/usr/share/gocode/src/github.com/influxdata/influxdb/services/continuous_querier/service.go is in golang-github-influxdb-influxdb-dev 1.1.1+dfsg1-4.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | package continuous_querier // import "github.com/influxdata/influxdb/services/continuous_querier"
import (
"errors"
"fmt"
"io"
"log"
"os"
"strings"
"sync"
"sync/atomic"
"time"
"github.com/influxdata/influxdb/influxql"
"github.com/influxdata/influxdb/models"
"github.com/influxdata/influxdb/services/meta"
)
const (
// NoChunkingSize specifies when not to chunk results. When planning
// a select statement, passing zero tells it not to chunk results.
// Only applies to raw queries.
NoChunkingSize = 0
// idDelimiter is used as a delimiter when creating a unique name for a
// Continuous Query.
idDelimiter = string(rune(31)) // unit separator
)
// Statistics for the CQ service.
const (
statQueryOK = "queryOk"
statQueryFail = "queryFail"
)
// ContinuousQuerier represents a service that executes continuous queries.
type ContinuousQuerier interface {
// Run executes the named query in the named database. Blank database or name matches all.
Run(database, name string, t time.Time) error
}
// metaClient is an internal interface to make testing easier.
type metaClient interface {
AcquireLease(name string) (l *meta.Lease, err error)
Databases() []meta.DatabaseInfo
Database(name string) *meta.DatabaseInfo
}
// RunRequest is a request to run one or more CQs.
type RunRequest struct {
// Now tells the CQ serivce what the current time is.
Now time.Time
// CQs tells the CQ service which queries to run.
// If nil, all queries will be run.
CQs []string
}
// matches returns true if the CQ matches one of the requested CQs.
func (rr *RunRequest) matches(cq *meta.ContinuousQueryInfo) bool {
if rr.CQs == nil {
return true
}
for _, q := range rr.CQs {
if q == cq.Name {
return true
}
}
return false
}
// Service manages continuous query execution.
type Service struct {
MetaClient metaClient
QueryExecutor *influxql.QueryExecutor
Config *Config
RunInterval time.Duration
// RunCh can be used by clients to signal service to run CQs.
RunCh chan *RunRequest
Logger *log.Logger
loggingEnabled bool
stats *Statistics
// lastRuns maps CQ name to last time it was run.
mu sync.RWMutex
lastRuns map[string]time.Time
stop chan struct{}
wg *sync.WaitGroup
}
// NewService returns a new instance of Service.
func NewService(c Config) *Service {
s := &Service{
Config: &c,
RunInterval: time.Duration(c.RunInterval),
RunCh: make(chan *RunRequest),
loggingEnabled: c.LogEnabled,
Logger: log.New(os.Stderr, "[continuous_querier] ", log.LstdFlags),
stats: &Statistics{},
lastRuns: map[string]time.Time{},
}
return s
}
// Open starts the service.
func (s *Service) Open() error {
s.Logger.Println("Starting continuous query service")
if s.stop != nil {
return nil
}
assert(s.MetaClient != nil, "MetaClient is nil")
assert(s.QueryExecutor != nil, "QueryExecutor is nil")
s.stop = make(chan struct{})
s.wg = &sync.WaitGroup{}
s.wg.Add(1)
go s.backgroundLoop()
return nil
}
// Close stops the service.
func (s *Service) Close() error {
if s.stop == nil {
return nil
}
close(s.stop)
s.wg.Wait()
s.wg = nil
s.stop = nil
return nil
}
// SetLogOutput sets the writer to which all logs are written. It must not be
// called after Open is called.
func (s *Service) SetLogOutput(w io.Writer) {
s.Logger = log.New(w, "[continuous_querier] ", log.LstdFlags)
}
// Statistics maintains the statistics for the continuous query service.
type Statistics struct {
QueryOK int64
QueryFail int64
}
// Statistics returns statistics for periodic monitoring.
func (s *Service) Statistics(tags map[string]string) []models.Statistic {
return []models.Statistic{{
Name: "cq",
Tags: tags,
Values: map[string]interface{}{
statQueryOK: atomic.LoadInt64(&s.stats.QueryOK),
statQueryFail: atomic.LoadInt64(&s.stats.QueryFail),
},
}}
}
// Run runs the specified continuous query, or all CQs if none is specified.
func (s *Service) Run(database, name string, t time.Time) error {
var dbs []meta.DatabaseInfo
if database != "" {
// Find the requested database.
db := s.MetaClient.Database(database)
if db == nil {
return influxql.ErrDatabaseNotFound(database)
}
dbs = append(dbs, *db)
} else {
// Get all databases.
dbs = s.MetaClient.Databases()
}
// Loop through databases.
s.mu.Lock()
defer s.mu.Unlock()
for _, db := range dbs {
// Loop through CQs in each DB executing the ones that match name.
for _, cq := range db.ContinuousQueries {
if name == "" || cq.Name == name {
// Remove the last run time for the CQ
id := fmt.Sprintf("%s%s%s", db.Name, idDelimiter, cq.Name)
if _, ok := s.lastRuns[id]; ok {
delete(s.lastRuns, id)
}
}
}
}
// Signal the background routine to run CQs.
s.RunCh <- &RunRequest{Now: t}
return nil
}
// backgroundLoop runs on a go routine and periodically executes CQs.
func (s *Service) backgroundLoop() {
leaseName := "continuous_querier"
defer s.wg.Done()
for {
select {
case <-s.stop:
s.Logger.Println("continuous query service terminating")
return
case req := <-s.RunCh:
if !s.hasContinuousQueries() {
continue
}
if _, err := s.MetaClient.AcquireLease(leaseName); err == nil {
s.Logger.Printf("running continuous queries by request for time: %v", req.Now)
s.runContinuousQueries(req)
}
case <-time.After(s.RunInterval):
if !s.hasContinuousQueries() {
continue
}
if _, err := s.MetaClient.AcquireLease(leaseName); err == nil {
s.runContinuousQueries(&RunRequest{Now: time.Now()})
}
}
}
}
// hasContinuousQueries returns true if any CQs exist.
func (s *Service) hasContinuousQueries() bool {
// Get list of all databases.
dbs := s.MetaClient.Databases()
// Loop through all databases executing CQs.
for _, db := range dbs {
if len(db.ContinuousQueries) > 0 {
return true
}
}
return false
}
// runContinuousQueries gets CQs from the meta store and runs them.
func (s *Service) runContinuousQueries(req *RunRequest) {
// Get list of all databases.
dbs := s.MetaClient.Databases()
// Loop through all databases executing CQs.
for _, db := range dbs {
// TODO: distribute across nodes
for _, cq := range db.ContinuousQueries {
if !req.matches(&cq) {
continue
}
if err := s.ExecuteContinuousQuery(&db, &cq, req.Now); err != nil {
s.Logger.Printf("error executing query: %s: err = %s", cq.Query, err)
atomic.AddInt64(&s.stats.QueryFail, 1)
} else {
atomic.AddInt64(&s.stats.QueryOK, 1)
}
}
}
}
// ExecuteContinuousQuery executes a single CQ.
func (s *Service) ExecuteContinuousQuery(dbi *meta.DatabaseInfo, cqi *meta.ContinuousQueryInfo, now time.Time) error {
// TODO: re-enable stats
//s.stats.Inc("continuousQueryExecuted")
// Local wrapper / helper.
cq, err := NewContinuousQuery(dbi.Name, cqi)
if err != nil {
return err
}
// Get the last time this CQ was run from the service's cache.
s.mu.Lock()
defer s.mu.Unlock()
id := fmt.Sprintf("%s%s%s", dbi.Name, idDelimiter, cqi.Name)
cq.LastRun, cq.HasRun = s.lastRuns[id]
// Set the retention policy to default if it wasn't specified in the query.
if cq.intoRP() == "" {
cq.setIntoRP(dbi.DefaultRetentionPolicy)
}
// See if this query needs to be run.
run, nextRun, err := cq.shouldRunContinuousQuery(now)
if err != nil {
return err
} else if !run {
return nil
}
// Get the group by interval.
interval, err := cq.q.GroupByInterval()
if err != nil {
return err
} else if interval == 0 {
return nil
}
// Get the group by offset.
offset, err := cq.q.GroupByOffset()
if err != nil {
return err
}
resampleEvery := interval
if cq.Resample.Every != 0 {
resampleEvery = cq.Resample.Every
}
// We're about to run the query so store the current time closest to the nearest interval.
// If all is going well, this time should be the same as nextRun.
cq.LastRun = now.Add(-offset).Truncate(resampleEvery).Add(offset)
s.lastRuns[id] = cq.LastRun
// Retrieve the oldest interval we should calculate based on the next time
// interval. We do this instead of using the current time just in case any
// time intervals were missed. The start time of the oldest interval is what
// we use as the start time.
resampleFor := interval
if cq.Resample.For != 0 {
resampleFor = cq.Resample.For
} else if interval < resampleEvery {
resampleFor = resampleEvery
}
// If the resample interval is greater than the interval of the query, use the
// query interval instead.
if interval < resampleEvery {
resampleEvery = interval
}
// Calculate and set the time range for the query.
startTime := nextRun.Add(interval - resampleFor - offset - 1).Truncate(interval).Add(offset)
endTime := now.Add(interval - resampleEvery - offset).Truncate(interval).Add(offset)
if !endTime.After(startTime) {
// Exit early since there is no time interval.
return nil
}
if err := cq.q.SetTimeRange(startTime, endTime); err != nil {
s.Logger.Printf("error setting time range: %s\n", err)
return err
}
var start time.Time
if s.loggingEnabled {
s.Logger.Printf("executing continuous query %s (%v to %v)", cq.Info.Name, startTime, endTime)
start = time.Now()
}
// Do the actual processing of the query & writing of results.
if err := s.runContinuousQueryAndWriteResult(cq); err != nil {
s.Logger.Printf("error: %s. running: %s\n", err, cq.q.String())
return err
}
if s.loggingEnabled {
s.Logger.Printf("finished continuous query %s (%v to %v) in %s", cq.Info.Name, startTime, endTime, time.Now().Sub(start))
}
return nil
}
// runContinuousQueryAndWriteResult will run the query against the cluster and write the results back in
func (s *Service) runContinuousQueryAndWriteResult(cq *ContinuousQuery) error {
// Wrap the CQ's inner SELECT statement in a Query for the QueryExecutor.
q := &influxql.Query{
Statements: influxql.Statements([]influxql.Statement{cq.q}),
}
closing := make(chan struct{})
defer close(closing)
// Execute the SELECT.
ch := s.QueryExecutor.ExecuteQuery(q, influxql.ExecutionOptions{
Database: cq.Database,
}, closing)
// There is only one statement, so we will only ever receive one result
res, ok := <-ch
if !ok {
panic("result channel was closed")
}
if res.Err != nil {
return res.Err
}
return nil
}
// ContinuousQuery is a local wrapper / helper around continuous queries.
type ContinuousQuery struct {
Database string
Info *meta.ContinuousQueryInfo
HasRun bool
LastRun time.Time
Resample ResampleOptions
q *influxql.SelectStatement
}
func (cq *ContinuousQuery) intoRP() string { return cq.q.Target.Measurement.RetentionPolicy }
func (cq *ContinuousQuery) setIntoRP(rp string) { cq.q.Target.Measurement.RetentionPolicy = rp }
// Customizes the resampling intervals and duration of this continuous query.
type ResampleOptions struct {
// The query will be resampled at this time interval. The first query will be
// performed at this time interval. If this option is not given, the resample
// interval is set to the group by interval.
Every time.Duration
// The query will continue being resampled for this time duration. If this
// option is not given, the resample duration is the same as the group by
// interval. A bucket's time is calculated based on the bucket's start time,
// so a 40m resample duration with a group by interval of 10m will resample
// the bucket 4 times (using the default time interval).
For time.Duration
}
// NewContinuousQuery returns a ContinuousQuery object with a parsed influxql.CreateContinuousQueryStatement
func NewContinuousQuery(database string, cqi *meta.ContinuousQueryInfo) (*ContinuousQuery, error) {
stmt, err := influxql.NewParser(strings.NewReader(cqi.Query)).ParseStatement()
if err != nil {
return nil, err
}
q, ok := stmt.(*influxql.CreateContinuousQueryStatement)
if !ok || q.Source.Target == nil || q.Source.Target.Measurement == nil {
return nil, errors.New("query isn't a valid continuous query")
}
cquery := &ContinuousQuery{
Database: database,
Info: cqi,
Resample: ResampleOptions{
Every: q.ResampleEvery,
For: q.ResampleFor,
},
q: q.Source,
}
return cquery, nil
}
// shouldRunContinuousQuery returns true if the CQ should be schedule to run. It will use the
// lastRunTime of the CQ and the rules for when to run set through the query to determine
// if this CQ should be run
func (cq *ContinuousQuery) shouldRunContinuousQuery(now time.Time) (bool, time.Time, error) {
// if it's not aggregated we don't run it
if cq.q.IsRawQuery {
return false, cq.LastRun, errors.New("continuous queries must be aggregate queries")
}
// since it's aggregated we need to figure how often it should be run
interval, err := cq.q.GroupByInterval()
if err != nil {
return false, cq.LastRun, err
}
// allow the interval to be overwritten by the query's resample options
resampleEvery := interval
if cq.Resample.Every != 0 {
resampleEvery = cq.Resample.Every
}
// if we've passed the amount of time since the last run, or there was no last run, do it up
if cq.HasRun {
nextRun := cq.LastRun.Add(resampleEvery)
if nextRun.UnixNano() <= now.UnixNano() {
return true, nextRun, nil
}
} else {
return true, now, nil
}
return false, cq.LastRun, nil
}
// assert will panic with a given formatted message if the given condition is false.
func assert(condition bool, msg string, v ...interface{}) {
if !condition {
panic(fmt.Sprintf("assert failed: "+msg, v...))
}
}
|