Files
versitygw/metrics/metrics.go
T
niksis02 9f786b3c2c feat: global error refactoring
Fixes #2123
Fixes #2120
Fixes #2116
Fixes #2111
Fixes #2108
Fixes #2086
Fixes #2085
Fixes #2083
Fixes #2081
Fixes #2080
Fixes #2073
Fixes #2072
Fixes #2071
Fixes #2069
Fixes #2044
Fixes #2043
Fixes #2042
Fixes #2041
Fixes #2040
Fixes #2039
Fixes #2036
Fixes #2035
Fixes #2034
Fixes #2028
Fixes #2020
Fixes #1842
Fixes #1810
Fixes #1780
Fixes #1775
Fixes #1736
Fixes #1705
Fixes #1663
Fixes #1645
Fixes #1583
Fixes #1526
Fixes #1514
Fixes #1493
Fixes #1487
Fixes #959
Fixes #779
Closes #823
Closes #85

Refactor global S3 error handling around structured error types and centralized XML response generation.

All S3 errors now share the common APIError base for the fields every error has: Code, HTTP status code, and Message. Non-traditional errors that need AWS-compatible XML fields now have dedicated typed errors in the s3err package. Each typed error implements the shared S3Error behavior so controllers and middleware can handle errors consistently while still emitting error-specific XML fields.

Add a dedicated InvalidArgumentError type because InvalidArgument is used widely across request validation, auth, copy source handling, object lock validation, multipart validation, and header parsing. The new InvalidArgument path uses explicit InvalidArgErrorCode constants with predefined descriptions and ArgumentName values, keeping call sites readable while preserving the correct InvalidArgument XML shape and optional ArgumentValue.

New structured errors added in s3err:
- `AccessForbiddenError`: Method, ResourceType
- `BadDigestError`: CalculatedDigest, ExpectedDigest
- `BucketError`: BucketName
- `ContentSHA256MismatchError`: ClientComputedContentSHA256, S3ComputedContentSHA256
- `EntityTooLargeError`: ProposedSize, MaxSizeAllowed
- `EntityTooSmallError`: ProposedSize, MinSizeAllowed
- `ExpiredPresignedURLError`: ServerTime, XAmzExpires, Expires
- `InvalidAccessKeyIdError`: AWSAccessKeyId
- `InvalidArgumentError`: Description, ArgumentName, ArgumentValue
- `InvalidChunkSizeError`: Chunk, BadChunkSize
- `InvalidDigestError`: ContentMD5
- `InvalidLocationConstraintError`: LocationConstraint
- `InvalidPartError`: UploadId, PartNumber, ETag
- `InvalidRangeError`: RangeRequested, ActualObjectSize
- `InvalidTagError`: TagKey, TagValue
- `KeyTooLongError`: Size, MaxSizeAllowed
- `MetadataTooLargeError`: Size, MaxSizeAllowed
- `MethodNotAllowedError`: Method, ResourceType, AllowedMethods
- `NoSuchUploadError`: UploadId
- `NoSuchVersionError`: Key, VersionId
- `NotImplementedError`: Header, AdditionalMessage
- `PreconditionFailedError`: Condition
- `RequestTimeTooSkewedError`: RequestTime, ServerTime, MaxAllowedSkewMilliseconds
- `SignatureDoesNotMatchError`: AWSAccessKeyId, StringToSign, SignatureProvided, StringToSignBytes, CanonicalRequest, CanonicalRequestBytes

Fix CompleteMultipartUpload validation in the Azure backend so missing or empty `ETag` values return the appropriate S3 error instead of allowing a gateway panic.

Fix presigned authentication expiration validation to compare server time in `UTC`, matching the `UTC` timestamp used by presigned URL signing.

Add request ID and host ID support across S3 requests. Each request now receives AWS S3-like identifiers, returned in response headers as `x-amz-request-id` and `x-amz-id-2` and included in all XML error responses as RequestId and HostId. The generated ID structure is designed to resemble AWS S3 request IDs and host IDs.

The request signature calculation/validation for streaming uploads was previously delayed until the request body was fully read, both for Authorization header authentication and presigned URLs.
Now, the signature is validated immediately in the authorization middlewares without reading the request body, since the signature calculation itself does not depend on the request body. Instead, only the `x-amz-content-sha256` SHA-256 hash calculation is delayed.
2026-05-21 23:49:34 +04:00

238 lines
5.2 KiB
Go

// Copyright 2024 Versity Software
// This file is 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 metrics
import (
"context"
"errors"
"fmt"
"net/http"
"os"
"strings"
"sync"
"github.com/gofiber/fiber/v2"
"github.com/versity/versitygw/s3err"
)
var (
// max size of data items to buffer before dropping
// new incoming data items
dataItemCount = 100000
)
// Tag is added metadata for metrics
type Tag struct {
// Key is tag name
Key string
// Value is tag data
Value string
}
// Manager is the interface definition for metrics manager
type Manager interface {
Send(ctx *fiber.Ctx, err error, action string, count int64, status int)
Close()
}
// manager is a manager of metrics plugins
type manager struct {
wg sync.WaitGroup
ctx context.Context
config Config
publishers []publisher
addDataChan chan datapoint
}
type Config struct {
ServiceName string
StatsdServers string
DogStatsdServers string
}
// NewManager initializes metrics plugins and returns a new metrics manager
func NewManager(ctx context.Context, conf Config) (Manager, error) {
if len(conf.StatsdServers) == 0 && len(conf.DogStatsdServers) == 0 {
return nil, nil
}
if conf.ServiceName == "" {
hostname, err := os.Hostname()
if err != nil {
return nil, fmt.Errorf("failed to get hostname: %w", err)
}
conf.ServiceName = hostname
}
addDataChan := make(chan datapoint, dataItemCount)
mgr := &manager{
addDataChan: addDataChan,
ctx: ctx,
config: conf,
}
// setup statsd endpoints
if len(conf.StatsdServers) > 0 {
statsdServers := strings.SplitSeq(conf.StatsdServers, ",")
for server := range statsdServers {
statsd, err := newStatsd(server, conf.ServiceName)
if err != nil {
return nil, err
}
mgr.publishers = append(mgr.publishers, statsd)
}
}
// setup dogstatsd endpoints
if len(conf.DogStatsdServers) > 0 {
dogStatsdServers := strings.SplitSeq(conf.DogStatsdServers, ",")
for server := range dogStatsdServers {
dogStatsd, err := newDogStatsd(server, conf.ServiceName)
if err != nil {
return nil, err
}
mgr.publishers = append(mgr.publishers, dogStatsd)
}
}
mgr.wg.Add(1)
go mgr.addForwarder(addDataChan)
return mgr, nil
}
func (m *manager) Send(ctx *fiber.Ctx, err error, action string, count int64, status int) {
// In case of Authentication failures, url parsing ...
if action == "" {
action = ActionUndetected
}
a := ActionMap[action]
reqTags := []Tag{
{Key: "method", Value: ctx.Method()},
{Key: "api", Value: a.Service},
{Key: "action", Value: a.Name},
}
// add tag bucket=<bucketname> if the request specifies a bucket
bucket := ctx.Params("bucket")
if bucket != "" {
reqTags = append(reqTags, Tag{Key: "bucket", Value: bucket})
}
reqStatus := status
if err != nil {
var apierr s3err.S3Error
if errors.As(err, &apierr) {
reqStatus = apierr.StatusCode()
} else {
reqStatus = http.StatusInternalServerError
}
}
if reqStatus == 0 {
reqStatus = http.StatusOK
}
reqTags = append(reqTags, Tag{
Key: "status",
Value: fmt.Sprintf("%v", reqStatus),
})
if err != nil {
m.increment("failed_count", reqTags...)
} else {
m.increment("success_count", reqTags...)
}
switch action {
case ActionPutObject:
m.add("bytes_written", count, reqTags...)
m.increment("object_created_count", reqTags...)
case ActionCompleteMultipartUpload:
m.increment("object_created_count", reqTags...)
case ActionUploadPart:
m.add("bytes_written", count, reqTags...)
case ActionGetObject:
m.add("bytes_read", count, reqTags...)
case ActionDeleteObject:
m.increment("object_removed_count", reqTags...)
case ActionDeleteObjects:
m.add("object_removed_count", count, reqTags...)
}
}
// increment increments the key by one
func (m *manager) increment(key string, tags ...Tag) {
m.add(key, 1, tags...)
}
// add adds value to key
func (m *manager) add(key string, value int64, tags ...Tag) {
if m.ctx.Err() != nil {
return
}
d := datapoint{
key: key,
value: value,
tags: tags,
}
select {
case m.addDataChan <- d:
default:
// channel full, drop the updates
}
}
// Close closes metrics channels, waits for data to complete, closes all plugins
func (m *manager) Close() {
// drain the datapoint channels
close(m.addDataChan)
m.wg.Wait()
// close all publishers
for _, p := range m.publishers {
p.Close()
}
}
// publisher is the interface for interacting with the metrics plugins
type publisher interface {
Add(key string, value int64, tags ...Tag)
Close()
}
func (m *manager) addForwarder(addChan <-chan datapoint) {
for data := range addChan {
for _, s := range m.publishers {
s.Add(data.key, data.value, data.tags...)
}
}
m.wg.Done()
}
type datapoint struct {
key string
value int64
tags []Tag
}