Merge branch 'master' into vasil.pashov/batch_read

.github/actions/setup_deps/action.yml

@@ -7,10 +7,10 @@ runs:
       shell: bash -l {0} 
       run: |
         dnf update -y
-        dnf remove -y 'gcc-toolset-13-*'
+        dnf remove -y 'gcc-toolset-*'
         dnf install -y zip flex bison gcc-toolset-10 gcc-toolset-10-gdb gcc-toolset-10-libatomic-devel krb5-devel cyrus-sasl-devel openssl-devel \
-        unzip tar epel-release jq wget libcurl-devel python3 \
-        python3-devel python3-pip perl-IPC-Cmd
+        unzip tar epel-release jq wget libcurl-devel \
+        python3.11-devel python3.11-pip perl-IPC-Cmd
 
         dnf groupinstall -y 'Development Tools'
 
@@ -19,7 +19,7 @@ runs:
         echo "CXX=/opt/rh/gcc-toolset-10/root/bin/g++" | tee -a $GITHUB_ENV
         echo "CMAKE_CXX_COMPILER=/opt/rh/gcc-toolset-10/root/bin/g++" | tee -a $GITHUB_ENV
         echo "LD_LIBRARY_PATH=/opt/rh/gcc-toolset-10/root/usr/lib64:/opt/rh/gcc-toolset-10/root/usr/lib:/opt/rh/gcc-toolset-10/root/usr/lib64/dyninst" | tee -a $GITHUB_ENV
-        echo "/opt/rh/devtoolset-10/root/usr/bin" | tee -a $GITHUB_PATH
+        echo "/opt/rh/devtoolset-10/root/usr/bin:/opt/python/cp311-cp311/bin" | tee -a $GITHUB_PATH
 
         echo $GITHUB_ENV
 

.github/workflows/analysis_workflow.yml

@@ -6,7 +6,7 @@ on:
         type: boolean
         default: false
 
-  schedule: # Schdeule the job to run at 12 a.m. daily
+  schedule: # Schedule the job to run at 12 a.m. daily
     - cron: '0 0 * * *'
 
   pull_request_target:

.github/workflows/benchmark_commits.yml

@@ -31,8 +31,14 @@ jobs:
     defaults:
       run: {shell: bash}
     steps:  
+      - name: Initialize LFS
+        shell: bash -l {0}
+        run: |
+          dnf install -y git-lfs
+
       - uses: actions/[email protected]
         with:
+          lfs: 'true'
           fetch-depth: 0
           submodules: recursive
           token: ${{ secrets.ARCTICDB_TEST_PAT }}
@@ -46,14 +52,15 @@ jobs:
       - name: Install deps
         uses: ./.github/actions/setup_deps
 
-      # We are changing the python here because we want to use the default python to build (it is devel version)
-      # and this python for the rest of the testing
-      - name: Select Python (Linux)
-        shell: bash -el {0}
+      - name: Extra envs
+        shell: bash -l {0}
         run: |
-          ls /opt/python  
-          echo /opt/python/cp36-cp36m/bin >> $GITHUB_PATH
-
+          . build_tooling/vcpkg_caching.sh # Linux follower needs another call in CIBW
+          echo -e "VCPKG_BINARY_SOURCES=$VCPKG_BINARY_SOURCES
+          VCPKG_ROOT=$PLATFORM_VCPKG_ROOT" | tee -a $GITHUB_ENV
+          cmake -P cpp/CMake/CpuCount.cmake | sed 's/^-- //' | tee -a $GITHUB_ENV
+        env:
+          CMAKE_BUILD_PARALLEL_LEVEL: ${{vars.CMAKE_BUILD_PARALLEL_LEVEL}}
 
       - name: Set persistent storage variables
         uses: ./.github/actions/set_persistent_storage_env_vars

.github/workflows/docs_build.yml

@@ -38,7 +38,7 @@ jobs:
       - id: download-wheel-artifact
         name: Download wheel artifact from last successful build
         if: ${{!inputs.version}}
-        uses: dawidd6/action-download-artifact@v2.28.0
+        uses: dawidd6/action-download-artifact@v6
         with:
           name: wheel-${{env.PY_IMPL}}-manylinux_x86_64
           workflow: build.yml

.github/workflows/failure_notification.yaml

@@ -0,0 +1,20 @@
+name: Check for master failure
+on:
+  workflow_run:
+    workflows: ["Build and Test", "Build with conda", "Build with analysis tools", "Coverity Static Analysis"]
+    types: [completed]
+    branches: [master]
+
+jobs:
+  on-failure:
+    runs-on: ubuntu-latest
+    if: github.event.workflow_run.conclusion == 'failure' || github.event.workflow_run.conclusion == 'timed_out'
+    steps:
+      - uses: ravsamhq/notify-slack-action@be814b201e233b2dc673608aa46e5447c8ab13f2
+        with:
+          status: ${{ github.event.workflow_run.conclusion }}
+          notification_title: " ${{github.event.workflow_run.name}} - ${{github.event.workflow_run.conclusion}} on ${{github.event.workflow_run.head_branch}} - <${{github.server_url}}/${{github.repository}}/actions/runs/${{github.event.workflow_run.id}}|View Failure>"
+          message_format: ":fire: *${{github.event.workflow_run.name}}* ${{github.event.workflow_run.conclusion}} in <${{github.server_url}}/${{github.repository}}/${{github.event.workflow_run.head_branch}}|${{github.repository}}>"
+          footer: "Linked Repo <${{github.server_url}}/${{github.repository}}|${{github.repository}}> | <${{github.server_url}}/${{github.repository}}/actions/runs/${{github.event.workflow_run.id}}|View Failure>"
+        env:
+          SLACK_WEBHOOK_URL: ${{ secrets.SLACK_WEBHOOK_URL }}

build_tooling/transform_asv_results.py

@@ -5,7 +5,11 @@
 
 As of the Change Date specified in that file, in accordance with the Business Source License, use of this software will be governed by the Apache License, version 2.0.
 """
+
 import pandas as pd
+
+# Importing inf and nan so they can be evaluated correctly during extraction
+from numpy import inf, nan
 from arcticdb.storage_fixtures.s3 import real_s3_from_environment_variables
 import json
 from pathlib import Path

cpp/arcticdb/CMakeLists.txt

@@ -308,6 +308,7 @@ set(arcticdb_srcs
         storage/storage.hpp
         storage/storage_override.hpp
         storage/store.hpp
+        storage/storage_utils.hpp
         stream/aggregator.hpp
         stream/aggregator-inl.hpp
         stream/append_map.hpp
@@ -328,6 +329,7 @@ set(arcticdb_srcs
         stream/stream_utils.hpp
         stream/stream_writer.hpp
         toolbox/library_tool.hpp
+        toolbox/storage_mover.hpp
         util/allocator.hpp
         util/bitset.hpp
         util/buffer.hpp
@@ -486,6 +488,7 @@ set(arcticdb_srcs
         storage/s3/s3_storage.cpp
         storage/s3/s3_storage_tool.cpp
         storage/storage_factory.cpp
+        storage/storage_utils.cpp
         stream/aggregator.cpp
         stream/append_map.cpp
         stream/index.cpp

cpp/arcticdb/async/async_store.hpp

@@ -51,11 +51,11 @@ class AsyncStore : public Store {
 public:
     AsyncStore(
         std::shared_ptr<storage::Library> library,
-        const arcticdb::proto::encoding::VariantCodec &codec,
+        const proto::encoding::VariantCodec &codec,
         EncodingVersion encoding_version
     ) :
         library_(std::move(library)),
-        codec_(std::make_shared<arcticdb::proto::encoding::VariantCodec>(codec)),
+        codec_(std::make_shared<proto::encoding::VariantCodec>(codec)),
         encoding_version_(encoding_version) {
     }
 

cpp/arcticdb/async/task_scheduler.hpp

@@ -300,13 +300,13 @@ inline auto& io_executor() {
 }
 
 template <typename Task>
-inline auto submit_cpu_task(Task&& task) {
+auto submit_cpu_task(Task&& task) {
     return TaskScheduler::instance()->submit_cpu_task(std::forward<decltype(task)>(task));
 }
 
 
 template <typename Task>
-inline auto submit_io_task(Task&& task) {
+auto submit_io_task(Task&& task) {
     return TaskScheduler::instance()->submit_io_task(std::forward<decltype(task)>(task));
 }
 

cpp/arcticdb/entity/atom_key.hpp

@@ -91,8 +91,8 @@ class AtomKeyImpl {
     }
 
     friend bool operator<(const AtomKeyImpl &l, const AtomKeyImpl &r) {
-        auto lt = std::tie(l.id_, l.version_id_, l.index_start_, l.index_end_, l.creation_ts_);
-        auto rt = std::tie(r.id_, r.version_id_, r.index_start_, r.index_end_, r.creation_ts_);
+        const auto lt = std::tie(l.id_, l.version_id_, l.index_start_, l.index_end_, l.creation_ts_);
+        const auto rt = std::tie(r.id_, r.version_id_, r.index_start_, r.index_end_, r.creation_ts_);
         return lt < rt;
     }
 

cpp/arcticdb/entity/key.cpp

@@ -90,6 +90,10 @@ KeyClass key_class_from_key_type(KeyType key_type) {
     return get_key_data(key_type).key_class_;
 }
 
+const char* get_key_description(KeyType key_type) {
+    return get_key_data(key_type).description_;
+}
+
 bool is_string_key_type(KeyType key_type){
     return variant_type_from_key_type(key_type) == VariantType::STRING_TYPE;
 }

cpp/arcticdb/entity/key.hpp

@@ -16,6 +16,10 @@
 #include <memory>
 #include <algorithm>
 #include <variant>
+#include <array>
+#include <ranges>
+
+namespace rng = std::ranges;
 
 namespace arcticdb::entity {
 
@@ -193,10 +197,10 @@ enum class KeyType : int {
     UNDEFINED
 };
 
-inline std::vector<KeyType> key_types_write_precedence() {
+consteval auto key_types_write_precedence() {
     // TOMBSTONE[_ALL] keys are not included because they're not written to the storage,
     // they just exist inside version keys
-    return {
+    return std::array {
         KeyType::LIBRARY_CONFIG,
         KeyType::TABLE_DATA,
         KeyType::TABLE_INDEX,
@@ -215,9 +219,9 @@ inline std::vector<KeyType> key_types_write_precedence() {
     };
 }
 
-inline std::vector<KeyType> key_types_read_precedence() {
+consteval auto key_types_read_precedence() {
     auto output = key_types_write_precedence();
-    std::reverse(std::begin(output), std::end(output));
+    rng::reverse(output);
     return output;
 }
 
@@ -247,7 +251,7 @@ enum class VariantType : char {
 
 VariantType variant_type_from_key_type(KeyType key_type);
 
-inline bool is_index_key_type(KeyType key_type) {
+constexpr bool is_index_key_type(KeyType key_type) {
     // TODO: Change name probably.
     return (key_type == KeyType::TABLE_INDEX) || (key_type == KeyType::MULTI_KEY);
 }
@@ -258,30 +262,26 @@ bool is_ref_key_class(KeyType k);
 
 bool is_block_ref_key_class(KeyType k);
 
-inline KeyType get_key_type_for_data_stream(const StreamId &) {
+constexpr KeyType get_key_type_for_data_stream(const StreamId &) {
     return KeyType::TABLE_DATA;
 }
 
-inline KeyType get_key_type_for_index_stream(const StreamId &) {
+constexpr KeyType get_key_type_for_index_stream(const StreamId &) {
     return KeyType::TABLE_INDEX;
 }
 
+const char* get_key_description(KeyType type);
 
 template <typename Function>
-auto foreach_key_type_read_precedence(Function&& func) {
-    auto types = key_types_read_precedence();
-    for(auto type : types) {
-        func(KeyType(type));
-    }
+constexpr auto foreach_key_type_read_precedence(Function&& func) {
+    rng::for_each(key_types_read_precedence(), func);
 }
 
 template <typename Function>
-auto foreach_key_type_write_precedence(Function&& func) {
-    auto types = key_types_write_precedence();
-    for(auto type : types) {
-        func(KeyType(type));
-    }
+constexpr auto foreach_key_type_write_precedence(Function&& func) {
+    rng::for_each(key_types_write_precedence(), func);
 }
+
 inline KeyType key_type_from_int(int type_num) {
     util::check(type_num > 0 && type_num < int(KeyType::UNDEFINED), "Unrecognized key type number {}", type_num);
     return KeyType(type_num);

cpp/arcticdb/entity/metrics.hpp

@@ -32,8 +32,8 @@ namespace arcticdb {
 
 const std::string MONGO_INSTANCE_LABEL = "mongo_instance";
 const std::string PROMETHEUS_ENV_LABEL = "env";
-const int SUMMARY_MAX_AGE = 30;
-const int SUMMARY_AGE_BUCKETS = 5;
+constexpr int SUMMARY_MAX_AGE = 30;
+constexpr int SUMMARY_AGE_BUCKETS = 5;
 
 class MetricsConfig {
 public: