minio/cmd/erasure-common.go

176 lines
4.6 KiB
Go
Raw Normal View History

// Copyright (c) 2015-2021 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 cmd
import (
"context"
"fmt"
"io"
"math/rand"
"sync"
"time"
2023-09-04 15:57:37 -04:00
"github.com/minio/pkg/v2/sync/errgroup"
)
feat: decommission feature for pools (#14012) ``` λ mc admin decommission start alias/ http://minio{1...2}/data{1...4} ``` ``` λ mc admin decommission status alias/ ┌─────┬─────────────────────────────────┬──────────────────────────────────┬────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Active │ │ 2nd │ http://minio{3...4}/data{1...4} │ 329 GiB (used) / 421 GiB (total) │ Active │ └─────┴─────────────────────────────────┴──────────────────────────────────┴────────┘ ``` ``` λ mc admin decommission status alias/ http://minio{1...2}/data{1...4} Progress: ===================> [1GiB/sec] [15%] [4TiB/50TiB] Time Remaining: 4 hours (started 3 hours ago) ``` ``` λ mc admin decommission status alias/ http://minio{1...2}/data{1...4} ERROR: This pool is not scheduled for decommissioning currently. ``` ``` λ mc admin decommission cancel alias/ ┌─────┬─────────────────────────────────┬──────────────────────────────────┬──────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Draining │ └─────┴─────────────────────────────────┴──────────────────────────────────┴──────────┘ ``` > NOTE: Canceled decommission will not make the pool active again, since we might have > Potentially partial duplicate content on the other pools, to avoid this scenario be > very sure to start decommissioning as a planned activity. ``` λ mc admin decommission cancel alias/ http://minio{1...2}/data{1...4} ┌─────┬─────────────────────────────────┬──────────────────────────────────┬────────────────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Draining(Canceled) │ └─────┴─────────────────────────────────┴──────────────────────────────────┴────────────────────┘ ```
2022-01-10 12:07:49 -05:00
func (er erasureObjects) getOnlineDisks() (newDisks []StorageAPI) {
disks := er.getDisks()
var wg sync.WaitGroup
var mu sync.Mutex
r := rand.New(rand.NewSource(time.Now().UnixNano()))
for _, i := range r.Perm(len(disks)) {
feat: decommission feature for pools (#14012) ``` λ mc admin decommission start alias/ http://minio{1...2}/data{1...4} ``` ``` λ mc admin decommission status alias/ ┌─────┬─────────────────────────────────┬──────────────────────────────────┬────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Active │ │ 2nd │ http://minio{3...4}/data{1...4} │ 329 GiB (used) / 421 GiB (total) │ Active │ └─────┴─────────────────────────────────┴──────────────────────────────────┴────────┘ ``` ``` λ mc admin decommission status alias/ http://minio{1...2}/data{1...4} Progress: ===================> [1GiB/sec] [15%] [4TiB/50TiB] Time Remaining: 4 hours (started 3 hours ago) ``` ``` λ mc admin decommission status alias/ http://minio{1...2}/data{1...4} ERROR: This pool is not scheduled for decommissioning currently. ``` ``` λ mc admin decommission cancel alias/ ┌─────┬─────────────────────────────────┬──────────────────────────────────┬──────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Draining │ └─────┴─────────────────────────────────┴──────────────────────────────────┴──────────┘ ``` > NOTE: Canceled decommission will not make the pool active again, since we might have > Potentially partial duplicate content on the other pools, to avoid this scenario be > very sure to start decommissioning as a planned activity. ``` λ mc admin decommission cancel alias/ http://minio{1...2}/data{1...4} ┌─────┬─────────────────────────────────┬──────────────────────────────────┬────────────────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Draining(Canceled) │ └─────┴─────────────────────────────────┴──────────────────────────────────┴────────────────────┘ ```
2022-01-10 12:07:49 -05:00
i := i
wg.Add(1)
go func() {
defer wg.Done()
if disks[i] == nil {
feat: decommission feature for pools (#14012) ``` λ mc admin decommission start alias/ http://minio{1...2}/data{1...4} ``` ``` λ mc admin decommission status alias/ ┌─────┬─────────────────────────────────┬──────────────────────────────────┬────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Active │ │ 2nd │ http://minio{3...4}/data{1...4} │ 329 GiB (used) / 421 GiB (total) │ Active │ └─────┴─────────────────────────────────┴──────────────────────────────────┴────────┘ ``` ``` λ mc admin decommission status alias/ http://minio{1...2}/data{1...4} Progress: ===================> [1GiB/sec] [15%] [4TiB/50TiB] Time Remaining: 4 hours (started 3 hours ago) ``` ``` λ mc admin decommission status alias/ http://minio{1...2}/data{1...4} ERROR: This pool is not scheduled for decommissioning currently. ``` ``` λ mc admin decommission cancel alias/ ┌─────┬─────────────────────────────────┬──────────────────────────────────┬──────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Draining │ └─────┴─────────────────────────────────┴──────────────────────────────────┴──────────┘ ``` > NOTE: Canceled decommission will not make the pool active again, since we might have > Potentially partial duplicate content on the other pools, to avoid this scenario be > very sure to start decommissioning as a planned activity. ``` λ mc admin decommission cancel alias/ http://minio{1...2}/data{1...4} ┌─────┬─────────────────────────────────┬──────────────────────────────────┬────────────────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Draining(Canceled) │ └─────┴─────────────────────────────────┴──────────────────────────────────┴────────────────────┘ ```
2022-01-10 12:07:49 -05:00
return
}
di, err := disks[i].DiskInfo(context.Background(), DiskInfoOptions{})
feat: decommission feature for pools (#14012) ``` λ mc admin decommission start alias/ http://minio{1...2}/data{1...4} ``` ``` λ mc admin decommission status alias/ ┌─────┬─────────────────────────────────┬──────────────────────────────────┬────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Active │ │ 2nd │ http://minio{3...4}/data{1...4} │ 329 GiB (used) / 421 GiB (total) │ Active │ └─────┴─────────────────────────────────┴──────────────────────────────────┴────────┘ ``` ``` λ mc admin decommission status alias/ http://minio{1...2}/data{1...4} Progress: ===================> [1GiB/sec] [15%] [4TiB/50TiB] Time Remaining: 4 hours (started 3 hours ago) ``` ``` λ mc admin decommission status alias/ http://minio{1...2}/data{1...4} ERROR: This pool is not scheduled for decommissioning currently. ``` ``` λ mc admin decommission cancel alias/ ┌─────┬─────────────────────────────────┬──────────────────────────────────┬──────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Draining │ └─────┴─────────────────────────────────┴──────────────────────────────────┴──────────┘ ``` > NOTE: Canceled decommission will not make the pool active again, since we might have > Potentially partial duplicate content on the other pools, to avoid this scenario be > very sure to start decommissioning as a planned activity. ``` λ mc admin decommission cancel alias/ http://minio{1...2}/data{1...4} ┌─────┬─────────────────────────────────┬──────────────────────────────────┬────────────────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Draining(Canceled) │ └─────┴─────────────────────────────────┴──────────────────────────────────┴────────────────────┘ ```
2022-01-10 12:07:49 -05:00
if err != nil || di.Healing {
// - Do not consume disks which are not reachable
// unformatted or simply not accessible for some reason.
//
// - Do not consume disks which are being healed
//
// - Future: skip busy disks
return
}
mu.Lock()
newDisks = append(newDisks, disks[i])
feat: decommission feature for pools (#14012) ``` λ mc admin decommission start alias/ http://minio{1...2}/data{1...4} ``` ``` λ mc admin decommission status alias/ ┌─────┬─────────────────────────────────┬──────────────────────────────────┬────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Active │ │ 2nd │ http://minio{3...4}/data{1...4} │ 329 GiB (used) / 421 GiB (total) │ Active │ └─────┴─────────────────────────────────┴──────────────────────────────────┴────────┘ ``` ``` λ mc admin decommission status alias/ http://minio{1...2}/data{1...4} Progress: ===================> [1GiB/sec] [15%] [4TiB/50TiB] Time Remaining: 4 hours (started 3 hours ago) ``` ``` λ mc admin decommission status alias/ http://minio{1...2}/data{1...4} ERROR: This pool is not scheduled for decommissioning currently. ``` ``` λ mc admin decommission cancel alias/ ┌─────┬─────────────────────────────────┬──────────────────────────────────┬──────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Draining │ └─────┴─────────────────────────────────┴──────────────────────────────────┴──────────┘ ``` > NOTE: Canceled decommission will not make the pool active again, since we might have > Potentially partial duplicate content on the other pools, to avoid this scenario be > very sure to start decommissioning as a planned activity. ``` λ mc admin decommission cancel alias/ http://minio{1...2}/data{1...4} ┌─────┬─────────────────────────────────┬──────────────────────────────────┬────────────────────┐ │ ID │ Pools │ Capacity │ Status │ │ 1st │ http://minio{1...2}/data{1...4} │ 439 GiB (used) / 561 GiB (total) │ Draining(Canceled) │ └─────┴─────────────────────────────────┴──────────────────────────────────┴────────────────────┘ ```
2022-01-10 12:07:49 -05:00
mu.Unlock()
}()
}
wg.Wait()
return newDisks
}
func (er erasureObjects) getOnlineLocalDisks() (newDisks []StorageAPI) {
disks := er.getOnlineDisks()
// Based on the random shuffling return back randomized disks.
r := rand.New(rand.NewSource(time.Now().UnixNano()))
for _, i := range r.Perm(len(disks)) {
if disks[i] != nil && disks[i].IsLocal() {
newDisks = append(newDisks, disks[i])
}
}
return newDisks
}
func (er erasureObjects) getLocalDisks() (newDisks []StorageAPI) {
disks := er.getDisks()
// Based on the random shuffling return back randomized disks.
r := rand.New(rand.NewSource(time.Now().UnixNano()))
for _, i := range r.Perm(len(disks)) {
if disks[i] != nil && disks[i].IsLocal() {
newDisks = append(newDisks, disks[i])
}
}
return newDisks
}
// readMultipleFiles Reads raw data from all specified files from all disks.
func readMultipleFiles(ctx context.Context, disks []StorageAPI, req ReadMultipleReq, readQuorum int) ([]ReadMultipleResp, error) {
resps := make([]chan ReadMultipleResp, len(disks))
for i := range resps {
resps[i] = make(chan ReadMultipleResp, len(req.Files))
}
g := errgroup.WithNErrs(len(disks))
// Read files in parallel across disks.
for index := range disks {
index := index
g.Go(func() (err error) {
if disks[index] == nil {
return errDiskNotFound
}
return disks[index].ReadMultiple(ctx, req, resps[index])
}, index)
}
dataArray := make([]ReadMultipleResp, 0, len(req.Files))
// Merge results. They should come in order from each.
for _, wantFile := range req.Files {
quorum := 0
toAdd := ReadMultipleResp{
Bucket: req.Bucket,
Prefix: req.Prefix,
File: wantFile,
}
for i := range resps {
if disks[i] == nil {
continue
}
select {
case <-ctx.Done():
case gotFile, ok := <-resps[i]:
if !ok {
continue
}
if gotFile.Error != "" || !gotFile.Exists {
continue
}
if gotFile.File != wantFile || gotFile.Bucket != req.Bucket || gotFile.Prefix != req.Prefix {
continue
}
quorum++
if toAdd.Modtime.After(gotFile.Modtime) || len(gotFile.Data) < len(toAdd.Data) {
// Pick latest, or largest to avoid possible truncated entries.
continue
}
toAdd = gotFile
}
}
if quorum < readQuorum {
toAdd.Exists = false
toAdd.Error = errErasureReadQuorum.Error()
toAdd.Data = nil
}
dataArray = append(dataArray, toAdd)
}
ignoredErrs := []error{
errFileNotFound,
errVolumeNotFound,
errFileVersionNotFound,
io.ErrUnexpectedEOF, // some times we would read without locks, ignore these errors
io.EOF, // some times we would read without locks, ignore these errors
context.DeadlineExceeded,
context.Canceled,
}
ignoredErrs = append(ignoredErrs, objectOpIgnoredErrs...)
errs := g.Wait()
for index, err := range errs {
if err == nil {
continue
}
if !IsErr(err, ignoredErrs...) {
storageLogOnceIf(ctx, fmt.Errorf("Drive %s, path (%s/%s) returned an error (%w)",
disks[index], req.Bucket, req.Prefix, err),
disks[index].String())
}
}
// Return all the metadata.
return dataArray, nil
}