|
5 | 5 | ], |
6 | 6 | "dashboard": { |
7 | 7 | "title": "AWS/Firehose", |
8 | | - "description": "Monitor Firehose delivery stream ingestion, S3 delivery throughput, data freshness, and delivery success.", |
| 8 | + "description": "Monitor Firehose delivery streams: ingestion, S3 and HTTP endpoint delivery, PutRecord API latency and requests, throttling and rate limits, and KMS/validation errors.", |
9 | 9 | "visuals": [ |
10 | 10 | { |
11 | 11 | "type": "timeseries", |
|
40 | 40 | } |
41 | 41 | ] |
42 | 42 | }, |
| 43 | + { |
| 44 | + "type": "timeseries", |
| 45 | + "display": "line", |
| 46 | + "format": "number", |
| 47 | + "draw_null_as_zero": true, |
| 48 | + "title": "Incoming Put Requests vs Incoming Records", |
| 49 | + "description": "Successful PutRecord and PutRecordBatch requests versus records ingested. A high records-to-requests ratio indicates effective batching.", |
| 50 | + "line_label": "%name% %DeliveryStreamName%", |
| 51 | + "metrics": [ |
| 52 | + { |
| 53 | + "name": "aws_firehose_incoming_put_requests", |
| 54 | + "fields": [{ "field": "GAUGE" }], |
| 55 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 56 | + }, |
| 57 | + { |
| 58 | + "name": "aws_firehose_incoming_records", |
| 59 | + "fields": [{ "field": "GAUGE" }], |
| 60 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 61 | + } |
| 62 | + ] |
| 63 | + }, |
43 | 64 | { |
44 | 65 | "type": "timeseries", |
45 | 66 | "display": "line", |
|
104 | 125 | "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
105 | 126 | } |
106 | 127 | ] |
| 128 | + }, |
| 129 | + { |
| 130 | + "type": "timeseries", |
| 131 | + "display": "line", |
| 132 | + "format": "size", |
| 133 | + "format_input": "byte", |
| 134 | + "draw_null_as_zero": true, |
| 135 | + "title": "Delivery to HTTP Endpoint - Bytes vs Processed Bytes", |
| 136 | + "description": "Bytes delivered successfully to the HTTP endpoint versus the bytes attempted, including retries.", |
| 137 | + "line_label": "%name% %DeliveryStreamName%", |
| 138 | + "metrics": [ |
| 139 | + { |
| 140 | + "name": "aws_firehose_delivery_to_http_endpoint_bytes", |
| 141 | + "fields": [{ "field": "GAUGE" }], |
| 142 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 143 | + }, |
| 144 | + { |
| 145 | + "name": "aws_firehose_delivery_to_http_endpoint_processed_bytes", |
| 146 | + "fields": [{ "field": "GAUGE" }], |
| 147 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 148 | + } |
| 149 | + ] |
| 150 | + }, |
| 151 | + { |
| 152 | + "type": "timeseries", |
| 153 | + "display": "line", |
| 154 | + "format": "number", |
| 155 | + "draw_null_as_zero": true, |
| 156 | + "title": "Delivery to HTTP Endpoint - Records vs Processed Records", |
| 157 | + "description": "Records delivered successfully to the HTTP endpoint versus the records attempted, including retries.", |
| 158 | + "line_label": "%name% %DeliveryStreamName%", |
| 159 | + "metrics": [ |
| 160 | + { |
| 161 | + "name": "aws_firehose_delivery_to_http_endpoint_records", |
| 162 | + "fields": [{ "field": "GAUGE" }], |
| 163 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 164 | + }, |
| 165 | + { |
| 166 | + "name": "aws_firehose_delivery_to_http_endpoint_processed_records", |
| 167 | + "fields": [{ "field": "GAUGE" }], |
| 168 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 169 | + } |
| 170 | + ] |
| 171 | + }, |
| 172 | + { |
| 173 | + "type": "timeseries", |
| 174 | + "display": "line", |
| 175 | + "format": "number", |
| 176 | + "draw_null_as_zero": false, |
| 177 | + "title": "Delivery to HTTP Endpoint - Success", |
| 178 | + "description": "Number of successful deliveries to the HTTP endpoint.", |
| 179 | + "line_label": "%name% %DeliveryStreamName%", |
| 180 | + "metrics": [ |
| 181 | + { |
| 182 | + "name": "aws_firehose_delivery_to_http_endpoint_success", |
| 183 | + "fields": [{ "field": "GAUGE" }], |
| 184 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 185 | + } |
| 186 | + ] |
| 187 | + }, |
| 188 | + { |
| 189 | + "type": "timeseries", |
| 190 | + "display": "line", |
| 191 | + "format": "duration", |
| 192 | + "draw_null_as_zero": false, |
| 193 | + "title": "Delivery to HTTP Endpoint - Data Freshness", |
| 194 | + "description": "Age of the oldest record awaiting delivery to the HTTP endpoint. Higher values indicate delivery delays.", |
| 195 | + "line_label": "%name% %DeliveryStreamName%", |
| 196 | + "metrics": [ |
| 197 | + { |
| 198 | + "name": "aws_firehose_delivery_to_http_endpoint_data_freshness", |
| 199 | + "fields": [{ "field": "GAUGE" }], |
| 200 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 201 | + } |
| 202 | + ] |
| 203 | + }, |
| 204 | + { |
| 205 | + "type": "timeseries", |
| 206 | + "display": "line", |
| 207 | + "format": "number", |
| 208 | + "draw_null_as_zero": true, |
| 209 | + "title": "PutRecord vs PutRecordBatch Requests", |
| 210 | + "description": "Number of PutRecord and PutRecordBatch requests.", |
| 211 | + "line_label": "%name% %DeliveryStreamName%", |
| 212 | + "metrics": [ |
| 213 | + { |
| 214 | + "name": "aws_firehose_put_record_requests", |
| 215 | + "fields": [{ "field": "GAUGE" }], |
| 216 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 217 | + }, |
| 218 | + { |
| 219 | + "name": "aws_firehose_put_record_batch_requests", |
| 220 | + "fields": [{ "field": "GAUGE" }], |
| 221 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 222 | + } |
| 223 | + ] |
| 224 | + }, |
| 225 | + { |
| 226 | + "type": "timeseries", |
| 227 | + "display": "line", |
| 228 | + "format": "duration", |
| 229 | + "draw_null_as_zero": false, |
| 230 | + "title": "PutRecord vs PutRecordBatch Latency", |
| 231 | + "description": "Latency of PutRecord and PutRecordBatch operations.", |
| 232 | + "line_label": "%name% %DeliveryStreamName%", |
| 233 | + "metrics": [ |
| 234 | + { |
| 235 | + "name": "aws_firehose_put_record_latency", |
| 236 | + "fields": [{ "field": "GAUGE" }], |
| 237 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 238 | + }, |
| 239 | + { |
| 240 | + "name": "aws_firehose_put_record_batch_latency", |
| 241 | + "fields": [{ "field": "GAUGE" }], |
| 242 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 243 | + } |
| 244 | + ] |
| 245 | + }, |
| 246 | + { |
| 247 | + "type": "timeseries", |
| 248 | + "display": "line", |
| 249 | + "format": "number", |
| 250 | + "draw_null_as_zero": true, |
| 251 | + "title": "Throttled Records", |
| 252 | + "description": "Records throttled because data ingestion exceeded a Firehose stream limit.", |
| 253 | + "line_label": "%name% %DeliveryStreamName%", |
| 254 | + "metrics": [ |
| 255 | + { |
| 256 | + "name": "aws_firehose_throttled_records", |
| 257 | + "fields": [{ "field": "GAUGE" }], |
| 258 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 259 | + } |
| 260 | + ] |
| 261 | + }, |
| 262 | + { |
| 263 | + "type": "timeseries", |
| 264 | + "display": "line", |
| 265 | + "format": "size", |
| 266 | + "format_input": "byte", |
| 267 | + "draw_null_as_zero": false, |
| 268 | + "title": "Bytes Per Second Limit", |
| 269 | + "description": "Current maximum bytes per second the Firehose stream can ingest before throttling.", |
| 270 | + "line_label": "%name% %DeliveryStreamName%", |
| 271 | + "metrics": [ |
| 272 | + { |
| 273 | + "name": "aws_firehose_bytes_per_second_limit", |
| 274 | + "fields": [{ "field": "GAUGE" }], |
| 275 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 276 | + } |
| 277 | + ] |
| 278 | + }, |
| 279 | + { |
| 280 | + "type": "timeseries", |
| 281 | + "display": "line", |
| 282 | + "format": "number", |
| 283 | + "draw_null_as_zero": false, |
| 284 | + "title": "Records Per Second Limit", |
| 285 | + "description": "Current maximum records per second the Firehose stream can ingest before throttling.", |
| 286 | + "line_label": "%name% %DeliveryStreamName%", |
| 287 | + "metrics": [ |
| 288 | + { |
| 289 | + "name": "aws_firehose_records_per_second_limit", |
| 290 | + "fields": [{ "field": "GAUGE" }], |
| 291 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 292 | + } |
| 293 | + ] |
| 294 | + }, |
| 295 | + { |
| 296 | + "type": "timeseries", |
| 297 | + "display": "line", |
| 298 | + "format": "number", |
| 299 | + "draw_null_as_zero": false, |
| 300 | + "title": "Put Requests Per Second Limit", |
| 301 | + "description": "Current maximum put requests per second the Firehose stream can ingest before throttling.", |
| 302 | + "line_label": "%name% %DeliveryStreamName%", |
| 303 | + "metrics": [ |
| 304 | + { |
| 305 | + "name": "aws_firehose_put_requests_per_second_limit", |
| 306 | + "fields": [{ "field": "GAUGE" }], |
| 307 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 308 | + } |
| 309 | + ] |
| 310 | + }, |
| 311 | + { |
| 312 | + "type": "timeseries", |
| 313 | + "display": "line", |
| 314 | + "format": "number", |
| 315 | + "draw_null_as_zero": true, |
| 316 | + "title": "KMS Key Errors", |
| 317 | + "description": "Occurrences of KMSAccessDenied, KMSDisabled, KMSInvalidState, and KMSNotFound exceptions for the Firehose stream.", |
| 318 | + "line_label": "%name% %DeliveryStreamName%", |
| 319 | + "metrics": [ |
| 320 | + { |
| 321 | + "name": "aws_firehose_kms_key_access_denied", |
| 322 | + "fields": [{ "field": "GAUGE" }], |
| 323 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 324 | + }, |
| 325 | + { |
| 326 | + "name": "aws_firehose_kms_key_disabled", |
| 327 | + "fields": [{ "field": "GAUGE" }], |
| 328 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 329 | + }, |
| 330 | + { |
| 331 | + "name": "aws_firehose_kms_key_invalid_state", |
| 332 | + "fields": [{ "field": "GAUGE" }], |
| 333 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 334 | + }, |
| 335 | + { |
| 336 | + "name": "aws_firehose_kms_key_not_found", |
| 337 | + "fields": [{ "field": "GAUGE" }], |
| 338 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 339 | + } |
| 340 | + ] |
| 341 | + }, |
| 342 | + { |
| 343 | + "type": "timeseries", |
| 344 | + "display": "line", |
| 345 | + "format": "number", |
| 346 | + "draw_null_as_zero": true, |
| 347 | + "title": "Failed Validation - Records", |
| 348 | + "description": "Number of records that failed record validation.", |
| 349 | + "line_label": "%name% %DeliveryStreamName%", |
| 350 | + "metrics": [ |
| 351 | + { |
| 352 | + "name": "aws_firehose_failed_validation_records", |
| 353 | + "fields": [{ "field": "GAUGE" }], |
| 354 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 355 | + } |
| 356 | + ] |
| 357 | + }, |
| 358 | + { |
| 359 | + "type": "timeseries", |
| 360 | + "display": "line", |
| 361 | + "format": "size", |
| 362 | + "format_input": "byte", |
| 363 | + "draw_null_as_zero": true, |
| 364 | + "title": "Failed Validation - Bytes", |
| 365 | + "description": "Number of bytes that failed record validation.", |
| 366 | + "line_label": "%name% %DeliveryStreamName%", |
| 367 | + "metrics": [ |
| 368 | + { |
| 369 | + "name": "aws_firehose_failed_validation_bytes", |
| 370 | + "fields": [{ "field": "GAUGE" }], |
| 371 | + "tags": [{ "key": "DeliveryStreamName", "value": "*" }] |
| 372 | + } |
| 373 | + ] |
107 | 374 | } |
108 | 375 | ] |
109 | 376 | } |
|
0 commit comments