[receiver/journald]: add support for identifiers (#25911)

Adds support for `identifiers` to journaldreceiver

.chloggen/drosiek-journald-identifier.yaml

@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: journaldreceiver
+
+# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: add support for identifiers
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [20295]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: []

pkg/stanza/operator/input/journald/journald.go

@@ -53,14 +53,15 @@ func NewConfigWithID(operatorID string) *Config {
 type Config struct {
  helper.InputConfig `mapstructure:",squash"`
 
- Directory *string `mapstructure:"directory,omitempty"`
- Files []string `mapstructure:"files,omitempty"`
- StartAt string `mapstructure:"start_at,omitempty"`
- Units []string `mapstructure:"units,omitempty"`
- Priority string `mapstructure:"priority,omitempty"`
- Matches []MatchConfig `mapstructure:"matches,omitempty"`
- Grep string `mapstructure:"grep,omitempty"`
- Dmesg bool `mapstructure:"dmesg,omitempty"`
+ Directory *string `mapstructure:"directory,omitempty"`
+ Files []string `mapstructure:"files,omitempty"`
+ StartAt string `mapstructure:"start_at,omitempty"`
+ Units []string `mapstructure:"units,omitempty"`
+ Priority string `mapstructure:"priority,omitempty"`
+ Matches []MatchConfig `mapstructure:"matches,omitempty"`
+ Identifiers []string `mapstructure:"identifiers,omitempty"`
+ Grep string `mapstructure:"grep,omitempty"`
+ Dmesg bool `mapstructure:"dmesg,omitempty"`
 }
 
 type MatchConfig map[string]string
@@ -114,6 +115,10 @@ func (c Config) buildArgs() ([]string, error) {
  args = append(args, "--unit", unit)
  }
 
+ for _, identifier := range c.Identifiers {
+ args = append(args, "--identifier", identifier)
+ }
+
  args = append(args, "--priority", c.Priority)
 
  if len(c.Grep) > 0 {

pkg/stanza/operator/input/journald/journald_test.go

@@ -183,6 +183,13 @@ func TestBuildConfig(t *testing.T) {
  },
  Expected: []string{"--utc", "--output=json", "--follow", "--unit", "ssh", "--priority", "info", "_SYSTEMD_UNIT=dbus.service"},
  },
+ {
+ Name: "identifiers",
+ Config: func(cfg *Config) {
+ cfg.Identifiers = []string{"wireplumber", "systemd"}
+ },
+ Expected: []string{"--utc", "--output=json", "--follow", "--identifier", "wireplumber", "--identifier", "systemd", "--priority", "info"},
+ },
  {
  Name: "grep",
  Config: func(cfg *Config) {

receiver/journaldreceiver/README.md

@@ -29,6 +29,7 @@ Journald receiver requires that:
 | `files` | | A list of journal files to read entries from |
 | `start_at` | `end` | At startup, where to start reading logs from the file. Options are beginning or end |
 | `units` | | A list of units to read entries from. See [Multiple filtering options](#multiple-filtering-options) examples. |
+| `identifiers` | | Filter output by message identifiers (`SYSTEMD_IDENTIFIER`). See [Multiple filtering options](#multiple-filtering-options) examples. |
 | `matches` | | A list of matches to read entries from. See [Matches](#matches) and [Multiple filtering options](#multiple-filtering-options) examples. |
 | `priority` | `info` | Filter output by message priorities or priority ranges. See [Multiple filtering options](#multiple-filtering-options) examples. |
 | `grep` | | Filter output to entries where the MESSAGE= field matches the specified regular expression. See [Multiple filtering options](#multiple-filtering-options) examples. |
@@ -92,6 +93,8 @@ AND
 AND
 ( units[0] OR units[1] OR units[2] OR ... units[U] )
 AND
+( identifier[0] OR identifier[1] OR identifier[2] OR ... identifier[I] )
+AND
 ( matches[0] OR matches[1] OR matches[2] OR ... matches[M] )
 AND
 ( grep )
@@ -109,14 +112,17 @@ Consider the following example:
  - kubelet
  - systemd
  priority: info
+ identifiers:
+ - systemd
 ```
 
 The above configuration will be passed to `journalctl` as the following arguments
-`journalctl ... --priority=info --unit=kubelet --unit=systemd _SYSTEMD_UNIT=ssh + _SYSTEMD_UNIT=kubelet _UID=1000`,
+`journalctl ... --priority=info --unit=kubelet --unit=systemd --identifier=systemd _SYSTEMD_UNIT=ssh + _SYSTEMD_UNIT=kubelet _UID=1000`,
 which is going to effectively retrieve all entries which matches the following set of rules:
 
 - `_PRIORITY` is `6`, and
 - `_SYSTEMD_UNIT` is `kubelet` or `systemd`, and
+- `SYSLOG_IDENTIFIER` `systemd`, and
 - entry matches at least one of the following rules:
 
  - `_SYSTEMD_UNIT` is `ssh`