VictoriaMetrics/app/vlstorage/main.go

179 lines
8.7 KiB
Go
Raw Normal View History

package vlstorage
import (
"context"
"flag"
"fmt"
"io"
lib/logstorage: follow-up for 8a23d08c210c7c2440c224debcff266de3353a64 - Compare the actual free disk space to the value provided via -storage.minFreeDiskSpaceBytes directly inside the Storage.IsReadOnly(). This should work fast in most cases. This simplifies the logic at lib/storage. - Do not take into account -storage.minFreeDiskSpaceBytes during background merges, since it results in uncontrolled growth of small parts when the free disk space approaches -storage.minFreeDiskSpaceBytes. The background merge logic uses another mechanism for determining whether there is enough disk space for the merge - it reserves the needed disk space before the merge and releases it after the merge. This prevents from out of disk space errors during background merge. - Properly handle corner cases for flushing in-memory data to disk when the storage enters read-only mode. This is better than losing the in-memory data. - Return back Storage.MustAddRows() instead of Storage.AddRows(), since the only case when AddRows() can return error is when the storage is in read-only mode. This case must be handled by the caller by calling Storage.IsReadOnly() before adding rows to the storage. This simplifies the code a bit, since the caller of Storage.MustAddRows() shouldn't handle errors returned by Storage.AddRows(). - Properly store parsed logs to Storage if parts of the request contain invalid log lines. Previously the parsed logs could be lost in this case. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4737 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/4945
2023-10-02 16:26:02 +02:00
"net/http"
"time"
"github.com/VictoriaMetrics/metrics"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/flagutil"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/fs"
lib/logstorage: follow-up for 8a23d08c210c7c2440c224debcff266de3353a64 - Compare the actual free disk space to the value provided via -storage.minFreeDiskSpaceBytes directly inside the Storage.IsReadOnly(). This should work fast in most cases. This simplifies the logic at lib/storage. - Do not take into account -storage.minFreeDiskSpaceBytes during background merges, since it results in uncontrolled growth of small parts when the free disk space approaches -storage.minFreeDiskSpaceBytes. The background merge logic uses another mechanism for determining whether there is enough disk space for the merge - it reserves the needed disk space before the merge and releases it after the merge. This prevents from out of disk space errors during background merge. - Properly handle corner cases for flushing in-memory data to disk when the storage enters read-only mode. This is better than losing the in-memory data. - Return back Storage.MustAddRows() instead of Storage.AddRows(), since the only case when AddRows() can return error is when the storage is in read-only mode. This case must be handled by the caller by calling Storage.IsReadOnly() before adding rows to the storage. This simplifies the code a bit, since the caller of Storage.MustAddRows() shouldn't handle errors returned by Storage.AddRows(). - Properly store parsed logs to Storage if parts of the request contain invalid log lines. Previously the parsed logs could be lost in this case. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4737 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/4945
2023-10-02 16:26:02 +02:00
"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
)
var (
retentionPeriod = flagutil.NewDuration("retentionPeriod", "7d", "Log entries with timestamps older than now-retentionPeriod are automatically deleted; "+
"log entries with timestamps outside the retention are also rejected during data ingestion; the minimum supported retention is 1d (one day); "+
"see https://docs.victoriametrics.com/VictoriaLogs/#retention")
futureRetention = flagutil.NewDuration("futureRetention", "2d", "Log entries with timestamps bigger than now+futureRetention are rejected during data ingestion; "+
"see https://docs.victoriametrics.com/VictoriaLogs/#retention")
storageDataPath = flag.String("storageDataPath", "victoria-logs-data", "Path to directory with the VictoriaLogs data; "+
"see https://docs.victoriametrics.com/VictoriaLogs/#storage")
inmemoryDataFlushInterval = flag.Duration("inmemoryDataFlushInterval", 5*time.Second, "The interval for guaranteed saving of in-memory data to disk. "+
"The saved data survives unclean shutdowns such as OOM crash, hardware reset, SIGKILL, etc. "+
"Bigger intervals may help increase the lifetime of flash storage with limited write cycles (e.g. Raspberry PI). "+
"Smaller intervals increase disk IO load. Minimum supported value is 1s")
logNewStreams = flag.Bool("logNewStreams", false, "Whether to log creation of new streams; this can be useful for debugging of high cardinality issues with log streams; "+
"see https://docs.victoriametrics.com/VictoriaLogs/keyConcepts.html#stream-fields ; see also -logIngestedRows")
logIngestedRows = flag.Bool("logIngestedRows", false, "Whether to log all the ingested log entries; this can be useful for debugging of data ingestion; "+
"see https://docs.victoriametrics.com/VictoriaLogs/data-ingestion/ ; see also -logNewStreams")
lib/logstorage: follow-up for 8a23d08c210c7c2440c224debcff266de3353a64 - Compare the actual free disk space to the value provided via -storage.minFreeDiskSpaceBytes directly inside the Storage.IsReadOnly(). This should work fast in most cases. This simplifies the logic at lib/storage. - Do not take into account -storage.minFreeDiskSpaceBytes during background merges, since it results in uncontrolled growth of small parts when the free disk space approaches -storage.minFreeDiskSpaceBytes. The background merge logic uses another mechanism for determining whether there is enough disk space for the merge - it reserves the needed disk space before the merge and releases it after the merge. This prevents from out of disk space errors during background merge. - Properly handle corner cases for flushing in-memory data to disk when the storage enters read-only mode. This is better than losing the in-memory data. - Return back Storage.MustAddRows() instead of Storage.AddRows(), since the only case when AddRows() can return error is when the storage is in read-only mode. This case must be handled by the caller by calling Storage.IsReadOnly() before adding rows to the storage. This simplifies the code a bit, since the caller of Storage.MustAddRows() shouldn't handle errors returned by Storage.AddRows(). - Properly store parsed logs to Storage if parts of the request contain invalid log lines. Previously the parsed logs could be lost in this case. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4737 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/4945
2023-10-02 16:26:02 +02:00
minFreeDiskSpaceBytes = flagutil.NewBytes("storage.minFreeDiskSpaceBytes", 10e6, "The minimum free disk space at -storageDataPath after which "+
"the storage stops accepting new data")
)
// Init initializes vlstorage.
//
// Stop must be called when vlstorage is no longer needed
func Init() {
if strg != nil {
logger.Panicf("BUG: Init() has been already called")
}
if retentionPeriod.Duration() < 24*time.Hour {
logger.Fatalf("-retentionPeriod cannot be smaller than a day; got %s", retentionPeriod)
}
cfg := &logstorage.StorageConfig{
Retention: retentionPeriod.Duration(),
FlushInterval: *inmemoryDataFlushInterval,
FutureRetention: futureRetention.Duration(),
LogNewStreams: *logNewStreams,
LogIngestedRows: *logIngestedRows,
MinFreeDiskSpaceBytes: minFreeDiskSpaceBytes.N,
}
logger.Infof("opening storage at -storageDataPath=%s", *storageDataPath)
startTime := time.Now()
strg = logstorage.MustOpenStorage(*storageDataPath, cfg)
var ss logstorage.StorageStats
strg.UpdateStats(&ss)
logger.Infof("successfully opened storage in %.3f seconds; smallParts: %d; bigParts: %d; smallPartBlocks: %d; bigPartBlocks: %d; smallPartRows: %d; bigPartRows: %d; "+
"smallPartSize: %d bytes; bigPartSize: %d bytes",
time.Since(startTime).Seconds(), ss.SmallParts, ss.BigParts, ss.SmallPartBlocks, ss.BigPartBlocks, ss.SmallPartRowsCount, ss.BigPartRowsCount,
ss.CompressedSmallPartSize, ss.CompressedBigPartSize)
// register storage metrics
storageMetrics = metrics.NewSet()
storageMetrics.RegisterMetricsWriter(func(w io.Writer) {
writeStorageMetrics(w, strg)
})
metrics.RegisterSet(storageMetrics)
}
// Stop stops vlstorage.
func Stop() {
metrics.UnregisterSet(storageMetrics)
storageMetrics = nil
strg.MustClose()
strg = nil
}
var strg *logstorage.Storage
var storageMetrics *metrics.Set
lib/logstorage: follow-up for 8a23d08c210c7c2440c224debcff266de3353a64 - Compare the actual free disk space to the value provided via -storage.minFreeDiskSpaceBytes directly inside the Storage.IsReadOnly(). This should work fast in most cases. This simplifies the logic at lib/storage. - Do not take into account -storage.minFreeDiskSpaceBytes during background merges, since it results in uncontrolled growth of small parts when the free disk space approaches -storage.minFreeDiskSpaceBytes. The background merge logic uses another mechanism for determining whether there is enough disk space for the merge - it reserves the needed disk space before the merge and releases it after the merge. This prevents from out of disk space errors during background merge. - Properly handle corner cases for flushing in-memory data to disk when the storage enters read-only mode. This is better than losing the in-memory data. - Return back Storage.MustAddRows() instead of Storage.AddRows(), since the only case when AddRows() can return error is when the storage is in read-only mode. This case must be handled by the caller by calling Storage.IsReadOnly() before adding rows to the storage. This simplifies the code a bit, since the caller of Storage.MustAddRows() shouldn't handle errors returned by Storage.AddRows(). - Properly store parsed logs to Storage if parts of the request contain invalid log lines. Previously the parsed logs could be lost in this case. Updates https://github.com/VictoriaMetrics/VictoriaMetrics/issues/4737 Updates https://github.com/VictoriaMetrics/VictoriaMetrics/pull/4945
2023-10-02 16:26:02 +02:00
// CanWriteData returns non-nil error if it cannot write data to vlstorage.
func CanWriteData() error {
if strg.IsReadOnly() {
return &httpserver.ErrorWithStatusCode{
Err: fmt.Errorf("cannot add rows into storage in read-only mode; the storage can be in read-only mode "+
"because of lack of free disk space at -storageDataPath=%s", *storageDataPath),
StatusCode: http.StatusTooManyRequests,
}
}
return nil
}
// MustAddRows adds lr to vlstorage
//
// It is advised to call CanWriteData() before calling MustAddRows()
func MustAddRows(lr *logstorage.LogRows) {
strg.MustAddRows(lr)
}
// RunQuery runs the given q and calls writeBlock for the returned data blocks
2024-05-20 04:08:30 +02:00
func RunQuery(ctx context.Context, tenantIDs []logstorage.TenantID, q *logstorage.Query, writeBlock logstorage.WriteBlockFunc) error {
return strg.RunQuery(ctx, tenantIDs, q, writeBlock)
}
2024-05-20 04:08:30 +02:00
// GetFieldNames executes q and returns field names seen in results.
func GetFieldNames(ctx context.Context, tenantIDs []logstorage.TenantID, q *logstorage.Query) ([]string, error) {
return strg.GetFieldNames(ctx, tenantIDs, q)
}
// GetFieldValues executes q and returns unique values for the fieldName seen in results.
//
// If limit > 0, then up to limit unique values are returned.
func GetFieldValues(ctx context.Context, tenantIDs []logstorage.TenantID, q *logstorage.Query, fieldName string, limit uint64) ([]string, error) {
return strg.GetFieldValues(ctx, tenantIDs, q, fieldName, limit)
}
func writeStorageMetrics(w io.Writer, strg *logstorage.Storage) {
var ss logstorage.StorageStats
strg.UpdateStats(&ss)
metrics.WriteGaugeUint64(w, fmt.Sprintf(`vl_free_disk_space_bytes{path=%q}`, *storageDataPath), fs.MustGetFreeSpace(*storageDataPath))
isReadOnly := uint64(0)
if ss.IsReadOnly {
isReadOnly = 1
}
metrics.WriteGaugeUint64(w, fmt.Sprintf(`vl_storage_is_read_only{path=%q}`, *storageDataPath), isReadOnly)
metrics.WriteGaugeUint64(w, `vl_active_merges{type="storage/inmemory"}`, ss.InmemoryActiveMerges)
metrics.WriteGaugeUint64(w, `vl_active_merges{type="storage/small"}`, ss.SmallPartActiveMerges)
metrics.WriteGaugeUint64(w, `vl_active_merges{type="storage/big"}`, ss.BigPartActiveMerges)
metrics.WriteCounterUint64(w, `vl_merges_total{type="storage/inmemory"}`, ss.InmemoryMergesTotal)
metrics.WriteCounterUint64(w, `vl_merges_total{type="storage/small"}`, ss.SmallPartMergesTotal)
metrics.WriteCounterUint64(w, `vl_merges_total{type="storage/big"}`, ss.BigPartMergesTotal)
metrics.WriteGaugeUint64(w, `vl_storage_rows{type="storage/inmemory"}`, ss.InmemoryRowsCount)
metrics.WriteGaugeUint64(w, `vl_storage_rows{type="storage/small"}`, ss.SmallPartRowsCount)
metrics.WriteGaugeUint64(w, `vl_storage_rows{type="storage/big"}`, ss.BigPartRowsCount)
metrics.WriteGaugeUint64(w, `vl_storage_parts{type="storage/inmemory"}`, ss.InmemoryParts)
metrics.WriteGaugeUint64(w, `vl_storage_parts{type="storage/small"}`, ss.SmallParts)
metrics.WriteGaugeUint64(w, `vl_storage_parts{type="storage/big"}`, ss.BigParts)
metrics.WriteGaugeUint64(w, `vl_storage_blocks{type="storage/inmemory"}`, ss.InmemoryBlocks)
metrics.WriteGaugeUint64(w, `vl_storage_blocks{type="storage/small"}`, ss.SmallPartBlocks)
metrics.WriteGaugeUint64(w, `vl_storage_blocks{type="storage/big"}`, ss.BigPartBlocks)
metrics.WriteGaugeUint64(w, `vl_partitions`, ss.PartitionsCount)
metrics.WriteCounterUint64(w, `vl_streams_created_total`, ss.StreamsCreatedTotal)
metrics.WriteGaugeUint64(w, `vl_indexdb_rows`, ss.IndexdbItemsCount)
metrics.WriteGaugeUint64(w, `vl_indexdb_parts`, ss.IndexdbPartsCount)
metrics.WriteGaugeUint64(w, `vl_indexdb_blocks`, ss.IndexdbBlocksCount)
metrics.WriteGaugeUint64(w, `vl_data_size_bytes{type="indexdb"}`, ss.IndexdbSizeBytes)
metrics.WriteGaugeUint64(w, `vl_data_size_bytes{type="storage"}`, ss.CompressedInmemorySize+ss.CompressedSmallPartSize+ss.CompressedBigPartSize)
metrics.WriteGaugeUint64(w, `vl_compressed_data_size_bytes{type="storage/inmemory"}`, ss.CompressedInmemorySize)
metrics.WriteGaugeUint64(w, `vl_compressed_data_size_bytes{type="storage/small"}`, ss.CompressedSmallPartSize)
metrics.WriteGaugeUint64(w, `vl_compressed_data_size_bytes{type="storage/big"}`, ss.CompressedBigPartSize)
metrics.WriteGaugeUint64(w, `vl_uncompressed_data_size_bytes{type="storage/inmemory"}`, ss.UncompressedInmemorySize)
metrics.WriteGaugeUint64(w, `vl_uncompressed_data_size_bytes{type="storage/small"}`, ss.UncompressedSmallPartSize)
metrics.WriteGaugeUint64(w, `vl_uncompressed_data_size_bytes{type="storage/big"}`, ss.UncompressedBigPartSize)
metrics.WriteCounterUint64(w, `vl_rows_dropped_total{reason="too_big_timestamp"}`, ss.RowsDroppedTooBigTimestamp)
metrics.WriteCounterUint64(w, `vl_rows_dropped_total{reason="too_small_timestamp"}`, ss.RowsDroppedTooSmallTimestamp)
}