Add latest changes from gitlab-org/gitlab@master

This commit is contained in:
GitLab Bot 2021-08-19 15:10:29 +00:00
parent 110225407f
commit 155f106fd5
26 changed files with 929 additions and 900 deletions

View File

@ -309,9 +309,7 @@ export default {
this.isLatestVersion,
);
if (this.glFeatures.usageDataDesignAction) {
servicePingDesignDetailView();
}
servicePingDesignDetailView();
},
updateActiveDiscussion(id, source = ACTIVE_DISCUSSION_SOURCE_TYPES.discussion) {
this.$apollo.mutate({

View File

@ -307,7 +307,7 @@ class Admin::UsersController < Admin::ApplicationController
end
def user
@user ||= find_routable!(User, params[:id], request.path_info)
@user ||= find_routable!(User, params[:id], request.fullpath)
end
def build_canonical_path(user)

View File

@ -3,7 +3,7 @@
module ProjectUnauthorized
module ControllerActions
def self.on_routable_not_found
lambda do |routable, path_info|
lambda do |routable, full_path|
return unless routable.is_a?(Project)
label = routable.external_authorization_classification_label

View File

@ -3,13 +3,13 @@
module RoutableActions
extend ActiveSupport::Concern
def find_routable!(routable_klass, routable_full_path, path_info, extra_authorization_proc: nil)
def find_routable!(routable_klass, routable_full_path, full_path, extra_authorization_proc: nil)
routable = routable_klass.find_by_full_path(routable_full_path, follow_redirects: request.get?)
if routable_authorized?(routable, extra_authorization_proc)
ensure_canonical_path(routable, routable_full_path)
routable
else
perform_not_found_actions(routable, not_found_actions, path_info)
perform_not_found_actions(routable, not_found_actions, full_path)
route_not_found unless performed?
@ -21,11 +21,11 @@ module RoutableActions
[ProjectUnauthorized::ControllerActions.on_routable_not_found]
end
def perform_not_found_actions(routable, actions, path_info)
def perform_not_found_actions(routable, actions, full_path)
actions.each do |action|
break if performed?
instance_exec(routable, path_info, &action)
instance_exec(routable, full_path, &action)
end
end

View File

@ -16,7 +16,7 @@ class Groups::ApplicationController < ApplicationController
private
def group
@group ||= find_routable!(Group, params[:group_id] || params[:id], request.path_info)
@group ||= find_routable!(Group, params[:group_id] || params[:id], request.fullpath)
end
def group_projects

View File

@ -13,6 +13,6 @@ class Groups::Clusters::IntegrationsController < Clusters::IntegrationsControlle
end
def group
@group ||= find_routable!(Group, params[:group_id] || params[:id], request.path_info)
@group ||= find_routable!(Group, params[:group_id] || params[:id], request.fullpath)
end
end

View File

@ -15,7 +15,7 @@ class Groups::ClustersController < Clusters::ClustersController
end
def group
@group ||= find_routable!(Group, params[:group_id] || params[:id], request.path_info)
@group ||= find_routable!(Group, params[:group_id] || params[:id], request.fullpath)
end
def metrics_dashboard_params

View File

@ -6,7 +6,7 @@ class Profiles::GroupsController < Profiles::ApplicationController
feature_category :users
def update
group = find_routable!(Group, params[:id], request.path_info)
group = find_routable!(Group, params[:id], request.fullpath)
notification_setting = current_user.notification_settings_for(group)
if notification_setting.update(update_params)

View File

@ -26,7 +26,7 @@ class Projects::ApplicationController < ApplicationController
path = File.join(params[:namespace_id], params[:project_id] || params[:id])
auth_proc = ->(project) { !project.pending_delete? }
@project = find_routable!(Project, path, request.path_info, extra_authorization_proc: auth_proc)
@project = find_routable!(Project, path, request.fullpath, extra_authorization_proc: auth_proc)
end
def build_canonical_path(project)

View File

@ -10,6 +10,6 @@ class Projects::Clusters::IntegrationsController < ::Clusters::IntegrationsContr
end
def project
@project ||= find_routable!(Project, File.join(params[:namespace_id], params[:project_id]), request.path_info)
@project ||= find_routable!(Project, File.join(params[:namespace_id], params[:project_id]), request.fullpath)
end
end

View File

@ -17,7 +17,7 @@ class Projects::ClustersController < Clusters::ClustersController
end
def project
@project ||= find_routable!(Project, File.join(params[:namespace_id], params[:project_id]), request.path_info)
@project ||= find_routable!(Project, File.join(params[:namespace_id], params[:project_id]), request.fullpath)
end
def repository

View File

@ -42,7 +42,6 @@ class Projects::IssuesController < Projects::ApplicationController
before_action do
push_frontend_feature_flag(:tribute_autocomplete, @project)
push_frontend_feature_flag(:vue_issuables_list, project)
push_frontend_feature_flag(:usage_data_design_action, project, default_enabled: true)
push_frontend_feature_flag(:improved_emoji_picker, project, default_enabled: :yaml)
push_frontend_feature_flag(:vue_issues_list, project)
push_frontend_feature_flag(:iteration_cadences, project&.group, default_enabled: :yaml)

View File

@ -172,7 +172,7 @@ class UsersController < ApplicationController
private
def user
@user ||= find_routable!(User, params[:username], request.path_info)
@user ||= find_routable!(User, params[:username], request.fullpath)
end
def personal_projects

View File

@ -1,8 +0,0 @@
---
name: usage_data_design_action
introduced_by_url: https://gitlab.com/gitlab-org/gitlab/-/merge_requests/46626
rollout_issue_url: https://gitlab.com/gitlab-org/gitlab/-/issues/287630
milestone: '13.7'
type: development
group: group::product planning
default_enabled: true

View File

@ -9,15 +9,19 @@ type: howto
Geo can be used in combination with Object Storage (AWS S3, or other compatible object storage).
The storage method for files is recorded in the database, and the database is replicated
from the **primary** Geo site to the **secondary** Geo site, so the **secondary** Geo site
must match the storage method of the **primary** Geo site.
Therefore, if the **primary** Geo site uses object storage, the **secondary** Geo site must use it too.
Currently, **secondary** sites can use either:
- The same storage bucket as the **primary** site.
- A replicated storage bucket.
- Local storage, if the primary uses local storage.
The storage method (local or object storage) for files is recorded in the database, and the database
is replicated from the **primary** Geo site to the **secondary** Geo site.
When accessing an uploaded object, we get its storage method (local or object storage) from the
database, so the **secondary** Geo site must match the storage method of the **primary** Geo site.
Therefore, if the **primary** Geo site uses object storage, the **secondary** Geo site must use it too.
To have:

View File

@ -4,20 +4,680 @@ group: Product Intelligence
info: To determine the technical writer assigned to the Stage/Group associated with this page, see https://about.gitlab.com/handbook/engineering/ux/technical-writing/#assignments
---
# Develop and test Service Ping
# Implement Service Ping
To add a new metric and test Service Ping:
Service Ping consists of two kinds of data:
- **Counters**: Track how often a certain event happened over time, such as how many CI/CD pipelines have run.
They are monotonic and always trend up.
- **Observations**: Facts collected from one or more GitLab instances and can carry arbitrary data.
There are no general guidelines for how to collect those, due to the individual nature of that data.
To implement a new metric in Service Ping, follow these steps:
1. [Implement the required counter](#types-of-counters)
1. [Name and place the metric](#name-and-place-the-metric)
1. [Test counters manually using your Rails console](#test-counters-manually-using-your-rails-console)
1. [Generate the SQL query](#generate-the-sql-query)
1. [Optimize queries with `#database-lab`](#optimize-queries-with-database-lab)
1. [Add the metric definition](#add-the-metric-definition)
1. [Add the metric definition to the Metrics Dictionary](#add-the-metric-definition)
1. [Add the metric to the Versions Application](#add-the-metric-to-the-versions-application)
1. [Create a merge request](#create-a-merge-request)
1. [Verify your metric](#verify-your-metric)
1. [Set up and test Service Ping locally](#set-up-and-test-service-ping-locally)
## Instrumentation classes
We recommend you use [instrumentation classes](metrics_instrumentation.md) in `usage_data.rb` where possible.
For example, we have the following instrumentation class:
`lib/gitlab/usage/metrics/instrumentations/count_boards_metric.rb`.
You should add it to `usage_data.rb` as follows:
```ruby
boards: add_metric('CountBoardsMetric', time_frame: 'all'),
```
## Types of counters
There are several types of counters in `usage_data.rb`:
- **[Batch counters](#batch-counters)**: Used for counts and sums.
- **[Redis counters](#redis-counters):** Used for in-memory counts.
- **[Alternative counters](#alternative-counters):** Used for settings and configurations.
NOTE:
Only use the provided counter methods. Each counter method contains a built-in fail-safe mechanism that isolates each counter to avoid breaking the entire Service Ping process.
### Batch counters
For large tables, PostgreSQL can take a long time to count rows due to MVCC [(Multi-version Concurrency Control)](https://en.wikipedia.org/wiki/Multiversion_concurrency_control). Batch counting is a counting method where a single large query is broken into multiple smaller queries. For example, instead of a single query querying 1,000,000 records, with batch counting, you can execute 100 queries of 10,000 records each. Batch counting is useful for avoiding database timeouts as each batch query is significantly shorter than one single long running query.
For GitLab.com, there are extremely large tables with 15 second query timeouts, so we use batch counting to avoid encountering timeouts. Here are the sizes of some GitLab.com tables:
| Table | Row counts in millions |
|------------------------------|------------------------|
| `merge_request_diff_commits` | 2280 |
| `ci_build_trace_sections` | 1764 |
| `merge_request_diff_files` | 1082 |
| `events` | 514 |
Batch counting requires indexes on columns to calculate max, min, and range queries. In some cases,
you must add a specialized index on the columns involved in a counter.
#### Ordinary batch counters
Simple count of a given `ActiveRecord_Relation`, does a non-distinct batch count, smartly reduces `batch_size`, and handles errors.
Handles the `ActiveRecord::StatementInvalid` error.
Method:
```ruby
count(relation, column = nil, batch: true, start: nil, finish: nil)
```
Arguments:
- `relation` the ActiveRecord_Relation to perform the count
- `column` the column to perform the count on, by default is the primary key
- `batch`: default `true` to use batch counting
- `start`: custom start of the batch counting to avoid complex min calculations
- `end`: custom end of the batch counting to avoid complex min calculations
Examples:
```ruby
count(User.active)
count(::Clusters::Cluster.aws_installed.enabled, :cluster_id)
count(::Clusters::Cluster.aws_installed.enabled, :cluster_id, start: ::Clusters::Cluster.minimum(:id), finish: ::Clusters::Cluster.maximum(:id))
```
#### Distinct batch counters
Distinct count of a given `ActiveRecord_Relation` on given column, a distinct batch count, smartly reduces `batch_size`, and handles errors.
Handles the `ActiveRecord::StatementInvalid` error.
Method:
```ruby
distinct_count(relation, column = nil, batch: true, batch_size: nil, start: nil, finish: nil)
```
Arguments:
- `relation`: the ActiveRecord_Relation to perform the count
- `column`: the column to perform the distinct count, by default is the primary key
- `batch`: default `true` to use batch counting
- `batch_size`: if none set it uses default value 10000 from `Gitlab::Database::BatchCounter`
- `start`: custom start of the batch counting to avoid complex min calculations
- `end`: custom end of the batch counting to avoid complex min calculations
WARNING:
Counting over non-unique columns can lead to performance issues. For more information, see the [iterating tables in batches](../iterating_tables_in_batches.md) guide.
Examples:
```ruby
distinct_count(::Project, :creator_id)
distinct_count(::Note.with_suggestions.where(time_period), :author_id, start: ::User.minimum(:id), finish: ::User.maximum(:id))
distinct_count(::Clusters::Applications::CertManager.where(time_period).available.joins(:cluster), 'clusters.user_id')
```
#### Sum batch operation
Sum the values of a given ActiveRecord_Relation on given column and handles errors.
Handles the `ActiveRecord::StatementInvalid` error
Method:
```ruby
sum(relation, column, batch_size: nil, start: nil, finish: nil)
```
Arguments:
- `relation`: the ActiveRecord_Relation to perform the operation
- `column`: the column to sum on
- `batch_size`: if none set it uses default value 1000 from `Gitlab::Database::BatchCounter`
- `start`: custom start of the batch counting to avoid complex min calculations
- `end`: custom end of the batch counting to avoid complex min calculations
Examples:
```ruby
sum(JiraImportState.finished, :imported_issues_count)
```
#### Grouping and batch operations
The `count`, `distinct_count`, and `sum` batch counters can accept an `ActiveRecord::Relation`
object, which groups by a specified column. With a grouped relation, the methods do batch counting,
handle errors, and returns a hash table of key-value pairs.
Examples:
```ruby
count(Namespace.group(:type))
# returns => {nil=>179, "Group"=>54}
distinct_count(Project.group(:visibility_level), :creator_id)
# returns => {0=>1, 10=>1, 20=>11}
sum(Issue.group(:state_id), :weight))
# returns => {1=>3542, 2=>6820}
```
#### Add operation
Sum the values given as parameters. Handles the `StandardError`.
Returns `-1` if any of the arguments are `-1`.
Method:
```ruby
add(*args)
```
Examples:
```ruby
project_imports = distinct_count(::Project.where.not(import_type: nil), :creator_id)
bulk_imports = distinct_count(::BulkImport, :user_id)
add(project_imports, bulk_imports)
```
#### Estimated batch counters
> - [Introduced](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/48233) in GitLab 13.7.
Estimated batch counter functionality handles `ActiveRecord::StatementInvalid` errors
when used through the provided `estimate_batch_distinct_count` method.
Errors return a value of `-1`.
WARNING:
This functionality estimates a distinct count of a specific ActiveRecord_Relation in a given column,
which uses the [HyperLogLog](http://algo.inria.fr/flajolet/Publications/FlFuGaMe07.pdf) algorithm.
As the HyperLogLog algorithm is probabilistic, the **results always include error**.
The highest encountered error rate is 4.9%.
When correctly used, the `estimate_batch_distinct_count` method enables efficient counting over
columns that contain non-unique values, which can not be assured by other counters.
##### estimate_batch_distinct_count method
Method:
```ruby
estimate_batch_distinct_count(relation, column = nil, batch_size: nil, start: nil, finish: nil)
```
The [method](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/utils/usage_data.rb#L63)
includes the following arguments:
- `relation`: The ActiveRecord_Relation to perform the count.
- `column`: The column to perform the distinct count. The default is the primary key.
- `batch_size`: From `Gitlab::Database::PostgresHll::BatchDistinctCounter::DEFAULT_BATCH_SIZE`. Default value: 10,000.
- `start`: The custom start of the batch count, to avoid complex minimum calculations.
- `finish`: The custom end of the batch count to avoid complex maximum calculations.
The method includes the following prerequisites:
- The supplied `relation` must include the primary key defined as the numeric column.
For example: `id bigint NOT NULL`.
- The `estimate_batch_distinct_count` can handle a joined relation. To use its ability to
count non-unique columns, the joined relation **must not** have a one-to-many relationship,
such as `has_many :boards`.
- Both `start` and `finish` arguments should always represent primary key relationship values,
even if the estimated count refers to another column, for example:
```ruby
estimate_batch_distinct_count(::Note, :author_id, start: ::Note.minimum(:id), finish: ::Note.maximum(:id))
```
Examples:
1. Simple execution of estimated batch counter, with only relation provided,
returned value represents estimated number of unique values in `id` column
(which is the primary key) of `Project` relation:
```ruby
estimate_batch_distinct_count(::Project)
```
1. Execution of estimated batch counter, where provided relation has applied
additional filter (`.where(time_period)`), number of unique values estimated
in custom column (`:author_id`), and parameters: `start` and `finish` together
apply boundaries that defines range of provided relation to analyze:
```ruby
estimate_batch_distinct_count(::Note.with_suggestions.where(time_period), :author_id, start: ::Note.minimum(:id), finish: ::Note.maximum(:id))
```
1. Execution of estimated batch counter with joined relation (`joins(:cluster)`),
for a custom column (`'clusters.user_id'`):
```ruby
estimate_batch_distinct_count(::Clusters::Applications::CertManager.where(time_period).available.joins(:cluster), 'clusters.user_id')
```
When instrumenting metric with usage of estimated batch counter please add
`_estimated` suffix to its name, for example:
```ruby
"counts": {
"ci_builds_estimated": estimate_batch_distinct_count(Ci::Build),
...
```
### Redis counters
Handles `::Redis::CommandError` and `Gitlab::UsageDataCounters::BaseCounter::UnknownEvent`.
Returns -1 when a block is sent or hash with all values and -1 when a `counter(Gitlab::UsageDataCounters)` is sent.
The different behavior is due to 2 different implementations of the Redis counter.
Method:
```ruby
redis_usage_data(counter, &block)
```
Arguments:
- `counter`: a counter from `Gitlab::UsageDataCounters`, that has `fallback_totals` method implemented
- or a `block`: which is evaluated
#### Ordinary Redis counters
Examples of implementation:
- Using Redis methods [`INCR`](https://redis.io/commands/incr), [`GET`](https://redis.io/commands/get), and [`Gitlab::UsageDataCounters::WikiPageCounter`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_data_counters/wiki_page_counter.rb)
- Using Redis methods [`HINCRBY`](https://redis.io/commands/hincrby), [`HGETALL`](https://redis.io/commands/hgetall), and [`Gitlab::UsageCounters::PodLogs`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_counters/pod_logs.rb)
##### UsageData API tracking
<!-- There's nearly identical content in `##### Adding new events`. If you fix errors here, you may need to fix the same errors in the other location. -->
1. Track event using `UsageData` API
Increment event count using ordinary Redis counter, for given event name.
Tracking events using the `UsageData` API requires the `usage_data_api` feature flag to be enabled, which is enabled by default.
API requests are protected by checking for a valid CSRF token.
To be able to increment the values, the related feature `usage_data_<event_name>` should be enabled.
```plaintext
POST /usage_data/increment_counter
```
| Attribute | Type | Required | Description |
| :-------- | :--- | :------- | :---------- |
| `event` | string | yes | The event name it should be tracked |
Response:
- `200` if event was tracked
- `400 Bad request` if event parameter is missing
- `401 Unauthorized` if user is not authenticated
- `403 Forbidden` for invalid CSRF token provided
1. Track events using JavaScript/Vue API helper which calls the API above
Note that `usage_data_api` and `usage_data_#{event_name}` should be enabled to be able to track events
```javascript
import api from '~/api';
api.trackRedisCounterEvent('my_already_defined_event_name'),
```
#### Redis HLL counters
WARNING:
HyperLogLog (HLL) is a probabilistic algorithm and its **results always includes some small error**. According to [Redis documentation](https://redis.io/commands/pfcount), data from
used HLL implementation is "approximated with a standard error of 0.81%".
With `Gitlab::UsageDataCounters::HLLRedisCounter` we have available data structures used to count unique values.
Implemented using Redis methods [PFADD](https://redis.io/commands/pfadd) and [PFCOUNT](https://redis.io/commands/pfcount).
##### Add new events
1. Define events in [`known_events`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_data_counters/known_events/).
Example event:
```yaml
- name: users_creating_epics
category: epics_usage
redis_slot: users
aggregation: weekly
feature_flag: track_epics_activity
```
Keys:
- `name`: unique event name.
Name format for Redis HLL events `<name>_<redis_slot>`.
[See Metric name](metrics_dictionary.md#metric-name) for a complete guide on metric naming suggestion.
Consider including in the event's name the Redis slot to be able to count totals for a specific category.
Example names: `users_creating_epics`, `users_triggering_security_scans`.
- `category`: event category. Used for getting total counts for events in a category, for easier
access to a group of events.
- `redis_slot`: optional Redis slot. Default value: event name. Only event data that is stored in the same slot
can be aggregated. Ensure keys are in the same slot. For example:
`users_creating_epics` with `redis_slot: 'users'` builds Redis key
`{users}_creating_epics-2020-34`. If `redis_slot` is not defined the Redis key will
be `{users_creating_epics}-2020-34`.
Recommended slots to use are: `users`, `projects`. This is the value we count.
- `expiry`: expiry time in days. Default: 29 days for daily aggregation and 6 weeks for weekly
aggregation.
- `aggregation`: may be set to a `:daily` or `:weekly` key. Defines how counting data is stored in Redis.
Aggregation on a `daily` basis does not pull more fine grained data.
- `feature_flag`: optional `default_enabled: :yaml`. If no feature flag is set then the tracking is enabled. One feature flag can be used for multiple events. For details, see our [GitLab internal Feature flags](../feature_flags/index.md) documentation. The feature flags are owned by the group adding the event tracking.
1. Use one of the following methods to track the event:
- In the controller using the `RedisTracking` module and the following format:
```ruby
track_redis_hll_event(*controller_actions, name:, if: nil, &block)
```
Arguments:
- `controller_actions`: the controller actions to track.
- `name`: the event name.
- `if`: optional custom conditions. Uses the same format as Rails callbacks.
- `&block`: optional block that computes and returns the `custom_id` that we want to track. This overrides the `visitor_id`.
Example:
```ruby
# controller
class ProjectsController < Projects::ApplicationController
include RedisTracking
skip_before_action :authenticate_user!, only: :show
track_redis_hll_event :index, :show, name: 'users_visiting_projects'
def index
render html: 'index'
end
def new
render html: 'new'
end
def show
render html: 'show'
end
end
```
- In the API using the `increment_unique_values(event_name, values)` helper method.
Arguments:
- `event_name`: the event name.
- `values`: the values counted. Can be one value or an array of values.
Example:
```ruby
get ':id/registry/repositories' do
repositories = ContainerRepositoriesFinder.new(
user: current_user, subject: user_group
).execute
increment_unique_values('users_listing_repositories', current_user.id)
present paginate(repositories), with: Entities::ContainerRegistry::Repository, tags: params[:tags], tags_count: params[:tags_count]
end
```
- Using `track_usage_event(event_name, values)` in services and GraphQL.
Increment unique values count using Redis HLL, for a given event name.
Examples:
- [Track usage event for an incident in a service](https://gitlab.com/gitlab-org/gitlab/-/blob/v13.8.3-ee/app/services/issues/update_service.rb#L66)
- [Track usage event for an incident in GraphQL](https://gitlab.com/gitlab-org/gitlab/-/blob/v13.8.3-ee/app/graphql/mutations/alert_management/update_alert_status.rb#L16)
```ruby
track_usage_event(:incident_management_incident_created, current_user.id)
```
- Using the `UsageData` API.
<!-- There's nearly identical content in `##### UsageData API Tracking`. If you find / fix errors here, you may need to fix errors in that section too. -->
Increment unique users count using Redis HLL, for a given event name.
To track events using the `UsageData` API, ensure the `usage_data_api` feature flag
is set to `default_enabled: true`. Enabled by default in GitLab 13.7 and later.
API requests are protected by checking for a valid CSRF token.
```plaintext
POST /usage_data/increment_unique_users
```
| Attribute | Type | Required | Description |
| :-------- | :--- | :------- | :---------- |
| `event` | string | yes | The event name to track |
Response:
- `200` if the event was tracked, or if tracking failed for any reason.
- `400 Bad request` if an event parameter is missing.
- `401 Unauthorized` if the user is not authenticated.
- `403 Forbidden` if an invalid CSRF token is provided.
- Using the JavaScript/Vue API helper, which calls the `UsageData` API.
To track events using the `UsageData` API, ensure the `usage_data_api` feature flag
is set to `default_enabled: true`. Enabled by default in GitLab 13.7 and later.
Example for an existing event already defined in [known events](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_data_counters/known_events/):
```javascript
import api from '~/api';
api.trackRedisHllUserEvent('my_already_defined_event_name'),
```
1. Get event data using `Gitlab::UsageDataCounters::HLLRedisCounter.unique_events(event_names:, start_date:, end_date:, context: '')`.
Arguments:
- `event_names`: the list of event names.
- `start_date`: start date of the period for which we want to get event data.
- `end_date`: end date of the period for which we want to get event data.
- `context`: context of the event. Allowed values are `default`, `free`, `bronze`, `silver`, `gold`, `starter`, `premium`, `ultimate`.
1. Testing tracking and getting unique events
Trigger events in rails console by using `track_event` method
```ruby
Gitlab::UsageDataCounters::HLLRedisCounter.track_event('users_viewing_compliance_audit_events', values: 1)
Gitlab::UsageDataCounters::HLLRedisCounter.track_event('users_viewing_compliance_audit_events', values: [2, 3])
```
Next, get the unique events for the current week.
```ruby
# Get unique events for metric for current_week
Gitlab::UsageDataCounters::HLLRedisCounter.unique_events(event_names: 'users_viewing_compliance_audit_events',
start_date: Date.current.beginning_of_week, end_date: Date.current.next_week)
```
##### Recommendations
We have the following recommendations for [adding new events](#add-new-events):
- Event aggregation: weekly.
- Key expiry time:
- Daily: 29 days.
- Weekly: 42 days.
- When adding new metrics, use a [feature flag](../../operations/feature_flags.md) to control the impact.
- For feature flags triggered by another service, set `default_enabled: false`,
- Events can be triggered using the `UsageData` API, which helps when there are > 10 events per change
##### Enable or disable Redis HLL tracking
Events are tracked behind optional [feature flags](../feature_flags/index.md) due to concerns for Redis performance and scalability.
For a full list of events and corresponding feature flags see, [known_events](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_data_counters/known_events/) files.
To enable or disable tracking for specific event in <https://gitlab.com> or <https://about.staging.gitlab.com>, run commands such as the following to
[enable or disable the corresponding feature](../feature_flags/index.md).
```shell
/chatops run feature set <feature_name> true
/chatops run feature set <feature_name> false
```
We can also disable tracking completely by using the global flag:
```shell
/chatops run feature set redis_hll_tracking true
/chatops run feature set redis_hll_tracking false
```
##### Known events are added automatically in Service Data payload
All events added in [`known_events/common.yml`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_data_counters/known_events/common.yml) are automatically added to Service Data generation under the `redis_hll_counters` key. This column is stored in [version-app as a JSON](https://gitlab.com/gitlab-services/version-gitlab-com/-/blob/master/db/schema.rb#L209).
For each event we add metrics for the weekly and monthly time frames, and totals for each where applicable:
- `#{event_name}_weekly`: Data for 7 days for daily [aggregation](#add-new-events) events and data for the last complete week for weekly [aggregation](#add-new-events) events.
- `#{event_name}_monthly`: Data for 28 days for daily [aggregation](#add-new-events) events and data for the last 4 complete weeks for weekly [aggregation](#add-new-events) events.
Redis HLL implementation calculates automatic total metrics, if there are more than one metric for the same category, aggregation, and Redis slot.
- `#{category}_total_unique_counts_weekly`: Total unique counts for events in the same category for the last 7 days or the last complete week, if events are in the same Redis slot and we have more than one metric.
- `#{category}_total_unique_counts_monthly`: Total unique counts for events in same category for the last 28 days or the last 4 complete weeks, if events are in the same Redis slot and we have more than one metric.
Example of `redis_hll_counters` data:
```ruby
{:redis_hll_counters=>
{"compliance"=>
{"users_viewing_compliance_dashboard_weekly"=>0,
"users_viewing_compliance_dashboard_monthly"=>0,
"users_viewing_compliance_audit_events_weekly"=>0,
"users_viewing_audit_events_monthly"=>0,
"compliance_total_unique_counts_weekly"=>0,
"compliance_total_unique_counts_monthly"=>0},
"analytics"=>
{"users_viewing_analytics_group_devops_adoption_weekly"=>0,
"users_viewing_analytics_group_devops_adoption_monthly"=>0,
"analytics_total_unique_counts_weekly"=>0,
"analytics_total_unique_counts_monthly"=>0},
"ide_edit"=>
{"users_editing_by_web_ide_weekly"=>0,
"users_editing_by_web_ide_monthly"=>0,
"users_editing_by_sfe_weekly"=>0,
"users_editing_by_sfe_monthly"=>0,
"ide_edit_total_unique_counts_weekly"=>0,
"ide_edit_total_unique_counts_monthly"=>0}
}
```
Example:
```ruby
# Redis Counters
redis_usage_data(Gitlab::UsageDataCounters::WikiPageCounter)
redis_usage_data { ::Gitlab::UsageCounters::PodLogs.usage_totals[:total] }
# Define events in common.yml https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_data_counters/known_events/common.yml
# Tracking events
Gitlab::UsageDataCounters::HLLRedisCounter.track_event('users_expanding_vulnerabilities', values: visitor_id)
# Get unique events for metric
redis_usage_data { Gitlab::UsageDataCounters::HLLRedisCounter.unique_events(event_names: 'users_expanding_vulnerabilities', start_date: 28.days.ago, end_date: Date.current) }
```
### Alternative counters
Handles `StandardError` and fallbacks into -1 this way not all measures fail if we encounter one exception.
Mainly used for settings and configurations.
Method:
```ruby
alt_usage_data(value = nil, fallback: -1, &block)
```
Arguments:
- `value`: a simple static value in which case the value is simply returned.
- or a `block`: which is evaluated
- `fallback: -1`: the common value used for any metrics that are failing.
Example:
```ruby
alt_usage_data { Gitlab::VERSION }
alt_usage_data { Gitlab::CurrentSettings.uuid }
alt_usage_data(999)
```
### Add counters to build new metrics
When adding the results of two counters, use the `add` Service Data method that
handles fallback values and exceptions. It also generates a valid [SQL export](index.md#export-service-ping-sql-queries-and-definitions).
Example:
```ruby
add(User.active, User.bot)
```
### Prometheus queries
In those cases where operational metrics should be part of Service Ping, a database or Redis query is unlikely
to provide useful data. Instead, Prometheus might be more appropriate, because most GitLab architectural
components publish metrics to it that can be queried back, aggregated, and included as Service Data.
NOTE:
Prometheus as a data source for Service Ping is only available for single-node Omnibus installations
that are running the [bundled Prometheus](../../administration/monitoring/prometheus/index.md) instance.
To query Prometheus for metrics, a helper method is available to `yield` a fully configured
`PrometheusClient`, given it is available as per the note above:
```ruby
with_prometheus_client do |client|
response = client.query('<your query>')
...
end
```
Refer to [the `PrometheusClient` definition](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/prometheus_client.rb)
for how to use its API to query for data.
### Fallback values for Service Ping
We return fallback values in these cases:
| Case | Value |
|-----------------------------|-------|
| Deprecated Metric | -1000 |
| Timeouts, general failures | -1 |
| Standard errors in counters | -2 |
## Name and place the metric
Add the metric in one of the top-level keys:
@ -159,7 +819,7 @@ To set up Service Ping locally, you must:
## Test Prometheus-based Service Ping
If the data submitted includes metrics [queried from Prometheus](index.md#prometheus-queries)
If the data submitted includes metrics [queried from Prometheus](#prometheus-queries)
you want to inspect and verify, you must:
- Ensure that a Prometheus server is running locally.
@ -208,3 +868,197 @@ However, it has the following limitations:
with any of the other running services. That is not how node metrics are reported in a production setup, where `node_exporter`
always runs as a process alongside other GitLab components on any given node. For Service Ping, none of the node data would therefore
appear to be associated to any of the services running, because they all appear to be running on different hosts. To alleviate this problem, the `node_exporter` in GCK was arbitrarily "assigned" to the `web` service, meaning only for this service `node_*` metrics appears in Service Ping.
## Aggregated metrics
> - [Introduced](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/45979) in GitLab 13.6.
WARNING:
This feature is intended solely for internal GitLab use.
To add data for aggregated metrics to the Service Ping payload, add a corresponding definition to:
- [`config/metrics/aggregates/*.yaml`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/config/metrics/aggregates/) for metrics available in the Community Edition.
- [`ee/config/metrics/aggregates/*.yaml`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/ee/config/metrics/aggregates/) for metrics available in the Enterprise Edition.
Each aggregate definition includes following parts:
- `name`: Unique name under which the aggregate metric is added to the Service Ping payload.
- `operator`: Operator that defines how the aggregated metric data is counted. Available operators are:
- `OR`: Removes duplicates and counts all entries that triggered any of listed events.
- `AND`: Removes duplicates and counts all elements that were observed triggering all of following events.
- `time_frame`: One or more valid time frames. Use these to limit the data included in aggregated metric to events within a specific date-range. Valid time frames are:
- `7d`: Last seven days of data.
- `28d`: Last twenty eight days of data.
- `all`: All historical data, only available for `database` sourced aggregated metrics.
- `source`: Data source used to collect all events data included in aggregated metric. Valid data sources are:
- [`database`](#database-sourced-aggregated-metrics)
- [`redis`](#redis-sourced-aggregated-metrics)
- `events`: list of events names to aggregate into metric. All events in this list must
relay on the same data source. Additional data source requirements are described in the
[Database sourced aggregated metrics](#database-sourced-aggregated-metrics) and
[Redis sourced aggregated metrics](#redis-sourced-aggregated-metrics) sections.
- `feature_flag`: Name of [development feature flag](../feature_flags/index.md#development-type)
that is checked before metrics aggregation is performed. Corresponding feature flag
should have `default_enabled` attribute set to `false`. The `feature_flag` attribute
is optional and can be omitted. When `feature_flag` is missing, no feature flag is checked.
Example aggregated metric entries:
```yaml
- name: example_metrics_union
operator: OR
events:
- 'users_expanding_secure_security_report'
- 'users_expanding_testing_code_quality_report'
- 'users_expanding_testing_accessibility_report'
source: redis
time_frame:
- 7d
- 28d
- name: example_metrics_intersection
operator: AND
source: database
time_frame:
- 28d
- all
events:
- 'dependency_scanning_pipeline_all_time'
- 'container_scanning_pipeline_all_time'
feature_flag: example_aggregated_metric
```
Aggregated metrics collected in `7d` and `28d` time frames are added into Service Ping payload under the `aggregated_metrics` sub-key in the `counts_weekly` and `counts_monthly` top level keys.
```ruby
{
:counts_monthly => {
:deployments => 1003,
:successful_deployments => 78,
:failed_deployments => 275,
:packages => 155,
:personal_snippets => 2106,
:project_snippets => 407,
:promoted_issues => 719,
:aggregated_metrics => {
:example_metrics_union => 7,
:example_metrics_intersection => 2
},
:snippets => 2513
}
}
```
Aggregated metrics for `all` time frame are present in the `count` top level key, with the `aggregate_` prefix added to their name.
For example:
`example_metrics_intersection`
Becomes:
`counts.aggregate_example_metrics_intersection`
```ruby
{
:counts => {
:deployments => 11003,
:successful_deployments => 178,
:failed_deployments => 1275,
:aggregate_example_metrics_intersection => 12
}
}
```
### Redis sourced aggregated metrics
> - [Introduced](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/45979) in GitLab 13.6.
To declare the aggregate of events collected with [Redis HLL Counters](#redis-hll-counters),
you must fulfill the following requirements:
1. All events listed at `events` attribute must come from
[`known_events/*.yml`](#known-events-are-added-automatically-in-service-data-payload) files.
1. All events listed at `events` attribute must have the same `redis_slot` attribute.
1. All events listed at `events` attribute must have the same `aggregation` attribute.
1. `time_frame` does not include `all` value, which is unavailable for Redis sourced aggregated metrics.
### Database sourced aggregated metrics
> - [Introduced](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/52784) in GitLab 13.9.
> - It's [deployed behind a feature flag](../../user/feature_flags.md), disabled by default.
> - It's enabled on GitLab.com.
To declare an aggregate of metrics based on events collected from database, follow
these steps:
1. [Persist the metrics for aggregation](#persist-metrics-for-aggregation).
1. [Add new aggregated metric definition](#add-new-aggregated-metric-definition).
#### Persist metrics for aggregation
Only metrics calculated with [Estimated Batch Counters](#estimated-batch-counters)
can be persisted for database sourced aggregated metrics. To persist a metric,
inject a Ruby block into the
[estimate_batch_distinct_count](#estimate_batch_distinct_count-method) method.
This block should invoke the
`Gitlab::Usage::Metrics::Aggregates::Sources::PostgresHll.save_aggregated_metrics`
[method](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage/metrics/aggregates/sources/postgres_hll.rb#L21),
which stores `estimate_batch_distinct_count` results for future use in aggregated metrics.
The `Gitlab::Usage::Metrics::Aggregates::Sources::PostgresHll.save_aggregated_metrics`
method accepts the following arguments:
- `metric_name`: The name of metric to use for aggregations. Should be the same
as the key under which the metric is added into Service Ping.
- `recorded_at_timestamp`: The timestamp representing the moment when a given
Service Ping payload was collected. You should use the convenience method `recorded_at`
to fill `recorded_at_timestamp` argument, like this: `recorded_at_timestamp: recorded_at`
- `time_period`: The time period used to build the `relation` argument passed into
`estimate_batch_distinct_count`. To collect the metric with all available historical
data, set a `nil` value as time period: `time_period: nil`.
- `data`: HyperLogLog buckets structure representing unique entries in `relation`.
The `estimate_batch_distinct_count` method always passes the correct argument
into the block, so `data` argument must always have a value equal to block argument,
like this: `data: result`
Example metrics persistence:
```ruby
class UsageData
def count_secure_pipelines(time_period)
...
relation = ::Security::Scan.latest_successful_by_build.by_scan_types(scan_type).where(security_scans: time_period)
pipelines_with_secure_jobs['dependency_scanning_pipeline'] = estimate_batch_distinct_count(relation, :commit_id, batch_size: 1000, start: start_id, finish: finish_id) do |result|
::Gitlab::Usage::Metrics::Aggregates::Sources::PostgresHll
.save_aggregated_metrics(metric_name: 'dependency_scanning_pipeline', recorded_at_timestamp: recorded_at, time_period: time_period, data: result)
end
end
end
```
#### Add new aggregated metric definition
After all metrics are persisted, you can add an aggregated metric definition at
[`aggregated_metrics/`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/config/metrics/aggregates/).
To declare the aggregate of metrics collected with [Estimated Batch Counters](#estimated-batch-counters),
you must fulfill the following requirements:
- Metrics names listed in the `events:` attribute, have to use the same names you passed in the `metric_name` argument while persisting metrics in previous step.
- Every metric listed in the `events:` attribute, has to be persisted for **every** selected `time_frame:` value.
Example definition:
```yaml
- name: example_metrics_intersection_database_sourced
operator: AND
source: database
events:
- 'dependency_scanning_pipeline'
- 'container_scanning_pipeline'
time_frame:
- 28d
- all
```

View File

@ -222,844 +222,7 @@ We also collect metrics specific to [Geo](../../administration/geo/index.md) sec
## Implementing Service Ping
Service Ping consists of two kinds of data, counters and observations. Counters track how often a certain event
happened over time, such as how many CI pipelines have run. They are monotonic and always trend up.
Observations are facts collected from one or more GitLab instances and can carry arbitrary data. There are no
general guidelines around how to collect those, due to the individual nature of that data.
### Types of counters
There are several types of counters in `usage_data.rb`:
- **Ordinary Batch Counters:** Simple count of a given ActiveRecord_Relation
- **Distinct Batch Counters:** Distinct count of a given ActiveRecord_Relation in a given column
- **Sum Batch Counters:** Sum the values of a given ActiveRecord_Relation in a given column
- **Alternative Counters:** Used for settings and configurations
- **Redis Counters:** Used for in-memory counts.
NOTE:
Only use the provided counter methods. Each counter method contains a built-in fail-safe mechanism that isolates each counter to avoid breaking the entire Service Ping process.
### Instrumentation classes
We recommend you use [instrumentation classes](metrics_instrumentation.md) in `usage_data.rb` where possible.
For example, we have the following instrumentation class:
`lib/gitlab/usage/metrics/instrumentations/count_boards_metric.rb`.
You should add it to `usage_data.rb` as follows:
```ruby
boards: add_metric('CountBoardsMetric', time_frame: 'all'),
```
### Batch counting
For large tables, PostgreSQL can take a long time to count rows due to MVCC [(Multi-version Concurrency Control)](https://en.wikipedia.org/wiki/Multiversion_concurrency_control). Batch counting is a counting method where a single large query is broken into multiple smaller queries. For example, instead of a single query querying 1,000,000 records, with batch counting, you can execute 100 queries of 10,000 records each. Batch counting is useful for avoiding database timeouts as each batch query is significantly shorter than one single long running query.
For GitLab.com, there are extremely large tables with 15 second query timeouts, so we use batch counting to avoid encountering timeouts. Here are the sizes of some GitLab.com tables:
| Table | Row counts in millions |
|------------------------------|------------------------|
| `merge_request_diff_commits` | 2280 |
| `ci_build_trace_sections` | 1764 |
| `merge_request_diff_files` | 1082 |
| `events` | 514 |
The following operation methods are available:
- [Ordinary batch counters](#ordinary-batch-counters)
- [Distinct batch counters](#distinct-batch-counters)
- [Sum batch operation](#sum-batch-operation)
- [Add operation](#add-operation)
- [Estimated batch counters](#estimated-batch-counters)
Batch counting requires indexes on columns to calculate max, min, and range queries. In some cases,
you may need to add a specialized index on the columns involved in a counter.
### Ordinary batch counters
Handles `ActiveRecord::StatementInvalid` error
Simple count of a given `ActiveRecord_Relation`, does a non-distinct batch count, smartly reduces `batch_size`, and handles errors.
Method: `count(relation, column = nil, batch: true, start: nil, finish: nil)`
Arguments:
- `relation` the ActiveRecord_Relation to perform the count
- `column` the column to perform the count on, by default is the primary key
- `batch`: default `true` to use batch counting
- `start`: custom start of the batch counting to avoid complex min calculations
- `end`: custom end of the batch counting to avoid complex min calculations
Examples:
```ruby
count(User.active)
count(::Clusters::Cluster.aws_installed.enabled, :cluster_id)
count(::Clusters::Cluster.aws_installed.enabled, :cluster_id, start: ::Clusters::Cluster.minimum(:id), finish: ::Clusters::Cluster.maximum(:id))
```
### Distinct batch counters
Handles `ActiveRecord::StatementInvalid` error
Distinct count of a given `ActiveRecord_Relation` on given column, a distinct batch count, smartly reduces `batch_size`, and handles errors.
Method: `distinct_count(relation, column = nil, batch: true, batch_size: nil, start: nil, finish: nil)`
Arguments:
- `relation` the ActiveRecord_Relation to perform the count
- `column` the column to perform the distinct count, by default is the primary key
- `batch`: default `true` to use batch counting
- `batch_size`: if none set it uses default value 10000 from `Gitlab::Database::BatchCounter`
- `start`: custom start of the batch counting to avoid complex min calculations
- `end`: custom end of the batch counting to avoid complex min calculations
WARNING:
Counting over non-unique columns can lead to performance issues. For more information, see the [iterating tables in batches](../iterating_tables_in_batches.md) guide.
Examples:
```ruby
distinct_count(::Project, :creator_id)
distinct_count(::Note.with_suggestions.where(time_period), :author_id, start: ::User.minimum(:id), finish: ::User.maximum(:id))
distinct_count(::Clusters::Applications::CertManager.where(time_period).available.joins(:cluster), 'clusters.user_id')
```
### Sum batch operation
Handles `ActiveRecord::StatementInvalid` error
Sum the values of a given ActiveRecord_Relation on given column and handles errors.
Method: `sum(relation, column, batch_size: nil, start: nil, finish: nil)`
Arguments:
- `relation` the ActiveRecord_Relation to perform the operation
- `column` the column to sum on
- `batch_size`: if none set it uses default value 1000 from `Gitlab::Database::BatchCounter`
- `start`: custom start of the batch counting to avoid complex min calculations
- `end`: custom end of the batch counting to avoid complex min calculations
Examples:
```ruby
sum(JiraImportState.finished, :imported_issues_count)
```
### Grouping and batch operations
The `count`, `distinct_count`, and `sum` batch counters can accept an `ActiveRecord::Relation`
object, which groups by a specified column. With a grouped relation, the methods do batch counting,
handle errors, and returns a hash table of key-value pairs.
Examples:
```ruby
count(Namespace.group(:type))
# returns => {nil=>179, "Group"=>54}
distinct_count(Project.group(:visibility_level), :creator_id)
# returns => {0=>1, 10=>1, 20=>11}
sum(Issue.group(:state_id), :weight))
# returns => {1=>3542, 2=>6820}
```
### Add operation
Handles `StandardError`.
Returns `-1` if any of the arguments are `-1`.
Sum the values given as parameters.
Method: `add(*args)`
Examples:
```ruby
project_imports = distinct_count(::Project.where.not(import_type: nil), :creator_id)
bulk_imports = distinct_count(::BulkImport, :user_id)
add(project_imports, bulk_imports)
```
### Estimated batch counters
> - [Introduced](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/48233) in GitLab 13.7.
Estimated batch counter functionality handles `ActiveRecord::StatementInvalid` errors
when used through the provided `estimate_batch_distinct_count` method.
Errors return a value of `-1`.
WARNING:
This functionality estimates a distinct count of a specific ActiveRecord_Relation in a given column,
which uses the [HyperLogLog](http://algo.inria.fr/flajolet/Publications/FlFuGaMe07.pdf) algorithm.
As the HyperLogLog algorithm is probabilistic, the **results always include error**.
The highest encountered error rate is 4.9%.
When correctly used, the `estimate_batch_distinct_count` method enables efficient counting over
columns that contain non-unique values, which can not be assured by other counters.
#### estimate_batch_distinct_count method
Method: `estimate_batch_distinct_count(relation, column = nil, batch_size: nil, start: nil, finish: nil)`
The [method](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/utils/usage_data.rb#L63)
includes the following arguments:
- `relation`: The ActiveRecord_Relation to perform the count.
- `column`: The column to perform the distinct count. The default is the primary key.
- `batch_size`: From `Gitlab::Database::PostgresHll::BatchDistinctCounter::DEFAULT_BATCH_SIZE`. Default value: 10,000.
- `start`: The custom start of the batch count, to avoid complex minimum calculations.
- `finish`: The custom end of the batch count to avoid complex maximum calculations.
The method includes the following prerequisites:
1. The supplied `relation` must include the primary key defined as the numeric column.
For example: `id bigint NOT NULL`.
1. The `estimate_batch_distinct_count` can handle a joined relation. To use its ability to
count non-unique columns, the joined relation **must not** have a one-to-many relationship,
such as `has_many :boards`.
1. Both `start` and `finish` arguments should always represent primary key relationship values,
even if the estimated count refers to another column, for example:
```ruby
estimate_batch_distinct_count(::Note, :author_id, start: ::Note.minimum(:id), finish: ::Note.maximum(:id))
```
Examples:
1. Simple execution of estimated batch counter, with only relation provided,
returned value represents estimated number of unique values in `id` column
(which is the primary key) of `Project` relation:
```ruby
estimate_batch_distinct_count(::Project)
```
1. Execution of estimated batch counter, where provided relation has applied
additional filter (`.where(time_period)`), number of unique values estimated
in custom column (`:author_id`), and parameters: `start` and `finish` together
apply boundaries that defines range of provided relation to analyze:
```ruby
estimate_batch_distinct_count(::Note.with_suggestions.where(time_period), :author_id, start: ::Note.minimum(:id), finish: ::Note.maximum(:id))
```
1. Execution of estimated batch counter with joined relation (`joins(:cluster)`),
for a custom column (`'clusters.user_id'`):
```ruby
estimate_batch_distinct_count(::Clusters::Applications::CertManager.where(time_period).available.joins(:cluster), 'clusters.user_id')
```
When instrumenting metric with usage of estimated batch counter please add
`_estimated` suffix to its name, for example:
```ruby
"counts": {
"ci_builds_estimated": estimate_batch_distinct_count(Ci::Build),
...
```
### Redis counters
Handles `::Redis::CommandError` and `Gitlab::UsageDataCounters::BaseCounter::UnknownEvent`
returns -1 when a block is sent or hash with all values -1 when a `counter(Gitlab::UsageDataCounters)` is sent
different behavior due to 2 different implementations of Redis counter
Method: `redis_usage_data(counter, &block)`
Arguments:
- `counter`: a counter from `Gitlab::UsageDataCounters`, that has `fallback_totals` method implemented
- or a `block`: which is evaluated
#### Ordinary Redis counters
Examples of implementation:
- Using Redis methods [`INCR`](https://redis.io/commands/incr), [`GET`](https://redis.io/commands/get), and [`Gitlab::UsageDataCounters::WikiPageCounter`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_data_counters/wiki_page_counter.rb)
- Using Redis methods [`HINCRBY`](https://redis.io/commands/hincrby), [`HGETALL`](https://redis.io/commands/hgetall), and [`Gitlab::UsageCounters::PodLogs`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_counters/pod_logs.rb)
##### UsageData API tracking
<!-- There's nearly identical content in `##### Adding new events`. If you fix errors here, you may need to fix the same errors in the other location. -->
1. Track event using `UsageData` API
Increment event count using ordinary Redis counter, for given event name.
Tracking events using the `UsageData` API requires the `usage_data_api` feature flag to be enabled, which is enabled by default.
API requests are protected by checking for a valid CSRF token.
To be able to increment the values, the related feature `usage_data_<event_name>` should be enabled.
```plaintext
POST /usage_data/increment_counter
```
| Attribute | Type | Required | Description |
| :-------- | :--- | :------- | :---------- |
| `event` | string | yes | The event name it should be tracked |
Response:
- `200` if event was tracked
- `400 Bad request` if event parameter is missing
- `401 Unauthorized` if user is not authenticated
- `403 Forbidden` for invalid CSRF token provided
1. Track events using JavaScript/Vue API helper which calls the API above
Note that `usage_data_api` and `usage_data_#{event_name}` should be enabled to be able to track events
```javascript
import api from '~/api';
api.trackRedisCounterEvent('my_already_defined_event_name'),
```
#### Redis HLL counters
WARNING:
HyperLogLog (HLL) is a probabilistic algorithm and its **results always includes some small error**. According to [Redis documentation](https://redis.io/commands/pfcount), data from
used HLL implementation is "approximated with a standard error of 0.81%".
With `Gitlab::UsageDataCounters::HLLRedisCounter` we have available data structures used to count unique values.
Implemented using Redis methods [PFADD](https://redis.io/commands/pfadd) and [PFCOUNT](https://redis.io/commands/pfcount).
##### Add new events
1. Define events in [`known_events`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_data_counters/known_events/).
Example event:
```yaml
- name: users_creating_epics
category: epics_usage
redis_slot: users
aggregation: weekly
feature_flag: track_epics_activity
```
Keys:
- `name`: unique event name.
Name format for Redis HLL events `<name>_<redis_slot>`.
[See Metric name](metrics_dictionary.md#metric-name) for a complete guide on metric naming suggestion.
Consider including in the event's name the Redis slot to be able to count totals for a specific category.
Example names: `users_creating_epics`, `users_triggering_security_scans`.
- `category`: event category. Used for getting total counts for events in a category, for easier
access to a group of events.
- `redis_slot`: optional Redis slot. Default value: event name. Only event data that is stored in the same slot
can be aggregated. Ensure keys are in the same slot. For example:
`users_creating_epics` with `redis_slot: 'users'` builds Redis key
`{users}_creating_epics-2020-34`. If `redis_slot` is not defined the Redis key will
be `{users_creating_epics}-2020-34`.
Recommended slots to use are: `users`, `projects`. This is the value we count.
- `expiry`: expiry time in days. Default: 29 days for daily aggregation and 6 weeks for weekly
aggregation.
- `aggregation`: may be set to a `:daily` or `:weekly` key. Defines how counting data is stored in Redis.
Aggregation on a `daily` basis does not pull more fine grained data.
- `feature_flag`: optional `default_enabled: :yaml`. If no feature flag is set then the tracking is enabled. One feature flag can be used for multiple events. For details, see our [GitLab internal Feature flags](../feature_flags/index.md) documentation. The feature flags are owned by the group adding the event tracking.
1. Use one of the following methods to track the event:
- In the controller using the `RedisTracking` module and the following format:
```ruby
track_redis_hll_event(*controller_actions, name:, if: nil, &block)
```
Arguments:
- `controller_actions`: the controller actions to track.
- `name`: the event name.
- `if`: optional custom conditions. Uses the same format as Rails callbacks.
- `&block`: optional block that computes and returns the `custom_id` that we want to track. This overrides the `visitor_id`.
Example:
```ruby
# controller
class ProjectsController < Projects::ApplicationController
include RedisTracking
skip_before_action :authenticate_user!, only: :show
track_redis_hll_event :index, :show, name: 'users_visiting_projects'
def index
render html: 'index'
end
def new
render html: 'new'
end
def show
render html: 'show'
end
end
```
- In the API using the `increment_unique_values(event_name, values)` helper method.
Arguments:
- `event_name`: the event name.
- `values`: the values counted. Can be one value or an array of values.
Example:
```ruby
get ':id/registry/repositories' do
repositories = ContainerRepositoriesFinder.new(
user: current_user, subject: user_group
).execute
increment_unique_values('users_listing_repositories', current_user.id)
present paginate(repositories), with: Entities::ContainerRegistry::Repository, tags: params[:tags], tags_count: params[:tags_count]
end
```
- Using `track_usage_event(event_name, values)` in services and GraphQL.
Increment unique values count using Redis HLL, for a given event name.
Examples:
- [Track usage event for an incident in a service](https://gitlab.com/gitlab-org/gitlab/-/blob/v13.8.3-ee/app/services/issues/update_service.rb#L66)
- [Track usage event for an incident in GraphQL](https://gitlab.com/gitlab-org/gitlab/-/blob/v13.8.3-ee/app/graphql/mutations/alert_management/update_alert_status.rb#L16)
```ruby
track_usage_event(:incident_management_incident_created, current_user.id)
```
- Using the `UsageData` API.
<!-- There's nearly identical content in `##### UsageData API Tracking`. If you find / fix errors here, you may need to fix errors in that section too. -->
Increment unique users count using Redis HLL, for a given event name.
To track events using the `UsageData` API, ensure the `usage_data_api` feature flag
is set to `default_enabled: true`. Enabled by default in GitLab 13.7 and later.
API requests are protected by checking for a valid CSRF token.
```plaintext
POST /usage_data/increment_unique_users
```
| Attribute | Type | Required | Description |
| :-------- | :--- | :------- | :---------- |
| `event` | string | yes | The event name to track |
Response:
- `200` if the event was tracked, or if tracking failed for any reason.
- `400 Bad request` if an event parameter is missing.
- `401 Unauthorized` if the user is not authenticated.
- `403 Forbidden` if an invalid CSRF token is provided.
- Using the JavaScript/Vue API helper, which calls the `UsageData` API.
To track events using the `UsageData` API, ensure the `usage_data_api` feature flag
is set to `default_enabled: true`. Enabled by default in GitLab 13.7 and later.
Example for an existing event already defined in [known events](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_data_counters/known_events/):
```javascript
import api from '~/api';
api.trackRedisHllUserEvent('my_already_defined_event_name'),
```
1. Get event data using `Gitlab::UsageDataCounters::HLLRedisCounter.unique_events(event_names:, start_date:, end_date:, context: '')`.
Arguments:
- `event_names`: the list of event names.
- `start_date`: start date of the period for which we want to get event data.
- `end_date`: end date of the period for which we want to get event data.
- `context`: context of the event. Allowed values are `default`, `free`, `bronze`, `silver`, `gold`, `starter`, `premium`, `ultimate`.
1. Testing tracking and getting unique events
Trigger events in rails console by using `track_event` method
```ruby
Gitlab::UsageDataCounters::HLLRedisCounter.track_event('users_viewing_compliance_audit_events', values: 1)
Gitlab::UsageDataCounters::HLLRedisCounter.track_event('users_viewing_compliance_audit_events', values: [2, 3])
```
Next, get the unique events for the current week.
```ruby
# Get unique events for metric for current_week
Gitlab::UsageDataCounters::HLLRedisCounter.unique_events(event_names: 'users_viewing_compliance_audit_events',
start_date: Date.current.beginning_of_week, end_date: Date.current.next_week)
```
##### Recommendations
We have the following recommendations for [adding new events](#add-new-events):
- Event aggregation: weekly.
- Key expiry time:
- Daily: 29 days.
- Weekly: 42 days.
- When adding new metrics, use a [feature flag](../../operations/feature_flags.md) to control the impact.
- For feature flags triggered by another service, set `default_enabled: false`,
- Events can be triggered using the `UsageData` API, which helps when there are > 10 events per change
##### Enable or disable Redis HLL tracking
Events are tracked behind optional [feature flags](../feature_flags/index.md) due to concerns for Redis performance and scalability.
For a full list of events and corresponding feature flags see, [known_events](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_data_counters/known_events/) files.
To enable or disable tracking for specific event in <https://gitlab.com> or <https://about.staging.gitlab.com>, run commands such as the following to
[enable or disable the corresponding feature](../feature_flags/index.md).
```shell
/chatops run feature set <feature_name> true
/chatops run feature set <feature_name> false
```
We can also disable tracking completely by using the global flag:
```shell
/chatops run feature set redis_hll_tracking true
/chatops run feature set redis_hll_tracking false
```
##### Known events are added automatically in Service Data payload
All events added in [`known_events/common.yml`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_data_counters/known_events/common.yml) are automatically added to Service Data generation under the `redis_hll_counters` key. This column is stored in [version-app as a JSON](https://gitlab.com/gitlab-services/version-gitlab-com/-/blob/master/db/schema.rb#L209).
For each event we add metrics for the weekly and monthly time frames, and totals for each where applicable:
- `#{event_name}_weekly`: Data for 7 days for daily [aggregation](#add-new-events) events and data for the last complete week for weekly [aggregation](#add-new-events) events.
- `#{event_name}_monthly`: Data for 28 days for daily [aggregation](#add-new-events) events and data for the last 4 complete weeks for weekly [aggregation](#add-new-events) events.
Redis HLL implementation calculates automatic total metrics, if there are more than one metric for the same category, aggregation, and Redis slot.
- `#{category}_total_unique_counts_weekly`: Total unique counts for events in the same category for the last 7 days or the last complete week, if events are in the same Redis slot and we have more than one metric.
- `#{category}_total_unique_counts_monthly`: Total unique counts for events in same category for the last 28 days or the last 4 complete weeks, if events are in the same Redis slot and we have more than one metric.
Example of `redis_hll_counters` data:
```ruby
{:redis_hll_counters=>
{"compliance"=>
{"users_viewing_compliance_dashboard_weekly"=>0,
"users_viewing_compliance_dashboard_monthly"=>0,
"users_viewing_compliance_audit_events_weekly"=>0,
"users_viewing_audit_events_monthly"=>0,
"compliance_total_unique_counts_weekly"=>0,
"compliance_total_unique_counts_monthly"=>0},
"analytics"=>
{"users_viewing_analytics_group_devops_adoption_weekly"=>0,
"users_viewing_analytics_group_devops_adoption_monthly"=>0,
"analytics_total_unique_counts_weekly"=>0,
"analytics_total_unique_counts_monthly"=>0},
"ide_edit"=>
{"users_editing_by_web_ide_weekly"=>0,
"users_editing_by_web_ide_monthly"=>0,
"users_editing_by_sfe_weekly"=>0,
"users_editing_by_sfe_monthly"=>0,
"ide_edit_total_unique_counts_weekly"=>0,
"ide_edit_total_unique_counts_monthly"=>0}
}
```
Example:
```ruby
# Redis Counters
redis_usage_data(Gitlab::UsageDataCounters::WikiPageCounter)
redis_usage_data { ::Gitlab::UsageCounters::PodLogs.usage_totals[:total] }
# Define events in common.yml https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage_data_counters/known_events/common.yml
# Tracking events
Gitlab::UsageDataCounters::HLLRedisCounter.track_event('users_expanding_vulnerabilities', values: visitor_id)
# Get unique events for metric
redis_usage_data { Gitlab::UsageDataCounters::HLLRedisCounter.unique_events(event_names: 'users_expanding_vulnerabilities', start_date: 28.days.ago, end_date: Date.current) }
```
### Alternative counters
Handles `StandardError` and fallbacks into -1 this way not all measures fail if we encounter one exception.
Mainly used for settings and configurations.
Method: `alt_usage_data(value = nil, fallback: -1, &block)`
Arguments:
- `value`: a simple static value in which case the value is simply returned.
- or a `block`: which is evaluated
- `fallback: -1`: the common value used for any metrics that are failing.
Example:
```ruby
alt_usage_data { Gitlab::VERSION }
alt_usage_data { Gitlab::CurrentSettings.uuid }
alt_usage_data(999)
```
### Add counters to build new metrics
When adding the results of two counters, use the `add` Service Data method that
handles fallback values and exceptions. It also generates a valid [SQL export](#export-service-ping-sql-queries-and-definitions).
Example:
```ruby
add(User.active, User.bot)
```
### Prometheus queries
In those cases where operational metrics should be part of Service Ping, a database or Redis query is unlikely
to provide useful data. Instead, Prometheus might be more appropriate, because most GitLab architectural
components publish metrics to it that can be queried back, aggregated, and included as Service Data.
NOTE:
Prometheus as a data source for Service Ping is only available for single-node Omnibus installations
that are running the [bundled Prometheus](../../administration/monitoring/prometheus/index.md) instance.
To query Prometheus for metrics, a helper method is available to `yield` a fully configured
`PrometheusClient`, given it is available as per the note above:
```ruby
with_prometheus_client do |client|
response = client.query('<your query>')
...
end
```
Refer to [the `PrometheusClient` definition](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/prometheus_client.rb)
for how to use its API to query for data.
### Fallback values for Service Ping
We return fallback values in these cases:
| Case | Value |
|-----------------------------|-------|
| Deprecated Metric | -1000 |
| Timeouts, general failures | -1 |
| Standard errors in counters | -2 |
## Aggregated metrics
> - [Introduced](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/45979) in GitLab 13.6.
WARNING:
This feature is intended solely for internal GitLab use.
To add data for aggregated metrics to the Service Ping payload, add a corresponding definition to:
- [`config/metrics/aggregates/*.yaml`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/config/metrics/aggregates/) for metrics available in the Community Edition.
- [`ee/config/metrics/aggregates/*.yaml`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/ee/config/metrics/aggregates/) for metrics available in the Enterprise Edition.
Each aggregate definition includes following parts:
- `name`: Unique name under which the aggregate metric is added to the Service Ping payload.
- `operator`: Operator that defines how the aggregated metric data is counted. Available operators are:
- `OR`: Removes duplicates and counts all entries that triggered any of listed events.
- `AND`: Removes duplicates and counts all elements that were observed triggering all of following events.
- `time_frame`: One or more valid time frames. Use these to limit the data included in aggregated metric to events within a specific date-range. Valid time frames are:
- `7d`: Last seven days of data.
- `28d`: Last twenty eight days of data.
- `all`: All historical data, only available for `database` sourced aggregated metrics.
- `source`: Data source used to collect all events data included in aggregated metric. Valid data sources are:
- [`database`](#database-sourced-aggregated-metrics)
- [`redis`](#redis-sourced-aggregated-metrics)
- `events`: list of events names to aggregate into metric. All events in this list must
relay on the same data source. Additional data source requirements are described in the
[Database sourced aggregated metrics](#database-sourced-aggregated-metrics) and
[Redis sourced aggregated metrics](#redis-sourced-aggregated-metrics) sections.
- `feature_flag`: Name of [development feature flag](../feature_flags/index.md#development-type)
that is checked before metrics aggregation is performed. Corresponding feature flag
should have `default_enabled` attribute set to `false`. The `feature_flag` attribute
is optional and can be omitted. When `feature_flag` is missing, no feature flag is checked.
Example aggregated metric entries:
```yaml
- name: example_metrics_union
operator: OR
events:
- 'users_expanding_secure_security_report'
- 'users_expanding_testing_code_quality_report'
- 'users_expanding_testing_accessibility_report'
source: redis
time_frame:
- 7d
- 28d
- name: example_metrics_intersection
operator: AND
source: database
time_frame:
- 28d
- all
events:
- 'dependency_scanning_pipeline_all_time'
- 'container_scanning_pipeline_all_time'
feature_flag: example_aggregated_metric
```
Aggregated metrics collected in `7d` and `28d` time frames are added into Service Ping payload under the `aggregated_metrics` sub-key in the `counts_weekly` and `counts_monthly` top level keys.
```ruby
{
:counts_monthly => {
:deployments => 1003,
:successful_deployments => 78,
:failed_deployments => 275,
:packages => 155,
:personal_snippets => 2106,
:project_snippets => 407,
:promoted_issues => 719,
:aggregated_metrics => {
:example_metrics_union => 7,
:example_metrics_intersection => 2
},
:snippets => 2513
}
}
```
Aggregated metrics for `all` time frame are present in the `count` top level key, with the `aggregate_` prefix added to their name.
For example:
`example_metrics_intersection`
Becomes:
`counts.aggregate_example_metrics_intersection`
```ruby
{
:counts => {
:deployments => 11003,
:successful_deployments => 178,
:failed_deployments => 1275,
:aggregate_example_metrics_intersection => 12
}
}
```
### Redis sourced aggregated metrics
> - [Introduced](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/45979) in GitLab 13.6.
To declare the aggregate of events collected with [Redis HLL Counters](#redis-hll-counters),
you must fulfill the following requirements:
1. All events listed at `events` attribute must come from
[`known_events/*.yml`](#known-events-are-added-automatically-in-service-data-payload) files.
1. All events listed at `events` attribute must have the same `redis_slot` attribute.
1. All events listed at `events` attribute must have the same `aggregation` attribute.
1. `time_frame` does not include `all` value, which is unavailable for Redis sourced aggregated metrics.
### Database sourced aggregated metrics
> - [Introduced](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/52784) in GitLab 13.9.
> - It's [deployed behind a feature flag](../../user/feature_flags.md), disabled by default.
> - It's enabled on GitLab.com.
To declare an aggregate of metrics based on events collected from database, follow
these steps:
1. [Persist the metrics for aggregation](#persist-metrics-for-aggregation).
1. [Add new aggregated metric definition](#add-new-aggregated-metric-definition).
#### Persist metrics for aggregation
Only metrics calculated with [Estimated Batch Counters](#estimated-batch-counters)
can be persisted for database sourced aggregated metrics. To persist a metric,
inject a Ruby block into the
[estimate_batch_distinct_count](#estimate_batch_distinct_count-method) method.
This block should invoke the
`Gitlab::Usage::Metrics::Aggregates::Sources::PostgresHll.save_aggregated_metrics`
[method](https://gitlab.com/gitlab-org/gitlab/-/blob/master/lib/gitlab/usage/metrics/aggregates/sources/postgres_hll.rb#L21),
which stores `estimate_batch_distinct_count` results for future use in aggregated metrics.
The `Gitlab::Usage::Metrics::Aggregates::Sources::PostgresHll.save_aggregated_metrics`
method accepts the following arguments:
- `metric_name`: The name of metric to use for aggregations. Should be the same
as the key under which the metric is added into Service Ping.
- `recorded_at_timestamp`: The timestamp representing the moment when a given
Service Ping payload was collected. You should use the convenience method `recorded_at`
to fill `recorded_at_timestamp` argument, like this: `recorded_at_timestamp: recorded_at`
- `time_period`: The time period used to build the `relation` argument passed into
`estimate_batch_distinct_count`. To collect the metric with all available historical
data, set a `nil` value as time period: `time_period: nil`.
- `data`: HyperLogLog buckets structure representing unique entries in `relation`.
The `estimate_batch_distinct_count` method always passes the correct argument
into the block, so `data` argument must always have a value equal to block argument,
like this: `data: result`
Example metrics persistence:
```ruby
class UsageData
def count_secure_pipelines(time_period)
...
relation = ::Security::Scan.latest_successful_by_build.by_scan_types(scan_type).where(security_scans: time_period)
pipelines_with_secure_jobs['dependency_scanning_pipeline'] = estimate_batch_distinct_count(relation, :commit_id, batch_size: 1000, start: start_id, finish: finish_id) do |result|
::Gitlab::Usage::Metrics::Aggregates::Sources::PostgresHll
.save_aggregated_metrics(metric_name: 'dependency_scanning_pipeline', recorded_at_timestamp: recorded_at, time_period: time_period, data: result)
end
end
end
```
#### Add new aggregated metric definition
After all metrics are persisted, you can add an aggregated metric definition at
[`aggregated_metrics/`](https://gitlab.com/gitlab-org/gitlab/-/blob/master/config/metrics/aggregates/).
To declare the aggregate of metrics collected with [Estimated Batch Counters](#estimated-batch-counters),
you must fulfill the following requirements:
- Metrics names listed in the `events:` attribute, have to use the same names you passed in the `metric_name` argument while persisting metrics in previous step.
- Every metric listed in the `events:` attribute, has to be persisted for **every** selected `time_frame:` value.
Example definition:
```yaml
- name: example_metrics_intersection_database_sourced
operator: AND
source: database
events:
- 'dependency_scanning_pipeline'
- 'container_scanning_pipeline'
time_frame:
- 28d
- all
```
See the [implement Service Ping](implement.md) guide.
## Example Service Ping payload

View File

@ -217,7 +217,7 @@ create ee/config/metrics/counts_7d/issues.yml
## Metrics added dynamic to Service Ping payload
The [Redis HLL metrics](index.md#known-events-are-added-automatically-in-service-data-payload) are added automatically to Service Ping payload.
The [Redis HLL metrics](implement.md#known-events-are-added-automatically-in-service-data-payload) are added automatically to Service Ping payload.
A YAML metric definition is required for each metric. A dedicated generator is provided to create metric definitions for Redis HLL events.

View File

@ -10,7 +10,7 @@ The following guidelines explain the steps to follow at each stage of a metric's
## Add a new metric
Please follow the [Implementing Service Ping](index.md#implementing-service-ping) guide.
Follow the [Implement Service Ping](implement.md) guide.
## Change an existing metric

View File

@ -59,7 +59,7 @@ are regular backend changes.
metrics that are based on Database.
- For tracking using Redis HLL (HyperLogLog):
- Check the Redis slot.
- Check if a [feature flag is needed](index.md#recommendations).
- Check if a [feature flag is needed](implement.md#recommendations).
- For a metric's YAML definition:
- Check the metric's `description`.
- Check the metric's `key_path`.

View File

@ -1138,7 +1138,8 @@ There are a few possible downsides to this:
the last project that gets backed up.
- Fork networks should be entirely read-only while the projects inside get backed up to prevent potential changes to the pool repository.
There is an **experimental** script that attempts to automate this process in [Snippet 2149205](https://gitlab.com/-/snippets/2149205).
There is an **experimental** script that attempts to automate this process in
[the Geo team Runbooks project](https://gitlab.com/gitlab-org/geo-team/runbooks/-/tree/main/experimental-online-backup-through-rsync).
## Backup and restore for installations using PgBouncer

View File

@ -358,6 +358,36 @@ NOTE:
Specific information that follow related to Ruby and Git versions do not apply to [Omnibus installations](https://docs.gitlab.com/omnibus/)
and [Helm Chart deployments](https://docs.gitlab.com/charts/). They come with appropriate Ruby and Git versions and are not using system binaries for Ruby and Git. There is no need to install Ruby or Git when utilizing these two approaches.
### 14.2.0
- Due to an issue where `BatchedBackgroundMigrationWorkers` were
[not working](https://gitlab.com/gitlab-org/charts/gitlab/-/issues/2785#note_614738345)
for self-managed instances, a [fix was created](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/65106)
and a [14.0.Z](#1400) version was released. If you haven't updated to 14.0.Z, you need
to update to at least 14.1.0 that contains the same fix before you update to
to 14.2.
- GitLab 14.2.0 contains background migrations to [address Primary Key overflow risk for tables with an integer PK](https://gitlab.com/groups/gitlab-org/-/epics/4785) for the tables listed below:
- [`ci_build_needs`](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/65216)
- [`ci_build_trace_chunks`](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/66123)
- [`ci_builds_runner_session`](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/66433)
- [`deployments`](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/67341)
- [`geo_job_artifact_deleted_events`](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/66763)
- [`push_event_payloads`](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/67299)
- `ci_job_artifacts`:
- [Finalize job_id conversion to `bigint` for `ci_job_artifacts`](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/67774)
- [Finalize `ci_job_artifacts` conversion to `bigint`](https://gitlab.com/gitlab-org/gitlab/-/merge_requests/65601)
If the migrations are executed as part of a no-downtime deployment, there's a risk of failure due to lock conflicts with the application logic, resulting in lock timeout or deadlocks. In each case, these migrations are safe to re-run until successful:
```shell
# For Omnibus GitLab
sudo gitlab-rake db:migrate
# For source installations
sudo -u git -H bundle exec rake db:migrate RAILS_ENV=production
```
### 14.1.0
- Due to an issue where `BatchedBackgroundMigrationWorkers` were

View File

@ -202,7 +202,7 @@ module API
options[:project] = user_project
if Feature.enabled?(:api_caching_merge_requests, user_project, type: :development, default_enabled: :yaml)
present_cached merge_requests, expires_in: 10.minutes, **options
present_cached merge_requests, expires_in: 12.hours, **options
else
present merge_requests, options
end

View File

@ -67,7 +67,6 @@
- name: design_action
category: source_code
aggregation: daily
feature_flag: usage_data_design_action
- name: project_action
category: source_code
aggregation: daily

View File

@ -390,28 +390,13 @@ describe('Design management design index page', () => {
);
});
describe('with usage_data_design_action enabled', () => {
it('tracks design view service ping', () => {
createComponent(
{ loading: true },
{
provide: {
glFeatures: { usageDataDesignAction: true },
},
},
);
expect(Api.trackRedisHllUserEvent).toHaveBeenCalledTimes(1);
expect(Api.trackRedisHllUserEvent).toHaveBeenCalledWith(
DESIGN_SERVICE_PING_EVENT_TYPES.DESIGN_ACTION,
);
});
});
it('tracks design view service ping', () => {
createComponent({ loading: true });
describe('with usage_data_design_action disabled', () => {
it("doesn't track design view service ping", () => {
createComponent({ loading: true });
expect(Api.trackRedisHllUserEvent).toHaveBeenCalledTimes(0);
});
expect(Api.trackRedisHllUserEvent).toHaveBeenCalledTimes(1);
expect(Api.trackRedisHllUserEvent).toHaveBeenCalledWith(
DESIGN_SERVICE_PING_EVENT_TYPES.DESIGN_ACTION,
);
});
});
});

View File

@ -52,6 +52,8 @@ RSpec.configure do |config|
example.run
delete_from_all_tables!(except: deletion_except_tables)
self.class.use_transactional_tests = true
end
config.around(:each, :migration) do |example|
@ -60,5 +62,7 @@ RSpec.configure do |config|
example.run
delete_from_all_tables!
self.class.use_transactional_tests = true
end
end