open-vault/vendor/go.etcd.io/bbolt/page.go
Brian Kassouf ed14061578
Raft Storage Backend (#6888)
* Work on raft backend

* Add logstore locally

* Add encryptor and unsealable interfaces

* Add clustering support to raft

* Remove client and handler

* Bootstrap raft on init

* Cleanup raft logic a bit

* More raft work

* Work on TLS config

* More work on bootstrapping

* Fix build

* More work on bootstrapping

* More bootstrapping work

* fix build

* Remove consul dep

* Fix build

* merged oss/master into raft-storage

* Work on bootstrapping

* Get bootstrapping to work

* Clean up FMS and node-id

* Update local node ID logic

* Cleanup node-id change

* Work on snapshotting

* Raft: Add remove peer API (#906)

* Add remove peer API

* Add some comments

* Fix existing snapshotting (#909)

* Raft get peers API (#912)

* Read raft configuration

* address review feedback

* Use the Leadership Transfer API to step-down the active node (#918)

* Raft join and unseal using Shamir keys (#917)

* Raft join using shamir

* Store AEAD instead of master key

* Split the raft join process to answer the challenge after a successful unseal

* get the follower to standby state

* Make unseal work

* minor changes

* Some input checks

* reuse the shamir seal access instead of new default seal access

* refactor joinRaftSendAnswer function

* Synchronously send answer in auto-unseal case

* Address review feedback

* Raft snapshots (#910)

* Fix existing snapshotting

* implement the noop snapshotting

* Add comments and switch log libraries

* add some snapshot tests

* add snapshot test file

* add TODO

* More work on raft snapshotting

* progress on the ConfigStore strategy

* Don't use two buckets

* Update the snapshot store logic to hide the file logic

* Add more backend tests

* Cleanup code a bit

* [WIP] Raft recovery (#938)

* Add recovery functionality

* remove fmt.Printfs

* Fix a few fsm bugs

* Add max size value for raft backend (#942)

* Add max size value for raft backend

* Include physical.ErrValueTooLarge in the message

* Raft snapshot Take/Restore API  (#926)

* Inital work on raft snapshot APIs

* Always redirect snapshot install/download requests

* More work on the snapshot APIs

* Cleanup code a bit

* On restore handle special cases

* Use the seal to encrypt the sha sum file

* Add sealer mechanism and fix some bugs

* Call restore while state lock is held

* Send restore cb trigger through raft log

* Make error messages nicer

* Add test helpers

* Add snapshot test

* Add shamir unseal test

* Add more raft snapshot API tests

* Fix locking

* Change working to initalize

* Add underlying raw object to test cluster core

* Move leaderUUID to core

* Add raft TLS rotation logic (#950)

* Add TLS rotation logic

* Cleanup logic a bit

* Add/Remove from follower state on add/remove peer

* add comments

* Update more comments

* Update request_forwarding_service.proto

* Make sure we populate all nodes in the followerstate obj

* Update times

* Apply review feedback

* Add more raft config setting (#947)

* Add performance config setting

* Add more config options and fix tests

* Test Raft Recovery (#944)

* Test raft recovery

* Leave out a node during recovery

* remove unused struct

* Update physical/raft/snapshot_test.go

* Update physical/raft/snapshot_test.go

* fix vendoring

* Switch to new raft interface

* Remove unused files

* Switch a gogo -> proto instance

* Remove unneeded vault dep in go.sum

* Update helper/testhelpers/testhelpers.go

Co-Authored-By: Calvin Leung Huang <cleung2010@gmail.com>

* Update vault/cluster/cluster.go

* track active key within the keyring itself (#6915)

* track active key within the keyring itself

* lookup and store using the active key ID

* update docstring

* minor refactor

* Small text fixes (#6912)

* Update physical/raft/raft.go

Co-Authored-By: Calvin Leung Huang <cleung2010@gmail.com>

* review feedback

* Move raft logical system into separate file

* Update help text a bit

* Enforce cluster addr is set and use it for raft bootstrapping

* Fix tests

* fix http test panic

* Pull in latest raft-snapshot library

* Add comment
2019-06-20 12:14:58 -07:00

198 lines
4.8 KiB
Go

package bbolt
import (
"fmt"
"os"
"sort"
"unsafe"
)
const pageHeaderSize = int(unsafe.Offsetof(((*page)(nil)).ptr))
const minKeysPerPage = 2
const branchPageElementSize = int(unsafe.Sizeof(branchPageElement{}))
const leafPageElementSize = int(unsafe.Sizeof(leafPageElement{}))
const (
branchPageFlag = 0x01
leafPageFlag = 0x02
metaPageFlag = 0x04
freelistPageFlag = 0x10
)
const (
bucketLeafFlag = 0x01
)
type pgid uint64
type page struct {
id pgid
flags uint16
count uint16
overflow uint32
ptr uintptr
}
// typ returns a human readable page type string used for debugging.
func (p *page) typ() string {
if (p.flags & branchPageFlag) != 0 {
return "branch"
} else if (p.flags & leafPageFlag) != 0 {
return "leaf"
} else if (p.flags & metaPageFlag) != 0 {
return "meta"
} else if (p.flags & freelistPageFlag) != 0 {
return "freelist"
}
return fmt.Sprintf("unknown<%02x>", p.flags)
}
// meta returns a pointer to the metadata section of the page.
func (p *page) meta() *meta {
return (*meta)(unsafe.Pointer(&p.ptr))
}
// leafPageElement retrieves the leaf node by index
func (p *page) leafPageElement(index uint16) *leafPageElement {
n := &((*[0x7FFFFFF]leafPageElement)(unsafe.Pointer(&p.ptr)))[index]
return n
}
// leafPageElements retrieves a list of leaf nodes.
func (p *page) leafPageElements() []leafPageElement {
if p.count == 0 {
return nil
}
return ((*[0x7FFFFFF]leafPageElement)(unsafe.Pointer(&p.ptr)))[:]
}
// branchPageElement retrieves the branch node by index
func (p *page) branchPageElement(index uint16) *branchPageElement {
return &((*[0x7FFFFFF]branchPageElement)(unsafe.Pointer(&p.ptr)))[index]
}
// branchPageElements retrieves a list of branch nodes.
func (p *page) branchPageElements() []branchPageElement {
if p.count == 0 {
return nil
}
return ((*[0x7FFFFFF]branchPageElement)(unsafe.Pointer(&p.ptr)))[:]
}
// dump writes n bytes of the page to STDERR as hex output.
func (p *page) hexdump(n int) {
buf := (*[maxAllocSize]byte)(unsafe.Pointer(p))[:n]
fmt.Fprintf(os.Stderr, "%x\n", buf)
}
type pages []*page
func (s pages) Len() int { return len(s) }
func (s pages) Swap(i, j int) { s[i], s[j] = s[j], s[i] }
func (s pages) Less(i, j int) bool { return s[i].id < s[j].id }
// branchPageElement represents a node on a branch page.
type branchPageElement struct {
pos uint32
ksize uint32
pgid pgid
}
// key returns a byte slice of the node key.
func (n *branchPageElement) key() []byte {
buf := (*[maxAllocSize]byte)(unsafe.Pointer(n))
return (*[maxAllocSize]byte)(unsafe.Pointer(&buf[n.pos]))[:n.ksize]
}
// leafPageElement represents a node on a leaf page.
type leafPageElement struct {
flags uint32
pos uint32
ksize uint32
vsize uint32
}
// key returns a byte slice of the node key.
func (n *leafPageElement) key() []byte {
buf := (*[maxAllocSize]byte)(unsafe.Pointer(n))
return (*[maxAllocSize]byte)(unsafe.Pointer(&buf[n.pos]))[:n.ksize:n.ksize]
}
// value returns a byte slice of the node value.
func (n *leafPageElement) value() []byte {
buf := (*[maxAllocSize]byte)(unsafe.Pointer(n))
return (*[maxAllocSize]byte)(unsafe.Pointer(&buf[n.pos+n.ksize]))[:n.vsize:n.vsize]
}
// PageInfo represents human readable information about a page.
type PageInfo struct {
ID int
Type string
Count int
OverflowCount int
}
type pgids []pgid
func (s pgids) Len() int { return len(s) }
func (s pgids) Swap(i, j int) { s[i], s[j] = s[j], s[i] }
func (s pgids) Less(i, j int) bool { return s[i] < s[j] }
// merge returns the sorted union of a and b.
func (a pgids) merge(b pgids) pgids {
// Return the opposite slice if one is nil.
if len(a) == 0 {
return b
}
if len(b) == 0 {
return a
}
merged := make(pgids, len(a)+len(b))
mergepgids(merged, a, b)
return merged
}
// mergepgids copies the sorted union of a and b into dst.
// If dst is too small, it panics.
func mergepgids(dst, a, b pgids) {
if len(dst) < len(a)+len(b) {
panic(fmt.Errorf("mergepgids bad len %d < %d + %d", len(dst), len(a), len(b)))
}
// Copy in the opposite slice if one is nil.
if len(a) == 0 {
copy(dst, b)
return
}
if len(b) == 0 {
copy(dst, a)
return
}
// Merged will hold all elements from both lists.
merged := dst[:0]
// Assign lead to the slice with a lower starting value, follow to the higher value.
lead, follow := a, b
if b[0] < a[0] {
lead, follow = b, a
}
// Continue while there are elements in the lead.
for len(lead) > 0 {
// Merge largest prefix of lead that is ahead of follow[0].
n := sort.Search(len(lead), func(i int) bool { return lead[i] > follow[0] })
merged = append(merged, lead[:n]...)
if n >= len(lead) {
break
}
// Swap lead and follow.
lead, follow = follow, lead[n:]
}
// Append what's left in follow.
_ = append(merged, follow...)
}