diff --git a/.chloggen/36005-add-bytes-array-message-parsing.yaml b/.chloggen/36005-add-bytes-array-message-parsing.yaml new file mode 100644 index 000000000000..a28f366e20c9 --- /dev/null +++ b/.chloggen/36005-add-bytes-array-message-parsing.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: adds ability to parse journald's MESSAGE field as a string if desired + +# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists. +issues: [36005] + +# (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: [user] diff --git a/pkg/stanza/operator/input/journald/config_all.go b/pkg/stanza/operator/input/journald/config_all.go index 7e579a5a4d87..1015fcf2f0d5 100644 --- a/pkg/stanza/operator/input/journald/config_all.go +++ b/pkg/stanza/operator/input/journald/config_all.go @@ -27,17 +27,18 @@ 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"` - Identifiers []string `mapstructure:"identifiers,omitempty"` - Grep string `mapstructure:"grep,omitempty"` - Dmesg bool `mapstructure:"dmesg,omitempty"` - All bool `mapstructure:"all,omitempty"` - Namespace string `mapstructure:"namespace,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"` + All bool `mapstructure:"all,omitempty"` + Namespace string `mapstructure:"namespace,omitempty"` + ConvertMessageBytes bool `mapstructure:"convert_message_bytes,omitempty"` } type MatchConfig map[string]string diff --git a/pkg/stanza/operator/input/journald/config_linux.go b/pkg/stanza/operator/input/journald/config_linux.go index 489a62111514..c011e44bcf85 100644 --- a/pkg/stanza/operator/input/journald/config_linux.go +++ b/pkg/stanza/operator/input/journald/config_linux.go @@ -48,7 +48,8 @@ func (c Config) Build(set component.TelemetrySettings) (operator.Operator, error return exec.CommandContext(ctx, "journalctl", journalArgs...) // #nosec - ... // journalctl is an executable that is required for this operator to function }, - json: jsoniter.ConfigFastest, + convertMessageBytes: c.ConvertMessageBytes, + json: jsoniter.ConfigFastest, }, nil } diff --git a/pkg/stanza/operator/input/journald/input.go b/pkg/stanza/operator/input/journald/input.go index f5758fab0ac9..d7969741daf8 100644 --- a/pkg/stanza/operator/input/journald/input.go +++ b/pkg/stanza/operator/input/journald/input.go @@ -30,11 +30,12 @@ type Input struct { newCmd func(ctx context.Context, cursor []byte) cmd - persister operator.Persister - json jsoniter.API - cancel context.CancelFunc - wg sync.WaitGroup - errChan chan error + persister operator.Persister + json jsoniter.API + convertMessageBytes bool + cancel context.CancelFunc + wg sync.WaitGroup + errChan chan error } type cmd interface { @@ -227,6 +228,21 @@ func (operator *Input) parseJournalEntry(line []byte) (*entry.Entry, string, err return nil, "", fmt.Errorf("parse timestamp: %w", err) } + if operator.convertMessageBytes { + // Convert the message bytes to string if given as a byte array + msgArr, msgArrayOk := body["MESSAGE"].([]any) + if msgArrayOk { + var bytes []byte + for _, val := range msgArr { + floatVal, floatCheckOk := val.(float64) + if floatCheckOk { + bytes = append(bytes, byte(int(floatVal))) + } + } + body["MESSAGE"] = string(bytes) + } + } + delete(body, "__REALTIME_TIMESTAMP") cursor, ok := body["__CURSOR"] diff --git a/receiver/journaldreceiver/README.md b/receiver/journaldreceiver/README.md index 6f3c3329cbb2..842c1db3571d 100644 --- a/receiver/journaldreceiver/README.md +++ b/receiver/journaldreceiver/README.md @@ -36,6 +36,7 @@ Journald receiver requires that: | `storage` | none | The ID of a storage extension to be used to store cursors. Cursors allow the receiver to pick up where it left off in the case of a collector restart. If no storage extension is used, the receiver will manage cursors in memory only. | | `all` | 'false' | If `true`, very long logs and logs with unprintable characters will also be included. | | `namespace` | | Will query the given namespace. See man page [`systemd-journald.service(8)`](https://www.man7.org/linux/man-pages/man8/systemd-journald.service.8.html#JOURNAL_NAMESPACES) for details. | +| `convert_message_bytes` | 'false' | If `true` and if the `MESSAGE` field is read [as an array of bytes](https://github.com/systemd/systemd/blob/main/docs/JOURNAL_EXPORT_FORMATS.md#journal-json-format), the array will be converted to string. | | `retry_on_failure.enabled` | `false` | If `true`, the receiver will pause reading a file and attempt to resend the current batch of logs if it encounters an error from downstream components. | | `retry_on_failure.initial_interval` | `1 second` | Time to wait after the first failure before retrying. | | `retry_on_failure.max_interval` | `30 seconds` | Upper bound on retry backoff interval. Once this value is reached the delay between consecutive retries will remain constant at the specified value. |