mirror of
https://github.com/prometheus/prometheus.git
synced 2024-12-27 06:29:42 -08:00
d1122e0743
* Append metadata to the WAL Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Remove extra whitespace; Reword some docstrings and comments Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Use RLock() for hasNewMetadata check Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Use single byte for metric type in RefMetadata Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Update proposed WAL format for single-byte type metadata Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Implementa MetadataAppender interface for the Agent Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Address first round of review comments Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Amend description of metadata in wal.md Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Correct key used to retrieve metadata from cache When we're setting metadata entries in the scrapeCace, we're using the p.Help(), p.Unit(), p.Type() helpers, which retrieve the series name and use it as the cache key. When checking for cache entries though, we used p.Series() as the key, which included the metric name _with_ its labels. That meant that we were never actually hitting the cache. We're fixing this by utiling the __name__ internal label for correctly getting the cache entries after they've been set by setHelp(), setType() or setUnit(). Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Put feature behind a feature flag Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Fix AppendMetadata docstring Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Reorder WAL format document Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Change error message of AppendMetadata; Fix access of s.meta in AppendMetadata Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Reuse temporary buffer in Metadata encoder Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Only keep latest metadata for each refID during checkpointing Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Fix test that's referencing decoding metadata Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Avoid creating metadata block if no new metadata are present Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Add tests for corrupt metadata block and relevant record type Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Fix CR comments Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Extract logic about changing metadata in an anonymous function Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Implement new proposed WAL format and amend relevant tests Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Use 'const' for metadata field names Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Apply metadata to head memSeries in Commit, not in AppendMetadata Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Add docstring and rename extracted helper in scrape.go Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Add tests for tsdb-related cases Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Fix linter issues vol1 Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Fix linter issues vol2 Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Fix Windows test by closing WAL reader files Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Use switch instead of two if statements in metadata decoding Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Fix review comments around TestMetadata* tests Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Add code for replaying WAL; test correctness of in-memory data after a replay Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Remove scrape-loop related code from PR Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Address first round of comments Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Simplify tests by sorting slices before comparison Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Fix test to use separate transactions Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Empty out buffer and record slices after encoding latest metadata Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Fix linting issue Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Update calculation for DroppedMetadata metric Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Rename MetadataAppender interface and AppendMetadata method to MetadataUpdater/UpdateMetadata Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Reuse buffer when encoding latest metadata for each series Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Fix review comments; Check all returned error values using two helpers Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Simplify use of helpers Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com> * Satisfy linter Signed-off-by: Paschalis Tsilias <paschalist0@gmail.com>
218 lines
6.1 KiB
Go
218 lines
6.1 KiB
Go
// Copyright 2017 The Prometheus Authors
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
|
|
package storage
|
|
|
|
import (
|
|
"context"
|
|
|
|
"github.com/go-kit/log"
|
|
"github.com/go-kit/log/level"
|
|
"github.com/prometheus/common/model"
|
|
|
|
"github.com/prometheus/prometheus/model/exemplar"
|
|
"github.com/prometheus/prometheus/model/labels"
|
|
"github.com/prometheus/prometheus/model/metadata"
|
|
tsdb_errors "github.com/prometheus/prometheus/tsdb/errors"
|
|
)
|
|
|
|
type fanout struct {
|
|
logger log.Logger
|
|
|
|
primary Storage
|
|
secondaries []Storage
|
|
}
|
|
|
|
// NewFanout returns a new fanout Storage, which proxies reads and writes
|
|
// through to multiple underlying storages.
|
|
//
|
|
// The difference between primary and secondary Storage is only for read (Querier) path and it goes as follows:
|
|
// * If the primary querier returns an error, then any of the Querier operations will fail.
|
|
// * If any secondary querier returns an error the result from that queries is discarded. The overall operation will succeed,
|
|
// and the error from the secondary querier will be returned as a warning.
|
|
//
|
|
// NOTE: In the case of Prometheus, it treats all remote storages as secondary / best effort.
|
|
func NewFanout(logger log.Logger, primary Storage, secondaries ...Storage) Storage {
|
|
return &fanout{
|
|
logger: logger,
|
|
primary: primary,
|
|
secondaries: secondaries,
|
|
}
|
|
}
|
|
|
|
// StartTime implements the Storage interface.
|
|
func (f *fanout) StartTime() (int64, error) {
|
|
// StartTime of a fanout should be the earliest StartTime of all its storages,
|
|
// both primary and secondaries.
|
|
firstTime, err := f.primary.StartTime()
|
|
if err != nil {
|
|
return int64(model.Latest), err
|
|
}
|
|
|
|
for _, s := range f.secondaries {
|
|
t, err := s.StartTime()
|
|
if err != nil {
|
|
return int64(model.Latest), err
|
|
}
|
|
if t < firstTime {
|
|
firstTime = t
|
|
}
|
|
}
|
|
return firstTime, nil
|
|
}
|
|
|
|
func (f *fanout) Querier(ctx context.Context, mint, maxt int64) (Querier, error) {
|
|
primary, err := f.primary.Querier(ctx, mint, maxt)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
secondaries := make([]Querier, 0, len(f.secondaries))
|
|
for _, storage := range f.secondaries {
|
|
querier, err := storage.Querier(ctx, mint, maxt)
|
|
if err != nil {
|
|
// Close already open Queriers, append potential errors to returned error.
|
|
errs := tsdb_errors.NewMulti(err, primary.Close())
|
|
for _, q := range secondaries {
|
|
errs.Add(q.Close())
|
|
}
|
|
return nil, errs.Err()
|
|
}
|
|
secondaries = append(secondaries, querier)
|
|
}
|
|
return NewMergeQuerier([]Querier{primary}, secondaries, ChainedSeriesMerge), nil
|
|
}
|
|
|
|
func (f *fanout) ChunkQuerier(ctx context.Context, mint, maxt int64) (ChunkQuerier, error) {
|
|
primary, err := f.primary.ChunkQuerier(ctx, mint, maxt)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
secondaries := make([]ChunkQuerier, 0, len(f.secondaries))
|
|
for _, storage := range f.secondaries {
|
|
querier, err := storage.ChunkQuerier(ctx, mint, maxt)
|
|
if err != nil {
|
|
// Close already open Queriers, append potential errors to returned error.
|
|
errs := tsdb_errors.NewMulti(err, primary.Close())
|
|
for _, q := range secondaries {
|
|
errs.Add(q.Close())
|
|
}
|
|
return nil, errs.Err()
|
|
}
|
|
secondaries = append(secondaries, querier)
|
|
}
|
|
return NewMergeChunkQuerier([]ChunkQuerier{primary}, secondaries, NewCompactingChunkSeriesMerger(ChainedSeriesMerge)), nil
|
|
}
|
|
|
|
func (f *fanout) Appender(ctx context.Context) Appender {
|
|
primary := f.primary.Appender(ctx)
|
|
secondaries := make([]Appender, 0, len(f.secondaries))
|
|
for _, storage := range f.secondaries {
|
|
secondaries = append(secondaries, storage.Appender(ctx))
|
|
}
|
|
return &fanoutAppender{
|
|
logger: f.logger,
|
|
primary: primary,
|
|
secondaries: secondaries,
|
|
}
|
|
}
|
|
|
|
// Close closes the storage and all its underlying resources.
|
|
func (f *fanout) Close() error {
|
|
errs := tsdb_errors.NewMulti(f.primary.Close())
|
|
for _, s := range f.secondaries {
|
|
errs.Add(s.Close())
|
|
}
|
|
return errs.Err()
|
|
}
|
|
|
|
// fanoutAppender implements Appender.
|
|
type fanoutAppender struct {
|
|
logger log.Logger
|
|
|
|
primary Appender
|
|
secondaries []Appender
|
|
}
|
|
|
|
func (f *fanoutAppender) Append(ref SeriesRef, l labels.Labels, t int64, v float64) (SeriesRef, error) {
|
|
ref, err := f.primary.Append(ref, l, t, v)
|
|
if err != nil {
|
|
return ref, err
|
|
}
|
|
|
|
for _, appender := range f.secondaries {
|
|
if _, err := appender.Append(ref, l, t, v); err != nil {
|
|
return 0, err
|
|
}
|
|
}
|
|
return ref, nil
|
|
}
|
|
|
|
func (f *fanoutAppender) AppendExemplar(ref SeriesRef, l labels.Labels, e exemplar.Exemplar) (SeriesRef, error) {
|
|
ref, err := f.primary.AppendExemplar(ref, l, e)
|
|
if err != nil {
|
|
return ref, err
|
|
}
|
|
|
|
for _, appender := range f.secondaries {
|
|
if _, err := appender.AppendExemplar(ref, l, e); err != nil {
|
|
return 0, err
|
|
}
|
|
}
|
|
return ref, nil
|
|
}
|
|
|
|
func (f *fanoutAppender) UpdateMetadata(ref SeriesRef, l labels.Labels, m metadata.Metadata) (SeriesRef, error) {
|
|
ref, err := f.primary.UpdateMetadata(ref, l, m)
|
|
if err != nil {
|
|
return ref, err
|
|
}
|
|
|
|
for _, appender := range f.secondaries {
|
|
if _, err := appender.UpdateMetadata(ref, l, m); err != nil {
|
|
return 0, err
|
|
}
|
|
}
|
|
return ref, nil
|
|
}
|
|
|
|
func (f *fanoutAppender) Commit() (err error) {
|
|
err = f.primary.Commit()
|
|
|
|
for _, appender := range f.secondaries {
|
|
if err == nil {
|
|
err = appender.Commit()
|
|
} else {
|
|
if rollbackErr := appender.Rollback(); rollbackErr != nil {
|
|
level.Error(f.logger).Log("msg", "Squashed rollback error on commit", "err", rollbackErr)
|
|
}
|
|
}
|
|
}
|
|
return
|
|
}
|
|
|
|
func (f *fanoutAppender) Rollback() (err error) {
|
|
err = f.primary.Rollback()
|
|
|
|
for _, appender := range f.secondaries {
|
|
rollbackErr := appender.Rollback()
|
|
if err == nil {
|
|
err = rollbackErr
|
|
} else if rollbackErr != nil {
|
|
level.Error(f.logger).Log("msg", "Squashed rollback error on rollback", "err", rollbackErr)
|
|
}
|
|
}
|
|
return nil
|
|
}
|