOGS_CONF_PATH);
match std::fs::remove_file(POSTGRES_LOGS_CONF_PATH) {
Ok(_) => {}
Err(err) if err.kind() == ErrorKind::NotFound => {}
Err(err) => return Err(err.into()),
}
restart_rsyslog()?;
return Ok(());
}
info!(
"configuring rsyslog for postgres logs export to: {:?}",
conf.host
);
let mut file = OpenOptions::new()
.create(true)
.write(true)
.truncate(true)
.open(POSTGRES_LOGS_CONF_PATH)?;
file.write_all(new_config.as_bytes())?;
info!(
"rsyslog configuration file {} added successfully. Starting rsyslogd",
POSTGRES_LOGS_CONF_PATH
);
restart_rsyslog()?;
Ok(())
}
#[instrument(skip_all)]
async fn pgaudit_gc_main_loop(log_directory: String) -> Result<()> {
info!("running pgaudit GC main loop");
loop {
// Check log_directory for old pgaudit logs and delete them.
// New log files are checked every 5 minutes, as set in pgaudit.log_rotation_age
// Find files that were not modified in the last 15 minutes and delete them.
// This should be enough time for rsyslog to process the logs and for us to catch the alerts.
//
// In case of a very high load, we might need to adjust this value and pgaudit.log_rotation_age.
//
// TODO: add some smarter logic to delete the files that are fully streamed according to rsyslog
// imfile-state files, but for now just do a simple GC to avoid filling up the disk.
let _ = Command::new("find")
.arg(&log_directory)
.arg("-name")
.arg("audit*.log")
.arg("-mmin")
.arg("+15")
.arg("-delete")
.output()?;
// also collect the metric for the size of the log directory
async fn get_log_files_size(path: &Path) -> Result<u64> {
let mut total_size = 0;
for entry in fs::read_dir(path)? {
let entry = entry?;
let entry_path = entry.path();
if entry_path.is_file() && entry_path.to_string_lossy().ends_with("log") {
total_size += entry.metadata()?.len();
}
}
Ok(total_size)
}
let log_directory_size = get_log_files_size(Path::new(&log_directory))
.await
.unwrap_or_else(|e| {
warn!("Failed to get log directory size: {}", e);
0
});
crate::metrics::AUDIT_LOG_DIR_SIZE.set(log_directory_size as f64);
tokio::time::sleep(Duration::from_secs(60)).await;
}
}
// launch pgaudit GC thread to clean up the old pgaudit logs stored in the log_directory
pub fn launch_pgaudit_gc(log_directory: String) {
tokio::spawn(async move {
if let Err(e) = pgaudit_gc_main_loop(log_directory).await {
error!("pgaudit GC main loop failed: {}", e);
}
});
}
#[cfg(test)]
mod tests {
use crate::rsyslog::PostgresLogsRsyslogConfig;
#[test]
fn test_postgres_logs_config() {
{
// Verify empty config
let conf = PostgresLogsRsyslogConfig::new(None);
let res = conf.build();
assert!(res.is_ok());
let conf_str = res.unwrap();
assert_eq!(&conf_str, "");
}
{
// Verify config
let conf = PostgresLogsRsyslogConfig::new(Some("collector.cvc.local:514"));
let res = conf.build();
assert!(res.is_ok());
let conf_str = res.unwrap();
assert!(conf_str.contains("omfwd"));
assert!(conf_str.contains(r#"target="collector.cvc.local""#));
assert!(conf_str.contains(r#"port="514""#));
}
{
// Verify invalid config
let conf = PostgresLogsRsyslogConfig::new(Some("invalid"));
let res = conf.build();
assert!(res.is_err());
}
{
// Verify config with default host
let host = PostgresLogsRsyslogConfig::default_host("shy-breeze-123");
let conf = PostgresLogsRsyslogConfig::new(Some(&host));
let res = conf.build();
assert!(res.is_ok());
let conf_str = res.unwrap();
assert!(conf_str.contains(r#"shy-breeze-123"#));
assert!(conf_str.contains(r#"port="10514""#));
}
}
}

View File

@@ -8,13 +8,12 @@ use compute_api::responses::{
use compute_api::spec::ComputeSpec;
use reqwest::StatusCode;
use tokio_postgres::Client;
use tracing::{error, info, instrument, warn};
use tracing::{error, info, instrument};
use crate::config;
use crate::metrics::{CPLANE_REQUESTS_TOTAL, CPlaneRequestRPC, UNKNOWN_HTTP_STATUS};
use crate::migration::MigrationRunner;
use crate::params::PG_HBA_ALL_MD5;
use crate::pg_helpers::*;
// Do control plane request and return response if any. In case of error it
// returns a bool flag indicating whether it makes sense to retry the request
@@ -212,122 +211,3 @@ pub async fn handle_migrations(client: &mut Client) -> Result<()> {
Ok(())
}
/// Connect to the database as superuser and pre-create anon extension
/// if it is present in shared_preload_libraries
#[instrument(skip_all)]
pub async fn handle_extension_anon(
spec: &ComputeSpec,
db_owner: &str,
db_client: &mut Client,
grants_only: bool,
) -> Result<()> {
info!("handle extension anon");
if let Some(libs) = spec.cluster.settings.find("shared_preload_libraries") {
if libs.contains("anon") {
if !grants_only {
// check if extension is already initialized using anon.is_initialized()
let query = "SELECT anon.is_initialized()";
match db_client.query(query, &[]).await {
Ok(rows) => {
if !rows.is_empty() {
let is_initialized: bool = rows[0].get(0);
if is_initialized {
info!("anon extension is already initialized");
return Ok(());
}
}
}
Err(e) => {
warn!(
"anon extension is_installed check failed with expected error: {}",
e
);
}
};
// Create anon extension if this compute needs it
// Users cannot create it themselves, because superuser is required.
let mut query = "CREATE EXTENSION IF NOT EXISTS anon CASCADE";
info!("creating anon extension with query: {}", query);
match db_client.query(query, &[]).await {
Ok(_) => {}
Err(e) => {
error!("anon extension creation failed with error: {}", e);
return Ok(());
}
}
// check that extension is installed
query = "SELECT extname FROM pg_extension WHERE extname = 'anon'";
let rows = db_client.query(query, &[]).await?;
if rows.is_empty() {
error!("anon extension is not installed");
return Ok(());
}
// Initialize anon extension
// This also requires superuser privileges, so users cannot do it themselves.
query = "SELECT anon.init()";
match db_client.query(query, &[]).await {
Ok(_) => {}
Err(e) => {
error!("anon.init() failed with error: {}", e);
return Ok(());
}
}
}
// check that extension is installed, if not bail early
let query = "SELECT extname FROM pg_extension WHERE extname = 'anon'";
match db_client.query(query, &[]).await {
Ok(rows) => {
if rows.is_empty() {
error!("anon extension is not installed");
return Ok(());
}
}
Err(e) => {
error!("anon extension check failed with error: {}", e);
return Ok(());
}
};
let query = format!("GRANT ALL ON SCHEMA anon TO {}", db_owner);
info!("granting anon extension permissions with query: {}", query);
db_client.simple_query(&query).await?;
// Grant permissions to db_owner to use anon extension functions
let query = format!("GRANT ALL ON ALL FUNCTIONS IN SCHEMA anon TO {}", db_owner);
info!("granting anon extension permissions with query: {}", query);
db_client.simple_query(&query).await?;
// This is needed, because some functions are defined as SECURITY DEFINER.
// In Postgres SECURITY DEFINER functions are executed with the privileges
// of the owner.
// In anon extension this it is needed to access some GUCs, which are only accessible to
// superuser. But we've patched postgres to allow db_owner to access them as well.
// So we need to change owner of these functions to db_owner.
let query = format!("
SELECT 'ALTER FUNCTION '||nsp.nspname||'.'||p.proname||'('||pg_get_function_identity_arguments(p.oid)||') OWNER TO {};'
from pg_proc p
join pg_namespace nsp ON p.pronamespace = nsp.oid
where nsp.nspname = 'anon';", db_owner);
info!("change anon extension functions owner to db owner");
db_client.simple_query(&query).await?;
// affects views as well
let query = format!("GRANT ALL ON ALL TABLES IN SCHEMA anon TO {}", db_owner);
info!("granting anon extension permissions with query: {}", query);
db_client.simple_query(&query).await?;
let query = format!("GRANT ALL ON ALL SEQUENCES IN SCHEMA anon TO {}", db_owner);
info!("granting anon extension permissions with query: {}", query);
db_client.simple_query(&query).await?;
}
}
Ok(())
}

View File

@@ -6,7 +6,7 @@ use std::sync::Arc;
use anyhow::{Context, Result};
use compute_api::responses::ComputeStatus;
use compute_api::spec::{ComputeAudit, ComputeFeature, ComputeSpec, Database, PgIdent, Role};
use compute_api::spec::{ComputeAudit, ComputeSpec, Database, PgIdent, Role};
use futures::future::join_all;
use tokio::sync::RwLock;
use tokio_postgres::Client;
@@ -26,7 +26,7 @@ use crate::spec_apply::ApplySpecPhase::{
RunInEachDatabase,
};
use crate::spec_apply::PerDatabasePhase::{
ChangeSchemaPerms, DeleteDBRoleReferences, DropLogicalSubscriptions, HandleAnonExtension,
ChangeSchemaPerms, DeleteDBRoleReferences, DropLogicalSubscriptions,
};
impl ComputeNode {
@@ -75,15 +75,12 @@ impl ComputeNode {
if spec.drop_subscriptions_before_start {
let timeline_id = self.get_timeline_id().context("timeline_id must be set")?;
let query = format!("select 1 from neon.drop_subscriptions_done where timeline_id = '{}'", timeline_id);
info!("Checking if drop subscription operation was already performed for timeline_id: {}", timeline_id);
drop_subscriptions_done = match
client.simple_query(&query).await {
Ok(result) => {
matches!(&result[0], postgres::SimpleQueryMessage::Row(_))
},
drop_subscriptions_done = match
client.query("select 1 from neon.drop_subscriptions_done where timeline_id = $1", &[&timeline_id.to_string()]).await {
Ok(result) => !result.is_empty(),
Err(e) =>
{
match e.code() {
@@ -238,7 +235,6 @@ impl ComputeNode {
let mut phases = vec![
DeleteDBRoleReferences,
ChangeSchemaPerms,
HandleAnonExtension,
];
if spec.drop_subscriptions_before_start && !drop_subscriptions_done {
@@ -287,7 +283,10 @@ impl ComputeNode {
phases.push(CreatePgauditlogtofileExtension);
phases.push(DisablePostgresDBPgAudit);
}
ComputeAudit::Log => { /* not implemented yet */ }
ComputeAudit::Log => {
phases.push(CreatePgauditExtension);
phases.push(DisablePostgresDBPgAudit);
}
ComputeAudit::Disabled => {}
}
@@ -420,7 +419,7 @@ impl ComputeNode {
.iter()
.filter_map(|val| val.parse::<usize>().ok())
.map(|val| if val > 1 { val - 1 } else { 1 })
.last()
.next_back()
.unwrap_or(3)
}
}
@@ -458,7 +457,6 @@ impl Debug for DB {
pub enum PerDatabasePhase {
DeleteDBRoleReferences,
ChangeSchemaPerms,
HandleAnonExtension,
/// This is a shared phase, used for both i) dropping dangling LR subscriptions
/// before dropping the DB, and ii) dropping all subscriptions after creating
/// a fresh branch.
@@ -1012,98 +1010,6 @@ async fn get_operations<'a>(
]
.into_iter();
Ok(Box::new(operations))
}
// TODO: remove this completely https://github.com/neondatabase/cloud/issues/22663
PerDatabasePhase::HandleAnonExtension => {
// Only install Anon into user databases
let db = match &db {
DB::SystemDB => return Ok(Box::new(empty())),
DB::UserDB(db) => db,
};
// Never install Anon when it's not enabled as feature
if !spec.features.contains(&ComputeFeature::AnonExtension) {
return Ok(Box::new(empty()));
}
// Only install Anon when it's added in preload libraries
let opt_libs = spec.cluster.settings.find("shared_preload_libraries");
let libs = match opt_libs {
Some(libs) => libs,
None => return Ok(Box::new(empty())),
};
if !libs.contains("anon") {
return Ok(Box::new(empty()));
}
let db_owner = db.owner.pg_quote();
let operations = vec![
// Create anon extension if this compute needs it
// Users cannot create it themselves, because superuser is required.
Operation {
query: String::from("CREATE EXTENSION IF NOT EXISTS anon CASCADE"),
comment: Some(String::from("creating anon extension")),
},
// Initialize anon extension
// This also requires superuser privileges, so users cannot do it themselves.
Operation {
query: String::from("SELECT anon.init()"),
comment: Some(String::from("initializing anon extension data")),
},
Operation {
query: format!("GRANT ALL ON SCHEMA anon TO {}", db_owner),
comment: Some(String::from(
"granting anon extension schema permissions",
)),
},
Operation {
query: format!(
"GRANT ALL ON ALL FUNCTIONS IN SCHEMA anon TO {}",
db_owner
),
comment: Some(String::from(
"granting anon extension schema functions permissions",
)),
},
// We need this, because some functions are defined as SECURITY DEFINER.
// In Postgres SECURITY DEFINER functions are executed with the privileges
// of the owner.
// In anon extension this it is needed to access some GUCs, which are only accessible to
// superuser. But we've patched postgres to allow db_owner to access them as well.
// So we need to change owner of these functions to db_owner.
Operation {
query: format!(
include_str!("sql/anon_ext_fn_reassign.sql"),
db_owner = db_owner,
),
comment: Some(String::from(
"change anon extension functions owner to database_owner",
)),
},
Operation {
query: format!(
"GRANT ALL ON ALL TABLES IN SCHEMA anon TO {}",
db_owner,
),
comment: Some(String::from(
"granting anon extension tables permissions",
)),
},
Operation {
query: format!(
"GRANT ALL ON ALL SEQUENCES IN SCHEMA anon TO {}",
db_owner,
),
comment: Some(String::from(
"granting anon extension sequences permissions",
)),
},
]
.into_iter();
Ok(Box::new(operations))
}
}

117
compute_tools/src/tls.rs Normal file
View File

@@ -0,0 +1,117 @@
use std::{io::Write, os::unix::fs::OpenOptionsExt, path::Path, time::Duration};
use anyhow::{Context, Result, bail};
use compute_api::responses::TlsConfig;
use ring::digest;
use spki::der::{Decode, PemReader};
use x509_cert::Certificate;
#[derive(Clone, Copy)]
pub struct CertDigest(digest::Digest);
pub async fn watch_cert_for_changes(cert_path: String) -> tokio::sync::watch::Receiver<CertDigest> {
let mut digest = compute_digest(&cert_path).await;
let (tx, rx) = tokio::sync::watch::channel(digest);
tokio::spawn(async move {
while !tx.is_closed() {
let new_digest = compute_digest(&cert_path).await;
if digest.0.as_ref() != new_digest.0.as_ref() {
digest = new_digest;
_ = tx.send(digest);
}
tokio::time::sleep(Duration::from_secs(60)).await
}
});
rx
}
async fn compute_digest(cert_path: &str) -> CertDigest {
loop {
match try_compute_digest(cert_path).await {
Ok(d) => break d,
Err(e) => {
tracing::error!("could not read cert file {e:?}");
tokio::time::sleep(Duration::from_secs(1)).await
}
}
}
}
async fn try_compute_digest(cert_path: &str) -> Result<CertDigest> {
let data = tokio::fs::read(cert_path).await?;
// sha256 is extremely collision resistent. can safely assume the digest to be unique
Ok(CertDigest(digest::digest(&digest::SHA256, &data)))
}
pub const SERVER_CRT: &str = "server.crt";
pub const SERVER_KEY: &str = "server.key";
pub fn update_key_path_blocking(pg_data: &Path, tls_config: &TlsConfig) {
loop {
match try_update_key_path_blocking(pg_data, tls_config) {
Ok(()) => break,
Err(e) => {
tracing::error!("could not create key file {e:?}");
std::thread::sleep(Duration::from_secs(1))
}
}
}
}
// Postgres requires the keypath be "secure". This means
// 1. Owned by the postgres user.
// 2. Have permission 600.
fn try_update_key_path_blocking(pg_data: &Path, tls_config: &TlsConfig) -> Result<()> {
let key = std::fs::read_to_string(&tls_config.key_path)?;
let crt = std::fs::read_to_string(&tls_config.cert_path)?;
// to mitigate a race condition during renewal.
verify_key_cert(&key, &crt)?;
let mut key_file = std::fs::OpenOptions::new()
.write(true)
.create(true)
.truncate(true)
.mode(0o600)
.open(pg_data.join(SERVER_KEY))?;
let mut crt_file = std::fs::OpenOptions::new()
.write(true)
.create(true)
.truncate(true)
.mode(0o600)
.open(pg_data.join(SERVER_CRT))?;
key_file.write_all(key.as_bytes())?;
crt_file.write_all(crt.as_bytes())?;
Ok(())
}
fn verify_key_cert(key: &str, cert: &str) -> Result<()> {
use x509_cert::der::oid::db::rfc5912::ECDSA_WITH_SHA_256;
let cert = Certificate::decode(&mut PemReader::new(cert.as_bytes()).context("pem reader")?)
.context("decode cert")?;
match cert.signature_algorithm.oid {
ECDSA_WITH_SHA_256 => {
let key = p256::SecretKey::from_sec1_pem(key).context("parse key")?;
let a = key.public_key().to_sec1_bytes();
let b = cert
.tbs_certificate
.subject_public_key_info
.subject_public_key
.raw_bytes();
if *a != *b {
bail!("private key file does not match certificate")
}
}
_ => bail!("unknown TLS key type"),
}
Ok(())
}

View File

@@ -64,7 +64,8 @@ test.escaping = 'here''s a backslash \\ and a quote '' and a double-quote " hoor
#[test]
fn ident_pg_quote_dollar() {
let test_cases = vec![
("name", ("$$name$$", "x")),
("name", ("$x$name$x$", "xx")),
("name$", ("$x$name$$x$", "xx")),
("name$$", ("$x$name$$$x$", "xx")),
("name$$$", ("$x$name$$$$x$", "xx")),
("name$$$$", ("$x$name$$$$$x$", "xx")),

View File

@@ -979,7 +979,7 @@ fn handle_init(args: &InitCmdArgs) -> anyhow::Result<LocalEnv> {
neon_distrib_dir: None,
default_tenant_id: TenantId::from_array(std::array::from_fn(|_| 0)),
storage_controller: None,
control_plane_compute_hook_api: None,
control_plane_hooks_api: None,
generate_local_ssl_certs: false,
}
};

View File

@@ -72,9 +72,9 @@ pub struct LocalEnv {
// be propagated into each pageserver's configuration.
pub control_plane_api: Url,
// Control plane upcall API for storage controller. If set, this will be propagated into the
// Control plane upcall APIs for storage controller. If set, this will be propagated into the
// storage controller's configuration.
pub control_plane_compute_hook_api: Option<Url>,
pub control_plane_hooks_api: Option<Url>,
/// Keep human-readable aliases in memory (and persist them to config), to hide ZId hex strings from the user.
// A `HashMap<String, HashMap<TenantId, TimelineId>>` would be more appropriate here,
@@ -104,6 +104,7 @@ pub struct OnDiskConfig {
pub pageservers: Vec<PageServerConf>,
pub safekeepers: Vec<SafekeeperConf>,
pub control_plane_api: Option<Url>,
pub control_plane_hooks_api: Option<Url>,
pub control_plane_compute_hook_api: Option<Url>,
branch_name_mappings: HashMap<String, Vec<(TenantId, TimelineId)>>,
// Note: skip serializing because in compat tests old storage controller fails
@@ -136,7 +137,7 @@ pub struct NeonLocalInitConf {
pub pageservers: Vec<NeonLocalInitPageserverConf>,
pub safekeepers: Vec<SafekeeperConf>,
pub control_plane_api: Option<Url>,
pub control_plane_compute_hook_api: Option<Option<Url>>,
pub control_plane_hooks_api: Option<Url>,
pub generate_local_ssl_certs: bool,
}
@@ -148,7 +149,7 @@ pub struct NeonBroker {
pub listen_addr: SocketAddr,
}
/// Broker config for cluster internal communication.
/// A part of storage controller's config the neon_local knows about.
#[derive(Serialize, Deserialize, PartialEq, Eq, Clone, Debug)]
#[serde(default)]
pub struct NeonStorageControllerConf {
@@ -164,8 +165,11 @@ pub struct NeonStorageControllerConf {
/// Database url used when running multiple storage controller instances
pub database_url: Option<SocketAddr>,
/// Threshold for auto-splitting a tenant into shards
/// Thresholds for auto-splitting a tenant into shards.
pub split_threshold: Option<u64>,
pub max_split_shards: Option<u8>,
pub initial_split_threshold: Option<u64>,
pub initial_split_shards: Option<u8>,
pub max_secondary_lag_bytes: Option<u64>,
@@ -175,10 +179,13 @@ pub struct NeonStorageControllerConf {
#[serde(with = "humantime_serde")]
pub long_reconcile_threshold: Option<Duration>,
#[serde(default)]
pub use_https_pageserver_api: bool,
pub timelines_onto_safekeepers: bool,
pub use_https_safekeeper_api: bool,
pub use_local_compute_notifications: bool,
}
impl NeonStorageControllerConf {
@@ -199,11 +206,16 @@ impl Default for NeonStorageControllerConf {
start_as_candidate: false,
database_url: None,
split_threshold: None,
max_split_shards: None,
initial_split_threshold: None,
initial_split_shards: None,
max_secondary_lag_bytes: None,
heartbeat_interval: Self::DEFAULT_HEARTBEAT_INTERVAL,
long_reconcile_threshold: None,
use_https_pageserver_api: false,
timelines_onto_safekeepers: false,
use_https_safekeeper_api: false,
use_local_compute_notifications: true,
}
}
}
@@ -301,6 +313,7 @@ pub struct SafekeeperConf {
pub pg_port: u16,
pub pg_tenant_only_port: Option<u16>,
pub http_port: u16,
pub https_port: Option<u16>,
pub sync: bool,
pub remote_storage: Option<String>,
pub backup_threads: Option<u32>,
@@ -315,6 +328,7 @@ impl Default for SafekeeperConf {
pg_port: 0,
pg_tenant_only_port: None,
http_port: 0,
https_port: None,
sync: true,
remote_storage: None,
backup_threads: None,
@@ -573,7 +587,8 @@ impl LocalEnv {
pageservers,
safekeepers,
control_plane_api,
control_plane_compute_hook_api,
control_plane_hooks_api,
control_plane_compute_hook_api: _,
branch_name_mappings,
generate_local_ssl_certs,
} = on_disk_config;
@@ -588,7 +603,7 @@ impl LocalEnv {
pageservers,
safekeepers,
control_plane_api: control_plane_api.unwrap(),
control_plane_compute_hook_api,
control_plane_hooks_api,
branch_name_mappings,
generate_local_ssl_certs,
}
@@ -695,7 +710,8 @@ impl LocalEnv {
pageservers: vec![], // it's skip_serializing anyway
safekeepers: self.safekeepers.clone(),
control_plane_api: Some(self.control_plane_api.clone()),
control_plane_compute_hook_api: self.control_plane_compute_hook_api.clone(),
control_plane_hooks_api: self.control_plane_hooks_api.clone(),
control_plane_compute_hook_api: None,
branch_name_mappings: self.branch_name_mappings.clone(),
generate_local_ssl_certs: self.generate_local_ssl_certs,
},
@@ -779,8 +795,8 @@ impl LocalEnv {
pageservers,
safekeepers,
control_plane_api,
control_plane_compute_hook_api,
generate_local_ssl_certs,
control_plane_hooks_api,
} = conf;
// Find postgres binaries.
@@ -827,7 +843,7 @@ impl LocalEnv {
pageservers: pageservers.iter().map(Into::into).collect(),
safekeepers,
control_plane_api: control_plane_api.unwrap(),
control_plane_compute_hook_api: control_plane_compute_hook_api.unwrap_or_default(),
control_plane_hooks_api,
branch_name_mappings: Default::default(),
generate_local_ssl_certs,
};
@@ -842,6 +858,9 @@ impl LocalEnv {
// create safekeeper dirs
for safekeeper in &env.safekeepers {
fs::create_dir_all(SafekeeperNode::datadir_path_by_id(&env, safekeeper.id))?;
SafekeeperNode::from_env(&env, safekeeper)
.initialize()
.context("safekeeper init failed")?;
}
// initialize pageserver state

View File

@@ -51,11 +51,19 @@ impl PageServerNode {
parse_host_port(&conf.listen_pg_addr).expect("Unable to parse listen_pg_addr");
let port = port.unwrap_or(5432);
let ssl_ca_cert = env.ssl_ca_cert_path().map(|ssl_ca_file| {
let ssl_ca_certs = env.ssl_ca_cert_path().map(|ssl_ca_file| {
let buf = std::fs::read(ssl_ca_file).expect("SSL root CA file should exist");
Certificate::from_pem(&buf).expect("CA certificate should be valid")
Certificate::from_pem_bundle(&buf).expect("SSL CA file should be valid")
});
let mut http_client = reqwest::Client::builder();
for ssl_ca_cert in ssl_ca_certs.unwrap_or_default() {
http_client = http_client.add_root_certificate(ssl_ca_cert);
}
let http_client = http_client
.build()
.expect("Client constructs with no errors");
let endpoint = if env.storage_controller.use_https_pageserver_api {
format!(
"https://{}",
@@ -72,6 +80,7 @@ impl PageServerNode {
conf: conf.clone(),
env: env.clone(),
http_client: mgmt_api::Client::new(
http_client,
endpoint,
{
match conf.http_auth_type {
@@ -83,9 +92,7 @@ impl PageServerNode {
}
}
.as_deref(),
ssl_ca_cert,
)
.expect("Client constructs with no errors"),
),
}
}
@@ -142,6 +149,10 @@ impl PageServerNode {
overrides.push("auth_validation_public_key_path='../auth_public_key.pem'".to_owned());
}
if let Some(ssl_ca_file) = self.env.ssl_ca_cert_path() {
overrides.push(format!("ssl_ca_file='{}'", ssl_ca_file.to_str().unwrap()));
}
// Apply the user-provided overrides
overrides.push({
let mut doc =
@@ -417,11 +428,6 @@ impl PageServerNode {
.map(|x| x.parse::<usize>())
.transpose()
.context("Failed to parse 'l0_flush_delay_threshold' as an integer")?,
l0_flush_wait_upload: settings
.remove("l0_flush_wait_upload")
.map(|x| x.parse::<bool>())
.transpose()
.context("Failed to parse 'l0_flush_wait_upload' as a boolean")?,
l0_flush_stall_threshold: settings
.remove("l0_flush_stall_threshold")
.map(|x| x.parse::<usize>())
@@ -539,6 +545,11 @@ impl PageServerNode {
.map(|x| x.parse::<u64>())
.transpose()
.context("Failed to parse 'gc_compaction_ratio_percent' as integer")?,
sampling_ratio: settings
.remove("sampling_ratio")
.map(serde_json::from_str)
.transpose()
.context("Falied to parse 'sampling_ratio'")?,
};
if !settings.is_empty() {
bail!("Unrecognized tenant settings: {settings:?}")

View File

@@ -111,6 +111,18 @@ impl SafekeeperNode {
.expect("non-Unicode path")
}
/// Initializes a safekeeper node by creating all necessary files,
/// e.g. SSL certificates.
pub fn initialize(&self) -> anyhow::Result<()> {
if self.env.generate_local_ssl_certs {
self.env.generate_ssl_cert(
&self.datadir_path().join("server.crt"),
&self.datadir_path().join("server.key"),
)?;
}
Ok(())
}
pub async fn start(
&self,
extra_opts: &[String],
@@ -196,6 +208,16 @@ impl SafekeeperNode {
]);
}
if let Some(https_port) = self.conf.https_port {
args.extend([
"--listen-https".to_owned(),
format!("{}:{}", self.listen_addr, https_port),
]);
}
if let Some(ssl_ca_file) = self.env.ssl_ca_cert_path() {
args.push(format!("--ssl-ca-file={}", ssl_ca_file.to_str().unwrap()));
}
args.extend_from_slice(extra_opts);
background_process::start_process(

View File

@@ -1,6 +1,5 @@
use std::ffi::OsStr;
use std::fs;
use std::net::SocketAddr;
use std::path::PathBuf;
use std::process::ExitStatus;
use std::str::FromStr;
@@ -18,7 +17,7 @@ use pageserver_api::models::{TenantConfigRequest, TimelineCreateRequest, Timelin
use pageserver_api::shard::TenantShardId;
use pageserver_client::mgmt_api::ResponseErrorMessageExt;
use postgres_backend::AuthType;
use reqwest::Method;
use reqwest::{Certificate, Method};
use serde::de::DeserializeOwned;
use serde::{Deserialize, Serialize};
use tokio::process::Command;
@@ -38,9 +37,9 @@ pub struct StorageController {
client: reqwest::Client,
config: NeonStorageControllerConf,
// The listen addresses is learned when starting the storage controller,
// The listen port is learned when starting the storage controller,
// hence the use of OnceLock to init it at the right time.
listen: OnceLock<SocketAddr>,
listen_port: OnceLock<u16>,
}
const COMMAND: &str = "storage_controller";
@@ -144,15 +143,26 @@ impl StorageController {
}
};
let ssl_ca_certs = env.ssl_ca_cert_path().map(|ssl_ca_file| {
let buf = std::fs::read(ssl_ca_file).expect("SSL CA file should exist");
Certificate::from_pem_bundle(&buf).expect("SSL CA file should be valid")
});
let mut http_client = reqwest::Client::builder();
for ssl_ca_cert in ssl_ca_certs.unwrap_or_default() {
http_client = http_client.add_root_certificate(ssl_ca_cert);
}
let http_client = http_client
.build()
.expect("HTTP client should construct with no error");
Self {
env: env.clone(),
private_key,
public_key,
client: reqwest::ClientBuilder::new()
.build()
.expect("Failed to construct http client"),
client: http_client,
config: env.storage_controller.clone(),
listen: OnceLock::default(),
listen_port: OnceLock::default(),
}
}
@@ -337,34 +347,34 @@ impl StorageController {
}
}
let (listen, postgres_port) = {
if let Some(base_port) = start_args.base_port {
(
format!("127.0.0.1:{base_port}"),
self.config
.database_url
.expect("--base-port requires NeonStorageControllerConf::database_url")
.port(),
)
} else {
let listen_url = self.env.control_plane_api.clone();
if self.env.generate_local_ssl_certs {
self.env.generate_ssl_cert(
&instance_dir.join("server.crt"),
&instance_dir.join("server.key"),
)?;
}
let listen = format!(
"{}:{}",
listen_url.host_str().unwrap(),
listen_url.port().unwrap()
);
let listen_url = &self.env.control_plane_api;
(listen, listen_url.port().unwrap() + 1)
}
let scheme = listen_url.scheme();
let host = listen_url.host_str().unwrap();
let (listen_port, postgres_port) = if let Some(base_port) = start_args.base_port {
(
base_port,
self.config
.database_url
.expect("--base-port requires NeonStorageControllerConf::database_url")
.port(),
)
} else {
let port = listen_url.port().unwrap();
(port, port + 1)
};
let socket_addr = listen
.parse()
.expect("listen address is a valid socket address");
self.listen
.set(socket_addr)
.expect("StorageController::listen is only set here");
self.listen_port
.set(listen_port)
.expect("StorageController::listen_port is only set here");
// Do we remove the pid file on stop?
let pg_started = self.is_postgres_running().await?;
@@ -500,20 +510,15 @@ impl StorageController {
drop(client);
conn.await??;
let listen = self
.listen
.get()
.expect("cell is set earlier in this function");
let addr = format!("{}:{}", host, listen_port);
let address_for_peers = Uri::builder()
.scheme("http")
.authority(format!("{}:{}", listen.ip(), listen.port()))
.scheme(scheme)
.authority(addr.clone())
.path_and_query("")
.build()
.unwrap();
let mut args = vec![
"-l",
&listen.to_string(),
"--dev",
"--database-url",
&database_url,
@@ -530,6 +535,14 @@ impl StorageController {
.map(|s| s.to_string())
.collect::<Vec<_>>();
match scheme {
"http" => args.extend(["--listen".to_string(), addr]),
"https" => args.extend(["--listen-https".to_string(), addr]),
_ => {
panic!("Unexpected url scheme in control_plane_api: {scheme}");
}
}
if self.config.start_as_candidate {
args.push("--start-as-candidate".to_string());
}
@@ -538,6 +551,14 @@ impl StorageController {
args.push("--use-https-pageserver-api".to_string());
}
if self.config.use_https_safekeeper_api {
args.push("--use-https-safekeeper-api".to_string());
}
if self.config.use_local_compute_notifications {
args.push("--use-local-compute-notifications".to_string());
}
if let Some(ssl_ca_file) = self.env.ssl_ca_cert_path() {
args.push(format!("--ssl-ca-file={}", ssl_ca_file.to_str().unwrap()));
}
@@ -558,16 +579,28 @@ impl StorageController {
args.push(format!("--public-key=\"{public_key}\""));
}
if let Some(control_plane_compute_hook_api) = &self.env.control_plane_compute_hook_api {
args.push(format!(
"--compute-hook-url={control_plane_compute_hook_api}"
));
if let Some(control_plane_hooks_api) = &self.env.control_plane_hooks_api {
args.push(format!("--control-plane-url={control_plane_hooks_api}"));
}
if let Some(split_threshold) = self.config.split_threshold.as_ref() {
args.push(format!("--split-threshold={split_threshold}"))
}
if let Some(max_split_shards) = self.config.max_split_shards.as_ref() {
args.push(format!("--max-split-shards={max_split_shards}"))
}
if let Some(initial_split_threshold) = self.config.initial_split_threshold.as_ref() {
args.push(format!(
"--initial-split-threshold={initial_split_threshold}"
))
}
if let Some(initial_split_shards) = self.config.initial_split_shards.as_ref() {
args.push(format!("--initial-split-shards={initial_split_shards}"))
}
if let Some(lag) = self.config.max_secondary_lag_bytes.as_ref() {
args.push(format!("--max-secondary-lag-bytes={lag}"))
}
@@ -588,6 +621,8 @@ impl StorageController {
args.push("--timelines-onto-safekeepers".to_string());
}
println!("Starting storage controller");
background_process::start_process(
COMMAND,
&instance_dir,
@@ -714,30 +749,26 @@ impl StorageController {
{
// In the special case of the `storage_controller start` subcommand, we wish
// to use the API endpoint of the newly started storage controller in order
// to pass the readiness check. In this scenario [`Self::listen`] will be set
// (see [`Self::start`]).
// to pass the readiness check. In this scenario [`Self::listen_port`] will
// be set (see [`Self::start`]).
//
// Otherwise, we infer the storage controller api endpoint from the configured
// control plane API.
let url = if let Some(socket_addr) = self.listen.get() {
Url::from_str(&format!(
"http://{}:{}/{path}",
socket_addr.ip().to_canonical(),
socket_addr.port()
))
.unwrap()
let port = if let Some(port) = self.listen_port.get() {
*port
} else {
// The configured URL has the /upcall path prefix for pageservers to use: we will strip that out
// for general purpose API access.
let listen_url = self.env.control_plane_api.clone();
Url::from_str(&format!(
"http://{}:{}/{path}",
listen_url.host_str().unwrap(),
listen_url.port().unwrap()
))
.unwrap()
self.env.control_plane_api.port().unwrap()
};
// The configured URL has the /upcall path prefix for pageservers to use: we will strip that out
// for general purpose API access.
let url = Url::from_str(&format!(
"{}://{}:{port}/{path}",
self.env.control_plane_api.scheme(),
self.env.control_plane_api.host_str().unwrap(),
))
.unwrap();
let mut builder = self.client.request(method, url);
if let Some(body) = body {
builder = builder.json(&body)

View File

@@ -20,7 +20,7 @@ use pageserver_api::models::{
};
use pageserver_api::shard::{ShardStripeSize, TenantShardId};
use pageserver_client::mgmt_api::{self};
use reqwest::{Method, StatusCode, Url};
use reqwest::{Certificate, Method, StatusCode, Url};
use storage_controller_client::control_api::Client;
use utils::id::{NodeId, TenantId, TimelineId};
@@ -274,7 +274,7 @@ struct Cli {
jwt: Option<String>,
#[arg(long)]
/// Trusted root CA certificate to use in https APIs.
/// Trusted root CA certificates to use in https APIs.
ssl_ca_file: Option<PathBuf>,
#[command(subcommand)]
@@ -385,19 +385,25 @@ where
async fn main() -> anyhow::Result<()> {
let cli = Cli::parse();
let storcon_client = Client::new(cli.api.clone(), cli.jwt.clone());
let ssl_ca_cert = match &cli.ssl_ca_file {
let ssl_ca_certs = match &cli.ssl_ca_file {
Some(ssl_ca_file) => {
let buf = tokio::fs::read(ssl_ca_file).await?;
Some(reqwest::Certificate::from_pem(&buf)?)
Certificate::from_pem_bundle(&buf)?
}
None => None,
None => Vec::new(),
};
let mut http_client = reqwest::Client::builder();
for ssl_ca_cert in ssl_ca_certs {
http_client = http_client.add_root_certificate(ssl_ca_cert);
}
let http_client = http_client.build()?;
let storcon_client = Client::new(http_client.clone(), cli.api.clone(), cli.jwt.clone());
let mut trimmed = cli.api.to_string();
trimmed.pop();
let vps_client = mgmt_api::Client::new(trimmed, cli.jwt.as_deref(), ssl_ca_cert)?;
let vps_client = mgmt_api::Client::new(http_client.clone(), trimmed, cli.jwt.as_deref());
match cli.command {
Command::NodeRegister {
@@ -1050,7 +1056,7 @@ async fn main() -> anyhow::Result<()> {
const DEFAULT_MIGRATE_CONCURRENCY: usize = 8;
let mut stream = futures::stream::iter(moves)
.map(|mv| {
let client = Client::new(cli.api.clone(), cli.jwt.clone());
let client = Client::new(http_client.clone(), cli.api.clone(), cli.jwt.clone());
async move {
client
.dispatch::<TenantShardMigrateRequest, TenantShardMigrateResponse>(

View File

@@ -31,10 +31,6 @@ reason = "the marvin attack only affects private key decryption, not public key
id = "RUSTSEC-2024-0436"
reason = "The paste crate is a build-only dependency with no runtime components. It is unlikely to have any security impact."
[[advisories.ignore]]
id = "RUSTSEC-2025-0014"
reason = "The humantime is widely used and is not easy to replace right now. It is unmaintained, but it has no known vulnerabilities to care about. #11179"
# This section is considered when running `cargo deny check licenses`
# More documentation for the licenses section can be found here:
# https://embarkstudios.github.io/cargo-deny/checks/licenses/cfg.html

View File

@@ -1,4 +1,4 @@
ARG REPOSITORY=neondatabase
ARG REPOSITORY=ghcr.io/neondatabase
ARG COMPUTE_IMAGE=compute-node-v14
ARG TAG=latest

View File

@@ -67,6 +67,14 @@ else
fi
fi
if [[ ${PG_VERSION} -ge 17 ]]; then
ulid_extension=pgx_ulid
else
ulid_extension=ulid
fi
echo "Adding pgx_ulid"
shared_libraries=$(jq -r '.cluster.settings[] | select(.name=="shared_preload_libraries").value' ${SPEC_FILE})
sed -i "s/${shared_libraries}/${shared_libraries},${ulid_extension}/" ${SPEC_FILE}
echo "Overwrite tenant id and timeline id in spec file"
sed -i "s/TENANT_ID/${tenant_id}/" ${SPEC_FILE}
sed -i "s/TIMELINE_ID/${timeline_id}/" ${SPEC_FILE}

View File

@@ -29,7 +29,7 @@ services:
pageserver:
restart: always
image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
image: ${REPOSITORY:-ghcr.io/neondatabase}/neon:${TAG:-latest}
environment:
- AWS_ACCESS_KEY_ID=minio
- AWS_SECRET_ACCESS_KEY=password
@@ -45,7 +45,7 @@ services:
safekeeper1:
restart: always
image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
image: ${REPOSITORY:-ghcr.io/neondatabase}/neon:${TAG:-latest}
environment:
- SAFEKEEPER_ADVERTISE_URL=safekeeper1:5454
- SAFEKEEPER_ID=1
@@ -75,7 +75,7 @@ services:
safekeeper2:
restart: always
image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
image: ${REPOSITORY:-ghcr.io/neondatabase}/neon:${TAG:-latest}
environment:
- SAFEKEEPER_ADVERTISE_URL=safekeeper2:5454
- SAFEKEEPER_ID=2
@@ -105,7 +105,7 @@ services:
safekeeper3:
restart: always
image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
image: ${REPOSITORY:-ghcr.io/neondatabase}/neon:${TAG:-latest}
environment:
- SAFEKEEPER_ADVERTISE_URL=safekeeper3:5454
- SAFEKEEPER_ID=3
@@ -135,7 +135,7 @@ services:
storage_broker:
restart: always
image: ${REPOSITORY:-neondatabase}/neon:${TAG:-latest}
image: ${REPOSITORY:-ghcr.io/neondatabase}/neon:${TAG:-latest}
ports:
- 50051:50051
command:
@@ -147,7 +147,7 @@ services:
build:
context: ./compute_wrapper/
args:
- REPOSITORY=${REPOSITORY:-neondatabase}
- REPOSITORY=${REPOSITORY:-ghcr.io/neondatabase}
- COMPUTE_IMAGE=compute-node-v${PG_VERSION:-16}
- TAG=${COMPUTE_TAG:-${TAG:-latest}}
- http_proxy=${http_proxy:-}
@@ -186,7 +186,7 @@ services:
neon-test-extensions:
profiles: ["test-extensions"]
image: ${REPOSITORY:-neondatabase}/neon-test-extensions-v${PG_TEST_VERSION:-16}:${TEST_EXTENSIONS_TAG:-${TAG:-latest}}
image: ${REPOSITORY:-ghcr.io/neondatabase}/neon-test-extensions-v${PG_TEST_VERSION:-16}:${TEST_EXTENSIONS_TAG:-${TAG:-latest}}
environment:
- PGPASSWORD=cloud_admin
entrypoint:

View File

@@ -69,7 +69,7 @@ for pg_version in ${TEST_VERSION_ONLY-14 15 16 17}; do
cat ../compute/patches/contrib_pg${pg_version}.patch | docker exec -i $TEST_CONTAINER_NAME bash -c "(cd /postgres && patch -p1)"
# We are running tests now
rm -f testout.txt testout_contrib.txt
docker exec -e USE_PGXS=1 -e SKIP=timescaledb-src,rdkit-src,postgis-src,pgx_ulid-src,pg_tiktoken-src,pg_jsonschema-src,kq_imcx-src,wal2json_2_5-src \
docker exec -e USE_PGXS=1 -e SKIP=timescaledb-src,rdkit-src,postgis-src,pg_jsonschema-src,kq_imcx-src,wal2json_2_5-src,rag_jina_reranker_v1_tiny_en-src,rag_bge_small_en_v15-src \
$TEST_CONTAINER_NAME /run-tests.sh /ext-src | tee testout.txt && EXT_SUCCESS=1 || EXT_SUCCESS=0
docker exec -e SKIP=start-scripts,postgres_fdw,ltree_plpython,jsonb_plpython,jsonb_plperl,hstore_plpython,hstore_plperl,dblink,bool_plperl \
$TEST_CONTAINER_NAME /run-tests.sh /postgres/contrib | tee testout_contrib.txt && CONTRIB_SUCCESS=1 || CONTRIB_SUCCESS=0

View File

@@ -0,0 +1,8 @@
PG_CONFIG ?= pg_config
PG_REGRESS = $(shell dirname $$($(PG_CONFIG) --pgxs))/../../src/test/regress/pg_regress
REGRESS = pg_tiktoken
installcheck: regression-test
regression-test:
$(PG_REGRESS) --inputdir=. --outputdir=. --dbname=contrib_regression $(REGRESS)

View File

@@ -0,0 +1,53 @@
-- Load the extension
CREATE EXTENSION IF NOT EXISTS pg_tiktoken;
-- Test encoding function
SELECT tiktoken_encode('cl100k_base', 'Hello world!');
tiktoken_encode
-----------------
{9906,1917,0}
(1 row)
-- Test token count function
SELECT tiktoken_count('cl100k_base', 'Hello world!');
tiktoken_count
----------------
3
(1 row)
-- Test encoding function with a different model
SELECT tiktoken_encode('r50k_base', 'PostgreSQL is amazing!');
tiktoken_encode
-------------------------
{6307,47701,318,4998,0}
(1 row)
-- Test token count function with the same model
SELECT tiktoken_count('r50k_base', 'PostgreSQL is amazing!');
tiktoken_count
----------------
5
(1 row)
-- Edge cases: Empty string
SELECT tiktoken_encode('cl100k_base', '');
tiktoken_encode
-----------------
{}
(1 row)
SELECT tiktoken_count('cl100k_base', '');
tiktoken_count
----------------
0
(1 row)
-- Edge cases: Long text
SELECT tiktoken_count('cl100k_base', repeat('word ', 100));
tiktoken_count
----------------
101
(1 row)
-- Edge case: Invalid encoding
SELECT tiktoken_encode('invalid_model', 'Test') AS should_fail;
ERROR: 'invalid_model': unknown model or encoder

View File

@@ -0,0 +1,24 @@
-- Load the extension
CREATE EXTENSION IF NOT EXISTS pg_tiktoken;
-- Test encoding function
SELECT tiktoken_encode('cl100k_base', 'Hello world!');
-- Test token count function
SELECT tiktoken_count('cl100k_base', 'Hello world!');
-- Test encoding function with a different model
SELECT tiktoken_encode('r50k_base', 'PostgreSQL is amazing!');
-- Test token count function with the same model
SELECT tiktoken_count('r50k_base', 'PostgreSQL is amazing!');
-- Edge cases: Empty string
SELECT tiktoken_encode('cl100k_base', '');
SELECT tiktoken_count('cl100k_base', '');
-- Edge cases: Long text
SELECT tiktoken_count('cl100k_base', repeat('word ', 100));
-- Edge case: Invalid encoding
SELECT tiktoken_encode('invalid_model', 'Test') AS should_fail;

View File

@@ -0,0 +1,10 @@
EXTENSION = rag
MODULE_big = rag
OBJS = $(patsubst %.rs,%.o,$(wildcard src/*.rs))
REGRESS = basic_functions text_processing api_keys chunking_functions document_processing embedding_api_functions voyageai_functions
REGRESS_OPTS = --load-extension=vector --load-extension=rag
PG_CONFIG = pg_config
PGXS := $(shell $(PG_CONFIG) --pgxs)
include $(PGXS)

View File

@@ -0,0 +1,49 @@
-- API key function tests
SELECT rag.anthropic_set_api_key('test_key');
anthropic_set_api_key
-----------------------
(1 row)
SELECT rag.anthropic_get_api_key();
anthropic_get_api_key
-----------------------
test_key
(1 row)
SELECT rag.openai_set_api_key('test_key');
openai_set_api_key
--------------------
(1 row)
SELECT rag.openai_get_api_key();
openai_get_api_key
--------------------
test_key
(1 row)
SELECT rag.fireworks_set_api_key('test_key');
fireworks_set_api_key
-----------------------
(1 row)
SELECT rag.fireworks_get_api_key();
fireworks_get_api_key
-----------------------
test_key
(1 row)
SELECT rag.voyageai_set_api_key('test_key');
voyageai_set_api_key
----------------------
(1 row)
SELECT rag.voyageai_get_api_key();
voyageai_get_api_key
----------------------
test_key
(1 row)

View File

@@ -0,0 +1,13 @@
-- Basic function tests
SELECT rag.markdown_from_html('<p>Hello</p>');
markdown_from_html
--------------------
Hello
(1 row)
SELECT array_length(rag.chunks_by_character_count('the cat sat on the mat', 10, 5), 1);
array_length
--------------
3
(1 row)

View File

@@ -0,0 +1,31 @@
-- Chunking function tests
SELECT rag.chunks_by_character_count('the cat sat on the mat', 10, 5);
chunks_by_character_count
---------------------------------------
{"the cat","cat sat on","on the mat"}
(1 row)
SELECT rag.chunks_by_character_count('Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.', 20, 10);
chunks_by_character_count
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
{"Lorem ipsum dolor","dolor sit amet,","amet, consectetur","adipiscing elit.","Sed do eiusmod","do eiusmod tempor","tempor incididunt ut","ut labore et dolore","et dolore magna","magna aliqua."}
(1 row)
SELECT (rag.chunks_by_character_count('the cat', 10, 0))[1];
chunks_by_character_count
---------------------------
the cat
(1 row)
SELECT rag.chunks_by_character_count('', 10, 5);
chunks_by_character_count
---------------------------
{}
(1 row)
SELECT rag.chunks_by_character_count('a b c d e f g h i j k l m n o p', 5, 2);
chunks_by_character_count
-----------------------------------------------------------------
{"a b c","c d e","e f g","g h i","i j k","k l m","m n o","o p"}
(1 row)

View File

@@ -0,0 +1,56 @@
-- HTML to Markdown conversion tests
SELECT rag.markdown_from_html('<p>Hello</p>');
markdown_from_html
--------------------
Hello
(1 row)
SELECT rag.markdown_from_html('<p>Hello <i>world</i></p>');
markdown_from_html
--------------------
Hello _world_
(1 row)
SELECT rag.markdown_from_html('<h1>Title</h1><p>Paragraph</p>');
markdown_from_html
--------------------
# Title +
+
Paragraph
(1 row)
SELECT rag.markdown_from_html('<ul><li>Item 1</li><li>Item 2</li></ul>');
markdown_from_html
--------------------
* Item 1 +
* Item 2
(1 row)
SELECT rag.markdown_from_html('<a href="https://example.com">Link</a>');
markdown_from_html
-----------------------------
[Link](https://example.com)
(1 row)
-- Note: text_from_pdf and text_from_docx require binary input which is harder to test in regression tests
-- We'll test that the functions exist and have the right signature
SELECT 'text_from_pdf_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'text_from_pdf'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
----------------------+--------
text_from_pdf_exists | t
(1 row)
SELECT 'text_from_docx_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'text_from_docx'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
-----------------------+--------
text_from_docx_exists | t
(1 row)

View File

@@ -0,0 +1,103 @@
-- Test embedding functions exist with correct signatures
-- OpenAI embedding functions
SELECT 'openai_text_embedding_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'openai_text_embedding'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
------------------------------+--------
openai_text_embedding_exists | t
(1 row)
SELECT 'openai_text_embedding_3_small_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'openai_text_embedding_3_small'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
--------------------------------------+--------
openai_text_embedding_3_small_exists | t
(1 row)
SELECT 'openai_text_embedding_3_large_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'openai_text_embedding_3_large'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
--------------------------------------+--------
openai_text_embedding_3_large_exists | t
(1 row)
SELECT 'openai_text_embedding_ada_002_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'openai_text_embedding_ada_002'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
--------------------------------------+--------
openai_text_embedding_ada_002_exists | t
(1 row)
-- Fireworks embedding functions
SELECT 'fireworks_nomic_embed_text_v1_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'fireworks_nomic_embed_text_v1'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
--------------------------------------+--------
fireworks_nomic_embed_text_v1_exists | t
(1 row)
SELECT 'fireworks_nomic_embed_text_v15_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'fireworks_nomic_embed_text_v15'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
---------------------------------------+--------
fireworks_nomic_embed_text_v15_exists | t
(1 row)
SELECT 'fireworks_text_embedding_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'fireworks_text_embedding'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
---------------------------------+--------
fireworks_text_embedding_exists | t
(1 row)
SELECT 'fireworks_text_embedding_thenlper_gte_base_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'fireworks_text_embedding_thenlper_gte_base'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
---------------------------------------------------+--------
fireworks_text_embedding_thenlper_gte_base_exists | t
(1 row)
SELECT 'fireworks_text_embedding_thenlper_gte_large_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'fireworks_text_embedding_thenlper_gte_large'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
----------------------------------------------------+--------
fireworks_text_embedding_thenlper_gte_large_exists | t
(1 row)
SELECT 'fireworks_text_embedding_whereisai_uae_large_v1_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'fireworks_text_embedding_whereisai_uae_large_v1'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
--------------------------------------------------------+--------
fireworks_text_embedding_whereisai_uae_large_v1_exists | t
(1 row)

View File

@@ -0,0 +1,9 @@
BEGIN
CREATE EXTENSION IF NOT EXISTS vector;
DROP EXTENSION IF EXISTS rag CASCADE;
CREATE EXTENSION rag CASCADE;
test_name|result
openai_embedding_dimensions_test|t
test_name|result
fireworks_embedding_dimensions_test|t
COMMIT

View File

@@ -0,0 +1,13 @@
-- Text processing function tests
SELECT rag.markdown_from_html('<p>Hello <i>world</i></p>');
markdown_from_html
--------------------
Hello _world_
(1 row)
SELECT rag.chunks_by_character_count('the cat sat on the mat', 10, 5);
chunks_by_character_count
---------------------------------------
{"the cat","cat sat on","on the mat"}
(1 row)

View File

@@ -0,0 +1,141 @@
-- Test VoyageAI API key functions
SELECT 'voyageai_api_key_test' AS test_name,
(SELECT rag.voyageai_set_api_key('test_key') IS NULL) AS result;
test_name | result
-----------------------+--------
voyageai_api_key_test | t
(1 row)
SELECT 'voyageai_get_api_key_test' AS test_name,
(SELECT rag.voyageai_get_api_key() = 'test_key') AS result;
test_name | result
---------------------------+--------
voyageai_get_api_key_test | t
(1 row)
-- Test VoyageAI embedding functions exist
SELECT 'voyageai_embedding_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'voyageai_embedding'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
---------------------------+--------
voyageai_embedding_exists | t
(1 row)
SELECT 'voyageai_embedding_3_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'voyageai_embedding_3'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
-----------------------------+--------
voyageai_embedding_3_exists | t
(1 row)
SELECT 'voyageai_embedding_3_lite_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'voyageai_embedding_3_lite'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
----------------------------------+--------
voyageai_embedding_3_lite_exists | t
(1 row)
SELECT 'voyageai_embedding_code_2_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'voyageai_embedding_code_2'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
----------------------------------+--------
voyageai_embedding_code_2_exists | t
(1 row)
SELECT 'voyageai_embedding_finance_2_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'voyageai_embedding_finance_2'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
-------------------------------------+--------
voyageai_embedding_finance_2_exists | t
(1 row)
SELECT 'voyageai_embedding_law_2_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'voyageai_embedding_law_2'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
---------------------------------+--------
voyageai_embedding_law_2_exists | t
(1 row)
SELECT 'voyageai_embedding_multilingual_2_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'voyageai_embedding_multilingual_2'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
------------------------------------------+--------
voyageai_embedding_multilingual_2_exists | t
(1 row)
-- Test VoyageAI reranking functions exist
SELECT 'voyageai_rerank_distance_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'voyageai_rerank_distance'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
---------------------------------+--------
voyageai_rerank_distance_exists | t
(1 row)
SELECT 'voyageai_rerank_score_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'voyageai_rerank_score'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
test_name | result
------------------------------+--------
voyageai_rerank_score_exists | t
(1 row)
-- Test VoyageAI function signatures
SELECT 'voyageai_embedding_signature' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'voyageai_embedding'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag')
AND pronargs = 3;
test_name | result
------------------------------+--------
voyageai_embedding_signature | t
(1 row)
SELECT 'voyageai_rerank_distance_signature' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'voyageai_rerank_distance'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag')
AND pronargs IN (3, 4);
test_name | result
------------------------------------+--------
voyageai_rerank_distance_signature | t
(1 row)
SELECT 'voyageai_rerank_score_signature' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'voyageai_rerank_score'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag')
AND pronargs IN (3, 4);
test_name | result
---------------------------------+--------
voyageai_rerank_score_signature | t
(1 row)

View File

@@ -0,0 +1,16 @@
-- API key function tests
SELECT rag.anthropic_set_api_key('test_key');
SELECT rag.anthropic_get_api_key();
SELECT rag.openai_set_api_key('test_key');
SELECT rag.openai_get_api_key();
SELECT rag.fireworks_set_api_key('test_key');
SELECT rag.fireworks_get_api_key();
SELECT rag.voyageai_set_api_key('test_key');
SELECT rag.voyageai_get_api_key();

View File

@@ -0,0 +1,4 @@
-- Basic function tests
SELECT rag.markdown_from_html('<p>Hello</p>');
SELECT array_length(rag.chunks_by_character_count('the cat sat on the mat', 10, 5), 1);

View File

@@ -0,0 +1,11 @@
-- Chunking function tests
SELECT rag.chunks_by_character_count('the cat sat on the mat', 10, 5);
SELECT rag.chunks_by_character_count('Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.', 20, 10);
SELECT (rag.chunks_by_character_count('the cat', 10, 0))[1];
SELECT rag.chunks_by_character_count('', 10, 5);
SELECT rag.chunks_by_character_count('a b c d e f g h i j k l m n o p', 5, 2);

View File

@@ -0,0 +1,24 @@
-- HTML to Markdown conversion tests
SELECT rag.markdown_from_html('<p>Hello</p>');
SELECT rag.markdown_from_html('<p>Hello <i>world</i></p>');
SELECT rag.markdown_from_html('<h1>Title</h1><p>Paragraph</p>');
SELECT rag.markdown_from_html('<ul><li>Item 1</li><li>Item 2</li></ul>');
SELECT rag.markdown_from_html('<a href="https://example.com">Link</a>');
-- Note: text_from_pdf and text_from_docx require binary input which is harder to test in regression tests
-- We'll test that the functions exist and have the right signature
SELECT 'text_from_pdf_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'text_from_pdf'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');
SELECT 'text_from_docx_exists' AS test_name,
count(*) > 0 AS result
FROM pg_proc
WHERE proname = 'text_from_docx'
AND pronamespace = (SELECT oid FROM pg_namespace WHERE nspname = 'rag');

Some files were not shown because too many files have changed in this diff Show More