Skip to content

Document simple_aggregation for kinesis/firehose #2299

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ShelbyZ wants to merge 1 commit into
base: master
Choose a base branch
from
+2 −0
Open

Document simple_aggregation for kinesis/firehose #2299

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions pipeline/outputs/firehose.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
| `sts_endpoint` | Custom endpoint for the STS API. | _none_ |
| `auto_retry_requests` | Immediately retry failed requests to AWS services once. This option doesn't affect the normal Fluent Bit retry mechanism with backoff. Instead, it enables an immediate retry with no delay for networking errors, which can help improve throughput when there are transient/random networking issues. | `true` |
| `external_id` | Specify an external ID for the STS API. Can be used with the `role_arn` parameter if your role requires an external ID. | _none_ |
| `simple_aggregation` | Enable simple aggregation to combine multiple records into single API calls. This reduces the number of requests and can improve throughput. When enabled, multiple log records are concatenated with newlines and sent as a single record to Firehose, up to the maximum record size limit (1,024,000 bytes). | `false` |

Check warning on line 30 in pipeline/outputs/firehose.md

View workflow job for this annotation

GitHub Actions / runner / vale 

[vale] reported by reviewdog 🐶
[FluentBit.Simplicity] Avoid words like "simple" that imply ease of use, because the user may find this action difficult.

Raw Output:
{"message": "[FluentBit.Simplicity] Avoid words like \"simple\" that imply ease of use, because the user may find this action difficult.", "location": {"path": "pipeline/outputs/firehose.md", "range": {"start": {"line": 30, "column": 33}}}, "severity": "WARNING"}
| `profile` | AWS profile name to use. | `default` |
| `workers` | The number of [workers](../../administration/multithreading.md#outputs) to perform flush operations for this output. | `1` |

Expand Down
1 change: 1 addition & 0 deletions pipeline/outputs/kinesis.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
| `sts_endpoint` | Custom endpoint for the STS API. | _none_ |
| `auto_retry_requests` | Immediately retry failed requests to AWS services once. This option doesn't affect the normal Fluent Bit retry mechanism with backoff. Instead, it enables an immediate retry with no delay for networking errors, which might help improve throughput when there are transient/random networking issues. | `true` |
| `external_id` | Specify an external ID for the STS API, can be used with the `role_arn` parameter if your role requires an external ID. | _none_ |
| `simple_aggregation` | Enable simple aggregation to combine multiple records into single API calls. This reduces the number of requests and can improve throughput. When enabled, multiple log records are concatenated with newlines and sent as a single record to Kinesis, up to the maximum record size limit (1,048,556 bytes). | `false` |

Check warning on line 30 in pipeline/outputs/kinesis.md

View workflow job for this annotation

GitHub Actions / runner / vale 

[vale] reported by reviewdog 🐶
[FluentBit.Simplicity] Avoid words like "simple" that imply ease of use, because the user may find this action difficult.

Raw Output:
{"message": "[FluentBit.Simplicity] Avoid words like \"simple\" that imply ease of use, because the user may find this action difficult.", "location": {"path": "pipeline/outputs/kinesis.md", "range": {"start": {"line": 30, "column": 33}}}, "severity": "WARNING"}
Copy link
Contributor

@coderabbitai coderabbitai bot Dec 12, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟠 Major

🧩 Analysis chain

🌐 Web query:

AWS Kinesis Data Streams maximum record size limit bytes PutRecords

💡 Result:

Maximum per-record size for PutRecords: 10 MiB (10,485,760 bytes). [1][2]

Sources:
[1] AWS Kinesis Data Streams quotas and limits.
[2] PutRecords API reference (each record can be as large as 10 MiB; whole request limit 10 MiB).

🌐 Web query:

Fluent Bit out_kinesis_streams simple_aggregation maximum record size 1048556 bytes

💡 Result:

Fluent Bit's Firehose/Kinesis output aggregation limit is 1 MiB (1,048,576 bytes) — the plugin's simple_aggregation will join records only while the aggregate doesn't exceed that 1 MiB maximum. [1][2]

If you see 1,048,556 bytes (1048556) that's almost certainly a typo/off-by-20 error; the documented limit is 1,048,576 bytes (1 MiB). [1][2]

Sources:

  • amazon-kinesis-firehose-for-fluent-bit plugin docs. [1]
  • AWS Kinesis Data Streams limits (data payload up to 10 MiB; per-record/aggregation guidance). [2]

Correct the Kinesis max record size to 1,048,576 bytes (1 MiB), not 1,048,556.
The value 1,048,556 appears to be a typo. AWS Kinesis Data Streams supports up to 10 MiB per record; Fluent Bit's simple_aggregation enforces a 1 MiB (1,048,576 bytes) limit for aggregated payloads. Also note that when simple_aggregation concatenates records with newlines, downstream consumers must split and parse them individually.

🤖 Prompt for AI Agents 
In pipeline/outputs/kinesis.md around line 30, the documented maximum record
size is incorrect (1,048,556 bytes); update the value to 1,048,576 bytes (1 MiB)
to match Fluent Bit's simple_aggregation enforced limit, and keep the note that
concatenated records are newline-delimited so downstream consumers must split
and parse each record individually.

| `profile` | AWS profile name to use. | `default` |
| `workers` | The number of [workers](../../administration/multithreading.md#outputs) to perform flush operations for this output. | `1` |

Expand Down