| Commit message (Collapse) | Author | Age | Files | Lines |
|\
| |
| |
| |
| | |
vespa-engine/renovate/github.com-klauspost-compress-1.x
Update module github.com/klauspost/compress to v1.17.3
|
| | |
|
|\ \
| | |
| | |
| | |
| | | |
vespa-engine/vekterli/gc-unused-persistence-metrics
GC old and unused persistence-level metrics
|
| |/
| |
| |
| |
| | |
These metrics are from the age of VDS and a dozen spinning disks
per node.
|
|\ \
| |/
|/|
| |
| | |
vespa-engine/vekterli/print-backtrace-on-invariant-failure
Explicitly print backtrace on bucket space invariant violation
|
|/
|
|
|
| |
This is to help catch an unknown edge case that can happen if
distributor operation cancellation is enabled.
|
|\
| |
| |
| |
| | |
vespa-engine/vekterli/add-metric-for-remove-by-gid-ops
Add fundamental metrics for async "remove by GID" SPI operation
|
| |
| |
| |
| |
| |
| | |
Tracks invocation count, latency and failures (although we don't
expect to see any failures in this pipeline, since the remove ops
logically happen atomically with the bucket iteration).
|
|\ \
| | |
| | | |
Install python as it is not part of base image anymore.
|
| | | |
|
|\ \ \
| | | |
| | | | |
GC unused method
|
|/ / / |
|
|\ \ \
| | | |
| | | |
| | | |
| | | | |
vespa-engine/balder/more-eager-to-create-bitvector
Only allow use of bitvector if it is a filter
|
| | | |
| | | |
| | | |
| | | |
| | | |
| | | | |
- Destruct bitvector when frequency falls below 1/128 instead of 1/64.
A posting is currently 8 bytes(docid+weight) + btree overhead, so that will give a smoother memory cost.
In addition filter queries should be faster.
|
| | | | |
|
|\ \ \ \
| |/ / /
|/| | |
| | | |
| | | | |
vespa-engine/toregge/slightly-less-aggressive-compaction-of-posting-store
Slightly less aggressive compaction of posting store.
|
| | |/
| |/| |
|
|\ \ \
| |/ /
|/| | |
Revert "Merge pull request #29328 from vespa-engine/revert-29314-brat…
|
| |/
| |
| |
| |
| |
| |
| | |
vespa-engine/revert-29314-bratseth/casing-take-2"
This reverts commit a72e949533a46d665440a9c72ca2b8fb58f3a9c3, reversing
changes made to 944d635d00e165166508ef23399e9ed65a87a9c8.
|
|\ \
| | |
| | |
| | |
| | | |
vespa-engine/vekterli/env-var-triggered-no-new-privs-in-sentinel
Add env var for setting `no_new_privs` process bit on Linux
|
|/ /
| |
| |
| |
| |
| |
| | |
If set, this will apply to all processes launched by the config
sentinel, directly or transitively. This is a one-way toggle.
See https://www.kernel.org/doc/Documentation/prctl/no_new_privs.txt
|
|/ |
|
|\
| |
| | |
Update dependency org.apache.aries.spifly:org.apache.aries.spifly.dynamic.bundle to v1.3.7
|
|/
|
|
| |
org.apache.aries.spifly:org.apache.aries.spifly.dynamic.bundle to v1.3.7
|
|\
| |
| | |
Revert "Bratseth/casing take 2"
|
|/ |
|
|\
| |
| | |
Add host_life metric to prometheus output
|
| | |
|
| | |
|
|\ \
| | |
| | | |
Add configuration for shutdown idle timeout
|
| | | |
|
|\ \ \
| | | |
| | | | |
extend conformance test with map_subspaces
|
| | | | |
|
|\ \ \ \
| | | | |
| | | | |
| | | | |
| | | | | |
vespa-engine/vekterli/add-delete-bucket-throttling-feature-flag
Add feature flag for controlling throttling-behavior of `DeleteBucket` operations
|
| |/ / / |
|
|\ \ \ \
| | | | |
| | | | | |
Bratseth/casing take 2
|
| | | | | |
|
| | | | | |
|
| | | | | |
|
| | | | |
| | | | |
| | | | |
| | | | | |
This reverts commit 0dfd4fe4c6ddbded490da36e71f27c4b70aa4226.
|
|\ \ \ \ \
| | | | | |
| | | | | | |
fix tsan error
|
| | |_|/ /
| |/| | |
| | | | |
| | | | | |
reported in VESPA-27749
|
|\ \ \ \ \
| |/ / / /
|/| | | |
| | | | |
| | | | | |
vespa-engine/vekterli/also-memory-throttle-queued-merges
Also memory limit-throttle enqueued merges
|
| | |/ /
| |/| |
| | | |
| | | |
| | | |
| | | |
| | | |
| | | |
| | | |
| | | |
| | | |
| | | |
| | | |
| | | | |
This plugs the hole where merges could enter the active window even
if doing so would exceeded the total memory limit, as dequeueing is
a separate code path from when a merge is initially evaluated for
inclusion in the active window.
There is a theoretical head-of-line blocking/queue starvation issue
if the merge at the front of the queue has an unrealistically large
footprint and the memory limit is unrealistically low. In practice
this is not expected to be a problem, and it should never cause merging
to stop (at least one merge is always guaranteed to be able to execute).
As such, not adding any kind of heuristics to deal with this for now.
|
|\ \ \ \
| | | | |
| | | | |
| | | | |
| | | | | |
vespa-engine/renovate/org.openrewrite.maven-rewrite-maven-plugin-5.x
Update dependency org.openrewrite.maven:rewrite-maven-plugin to v5.11.0
|
| |/ / / |
|
|\ \ \ \
| | | | |
| | | | |
| | | | |
| | | | | |
vespa-engine/renovate/org.openrewrite.recipe-rewrite-recipe-bom-2.x
Update dependency org.openrewrite.recipe:rewrite-recipe-bom to v2.5.0
|
| |/ / / |
|
|\ \ \ \
| |_|_|/
|/| | | |
Update dependency prettier to v3.1.0
|
| |/ / |
|