VictoriaMetrics/app/vlinsert/elasticsearch/elasticsearch_test.go

123 lines
3.7 KiB
Go
Raw Normal View History

package elasticsearch
import (
"bytes"
"compress/gzip"
"fmt"
"reflect"
"testing"
"github.com/VictoriaMetrics/VictoriaMetrics/lib/logstorage"
)
func TestReadBulkRequestFailure(t *testing.T) {
f := func(data string) {
t.Helper()
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 14:26:02 +00:00
processLogMessage := func(timestamp int64, fields []logstorage.Field) {
t.Fatalf("unexpected call to processLogMessage with timestamp=%d, fields=%s", timestamp, fields)
}
r := bytes.NewBufferString(data)
rows, err := readBulkRequest(r, false, "_time", "_msg", processLogMessage)
if err == nil {
t.Fatalf("expecting non-empty error")
}
if rows != 0 {
t.Fatalf("unexpected non-zero rows=%d", rows)
}
}
f("foobar")
f(`{}`)
f(`{"create":{}}`)
f(`{"creat":{}}
{}`)
f(`{"create":{}}
foobar`)
}
func TestReadBulkRequestSuccess(t *testing.T) {
f := func(data, timeField, msgField string, rowsExpected int, timestampsExpected []int64, resultExpected string) {
t.Helper()
var timestamps []int64
var result string
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 14:26:02 +00:00
processLogMessage := func(timestamp int64, fields []logstorage.Field) {
timestamps = append(timestamps, timestamp)
2024-06-17 10:13:18 +00:00
result += string(logstorage.MarshalFieldsToJSON(nil, fields)) + "\n"
}
// Read the request without compression
r := bytes.NewBufferString(data)
rows, err := readBulkRequest(r, false, timeField, msgField, processLogMessage)
if err != nil {
t.Fatalf("unexpected error: %s", err)
}
if rows != rowsExpected {
t.Fatalf("unexpected rows read; got %d; want %d", rows, rowsExpected)
}
if !reflect.DeepEqual(timestamps, timestampsExpected) {
t.Fatalf("unexpected timestamps;\ngot\n%d\nwant\n%d", timestamps, timestampsExpected)
}
if result != resultExpected {
t.Fatalf("unexpected result;\ngot\n%s\nwant\n%s", result, resultExpected)
}
// Read the request with compression
timestamps = nil
result = ""
compressedData := compressData(data)
r = bytes.NewBufferString(compressedData)
rows, err = readBulkRequest(r, true, timeField, msgField, processLogMessage)
if err != nil {
t.Fatalf("unexpected error: %s", err)
}
if rows != rowsExpected {
t.Fatalf("unexpected rows read; got %d; want %d", rows, rowsExpected)
}
if !reflect.DeepEqual(timestamps, timestampsExpected) {
t.Fatalf("unexpected timestamps;\ngot\n%d\nwant\n%d", timestamps, timestampsExpected)
}
if result != resultExpected {
t.Fatalf("unexpected result;\ngot\n%s\nwant\n%s", result, resultExpected)
}
}
// Verify an empty data
f("", "_time", "_msg", 0, nil, "")
f("\n", "_time", "_msg", 0, nil, "")
f("\n\n", "_time", "_msg", 0, nil, "")
// Verify non-empty data
data := `{"create":{"_index":"filebeat-8.8.0"}}
{"@timestamp":"2023-06-06T04:48:11.735Z","log":{"offset":71770,"file":{"path":"/var/log/auth.log"}},"message":"foobar"}
{"create":{"_index":"filebeat-8.8.0"}}
{"@timestamp":"2023-06-06T04:48:12.735Z","message":"baz"}
{"index":{"_index":"filebeat-8.8.0"}}
{"message":"xyz","@timestamp":"2023-06-06T04:48:13.735Z","x":"y"}
`
timeField := "@timestamp"
msgField := "message"
rowsExpected := 3
timestampsExpected := []int64{1686026891735000000, 1686026892735000000, 1686026893735000000}
resultExpected := `{"@timestamp":"","log.offset":"71770","log.file.path":"/var/log/auth.log","_msg":"foobar"}
{"@timestamp":"","_msg":"baz"}
{"_msg":"xyz","@timestamp":"","x":"y"}
`
f(data, timeField, msgField, rowsExpected, timestampsExpected, resultExpected)
}
func compressData(s string) string {
var bb bytes.Buffer
zw := gzip.NewWriter(&bb)
if _, err := zw.Write([]byte(s)); err != nil {
panic(fmt.Errorf("unexpected error when compressing data: %w", err))
}
if err := zw.Close(); err != nil {
panic(fmt.Errorf("unexpected error when closing gzip writer: %w", err))
}
return bb.String()
}