1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
# Generated by rivet init — MySQL database "rivet" (26 objects)
# Review and adjust before running: rivet check -c rivet.yaml
source:
type: mysql
url_env: DATABASE_URL # reads the variable you already exported
# One export per table/view — per-table prefix `exports/<name>/` under the given bucket; review
# modes before running.
exports:
- name: bench_decimal
wave: 3
parallel_safe: false
query: >
SELECT id, price, qty, discount, total, updated_at
FROM bench_decimal
# auto: ~183K rows ≥ 100K threshold and chunk column 'id' is available. NOTE: chunked re-reads
# the whole table each run — for scheduled re-runs, `mode: incremental` on 'updated_at' pulls
# only changed rows
mode: chunked
chunk_column: id
chunk_size: 100000
chunk_checkpoint: true # record per-chunk progress so `rivet run --resume` can finish a crashed
# run
format: parquet
parquet:
row_group_strategy: auto
target_row_group_mb: 128
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/bench_decimal/
columns:
price: decimal(18,4)
qty: decimal(10,2)
discount: decimal(5,4)
total: decimal(20,4)
- name: bench_hc
wave: 3
parallel_safe: false
query: >
SELECT id, uuid_col, email, session_id, updated_at
FROM bench_hc
# auto: ~190K rows ≥ 100K threshold and chunk column 'id' is available. NOTE: chunked re-reads
# the whole table each run — for scheduled re-runs, `mode: incremental` on 'updated_at' pulls
# only changed rows
mode: chunked
chunk_column: id
chunk_size: 100000
chunk_checkpoint: true # record per-chunk progress so `rivet run --resume` can finish a crashed
# run
format: parquet
parquet:
row_group_strategy: auto
target_row_group_mb: 128
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/bench_hc/
- name: bench_narrow
wave: 4
parallel_safe: false
query: >
SELECT id, user_id, amount, status, created_at
FROM bench_narrow
# auto: ~9.8M rows ≥ 100K threshold and chunk column 'id' is available. NOTE: chunked re-reads
# the whole table each run — for scheduled re-runs, `mode: incremental` on 'created_at' pulls
# only changed rows
mode: chunked
chunk_column: id
chunk_size: 250000
chunk_checkpoint: true # record per-chunk progress so `rivet run --resume` can finish a crashed
# run
# est. peak RSS ≈ 92 MB (4 workers × ~19 MB/worker @ ~51 B/row); lower `parallel` to spend less
# memory
parallel: 4
format: parquet
parquet:
row_group_strategy: auto
target_row_group_mb: 128
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/bench_narrow/
- name: bench_sparse
wave: 2
parallel_safe: true
query: >
SELECT id, val_a, val_b, val_c, val_d, val_e, updated_at
FROM bench_sparse
# auto: ~9K rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/bench_sparse/
- name: bench_wide
wave: 2
parallel_safe: true
query: >
SELECT id, col_a, col_b, col_c, col_d, col_e, col_f, col_g, col_h, col_i, col_j, updated_at
FROM bench_wide
# auto: ~82K rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/bench_wide/
- name: cdc_demo
wave: 2
parallel_safe: true
query: >
SELECT id, name, amount
FROM cdc_demo
# auto: ~2 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/cdc_demo/
- name: cdc_e2e
wave: 2
parallel_safe: true
query: >
SELECT id, name, amount
FROM cdc_e2e
# auto: ~0 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/cdc_e2e/
- name: cdc_f
wave: 2
parallel_safe: true
query: >
SELECT id, v
FROM cdc_f
# auto: ~0 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/cdc_f/
- name: cdc_m
wave: 2
parallel_safe: true
query: >
SELECT id, name
FROM cdc_m
# auto: ~2 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/cdc_m/
- name: cdc_reg
wave: 2
parallel_safe: true
query: >
SELECT id, amount
FROM cdc_reg
# auto: ~0 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/cdc_reg/
columns:
amount: decimal(10,2)
- name: cdc_resume
wave: 2
parallel_safe: true
query: >
SELECT id, v
FROM cdc_resume
# auto: ~2 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/cdc_resume/
- name: cdc_sec
wave: 2
parallel_safe: true
query: >
SELECT id
FROM cdc_sec
# auto: ~0 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/cdc_sec/
- name: cdc_tx
wave: 2
parallel_safe: true
query: >
SELECT id, v
FROM cdc_tx
# auto: ~2 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/cdc_tx/
- name: cdc_typed
wave: 2
parallel_safe: true
query: >
SELECT id, name, ts, amount
FROM cdc_typed
# auto: ~0 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/cdc_typed/
columns:
amount: decimal(10,2)
- name: cdc_unit
wave: 2
parallel_safe: true
query: >
SELECT id, v
FROM cdc_unit
# auto: ~0 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/cdc_unit/
- name: ck_dec_my
wave: 2
parallel_safe: true
query: >
SELECT id, amount, fee, neg
FROM ck_dec_my
# auto: ~4 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/ck_dec_my/
columns:
amount: decimal(18,2)
fee: decimal(20,6)
neg: decimal(10,2)
- name: content_items
wave: 3
parallel_safe: false
query: >
SELECT id, title, body, raw_html, metadata, tags, author_name, author_email, source_url, category, status, priority, view_count, comment_count, word_count, language, published_at, updated_at, created_at, extra_data
FROM content_items
# auto: ~1.3M rows ≥ 100K threshold and chunk column 'id' is available. NOTE: chunked re-reads
# the whole table each run — for scheduled re-runs, `mode: incremental` on 'updated_at' pulls
# only changed rows
mode: chunked
chunk_column: id
chunk_size: 250000
chunk_checkpoint: true # record per-chunk progress so `rivet run --resume` can finish a crashed
# run
# parallel: 1 (wide rows on MySQL: single scan is faster than chunks)
format: parquet
parquet:
row_group_strategy: auto
target_row_group_mb: 64
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/content_items/
- name: events
wave: 2
parallel_safe: true
query: >
SELECT id, user_id, event_type, payload, ip_address, created_at
FROM events
# auto: ~5K rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/events/
- name: orders
wave: 2
parallel_safe: true
query: >
SELECT id, user_id, product, quantity, price, status, notes, ordered_at, updated_at
FROM orders
# auto: ~2K rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/orders/
columns:
price: decimal(10,2)
- name: orders_coalesce
wave: 2
parallel_safe: true
query: >
SELECT id, product, quantity, price, updated_at, created_at
FROM orders_coalesce
# auto: ~0 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/orders_coalesce/
columns:
price: decimal(10,2)
- name: orders_sparse
wave: 2
parallel_safe: true
query: >
SELECT id, payload
FROM orders_sparse
# auto: ~0 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/orders_sparse/
- name: page_views
wave: 2
parallel_safe: true
query: >
SELECT id, session_id, user_id, url, referrer, user_agent, ip_address, country_code, region, city, device_type, browser, os, screen_width, screen_height, viewport_width, viewport_height, page_load_ms, dom_ready_ms, time_on_page_ms, scroll_depth_pct, click_count, is_bounce, utm_source, utm_medium, utm_campaign, utm_term, utm_content, custom_props, created_at
FROM page_views
# auto: ~60K rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/page_views/
- name: rivet_harm
wave: 2
parallel_safe: true
query: >
SELECT txn_ms, q_s, active, sessions
FROM rivet_harm
# auto: ~7K rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/rivet_harm/
- name: rivet_type_matrix
wave: 2
parallel_safe: true
query: >
SELECT id, label, amount, fee, created_at_dt, created_at_ts, raw_bytes, uid, extras
FROM rivet_type_matrix
# auto: ~4 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/rivet_type_matrix/
columns:
amount: decimal(18,2)
fee: decimal(18,6)
- name: rivet_type_matrix_full
wave: 2
parallel_safe: true
query: >
SELECT id, flag, bit1_col, bit8_col, tiny_col, date_col, time_col, year_col, enum_col, varbinary_col, blob_col
FROM rivet_type_matrix_full
# auto: ~3 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/rivet_type_matrix_full/
- name: users
wave: 2
parallel_safe: true
query: >
SELECT id, name, email, age, balance, is_active, bio, created_at, updated_at
FROM users
# auto: ~500 rows below 100K chunked threshold
mode: full
format: parquet
meta_columns: # adds 2 columns to the output (drop this block to omit them)
exported_at: true # _rivet_exported_at: when the row was exported
row_hash: true # _rivet_row_hash: per-row hash for change detection
destination:
type: gcs
bucket: rivet_data_test
prefix: exports/users/
columns:
balance: decimal(12,2)