feat(ilm): relocate hot objects across server pools by GET frequency

Keep NVMe/HDD pool pairs useful without remote tiering: promote objects that
are read often, demote previously moved objects once they go idle, and leave
the feature off until operators set a two-pool topology.

Signed-off-by: mr javad seydi <seydi.birjand@gmail.com>
This commit is contained in:
mr javad seydi
2026-08-15 13:39:02 +03:30
parent 100e2e57a7
commit 7a060cab1e
31 changed files with 5042 additions and 42 deletions
@@ -0,0 +1,129 @@
// Copyright (c) 2015-2026 MinIO, Inc.
//
// This file is part of MinIO Object Storage stack
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// This program is distributed in the hope that it will be useful
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
package lifecycle
import (
"encoding/xml"
"time"
)
var (
errAccessInvalidDuration = Errorf("Window and DemoteAfterIdle must be valid Go durations, e.g. 10m or 24h")
errAccessInvalidWindow = Errorf("Window must be a positive duration with AccessTransition")
errAccessInvalidPromote = Errorf("PromoteAfterAccesses must be a positive integer with AccessTransition")
errAccessInvalidDemote = Errorf("DemoteAfterAccesses must be smaller than PromoteAfterAccesses and 0 or greater")
errAccessInvalidIdle = Errorf("DemoteAfterIdle must be a positive duration no shorter than Window")
errAccessInvalidQuotaSize = Errorf("AccessTierQuota must be a valid size, e.g. 500GiB")
)
// Duration is a time.Duration that marshals to and from an XML element
// holding a Go duration string, e.g. <Window>10m</Window>.
type Duration time.Duration
// UnmarshalXML parses a duration string such as "10m" or "24h".
func (d *Duration) UnmarshalXML(dec *xml.Decoder, start xml.StartElement) error {
var s string
if err := dec.DecodeElement(&s, &start); err != nil {
return err
}
dur, err := time.ParseDuration(s)
if err != nil {
return errAccessInvalidDuration
}
*d = Duration(dur)
return nil
}
// MarshalXML encodes a non-zero duration, and nothing otherwise.
func (d Duration) MarshalXML(enc *xml.Encoder, start xml.StartElement) error {
if d == 0 {
return nil
}
return enc.EncodeElement(time.Duration(d).String(), start)
}
// D returns the value as a time.Duration.
func (d Duration) D() time.Duration {
return time.Duration(d)
}
// AccessTransition is a Silo extension to the S3 lifecycle rule. It relocates
// an object between server pools based on how often it is read, rather than on
// its age: an object read at least PromoteAfterAccesses times within Window
// moves to the fastest configured pool, and moves back once it has been idle
// for DemoteAfterIdle and its windowed hit count has fallen to
// DemoteAfterAccesses or below.
//
// The gap between the two thresholds, together with DemoteAfterIdle and the
// server-side access_min_residency, is what keeps an object from oscillating
// between pools.
type AccessTransition struct {
XMLName xml.Name `xml:"AccessTransition"`
Window Duration `xml:"Window,omitempty"`
PromoteAfterAccesses int `xml:"PromoteAfterAccesses,omitempty"`
DemoteAfterAccesses int `xml:"DemoteAfterAccesses,omitempty"`
DemoteAfterIdle Duration `xml:"DemoteAfterIdle,omitempty"`
set bool
}
// IsNull returns true if no usable access transition is configured.
func (a AccessTransition) IsNull() bool {
return !a.set || a.PromoteAfterAccesses <= 0
}
// MarshalXML encodes an AccessTransition element, and nothing if unset.
func (a AccessTransition) MarshalXML(enc *xml.Encoder, start xml.StartElement) error {
if !a.set {
return nil
}
type accessTransitionWrapper AccessTransition
return enc.EncodeElement(accessTransitionWrapper(a), start)
}
// UnmarshalXML decodes an AccessTransition element.
func (a *AccessTransition) UnmarshalXML(dec *xml.Decoder, start xml.StartElement) error {
type accessTransitionWrapper AccessTransition
var atw accessTransitionWrapper
if err := dec.DecodeElement(&atw, &start); err != nil {
return err
}
*a = AccessTransition(atw)
a.set = true
return nil
}
// Validate checks the AccessTransition element.
func (a AccessTransition) Validate() error {
if !a.set {
return nil
}
if a.Window <= 0 {
return errAccessInvalidWindow
}
if a.PromoteAfterAccesses <= 0 {
return errAccessInvalidPromote
}
if a.DemoteAfterAccesses < 0 || a.DemoteAfterAccesses >= a.PromoteAfterAccesses {
return errAccessInvalidDemote
}
if a.DemoteAfterIdle <= 0 || a.DemoteAfterIdle < a.Window {
return errAccessInvalidIdle
}
return nil
}
@@ -0,0 +1,219 @@
// Copyright (c) 2015-2026 MinIO, Inc.
//
// This file is part of MinIO Object Storage stack
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// This program is distributed in the hope that it will be useful
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
package lifecycle
import (
"bytes"
"encoding/xml"
"strings"
"testing"
"time"
"github.com/minio/minio/internal/bucket/object/lock"
)
const accessTieringXML = `<LifecycleConfiguration>
<AccessTierQuota>500GiB</AccessTierQuota>
<Rule>
<ID>hot-logs</ID>
<Status>Enabled</Status>
<Filter><And><Prefix>logs/</Prefix><ObjectSizeGreaterThan>65536</ObjectSizeGreaterThan></And></Filter>
<AccessTransition>
<Window>10m</Window>
<PromoteAfterAccesses>100</PromoteAfterAccesses>
<DemoteAfterAccesses>5</DemoteAfterAccesses>
<DemoteAfterIdle>24h</DemoteAfterIdle>
</AccessTransition>
</Rule>
</LifecycleConfiguration>`
func TestAccessTransitionParse(t *testing.T) {
lc, err := ParseLifecycleConfig(strings.NewReader(accessTieringXML))
if err != nil {
t.Fatalf("parse: %v", err)
}
if err := lc.Validate(lock.Retention{}); err != nil {
t.Fatalf("validate: %v", err)
}
if got := lc.AccessQuotaBytes(); got != 500*1024*1024*1024 {
t.Fatalf("quota = %d, want %d", got, 500*1024*1024*1024)
}
if !lc.HasAccessTransition() {
t.Fatal("HasAccessTransition = false, want true")
}
at := lc.Rules[0].AccessTransition
if at.Window.D() != 10*time.Minute {
t.Fatalf("window = %v, want 10m", at.Window.D())
}
if at.DemoteAfterIdle.D() != 24*time.Hour {
t.Fatalf("idle = %v, want 24h", at.DemoteAfterIdle.D())
}
if at.PromoteAfterAccesses != 100 || at.DemoteAfterAccesses != 5 {
t.Fatalf("thresholds = %d/%d, want 100/5", at.PromoteAfterAccesses, at.DemoteAfterAccesses)
}
}
// A round trip through Marshal must preserve both the rule element and the
// bucket-wide quota, since PutBucketLifecycle stores whatever we re-encode.
func TestAccessTransitionRoundTrip(t *testing.T) {
lc, err := ParseLifecycleConfig(strings.NewReader(accessTieringXML))
if err != nil {
t.Fatalf("parse: %v", err)
}
buf, err := xml.Marshal(lc)
if err != nil {
t.Fatalf("marshal: %v", err)
}
if !bytes.Contains(buf, []byte("<AccessTierQuota>500GiB</AccessTierQuota>")) {
t.Fatalf("quota lost in round trip: %s", buf)
}
got, err := ParseLifecycleConfig(bytes.NewReader(buf))
if err != nil {
t.Fatalf("reparse: %v", err)
}
if got.AccessQuotaBytes() != lc.AccessQuotaBytes() {
t.Fatalf("quota %d != %d", got.AccessQuotaBytes(), lc.AccessQuotaBytes())
}
if got.Rules[0].AccessTransition != lc.Rules[0].AccessTransition {
t.Fatalf("rule %+v != %+v", got.Rules[0].AccessTransition, lc.Rules[0].AccessTransition)
}
}
// A rule with no AccessTransition must not emit an empty element - otherwise
// every existing lifecycle config would change shape on rewrite.
func TestAccessTransitionUnsetNotMarshalled(t *testing.T) {
lc, err := ParseLifecycleConfig(strings.NewReader(`<LifecycleConfiguration><Rule>
<ID>old</ID><Status>Enabled</Status><Filter><Prefix>a/</Prefix></Filter>
<Expiration><Days>3</Days></Expiration></Rule></LifecycleConfiguration>`))
if err != nil {
t.Fatalf("parse: %v", err)
}
buf, err := xml.Marshal(lc)
if err != nil {
t.Fatalf("marshal: %v", err)
}
if bytes.Contains(buf, []byte("AccessTransition")) || bytes.Contains(buf, []byte("AccessTierQuota")) {
t.Fatalf("unset elements emitted: %s", buf)
}
if lc.HasAccessTransition() {
t.Fatal("HasAccessTransition = true for a plain expiry rule")
}
}
func TestAccessTransitionValidate(t *testing.T) {
tests := []struct {
name string
at AccessTransition
err error
}{
{"ok", AccessTransition{Window: Duration(10 * time.Minute), PromoteAfterAccesses: 100, DemoteAfterAccesses: 5, DemoteAfterIdle: Duration(time.Hour), set: true}, nil},
{"unset", AccessTransition{}, nil},
{"zero window", AccessTransition{PromoteAfterAccesses: 100, DemoteAfterIdle: Duration(time.Hour), set: true}, errAccessInvalidWindow},
{"zero promote", AccessTransition{Window: Duration(time.Minute), DemoteAfterIdle: Duration(time.Hour), set: true}, errAccessInvalidPromote},
{"demote >= promote", AccessTransition{Window: Duration(time.Minute), PromoteAfterAccesses: 5, DemoteAfterAccesses: 5, DemoteAfterIdle: Duration(time.Hour), set: true}, errAccessInvalidDemote},
{"negative demote", AccessTransition{Window: Duration(time.Minute), PromoteAfterAccesses: 5, DemoteAfterAccesses: -1, DemoteAfterIdle: Duration(time.Hour), set: true}, errAccessInvalidDemote},
{"idle shorter than window", AccessTransition{Window: Duration(time.Hour), PromoteAfterAccesses: 5, DemoteAfterIdle: Duration(time.Minute), set: true}, errAccessInvalidIdle},
{"zero idle", AccessTransition{Window: Duration(time.Minute), PromoteAfterAccesses: 5, set: true}, errAccessInvalidIdle},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
if err := tc.at.Validate(); err != tc.err {
t.Fatalf("err = %v, want %v", err, tc.err)
}
})
}
}
func TestAccessTierQuotaInvalid(t *testing.T) {
lc, err := ParseLifecycleConfig(strings.NewReader(`<LifecycleConfiguration>
<AccessTierQuota>not-a-size</AccessTierQuota>
<Rule><ID>r</ID><Status>Enabled</Status><Expiration><Days>3</Days></Expiration></Rule>
</LifecycleConfiguration>`))
if err != nil {
t.Fatalf("parse: %v", err)
}
if err := lc.Validate(lock.Retention{}); err != errAccessInvalidQuotaSize {
t.Fatalf("err = %v, want %v", err, errAccessInvalidQuotaSize)
}
// An invalid quota that somehow reached the evaluator means "unlimited",
// never "zero bytes allowed".
if got := lc.AccessQuotaBytes(); got != 0 {
t.Fatalf("quota = %d, want 0 (unlimited)", got)
}
}
func TestAccessTransitionBadDuration(t *testing.T) {
_, err := ParseLifecycleConfig(strings.NewReader(`<LifecycleConfiguration><Rule>
<ID>r</ID><Status>Enabled</Status>
<AccessTransition><Window>ten minutes</Window><PromoteAfterAccesses>1</PromoteAfterAccesses></AccessTransition>
</Rule></LifecycleConfiguration>`))
if err == nil {
t.Fatal("expected a parse error for a malformed duration")
}
}
// AccessRule must reuse the standard rule filtering: prefix, tags, size and
// Status all have to be honored.
func TestAccessRuleFiltering(t *testing.T) {
lc, err := ParseLifecycleConfig(strings.NewReader(accessTieringXML))
if err != nil {
t.Fatalf("parse: %v", err)
}
tests := []struct {
name string
obj ObjectOpts
want bool
}{
{"match", ObjectOpts{Name: "logs/a.log", Size: 1 << 20, IsLatest: true}, true},
{"wrong prefix", ObjectOpts{Name: "data/a.log", Size: 1 << 20, IsLatest: true}, false},
{"too small", ObjectOpts{Name: "logs/a.log", Size: 1024, IsLatest: true}, false},
{"no name", ObjectOpts{Size: 1 << 20}, false},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
_, id, ok := lc.AccessRule(tc.obj)
if ok != tc.want {
t.Fatalf("ok = %v, want %v", ok, tc.want)
}
if ok && id != "hot-logs" {
t.Fatalf("ruleID = %q, want hot-logs", id)
}
})
}
lc.Rules[0].Status = Disabled
if _, _, ok := lc.AccessRule(ObjectOpts{Name: "logs/a.log", Size: 1 << 20, IsLatest: true}); ok {
t.Fatal("disabled rule still matched")
}
if lc.HasAccessTransition() {
t.Fatal("HasAccessTransition = true with only a disabled rule")
}
}
func TestAccessTransitionCountsAsActiveRule(t *testing.T) {
lc, err := ParseLifecycleConfig(strings.NewReader(accessTieringXML))
if err != nil {
t.Fatal(err)
}
if !lc.HasActiveRules("logs/2026") {
t.Fatal("access-only lifecycle rule was not active for its prefix")
}
if lc.HasActiveRules("data/") {
t.Fatal("access rule was active outside its prefix")
}
}
+62 -1
View File
@@ -26,6 +26,7 @@ import (
"strings"
"time"
"github.com/dustin/go-humanize"
"github.com/google/uuid"
"github.com/minio/minio/internal/bucket/object/lock"
"github.com/minio/minio/internal/bucket/replication"
@@ -101,11 +102,56 @@ func (a Action) Delete() bool {
// Lifecycle - Configuration for bucket lifecycle.
type Lifecycle struct {
XMLName xml.Name `xml:"LifecycleConfiguration"`
XMLName xml.Name `xml:"LifecycleConfiguration"`
// AccessTierQuota caps how many bytes of this bucket access-based ILM
// may keep on the fastest pool, e.g. "500GiB". Empty means unlimited.
// It is bucket-wide rather than per-rule so it cannot be declared
// inconsistently by two rules matching the same object.
AccessTierQuota string `xml:"AccessTierQuota,omitempty"`
Rules []Rule `xml:"Rule"`
ExpiryUpdatedAt *time.Time `xml:"ExpiryUpdatedAt,omitempty"`
}
// HasAccessTransition returns 'true' if any enabled rule carries a usable
// AccessTransition. Used as a cheap per-bucket gate before consulting the
// access tracker.
func (lc Lifecycle) HasAccessTransition() bool {
for _, rule := range lc.Rules {
if rule.Status == Disabled {
continue
}
if !rule.AccessTransition.IsNull() {
return true
}
}
return false
}
// AccessRule returns the first enabled rule matching obj that carries a usable
// AccessTransition, along with its rule ID.
func (lc Lifecycle) AccessRule(obj ObjectOpts) (AccessTransition, string, bool) {
for _, rule := range lc.FilterRules(obj) {
if !rule.AccessTransition.IsNull() {
return rule.AccessTransition, rule.ID, true
}
}
return AccessTransition{}, "", false
}
// AccessQuotaBytes returns the bucket-wide fast-pool byte cap, 0 meaning
// unlimited. The value is validated at PUT time, so a parse failure here is
// treated as unlimited rather than as an error.
func (lc Lifecycle) AccessQuotaBytes() uint64 {
if lc.AccessTierQuota == "" {
return 0
}
sz, err := humanize.ParseBytes(lc.AccessTierQuota)
if err != nil {
return 0
}
return sz
}
// HasTransition returns 'true' if lifecycle document has Transition enabled.
func (lc Lifecycle) HasTransition() bool {
for _, rule := range lc.Rules {
@@ -158,6 +204,12 @@ func (lc *Lifecycle) UnmarshalXML(d *xml.Decoder, start xml.StartElement) (err e
return err
}
lc.ExpiryUpdatedAt = &t
case "AccessTierQuota":
var q string
if err = d.DecodeElement(&q, &se); err != nil {
return err
}
lc.AccessTierQuota = q
default:
return xml.UnmarshalError(fmt.Sprintf("expected element type <Rule> but have <%s>", se.Name.Local))
}
@@ -208,6 +260,9 @@ func (lc Lifecycle) HasActiveRules(prefix string) bool {
if !rule.Transition.IsNull() { // this allows for Transition.Days to be zero.
return true
}
if !rule.AccessTransition.IsNull() {
return true
}
}
return false
}
@@ -248,6 +303,12 @@ func (lc Lifecycle) Validate(lr lock.Retention) error {
return errLifecycleNoRule
}
if lc.AccessTierQuota != "" {
if _, err := humanize.ParseBytes(lc.AccessTierQuota); err != nil {
return errAccessInvalidQuotaSize
}
}
// Validate all the rules in the lifecycle config
for _, r := range lc.Rules {
if err := r.Validate(); err != nil {
+5 -1
View File
@@ -41,6 +41,7 @@ type Rule struct {
Expiration Expiration `xml:"Expiration,omitempty"`
Transition Transition `xml:"Transition,omitempty"`
DelMarkerExpiration DelMarkerExpiration `xml:"DelMarkerExpiration,omitempty"`
AccessTransition AccessTransition `xml:"AccessTransition,omitempty"`
// FIXME: add a type to catch unsupported AbortIncompleteMultipartUpload AbortIncompleteMultipartUpload `xml:"AbortIncompleteMultipartUpload,omitempty"`
NoncurrentVersionExpiration NoncurrentVersionExpiration `xml:"NoncurrentVersionExpiration,omitempty"`
NoncurrentVersionTransition NoncurrentVersionTransition `xml:"NoncurrentVersionTransition,omitempty"`
@@ -171,10 +172,13 @@ func (r Rule) Validate() error {
if err := r.validateNoncurrentTransition(); err != nil {
return err
}
if err := r.AccessTransition.Validate(); err != nil {
return err
}
if (!r.Filter.Tag.IsEmpty() || len(r.Filter.And.Tags) != 0) && !r.DelMarkerExpiration.Empty() {
return errInvalidRuleDelMarkerExpiration
}
if !r.Expiration.set && !r.Transition.set && !r.NoncurrentVersionExpiration.set && !r.NoncurrentVersionTransition.set && r.DelMarkerExpiration.Empty() {
if !r.Expiration.set && !r.Transition.set && !r.NoncurrentVersionExpiration.set && !r.NoncurrentVersionTransition.set && r.DelMarkerExpiration.Empty() && !r.AccessTransition.set {
return errXMLNotWellFormed
}
return nil