* refactor: do not run de-dup in ingester for querier requests
This removes the entire de-dup logic from the inegster for querier
requests. Furthermore, it even removes the entire datafusion execution
from the querier and just dumps the in-memory record batches as quickly
as possible. No filters are applied. Note that even prior to this PR,
we've never applied projections (tracked by #5624).
**Pros:**
- speed up query planning within the querier (since we need the ingester
response for state reconciling)
- lowered ingester CPU load
**Cons:**
- more querier<>ingester network traffic
Closes#5602.
* test: extend query test case
* fix: ingester tests
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
* refactor: arc the cached table
* refactor: use cheaper hash keys for projected schemas
Instead of using the column names to address projected schemas, let's
use the column IDs.
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
But still pass them to hot_partitions_for_shard.
And make the order of the arguments the same as for
recent_highest_throughput_partitions because I've already messed the
order up. And make the names the same throughout.
This makes the closure passed to get_candidates_with_retry simpler.
* fix: retry ingester requests faster
The retries introduced in #5695 are too slow and block the entire
querier for minutes (until the very long gRPC timeout kicks in).
* fix: add error details on why the query planning failed
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
* chore: Improve debug logging when parquet files are created
* fix: add duration for encoding parqut
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
* refactor: retry querier->ingester requests
Esp. for InfluxRPC requests that scan multiple tables, it may be that
one ingester requests fails. We shall retry that request instead of
failing the entire query.
* refactor: improve docs
Co-authored-by: Andrew Lamb <andrew@nerdnetworks.org>
* fix: less foo
* docs: remove outdated TODO
* test: assert that panic happened
Co-authored-by: Andrew Lamb <andrew@nerdnetworks.org>
Changes many pub fields / methods to be pub(super), or if necessary,
pub(crate).
This helps maintain an internal API boundary for code hygiene, and helps
identify functions that are unused / only used in tests (which I've
annotated with cfg(test) and intend to remove - we should be driving
code under test via the public API rather than using test-only state
mutation, otherwise we're just testing our tests!)
This commit changes the prepare_data_to_querier() tests to drive the
ingester state by applying DML ops, therefore driving the prod code
paths (and testing them!) rather than having the tests set up what the
tests believe is the correct internal ingester state, and then asserting
on that state.
This gives us much better coverage of prod code paths, decouples the
tests from the internal state/representation of ingesters (making the
tests less fragile), and removes a bunch of special-cased, test-only
functions that are functionally similar, but not the same as, the prod
functions.
Unblocks #5658, further clean-up to come.
* test: improve test assertion
* refactor: LRU SETs should NOT be treated as "used"
Improves interaction of refresh and LRU.
* docs: improve
Co-authored-by: Andrew Lamb <andrew@nerdnetworks.org>
Co-authored-by: Andrew Lamb <andrew@nerdnetworks.org>
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
* refactor: improve consistent access under "remove if"
With all the concurrency introduced in #5668, we should be a bit more
careful with our "remove if" handling, esp. if a removal is triggered
while a load is running concurrently. This change introduces as
`remove_if_and_get` helper that ensures this and the querier over to use
it. The parquet file and tombstone caches required a bit of a larger
change because there the invalidation and the actual GET were kinda
separate. We had this separation for the other caches as well at some
point and decided that this easily leads to API misuse, so I took this
opportunity to "fix" the parquet file and tombstone cache as well.
* docs: improve
* refactor: use concrete backend type in `ChangeRequest`
* refactor: "remove if"-checks shall NOT count as "used"
* test: improve docs
Co-authored-by: Andrew Lamb <andrew@nerdnetworks.org>
Co-authored-by: Andrew Lamb <andrew@nerdnetworks.org>
* chore: Refactor `FROM` clause parser to be generic
This will allow us to use it for `DELETE` statements, which has
a more restrictive requirement, only allowing regular expressions
or single part identifiers.
* feat: Add `DELETE` series statement
* chore: Add test case for insignificant whitespace between operators
NOTE: Added a skipped test until #5663 is implemented
* feat: Add `DROP MEASUREMENT` statement
* chore: Add DropMeasurementStatement struct
* chore: `Statement` enum contains only `Box`ed types
Co-authored-by: kodiakhq[bot] <49736102+kodiakhq[bot]@users.noreply.github.com>
dependabot[bot]
Marco Neumann
kodiakhq[bot]
Carol (Nichols || Goulding)
Andrew Lamb
Nga Tran
Dom Dwyer
Marko Mikulicic
Stuart Carnie