mirror of
https://github.com/prometheus/prometheus.git
synced 2024-12-29 07:29:42 -08:00
740d448983
So far we've been using Go's native time.Time for anything related to sample timestamps. Since the range of time.Time is much bigger than what we need, this has created two problems: - there could be time.Time values which were out of the range/precision of the time type that we persist to disk, therefore causing incorrectly ordered keys. One bug caused by this was: https://github.com/prometheus/prometheus/issues/367 It would be good to use a timestamp type that's more closely aligned with what the underlying storage supports. - sizeof(time.Time) is 192, while Prometheus should be ok with a single 64-bit Unix timestamp (possibly even a 32-bit one). Since we store samples in large numbers, this seriously affects memory usage. Furthermore, copying/working with the data will be faster if it's smaller. *MEMORY USAGE RESULTS* Initial memory usage comparisons for a running Prometheus with 1 timeseries and 100,000 samples show roughly a 13% decrease in total (VIRT) memory usage. In my tests, this advantage for some reason decreased a bit the more samples the timeseries had (to 5-7% for millions of samples). This I can't fully explain, but perhaps garbage collection issues were involved. *WHEN TO USE THE NEW TIMESTAMP TYPE* The new clientmodel.Timestamp type should be used whenever time calculations are either directly or indirectly related to sample timestamps. For example: - the timestamp of a sample itself - all kinds of watermarks - anything that may become or is compared to a sample timestamp (like the timestamp passed into Target.Scrape()). When to still use time.Time: - for measuring durations/times not related to sample timestamps, like duration telemetry exporting, timers that indicate how frequently to execute some action, etc. *NOTE ON OPERATOR OPTIMIZATION TESTS* We don't use operator optimization code anymore, but it still lives in the code as dead code. It still has tests, but I couldn't get all of them to pass with the new timestamp format. I commented out the failing cases for now, but we should probably remove the dead code soon. I just didn't want to do that in the same change as this. Change-Id: I821787414b0debe85c9fffaeb57abd453727af0f
100 lines
3.2 KiB
Go
100 lines
3.2 KiB
Go
// Copyright 2013 Prometheus Team
|
|
// 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.
|
|
|
|
// Dumper is responsible for dumping all samples along with metadata contained
|
|
// in a given Prometheus metrics storage. It prints samples in unquoted CSV
|
|
// format, with commas as field separators:
|
|
//
|
|
// <fingerprint>,<chunk_first_time>,<chunk_last_time>,<chunk_sample_count>,<chunk_index>,<timestamp>,<value>
|
|
package main
|
|
|
|
import (
|
|
"encoding/csv"
|
|
"flag"
|
|
"fmt"
|
|
"os"
|
|
"strconv"
|
|
|
|
"github.com/golang/glog"
|
|
|
|
"github.com/prometheus/prometheus/storage"
|
|
"github.com/prometheus/prometheus/storage/metric"
|
|
)
|
|
|
|
var (
|
|
storageRoot = flag.String("storage.root", "", "The path to the storage root for Prometheus.")
|
|
dieOnBadChunk = flag.Bool("dieOnBadChunk", false, "Whether to die upon encountering a bad chunk.")
|
|
)
|
|
|
|
type SamplesDumper struct {
|
|
*csv.Writer
|
|
}
|
|
|
|
func (d *SamplesDumper) Operate(key, value interface{}) *storage.OperatorError {
|
|
sampleKey := key.(*metric.SampleKey)
|
|
if *dieOnBadChunk && sampleKey.FirstTimestamp.After(sampleKey.LastTimestamp) {
|
|
glog.Fatalf("Chunk: First time (%v) after last time (%v): %v\n", sampleKey.FirstTimestamp.Unix(), sampleKey.LastTimestamp.Unix(), sampleKey)
|
|
}
|
|
for i, sample := range value.(metric.Values) {
|
|
if *dieOnBadChunk && (sample.Timestamp.Before(sampleKey.FirstTimestamp) || sample.Timestamp.After(sampleKey.LastTimestamp)) {
|
|
glog.Fatalf("Sample not within chunk boundaries: chunk FirstTimestamp (%v), chunk LastTimestamp (%v) vs. sample Timestamp (%v)\n", sampleKey.FirstTimestamp.Unix(), sampleKey.LastTimestamp.Unix(), sample.Timestamp)
|
|
}
|
|
d.Write([]string{
|
|
sampleKey.Fingerprint.String(),
|
|
strconv.FormatInt(sampleKey.FirstTimestamp.Unix(), 10),
|
|
strconv.FormatInt(sampleKey.LastTimestamp.Unix(), 10),
|
|
strconv.FormatUint(uint64(sampleKey.SampleCount), 10),
|
|
strconv.Itoa(i),
|
|
strconv.FormatInt(sample.Timestamp.Unix(), 10),
|
|
fmt.Sprintf("%v", sample.Value),
|
|
})
|
|
if err := d.Error(); err != nil {
|
|
return &storage.OperatorError{
|
|
error: err,
|
|
Continuable: false,
|
|
}
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
func main() {
|
|
flag.Parse()
|
|
|
|
if storageRoot == nil || *storageRoot == "" {
|
|
glog.Fatal("Must provide a path...")
|
|
}
|
|
|
|
persistence, err := metric.NewLevelDBMetricPersistence(*storageRoot)
|
|
if err != nil {
|
|
glog.Fatal(err)
|
|
}
|
|
defer persistence.Close()
|
|
|
|
dumper := &SamplesDumper{
|
|
csv.NewWriter(os.Stdout),
|
|
}
|
|
|
|
entire, err := persistence.MetricSamples.ForEach(&metric.MetricSamplesDecoder{}, &metric.AcceptAllFilter{}, dumper)
|
|
if err != nil {
|
|
glog.Fatal("Error dumping samples: ", err)
|
|
}
|
|
if !entire {
|
|
glog.Fatal("Didn't scan entire corpus")
|
|
}
|
|
dumper.Flush()
|
|
if err = dumper.Error(); err != nil {
|
|
glog.Fatal("Error flushing CSV: ", err)
|
|
}
|
|
}
|