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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498
#[cfg(feature = "bigtable")]
use bigtable_rs::{
bigtable::{BigTable, Error},
google::bigtable::v2::{
mutate_rows_request::Entry, MutateRowsRequest, Mutation, ReadRowsRequest, RowSet,
},
};
#[cfg(feature = "bigtable")]
use std::collections::HashMap;
#[cfg(feature = "bigtable")]
use std::time::Duration;
use tokio::task::JoinHandle;
#[cfg(feature = "bigtable")]
use tonic::Code;
#[cfg(feature = "bigtable")]
use tracing::{error, info, warn};
#[cfg(feature = "bigtable")]
use crate::utils::backoff::obtain_next_interval;
#[cfg(feature = "bigtable")]
fn process_bt_status(
status: tonic::Status,
retry_limit: &usize,
mut retry_count: usize,
task_table_name: &str,
) -> usize {
match status.code() {
// Do nothing.
Code::NotFound | Code::Ok | Code::OutOfRange => {}
Code::ResourceExhausted => {
warn!("BigTable resources are currently exhausted. Let's wait");
}
Code::Unknown => {
error!(
"There was an issue ingesting {} data to BigTable. {:?}",
task_table_name, status
);
retry_count += 1;
}
Code::Cancelled => {
warn!("BigTable request cancelled on our side. Trying again");
}
Code::InvalidArgument => {
error!(
"Invalid Argument for ingestion {} data to BigTable. {:?}",
task_table_name, status
);
retry_count = retry_limit.clone();
}
Code::DeadlineExceeded => {
warn!(
"BigTable DeadlineExceeded. Let's wait; Data ingestion \
might be too overwhelming at the moment."
);
}
Code::AlreadyExists => {
error!(
"Row/s already exists for {} data. {:?}",
task_table_name, status
);
retry_count = retry_limit.clone();
}
Code::PermissionDenied => {
error!(
"Invalid Permissions for ingesting {} data to \
BigTable. {:?}",
task_table_name, status
);
retry_count = retry_limit.clone();
}
Code::FailedPrecondition => {
warn!("BigTable failed precondition. Let's wait and try again.");
}
Code::Aborted => {
warn!("BigTable request aborted. Let's wait and try again.");
}
Code::Unimplemented => {
error!(
"Unimplemented API.. | table: {} | reason: {:?}",
task_table_name, status
);
retry_count = retry_limit.clone();
}
Code::Internal => {
error!(
"BigTable internal error. Report!! | table: {} | \
reason: {:?}",
task_table_name, status
);
retry_count = retry_limit.clone();
}
Code::Unavailable => {
warn!("BigTable resources are currently unavailable. Let's wait");
}
Code::DataLoss => {
error!(
"BigTable DataLoss while ingesting {} data to \
BigTable. {:?}",
task_table_name, status
);
retry_count = retry_limit.clone();
}
Code::Unauthenticated => {
error!(
"Invalid Authentication for ingesting {} data to \
BigTable. {:?}",
task_table_name, status
);
retry_count = retry_limit.clone();
}
}
if retry_count.eq(retry_limit) {
error!("Ditching this job.");
}
retry_count
}
#[cfg(feature = "bigtable")]
pub async fn ingest_entries(
bt_client: &mut BigTable,
table_name: String,
table_prefix: String,
mutations_per_entry: usize,
entries: Vec<Entry>,
retry_limit: &usize,
retry_interval: &Duration,
) {
let mut bt_tasks: Vec<_> = Vec::new();
// Chunk by 100k mutations, via mutations_per_entry
let chunks = entries.chunks(100000 / mutations_per_entry);
let chunk_count = chunks.len();
for (idx, chunk) in chunks.enumerate() {
let mut chunk_rows = chunk.to_owned();
let mut client = bt_client.clone();
let mut retry_count = 0;
let task_table_name = table_name.clone();
let task_table_prefix = table_prefix.clone();
let task_retry_limit = retry_limit.clone();
let task_retry_interval = retry_interval.clone();
let task_chunk_count = chunk_count.clone();
info!("Writing to BT");
info!("{:?}", task_table_name);
bt_tasks.push(tokio::spawn(async move {
loop {
let push_result = client
.mutate_rows(MutateRowsRequest {
table_name: client.get_full_table_name(&task_table_name),
entries: chunk_rows.clone(),
..MutateRowsRequest::default()
})
.await;
if let Err(err) = push_result {
// error!("There was an issue ingesting {} data to BigTable. {:?}", task_table_name, err);
// Check varying types of errors and only increment retry_count if bad.
match err {
Error::AccessTokenError(error) => {
error!(
"AccessTokenError for ingesting {} data to BigTable. {:?}",
task_table_name, error
);
retry_count = task_retry_limit;
}
Error::CertificateError(error) => {
error!(
"CertificateError for ingesting {} data to BigTable. {:?}",
task_table_name, error
);
retry_count = task_retry_limit;
}
Error::GCPAuthError(error) => {
error!(
"GCPAuthError for ingesting {} data to BigTable. {:?}",
task_table_name, error
);
retry_count = task_retry_limit;
}
Error::IoError(error) => {
error!(
"IoError for ingesting {} data to BigTable. {:?}",
task_table_name, error
);
retry_count += 1;
}
Error::TransportError(tonic_tpt_err) => {
error!(
"TransportError while ingesting {} data to BigTable. {:?}",
task_table_name, tonic_tpt_err
);
retry_count += 1;
}
Error::ChunkError(error) => {
error!(
"ChunkError for ingesting {} data to BigTable. {:?}",
task_table_name, error
);
retry_count = task_retry_limit;
}
Error::RowWriteFailed => {
error!(
"RowWriteFailed while ingesting {} data to BigTable. {:?}",
task_table_name, err
);
retry_count += 1;
}
Error::RpcError(tonic_status) => {
retry_count = process_bt_status(
tonic_status,
&task_retry_limit,
task_chunk_count,
task_table_prefix.as_str(),
);
}
Error::TimeoutError(seconds) => {
error!(
"BigTable ingestion timed out after {} seconds. Trying again | \
table: {} | reason: {:?}",
seconds, task_table_name, err
);
}
// Do nothing, read-based errors.
Error::ObjectCorrupt(_) | Error::ObjectNotFound(_) | Error::RowNotFound => {
}
}
if &retry_count >= &task_retry_limit {
error!("Retry limit exceeded. Abandoning ship.");
break;
}
// Sleep for the backoff interval
let interval =
obtain_next_interval(&retry_count, &task_retry_limit, &task_retry_interval);
tokio::time::sleep(interval.unwrap()).await;
} else {
// Push may not be successful, check if the GCP req is successful
if let Ok(mut gcp_result) = push_result {
// Since its successful, check if the Inner GCP msg is successful
match gcp_result.message().await {
Ok(msg) => {
// Ensure a message from GCP actually comes back
if let Some(gcp_res) = msg {
// Iterate every entry im pushing
// if one of the entries fail, we should add it to
// a new collection to re-ingest again.
let mut failed = false;
let mut new_rows = Vec::new();
let orig_size = gcp_res.entries.len();
for entry in gcp_res.entries {
match entry.status {
Some(code) => {
if code.code != 0 {
failed = true;
new_rows.push(
chunk_rows[entry.index as usize].clone(),
);
}
}
None => {} // ???
}
}
if failed {
chunk_rows = new_rows.to_owned();
warn!(
"{}/{} entries failed to ingest. Trying again",
chunk_rows.len(),
orig_size
);
} else {
match &task_table_prefix.is_empty() {
true => {
info!(
"{}/{} {} push complete!",
idx + 1,
&task_chunk_count,
&task_table_name
);
}
_ => {
info!(
"{}/{} {}/{} push complete!",
idx + 1,
&task_chunk_count,
&task_table_name,
&task_table_prefix
);
}
}
break;
}
} else {
error!("Empty message from GCP! Trying again...");
}
}
Err(tonic_status) => {
retry_count = process_bt_status(
tonic_status,
&task_retry_limit,
task_chunk_count,
task_table_prefix.as_str(),
);
if &retry_count >= &task_retry_limit {
error!("Retry limit exceeded. Abandoning ship.");
break;
}
}
}
} else {
error!("GCP Dispatch failed! Trying again...");
}
}
}
}));
}
for task in bt_tasks {
task.await.unwrap();
}
}
#[cfg(feature = "bigtable")]
pub async fn check_entries(
bt_client: &mut BigTable,
table_name: String,
table_prefix: String,
mutations_per_entry: usize,
entries: Vec<Entry>,
retry_limit: &usize,
retry_interval: &Duration,
) -> Vec<Entry> {
let mut bt_tasks: Vec<JoinHandle<Vec<Entry>>> = Vec::new();
let mut entries_to_push = vec![];
// Chunk by 100k mutations, via mutations_per_entry
let chunks = entries.chunks(100000 / mutations_per_entry);
let chunk_count = chunks.len();
for (_idx, chunk) in chunks.enumerate() {
let chunk_rows = chunk.to_owned();
let mut entry_map: HashMap<Vec<u8>, Vec<Mutation>> = HashMap::new();
for entry in chunk_rows {
entry_map.insert(entry.row_key, entry.mutations);
}
let mut client = bt_client.clone();
let mut retry_count = 0;
let task_table_name = table_name.clone();
let task_table_prefix = table_prefix.clone();
let task_retry_limit = retry_limit.clone();
let task_retry_interval = retry_interval.clone();
let task_chunk_count = chunk_count.clone();
info!("Reading from BT");
info!("{:?}", task_table_name);
bt_tasks.push(tokio::spawn(async move {
let mut cloned_entry_map = entry_map.clone();
let mut entry_input = vec![];
loop {
let read_result = client
.read_rows(ReadRowsRequest {
table_name: client.get_full_table_name(&task_table_name),
rows: Some(RowSet {
row_keys: cloned_entry_map.keys().map(|key| key.clone()).collect(),
row_ranges: vec![],
}),
..ReadRowsRequest::default()
})
.await;
if let Err(err) = read_result {
// Check varying types of errors and only increment retry_count if bad.
match err {
Error::AccessTokenError(error) => {
error!(
"AccessTokenError for ingesting {} data to BigTable. {:?}",
task_table_name, error
);
retry_count = task_retry_limit;
}
Error::CertificateError(error) => {
error!(
"CertificateError for ingesting {} data to BigTable. {:?}",
task_table_name, error
);
retry_count = task_retry_limit;
}
Error::GCPAuthError(error) => {
error!(
"GCPAuthError for ingesting {} data to BigTable. {:?}",
task_table_name, error
);
retry_count = task_retry_limit;
}
Error::IoError(error) => {
error!(
"IoError for ingesting {} data to BigTable. {:?}",
task_table_name, error
);
retry_count += 1;
}
Error::TransportError(tonic_tpt_err) => {
error!(
"TransportError while ingesting {} data to BigTable. {:?}",
task_table_name, tonic_tpt_err
);
retry_count += 1;
}
Error::ChunkError(error) => {
error!(
"ChunkError for ingesting {} data to BigTable. {:?}",
task_table_name, error
);
retry_count = task_retry_limit;
}
Error::RowWriteFailed => {
error!(
"RowWriteFailed while ingesting {} data to BigTable. {:?}",
task_table_name, err
);
retry_count += 1;
}
Error::RpcError(tonic_status) => {
retry_count = process_bt_status(
tonic_status,
&task_retry_limit,
task_chunk_count,
task_table_prefix.as_str(),
);
}
Error::TimeoutError(seconds) => {
error!(
"BigTable ingestion timed out after {} seconds. Trying again | \
table: {} | reason: {:?}",
seconds, task_table_name, err
);
}
// Do nothing, read-based errors.
Error::ObjectCorrupt(_) | Error::ObjectNotFound(_) | Error::RowNotFound => {
}
}
if &retry_count >= &task_retry_limit {
error!("Retry limit exceeded. Abandoning ship.");
break;
}
// Sleep for the backoff interval
let interval =
obtain_next_interval(&retry_count, &task_retry_limit, &task_retry_interval);
tokio::time::sleep(interval.unwrap()).await;
} else {
if let Ok(gcp_result) = read_result {
// We want to remove all the entries that have been found in BT
for (key, _cell_val) in gcp_result {
// let idx = rowkeys_to_check
cloned_entry_map.remove(&key);
}
}
// cloned_entry_map.clone().values().map()
entry_input = cloned_entry_map
.clone()
.iter()
.map(|(key, val)| Entry {
row_key: key.to_owned(),
mutations: val.to_owned(),
})
.collect();
}
}
entry_input
}));
}
// We want to append all the entries that are not in BT and try to add them in
for task in bt_tasks {
let ret = task.await;
match ret {
Ok(mut entries) => entries_to_push.append(&mut entries),
Err(_) => error!("There was an error retrieving entries"),
}
}
info!("There are {} transactions missing!", &entries_to_push.len());
entries_to_push
}