Problem
-------
Secondary indexes are implemented via materialized views under the
hood. The way an index behaves is determined by the configuration
of the view. Currently, it can be modified by performing the CQL
statement `ALTER MATERIALIZED VIEW` on it. However, that raises some
concerns.
Consider, for instance, the following scenario:
1. The user creates a secondary index on a table.
2. In parallel, the user performs writes to the base table.
3. The user modifies the underlying materialized view, e.g. by setting
the `synchronous_updates` to `true` [1].
Some of the writes that happened before step 3 used the default value
of the property (which is `false`). That had an actual consequence
on what happened later on: the view updates were performed
asynchronously. Only after step 3 had finished did it change.
Unfortunately, as of now, there is no way to avoid a situation like
that. Whenever the user wants to configure a secondary index they're
creating, they need to do it in another schema change. Since it's
not always possible to control how the database is manipulated in
the meantime, it leads to problems like the one described.
That's not all, though. The fact that it's not possible to configure
secondary indexes is inconsistent with other schema entities. When
it comes to tables or materialized views, the user always have a means
to set some or even all of the properties during their creation.
Solution
--------
The solution to this problem is extending the `CREATE INDEX` CQL
statement by view properties. The syntax is of form:
```
> CREATE INDEX <index name>
> .. ON <keyspace>.<table> (<columns>)
> .. WITH <properties>
```
where `<properties>` corresponds to both index-specific and view
properties [2, 3]. View properties can only be used with indexes
implemented with materialized views; for example, it will be impossible
to create a vector index when specifying any view property (see
examples below).
When a view property is provided, it will be applied when creating the
underlying materialized view. The behavior should be similar to how
other CQL statements responsible for creating schema entities work.
High-level implementation strategy
----------------------------------
1. Make auxiliary changes.
2. Introduce data structures representing the new set of index
properties: both index-specific and those corresponding to the
underlying view.
3. Extend `CREATE INDEX` to accept view properties.
4. Extend `DESCRIBE INDEX` and other `DESCRIBE` statements to include
view properties in their output.
User documentation is also updated at the steps to reflect the
corresponding changes.
Implementation considerations
-----------------------------
There are a number of schema properties that are now obsolete. They're
accepted by other CQL statements, but they have no effect. They
include:
* `index_interval`
* `replicate_on_write`
* `populate_io_cache_on_flush`
* `read_repair_chance`
* `dclocal_read_repair_chance`
If the user tries to create a secondary index specifying any of those
keywords, the statement will fail with an appropriate error (see
examples below).
Unlike materialized views, we forbid specifying the clustering order
when creating a secondary index [4]. This limitation may be lifted
later on, but it's a detail that may or may not prove troublesome. It's
better to postpone covering it to when we have a better perspective on
the consequences it would bring.
Examples
--------
Good examples
```
> CREATE INDEX idx ON ks.t (v);
> CREATE INDEX idx ON ks.t (v) WITH comment = 'ok view property';
> CREATE INDEX idx ON ks.t (v)
.. WITH comment = 'multiple view properties are ok'
.. AND synchronous_updates = true;
> CREATE INDEX idx ON ks.t (v)
.. WITH comment = 'default value ok'
.. AND synchronous_updates = false;
```
Bad examples
```
> CREATE INDEX idx ON ks.t (v) WITH replicate_on_write = true;
SyntaxException: Unknown property 'replicate_on_write'
> CREATE INDEX idx ON ks.t (v)
.. WITH OPTIONS = {'option1': 'value1'}
.. AND comment = 'some text';
InvalidRequest: Error from server: code=2200 [Invalid query]
message="Cannot specify options for a non-CUSTOM index"
> CREATE CUSTOM INDEX idx ON ks.t (v)
.. WITH OPTIONS = {'option1': 'value1'}
.. AND comment = 'some text';
InvalidRequest: Error from server: code=2200 [Invalid query]
message="CUSTOM index requires specifying the index class"
> CREATE CUSTOM INDEX idx ON ks.t (v)
.. USING 'vector_index'
.. WITH OPTIONS = {'option1': 'value1'}
.. AND comment = 'some text';
InvalidRequest: Error from server: code=2200 [Invalid query]
message="You cannot use view properties with a vector index"
> CREATE INDEX idx ON ks.t (v) WITH CLUSTERING ORDER BY (v ASC);
InvalidRequest: Error from server: code=2200 [Invalid query]
message="Indexes do not allow for specifying the clustering order"
```
and so on. For more examples, see the relevant tests.
References:
[1] https://docs.scylladb.com/manual/branch-2025.4/cql/cql-extensions.html#synchronous-materialized-views
[2] https://docs.scylladb.com/manual/branch-2025.4/cql/secondary-indexes.html#create-index
[3] https://docs.scylladb.com/manual/branch-2025.4/cql/mv.html#mv-options
[4] https://docs.scylladb.com/manual/branch-2025.4/cql/dml/select.html#ordering-clauseFixesscylladb/scylladb#16454
Backport: not needed. This is an enhancement.
Closesscylladb/scylladb#24977
* github.com:scylladb/scylladb:
cql3: Extend DESC INDEX by view properties
cql3: Forbid using CLUSTERING ORDER BY when creating index
cql3: Extend CREATE INDEX by MV properties
cql3/statements/create_index_statement: Allow for view options
cql3/statements/create_index_statement: Rename member
cql3/statements/index_prop_defs: Re-introduce index_prop_defs
cql3/statements/property_definitions: Add extract_property()
cql3/statements/index_prop_defs.cc: Add namespace
cql3/statements/index_prop_defs.hh: Rename type
cql3/statements/view_prop_defs.cc: Move validation logic into file
cql3/statements: Introduce view_prop_defs.{hh,cc}
cql3/statements/create_view_statement.cc: Move validation of ID
schema/schema.hh: Do not include index_prop_defs.hh
Read timeouts are a common occurence and they typically occur when the replica is overloaded. So throwing exceptions for read timeouts is very harmful. Be careful not to thow exceptions while propagating them up the future chain. Add a test to enfore and detect regressions.
Fixes: scylladb/scylladb#25062
Improvement, normally not a backport candidate, but we may decide to backport if customer(s) are found to suffer from this.
Closesscylladb/scylladb#25068
* github.com:scylladb/scylladb:
reader_permit: remove check_abort()
test/boost/database_test: add test for read timeout exceptions
sstables/mx/reader: don't throw exceptions on the read-path
readers/multishard: don't throw exceptions on the read-path
replica/table: don't throw exceptions on the read-path
multishard_mutation_query: fix indentation
multishard_mutation_query: don't throw exceptions on the read-path
service/storage_proxy: don't throw exceptions on the full-scan path
cql3/query_processor: don't throw exceptions on the read-path
reader_permit: add get_abort_exception()
Use coroutine::try_future() to avoid exceptions taking flight and
triggering expensive stack-unwinding.
Especially bad for common exceptions like timeouts.
To prepare for implementation of filtering we skip validation
of where clauses in vector search queries. All queries that would
be blocked by the lack of ALLOW FILTERING now will pass through.
Fixes: VECTOR-410
Closesscylladb/scylladb#27758
Allow creating materialized views and secondary indexes in a tablets keyspace only if it's RF-rack-valid, and enforce RF-rack-validity while the keyspace has views by restricting some operations:
* Altering a keyspace's RF if it would make the keyspace RF-rack-invalid
* Adding a node in a new rack
* Removing / Decommissioning the last node in a rack
Previously the config option `rf_rack_valid_keyspaces` was required for creating views. We now remove this restriction - it's not needed because we always maintain RF-rack-validity for keyspaces with views.
The restrictions are relevant only for keyspaces with numerical RF. Keyspace with rack-list-based RF are always RF-rack-valid.
Fixesscylladb/scylladb#23345
Fixes https://github.com/scylladb/scylladb/issues/26820
backport to relevant versions for materialized views with tablets since it depends on rf-rack validity
Closesscylladb/scylladb#26354
* github.com:scylladb/scylladb:
docs: update RF-rack restrictions
cql3: don't apply RF-rack restrictions on vector indexes
cql3: add warning when creating mv/index with tablets about rf-rack
service/tablet_allocator: always allow tablet merge of tables with views
locator: extend rf-rack validation for rack lists
test: test rf-rack validity when creating keyspace during node ops
locator: fix rf-rack validation during node join/remove
test: test topology restrictions for views with tablets
test: add test_topology_ops_with_rf_rack_valid
topology coordinator: restrict node join/remove to preserve RF-rack validity
topology coordinator: add validation to node remove
locator: extend rf-rack validation functions
view: change validate_view_keyspace to allow MVs if RF=Racks
db: enforce rf-rack-validity for keyspaces with views
replica/db: add enforce_rf_rack_validity_for_keyspace helper
db: remove enforce parameter from check_rf_rack_validity
test: adjust test to not break rf-rack validity
VECTOR_SEARCH_INDEXING permission didn't work on cdc tables as we mistakenly checked for vector indexes on the cdc table insted of the base.
This patch fixes that and adds a test that validates this behavior.
Fixes: VECTOR-476
Closesscylladb/scylladb#28050
It should be possible to return the similarity of vectors in CQL statements following the [Cassandra compatible syntax](https://cassandra.apache.org/doc/latest/cassandra/getting-started/vector-search-quickstart.html#query-vector-data-with-cql):
```
SELECT comment, similarity_cosine(comment_vector, [0.1, 0.15, 0.3, 0.12, 0.05])
FROM cycling.comments_vs;
```
Although the calculations are slow, and we already have calculated results returned via Vector Store API,
we need the functionality as it allows us to calculate similarity of vectors not stored in vector indexes.
It will be needed for [quantization and rescoring](https://scylladb.atlassian.net/wiki/spaces/RND/pages/195985800/Quantization+and+Rescoring).
The feature is also a nice-to-have in testing as requested many times by testing and CX teams.
The optimized version utilizing already calculated distances from Vector Store without a need of rescoring will be coming soon after via https://github.com/scylladb/scylladb/pull/27991.
---
The patch adds functions:
- `similarity_cosine(<vector>, <vector>)`,
- `similarity_euclidean(<vector>, <vector>)`,
- `similarity_dot_product(<vector>, <vector>)`
Where `<vector>` is either a column of type `VECTOR<FLOAT, N>` or a vector of floats literal.
These functions can be called with every `SELECT` query, not only ANN vector queries as opposed to https://github.com/scylladb/scylladb/pull/25993.
The similarity calculations are implemented inspired by [USearch's implementation](
a2f1759910/include/usearch/index_plugins.hpp (L1304-L1385)) and made compatible with [Cassandra's documentation](https://cassandra.apache.org/doc/5.0/cassandra/developing/cql/functions.html#vector-similarity-functions).
That would guarantee the results in ScyllaDB are calculated using the exact same algorithms as used in Vector Store indexes.
---
Fixes: SCYLLADB-88
Fixes: SCYLLADB-89
New feature, should land into 2026.1
Closesscylladb/scylladb#27524
* github.com:scylladb/scylladb:
docs: add vector similarity functions documentation
test/cqlpy: add similarity functions correctness tests
test/cqlpy: add similarity functions invalid call tests
cql3: introduce similarity functions syntax
vector_similarity_fcts: introduce similarity functions
vector_similarity_fcts: retrieve similarity function argument types
vector_similarity_fcts: add calculating similarity between vectors
If a CQL session USEs a keyspace and then calls DESC TABLES, the user
expects to see only the tables in the chosen keyspace. However, calling
DESC KEYSPACES should still return list all the keyspaces - returning
just the USEd one is not useful - and also not what Cassandra does.
We had an xfailing test test_describe.py::test_keyspaces_with_use which
reproduces this bug (and passes on Cassandra).
In this patch we fix this bug. The fix is simple - USE should affect
DESC statements, but be ignored for DESC KEYSPACES. We can then remove
the xfail marker from the test.
The patch also includes a new test for the DESC TABLES case, where the
USE *does* have an affect. And I wanted to make sure the patch doesn't
break this case. As usual, the new test passes on both Cassandra and
ScyllaDB.
Fixes#26334
Signed-off-by: Nadav Har'El <nyh@scylladb.com>
Closesscylladb/scylladb#27971
The similarity function syntax is:
`similarity_<metric_name>(<vector>, <vector>)`
Where `<metric_name>` is one of `cosine`, `euclidean` and `dot_product`
matching the intended similarity metric to be used within calculations.
Where `<vector>` is either a vector column name or vector literal.
Add `vectorSimilarityArgs` symbol that is an extension of `selectionFunctionArgs`,
but allowing to use the `value` as an argument as well as the `unaliasedSelector`.
This is needed as the similarity function syntax allows both the arguments to be
a vector value, so the grammar needs to recognize the vector literal there as well.
Since we actually support `SELECT`s with constants since this patch,
return true instead of throwing an error while trying to convert the function call
to constant.
This patch introduces scalar functions `similarity_cosine()`,
`similarity_euclidean()`, and `similarity_dot_product()`
which should return a float - similarity of the given vectors
calculated according to the function's similarity metric.
The argument types of this function are retrieved with
the `retrieve_vector_arg_types`, but shall be assignable to
`vector<float, N>` where `N` is the same for both arguments.
This patch introduces a dimensionality check during the execusion
of those functions.
This patch retrieves the argument types for similarity functions.
Newly introduced `retrieve_vector_arg_types` function checks if
the provided arguments are vectors of floats and if
both the vector values match the same type (dimension).
If so, we know the exact type and set it as the function arguments type.
Otherwise, if the exact type is unkown, but we can assign to vector<float, N>
then the dimensionality check will be done during execution of
the similarity function.
This also takes care of null values and bind variables the same way
as implemented in Cassandra to stay compatible.
Meaning that if we can infer the type from one argument, then the latter
may be unknown (null or ?).
Additionally this patch adds `test_assignment_any_vector` function
which tests the weak assignment to vector<float, N> as mentioned
above.
This commit introduces `compute_cosine_similarity`, `compute_euclidean_similarity`,
`compute_dot_product_similarity` functions to calculate the vectors similarity
in respective metric.
The similarity is a float value meaning how similar the vectors are in a range of [0, 1].
Values closer to 1 indicate greater similarity.
The `dot_product` similarity requires L2 normalized vectors as arguments.
The similarity is calculated based on the jVector's implementation used by Cassandra.
f967f1c924/jvector-base/src/main/java/io/github/jbellis/jvector/vector/VectorSimilarityFunction.java (L36-L69)
Mention the type of batch: Logged or Unlogged. The size (warn/fail on
too large size) error has different significance depending on the type.
Refs: #27605Closesscylladb/scylladb#27664
Creating a MV or index in a tablets-based keyspace now forces additional
restrictions on the keyspace. The keyspace must be RF-rack-valid and it
must remain RF-rack-valid while the view exists.
Add a CQL warning about these restrictions.
The function validate_view_keyspace checks if a keyspace is eligible for
having materialized views, and it is used for validation when creating a
MV or a MV-based index.
Previously, it was required that the rf_rack_valid_keyspaces option is
set in order for tablets-based keyspaces to be considered eligible, and
the RF-rack condition was enforced when the option is set.
Instead of this, we change the validation to allow MVs in a keyspace if
the RF-rack condition is satisfied for the keyspace - regardless of the
config option.
We remove the config validation for views on startup that validates the
option `rf_rack_valid_keyspaces` is set if there are any views with
tablets, since this is not required anymore.
We can do this without worrying about upgrades because this change will
be effective from 2025.4 where MVs with tablets are first out of
experimental phase.
We update the test for MV and index restrictions in tablets keyspaces
according to the new requirements.
* Create MV/index: previously the test checked that it's allowed only if
the config option `rf_rack_valid_keyspaces` is set. This is changed
now so it's always allowed to create MV/index if the keyspace is
RF-rack-valid. Update the test to verify that we can create MV/index
when the keyspace is RF-rack-valid, even if the rf_rack option is not
set, and verify that it fails when the keyspace is RF-rack-invalid.
* Alter: Add a new test to verify that while a keyspace has views, it
can't be altered to become RF-rack-invalid.
Add the helper function enforce_rf_rack_validity_for_keyspace that
returns true if RF-rack-validity should be enforced for a keyspace, and
use it wherever we need to check this instead of checking the config
option directly.
This is useful because this condition is used in multiple places, and
having it defined in a single helper function will make it easier to
see and change the enforcement conditions.
If a keyspace has a numeric replication factor in a DC and rf < #racks,
then the replicas of tablets in this keyspace can be distributed among
all racks in the DC (different for each tablet). With rack list, we need all
tablet replicas to be placed on the same racks. Hence, the conversion
requires tablet co-location.
After this series, the conversion can be done using ALTER KEYSPACE
statement. The statement that does this conversion in any DC is not
allowed to change a rf in any DC. So, if we have dc1 and dc2 with 3 racks
each and a keyspace ks then with a single ALTER KEYSPACE we can do:
- {dc1 : 2} -> {dc1 : [r1, r2]};
- {dc1 : 2, dc2: 2} -> {dc1 : [r1, r2], dc2: [r2,r3]};
- {dc1 : 2, dc2: 2} -> {dc1 : [r1, r2], dc2: 2}
- {dc1 : 2} -> {dc1 : 2, dc2 : [r1]}
But we cannot do:
- {dc1 : 2} -> {dc1 : [r1, r2, r3]};
- {dc1 : 1, dc2 : [r1, r2] → dc1: [r1], dc2: [r1].
In order to do the co-locations rf change request is paused. Tablet
load balancer examines the paused rf change requests and schedules
necessary tablet migrations. During the process of co-location, no other
cross-rack migration is allowed.
Load balancer checks whether any paused rf change request is
ready to be resumed. If so, it puts the request back to global topology
request queue.
While an rf change request for a keyspace is running, any other rf change
of this keyspace will fail.
Fixes: #26398.
New feature, no backport
Closesscylladb/scylladb#27279
* github.com:scylladb/scylladb:
test: add est_rack_list_conversion_with_two_replicas_in_rack
test: test creating tablet_rack_list_colocation_plan
test: add test_numeric_rf_to_rack_list_conversion test
tasks: service: add global_topology_request_virtual_task
cql3: statements: allow altering from numeric rf to rack list
service: topology_coordinator: pause keyspace_rf_change request
service: implement make_rack_list_colocation_plan
service: add tablet_rack_list_colocation_plan
cql3: reject concurrent alter of the same keyspace
test: check paused rf change requests persistence
db: service: add paused_rf_change_requests to system.topology
service: pass topology and system_keyspace to load_balancer ctor
service: tablet_allocator: extract load updates
service: tablet_allocator: extract ensure_node
tasks, system_keyspace: Introduce get_topology_request_entry_opt()
node_ops: Drop get_pending_ids()
node_ops: Drop redundant get_status_helper()
Allow altering from numeric replication factor to rack list. Ensure
that a single ALTER KEYSPACE statement doesn't try to both convert
to rack list and change rf.
Reject ALTER KEYSPACE request if there is unfinished (queued, pending,
or paused) alter request of the same keyspace.
This is required as in the following changes, global request queue
will contain rf change requests meant to be resumed.
This is a temporary solution as handling this property may require
a bit more attention or at least a bit more focus. For now, let's
forbid using it so it's clear it won't get applied. A simple test
is provided to cover it.
We document the restriction.
After the previous patch that extended the grammar and provided
basic functionalities to accommodate properties of materialized views
in indexes, this commit takes another step and actually applies them
to the underlying view when it's being created.
We're providing validation tests for each property, with the single
exception of CLUSTERING ORDER BY. That one will be handled separately
in an upcoming commit.
We also update the user documentation.
We're allowing CREATE INDEX to accept the same set of properties as
materialized views do. Our goal is to give the user an ability to
configure the underlying materialized view of an index directly,
when creating it.
This commit doesn't do anything except for extending the grammar
and passing the right pieces of information to the right destinations.
There's no validation and the options have no effect yet. That will
be done in the following patch.
The type represents a mix of both index-specific and view properties.
Since we cannot easily distinguish which properties belong to which
entity, let's use this abstraction and filter them from the C++ level.
This is a prerequisite for extending the capabilities of CREATE INDEX
by allowing it to configuring the underlying materialized view.
We rename the type `index_prop_defs` to `index_specific_prop_defs`.
The rationale for the change is to distinguish between properties
related directly to a index and properties related to the underlying
view (if applicable).
The type `index_prop_defs` will be re-introduced in an upcomming commit
where it'll encompass both index-related and view-related properties.
This is a prerequisite for it.
We're introducing a new type wrapping properties that can be used with
materialized views. Doing that, we achieve the following things:
(1) We can keep validation logic in one place.
(2) We differentiate between properties of a regular table and
properties of a materialized view.
(3) It provides better modularization and allows for reusing the code.
(4) It gets rid of inconsistencies in the existing code, e.g.
CREATE MV using one type for properties, while ALTER MV another.
The actual end goal of this commit is to be able to reuse at least part
of the validation logic of MVs in CREATE INDEX and, when it gets added,
ALTER INDEX: we want to endow those statements with an ability to modify
the underlying materialized view without having to modify it directly.
This patch does NOT implement the whole validation logic yet. It will be
done in a following commit.
Refs scylladb/scylladb#16454
The end goal we have in mind in this commit is to extract the validation
logic of the options used for creating and altering an MV to a separate
place and be able to call from different places in the code.
It will be useful when extending the capabilities of the CREATE INDEX
statement.
In this patch, we move the part of validation responsible for checking
the ID option to keep it close to the other parts of validation of the
options in their "raw" form.
We currently allow restrictions on single column primary key,
but we ignore the restriction and return all results.
This can confuse the users. We change it so such a restriction
will throw an error and add a test to validate it.
Fixes: VECTOR-331
Closesscylladb/scylladb#27143
In the next commit we want to add an optimization that relies on
precise control over the lifetime of cas_request. In particular, we
want the implementation of this interface in Alternator to operate on
raw references that are guaranteed to remain valid only until the
cas() future is resolved. We already depend on the same lifetime
assumptions in cas_request when used by modification_statement.
However, these assumptions are not clearly expressed in the current
interface: cas_request is taken by shared_ptr, and nothing prevents
cas() from storing that pointer inside paxos_response_handler, which
may outlive the cas() future.
This commit fixes that by taking cas_request by raw reference. This
makes it explicit that cas() does not assume ownership of the object.
Callers must ensure that the referenced object remains valid until
the returned future is resolved.
The rf_rack_valid_keyspaces option needs to be turned on in order to
allow creating materialized views in tablet keyspaces with numeric RF
per DC. This is also necessary for secondary indexes because they use
materialized views underneath. However, this option is _not_ necessary
for vector store indexes because those use the external vector store
service for querying the list of keys to fetch from the main table, they
do not create a materialized view. The rf_rack_valid_keyspaces was, by
accident, required for vector indexes, too.
Remove the restriction for vector store indexes as it is completely
unnecessary.
Fixes: SCYLLADB-81
Closesscylladb/scylladb#27447
The PRUNE MATERALIZED VIEW statement is performed as follows:
1. Perform a range scan of the view table from the view replicas based
on the ranges specified in the statement.
2. While reading the paged scan above, for each view row perform a read
from all base replicas at the corresponding primary key. If a discrepancy
is detected, delete the row in the view table.
When reading multiple rows, this is very slow because for each view row
we need to performe a single row query on multiple replicas.
In this patch we add an option to speed this up by performing many of the
single base row reads concurrently, at the concurrency specified in the
USING CONCURRENCY clause.
Aside from the unit test, I checked manually on a 3-node cluster with 10M rows, using vnodes. There were actually no ghost rows in the test, but we still had to iterate over all view rows and read the corresponding base rows. And actual ghost rows, if there are any, should be a tiny fraction of all rows. I compared concurrencies 1,2,10,100 and the results were:
* Pruning with concurrency 1 took total 1416 seconds
* Pruning with concurrency 2 took total 731 seconds
* Pruning with concurrency 10 took total 234 seconds
* Pruning with concurrency 100 took total 171 seconds
So after a concurrency of 10 or so we're hitting diminishing returns (at least in this setup). At that point we may be no longer bottlenecked by the reads, but by CPU on the shard that's handling the PRUNE
Fixes https://github.com/scylladb/scylladb/issues/27070Closesscylladb/scylladb#27097
* github.com:scylladb/scylladb:
mv: allow setting concurrency in PRUNE MATERIALIZED VIEW
cql: add CONCURRENCY to the USING clause
This PR introduces two key improvements to the robustness and resource management of vector search:
Proper Abort on CQL Timeout: Previously, when a CQL query involving a vector search timed out
, the underlying ANN query to the vector store was not aborted and would continue to run. This has been fixed by ensuring the abort source is correctly signaled, terminating the ANN request when its parent CQL query expires and preventing unnecessary resource consumption.
Faster Failure Detection: The connection and keep-alive timeouts for vector store nodes were excessively long (2 and 11 minutes, respectively), causing significant delays in detecting and recovering from unreachable nodes. These timeouts are now aligned with the request_timeout_in_ms setting, allowing for much faster failure detection and improving high availability by failing over from unresponsive nodes more quickly.
Fixes: SCYLLADB-76
This issue affects the 2025.4 branch, where similar HA recovery delays have been observed.
Closesscylladb/scylladb#27377
* github.com:scylladb/scylladb:
vector_search: Fix ANN query abort on CQL timeout
vector_search: Reduce connection and keep-alive timeouts
When a CQL vector search request timed out, the underlying ANN query was
not aborted and continued to run. This happened because the abort source
was not being signaled upon request expiration.
This commit ensures the ANN query is aborted when the CQL request times out
preventing unnecessary resource consumption.
Before this commit, any attempt to create, alter, attach, or drop
the default service level would result in a syntax error whose
error message was unclear:
```
cqlsh> attach service level default to cassandra;
SyntaxException: line 1:21 no viable alternative at input 'default'
```
The error stems from the grammar not being able to parse `default`
as a correct service level name. To fix that, we cover it manually.
This way, the grammar accepts it and we can process it in Scylla.
The reason why we'd like to cover the default service level is that
it's an actual service level that the user should reference. Getting
a syntax error is not what should happen. Hence this fix.
We validate the input and if the given role is really the default
service level, we reject the query and provide an informative error
message.
Two validation tests are provided.
Fixesscylladb/scylladb#26699Closesscylladb/scylladb#27162
The PRUNE MATERALIZED VIEW statement is performed as follows:
1. Perform a range scan of the view table from the view replicas based
on the ranges specified in the statement.
2. While reading the paged scan above, for each view row perform a read
from all base replicas at the corresponding primary key. If a discrepancy
is detected, delete the row in the view table.
When reading multiple rows, this is very slow because for each view row
we need to performe a single row query on multiple replicas.
In this patch we add an option to speed this up by performing many of the
single base row reads concurrently, at the concurrency specified in the
USING CONCURRENCY clause.
Fixes https://github.com/scylladb/scylladb/issues/27070
This patch enforces that vector indexes can only be created on keyspaces
that use tablets. During index validation, `check_uses_tablets()` verifies
the base keyspace configuration and rejects creation otherwise.
To support this, the `custom_index::validate()` API now receives a
`const data_dictionary::database&` parameter, allowing index
implementations to access keyspace-level settings during DDL validation.
Fixes https://scylladb.atlassian.net/browse/VECTOR-322Closesscylladb/scylladb#26786
For tables of special types that can be located: MV, CDC, and paxos
table, we should not use tombstone_gc=repair mode because colocated
tablets are never repaired, hence they will not have repair_time set and
will never be GC'd using 'repair' mode.
In ALTER KEYSPACE, when a datacenter name is omitted, its replication
factor is implicitly set to zero with vnodes, while with tablets,
it remains unchanged.
ALTER KEYSPACE should behave the same way for tablets as it does
for vnodes. However, this can be dangerous as we may mistakenly
drop the whole datacenter.
Reject ALTER KEYSPACE if it changes replication factor, but omits
a datacenter that currently contains tablet replicas.
Fixes: https://github.com/scylladb/scylladb/issues/25549.
Closesscylladb/scylladb#25731
Currently, the PRUNE MATERIALIZED VIEW statement performs all its
reads and writes in a single, continous sequence. This takes too
much time even for a moderate amount of 'PRUNED' data.
Instead, we want to make it possible to set a concurrency of the
reads and writes performed while processing the PRUNE statement,
so that if the user so desires, it may finish the PRUNING quicker
at the cost of adding more load on the cluster.
In this patch we add the CONCURRENCY setting to the USING clause
in cql. In the next patch, we'll be using it to actually set the
concurrency of PRUNE MATERIALIZED VIEW.
Add precompiled header support to CMakeLists.txt and configure.py -
it improves compilation time by approximately 10%.
New header `stdafx.hh` is added, don't include it manually -
the compiler will include it for you. The header contains includes from
external libraries used by Scylla - seastar, standard library,
linux headers and zlib.
The feature is enabled by default, use CMake option `Scylla_USE_PRECOMPILED_HEADER`
or configure.py --disable-precompiled-header to disable.
The feature should be disabled, when trying to check headers - otherwise
you might get false negatives on missing includes from seastar / abseil and so on.
Note: following configuration needs to be added to ccache.conf:
sloppiness = pch_defines,time_macros,include_file_mtime,include_file_ctime
Closesscylladb/scylladb#26617
Currently we do not support paging for vector search queries.
When we get such a query with paging enabled we ignore the paging
and return the entire result. This behavior can be confusing for users,
as there is no warning about paging not working with vector search.
This patch fixes that by adding a warning to the result of ANN queries
with paging enabled.
Closesscylladb/scylladb#26384
The polymorphic abstract_type class serves as an interface and should not be copied.
To prevent accidental and unsafe copies, make it explicitly uncopyable.
When deserializing a vector whose elements are collections (e.g., set, list),
the operation raises a `std::bad_cast` exception.
This was caused by type slicing due to an incorrect assignment of a
polymorphic type by value instead of by reference. This resulted in a
failed `dynamic_cast` even when the underlying type was correct.
When creating a keyspace with tablets, a warning is shown with all the
unsupported features for tablets, which is only counters currently.
Now that counters is also supported with tablets, we can remove this
warning entirely.
Now that counters work with tablets, allow to create a table with
counters in a tablets-enabled keyspace, and remove the warning about
counters not being supported when creating a keyspace with tablets.
We allow to use counters with tablets only when all nodes are upgraded
and support counters with tablets. We add a new feature flag to
determine if this is the case.
Fixesscylladb/scylladb#18180
