zrepl/platformtest/platformtest_ops.go
Christian Schwarz 58c08c855f new features: {resumable,encrypted,hold-protected} send-recv, last-received-hold
- **Resumable Send & Recv Support**
  No knobs required, automatically used where supported.
- **Hold-Protected Send & Recv**
  Automatic ZFS holds to ensure that we can always resume a replication step.
- **Encrypted Send & Recv Support** for OpenZFS native encryption.
  Configurable at the job level, i.e., for all filesystems a job is responsible for.
- **Receive-side hold on last received dataset**
  The counterpart to the replication cursor bookmark on the send-side.
  Ensures that incremental replication will always be possible between a sender and receiver.

Design Doc
----------

`replication/design.md` doc describes how we use ZFS holds and bookmarks to ensure that a single replication step is always resumable.

The replication algorithm described in the design doc introduces the notion of job IDs (please read the details on this design doc).
We reuse the job names for job IDs and use `JobID` type to ensure that a job name can be embedded into hold tags, bookmark names, etc.
This might BREAK CONFIG on upgrade.

Protocol Version Bump
---------------------

This commit makes backwards-incompatible changes to the replication/pdu protobufs.
Thus, bump the version number used in the protocol handshake.

Replication Cursor Format Change
--------------------------------

The new replication cursor bookmark format is: `#zrepl_CURSOR_G_${this.GUID}_J_${jobid}`
Including the GUID enables transaction-safe moving-forward of the cursor.
Including the job id enables that multiple sending jobs can send the same filesystem without interfering.
The `zrepl migrate replication-cursor:v1-v2` subcommand can be used to safely destroy old-format cursors once zrepl has created new-format cursors.

Changes in This Commit
----------------------

- package zfs
  - infrastructure for holds
  - infrastructure for resume token decoding
  - implement a variant of OpenZFS's `entity_namecheck` and use it for validation in new code
  - ZFSSendArgs to specify a ZFS send operation
    - validation code protects against malicious resume tokens by checking that the token encodes the same send parameters that the send-side would use if no resume token were available (i.e. same filesystem, `fromguid`, `toguid`)
  - RecvOptions support for `recv -s` flag
  - convert a bunch of ZFS operations to be idempotent
    - achieved through more differentiated error message scraping / additional pre-/post-checks

- package replication/pdu
  - add field for encryption to send request messages
  - add fields for resume handling to send & recv request messages
  - receive requests now contain `FilesystemVersion To` in addition to the filesystem into which the stream should be `recv`d into
    - can use `zfs recv $root_fs/$client_id/path/to/dataset@${To.Name}`, which enables additional validation after recv (i.e. whether `To.Guid` matched what we received in the stream)
    - used to set `last-received-hold`
- package replication/logic
  - introduce `PlannerPolicy` struct, currently only used to configure whether encrypted sends should be requested from the sender
  - integrate encryption and resume token support into `Step` struct

- package endpoint
  - move the concepts that endpoint builds on top of ZFS to a single file `endpoint/endpoint_zfs.go`
    - step-holds + step-bookmarks
    - last-received-hold
    - new replication cursor + old replication cursor compat code
  - adjust `endpoint/endpoint.go` handlers for
    - encryption
    - resumability
    - new replication cursor
    - last-received-hold

- client subcommand `zrepl holds list`: list all holds and hold-like bookmarks that zrepl thinks belong to it
- client subcommand `zrepl migrate replication-cursor:v1-v2`
2020-02-14 22:00:13 +01:00

296 lines
6.8 KiB
Go

package platformtest
import (
"bufio"
"bytes"
"context"
"fmt"
"io/ioutil"
"os"
"os/exec"
"strings"
"unicode"
)
type Execer interface {
RunExpectSuccessNoOutput(ctx context.Context, cmd string, args ...string) error
RunExpectFailureNoOutput(ctx context.Context, cmd string, args ...string) error
}
type Stmt interface {
Run(context context.Context, e Execer) error
}
type Op string
const (
AssertExists Op = "!E"
AssertNotExists Op = "!N"
Add Op = "+"
Del Op = "-"
RunCmd Op = "R"
DestroyRoot Op = "DESTROYROOT"
CreateRoot Op = "CREATEROOT"
)
type DestroyRootOp struct {
Path string
}
func (o *DestroyRootOp) Run(ctx context.Context, e Execer) error {
// early-exit if it doesn't exist
if err := e.RunExpectSuccessNoOutput(ctx, "zfs", "get", "-H", "name", o.Path); err != nil {
GetLog(ctx).WithField("root_ds", o.Path).Info("assume root ds doesn't exist")
return nil
}
return e.RunExpectSuccessNoOutput(ctx, "zfs", "destroy", "-r", o.Path)
}
type FSOp struct {
Op Op
Path string
Encrypted bool // only for Op=Add
}
func (o *FSOp) Run(ctx context.Context, e Execer) error {
switch o.Op {
case AssertExists:
return e.RunExpectSuccessNoOutput(ctx, "zfs", "get", "-H", "name", o.Path)
case AssertNotExists:
return e.RunExpectFailureNoOutput(ctx, "zfs", "get", "-H", "name", o.Path)
case Add:
opts := []string{"create"}
if o.Encrypted {
const passphraseFilePath = "/tmp/zreplplatformtest.encryption.passphrase"
const passphrase = "foobar2342"
err := ioutil.WriteFile(passphraseFilePath, []byte(passphrase), 0600)
if err != nil {
panic(err)
}
opts = append(opts,
"-o", "encryption=on",
"-o", "keylocation=file:///"+passphraseFilePath,
"-o", "keyformat=passphrase",
)
}
opts = append(opts, o.Path)
return e.RunExpectSuccessNoOutput(ctx, "zfs", opts...)
case Del:
return e.RunExpectSuccessNoOutput(ctx, "zfs", "destroy", o.Path)
default:
panic(o.Op)
}
}
type SnapOp struct {
Op Op
Path string
}
func (o *SnapOp) Run(ctx context.Context, e Execer) error {
switch o.Op {
case AssertExists:
return e.RunExpectSuccessNoOutput(ctx, "zfs", "get", "-H", "name", o.Path)
case AssertNotExists:
return e.RunExpectFailureNoOutput(ctx, "zfs", "get", "-H", "name", o.Path)
case Add:
return e.RunExpectSuccessNoOutput(ctx, "zfs", "snapshot", o.Path)
case Del:
return e.RunExpectSuccessNoOutput(ctx, "zfs", "destroy", o.Path)
default:
panic(o.Op)
}
}
type RunOp struct {
RootDS string
Script string
}
func (o *RunOp) Run(ctx context.Context, e Execer) error {
cmd := exec.CommandContext(ctx, "/usr/bin/env", "bash", "-c", o.Script)
cmd.Env = os.Environ()
cmd.Env = append(cmd.Env, fmt.Sprintf("ROOTDS=%s", o.RootDS))
log := GetLog(ctx).WithField("script", o.Script)
log.Info("start script")
defer log.Info("script done")
output, err := cmd.CombinedOutput()
if _, ok := err.(*exec.ExitError); err != nil && !ok {
panic(err)
}
log.Printf("script output:\n%s", output)
return err
}
type LineError struct {
Line string
What string
}
func (e LineError) Error() string {
return fmt.Sprintf("%q: %s", e.Line, e.What)
}
type RunKind int
const (
PanicErr RunKind = 1 << iota
RunAll
)
func Run(ctx context.Context, rk RunKind, rootds string, stmtsStr string) {
stmt, err := parseSequence(rootds, stmtsStr)
if err != nil {
panic(err)
}
execer := NewEx(GetLog(ctx))
for _, s := range stmt {
err := s.Run(ctx, execer)
if err == nil {
continue
}
if rk == PanicErr {
panic(err)
} else if rk == RunAll {
continue
} else {
panic(rk)
}
}
}
func isNoSpace(r rune) bool {
return !unicode.IsSpace(r)
}
func splitQuotedWords(data []byte, atEOF bool) (advance int, token []byte, err error) {
begin := bytes.IndexFunc(data, isNoSpace)
if begin == -1 {
return len(data), nil, nil
}
if data[begin] == '"' {
end := begin + 1
for end < len(data) {
endCandidate := bytes.Index(data[end:], []byte(`"`))
if endCandidate == -1 {
return 0, nil, nil
}
end += endCandidate
if data[end-1] != '\\' {
// unescaped quote, end of this string
// remove backslash-escapes
withBackslash := data[begin+1 : end]
withoutBaskslash := bytes.Replace(withBackslash, []byte("\\\""), []byte("\""), -1)
return end + 1, withoutBaskslash, nil
} else {
// continue to next quote
end += 1
}
}
} else {
endOffset := bytes.IndexFunc(data[begin:], unicode.IsSpace)
var end int
if endOffset == -1 {
if !atEOF {
return 0, nil, nil
} else {
end = len(data)
}
} else {
end = begin + endOffset
}
return end, data[begin:end], nil
}
return 0, nil, fmt.Errorf("unexpected")
}
func parseSequence(rootds, stmtsStr string) (stmts []Stmt, err error) {
scan := bufio.NewScanner(strings.NewReader(stmtsStr))
nextLine:
for scan.Scan() {
if len(bytes.TrimSpace(scan.Bytes())) == 0 {
continue
}
comps := bufio.NewScanner(bytes.NewReader(scan.Bytes()))
comps.Split(splitQuotedWords)
expectMoreTokens := func() error {
if !comps.Scan() {
return &LineError{scan.Text(), "unexpected EOL"}
}
return nil
}
// Op
if err := expectMoreTokens(); err != nil {
return nil, err
}
var op Op
switch comps.Text() {
case string(RunCmd):
script := strings.TrimPrefix(strings.TrimSpace(scan.Text()), string(RunCmd))
stmts = append(stmts, &RunOp{RootDS: rootds, Script: script})
continue nextLine
case string(DestroyRoot):
if comps.Scan() {
return nil, &LineError{scan.Text(), fmt.Sprintf("unexpected tokens at EOL")}
}
stmts = append(stmts, &DestroyRootOp{rootds})
continue nextLine
case string(CreateRoot):
if comps.Scan() {
return nil, &LineError{scan.Text(), fmt.Sprintf("unexpected tokens at EOL")}
}
stmts = append(stmts, &FSOp{Op: Add, Path: rootds})
continue nextLine
case string(Add):
op = Add
case string(Del):
op = Del
case string(AssertExists):
op = AssertExists
case string(AssertNotExists):
op = AssertNotExists
default:
return nil, &LineError{scan.Text(), fmt.Sprintf("invalid op %q", comps.Text())}
}
// FS / SNAP
if err := expectMoreTokens(); err != nil {
return nil, err
}
if strings.ContainsAny(comps.Text(), "@") {
stmts = append(stmts, &SnapOp{Op: op, Path: fmt.Sprintf("%s/%s", rootds, comps.Text())})
} else {
// FS
fs := comps.Text()
var encrypted bool = false
if op == Add {
if comps.Scan() {
t := comps.Text()
switch t {
case "encrypted":
encrypted = true
default:
panic(fmt.Sprintf("unexpected token %q", t))
}
}
}
stmts = append(stmts, &FSOp{
Op: op,
Path: fmt.Sprintf("%s/%s", rootds, fs),
Encrypted: encrypted,
})
}
if comps.Scan() {
return nil, &LineError{scan.Text(), fmt.Sprintf("unexpected tokens at EOL")}
}
}
return stmts, nil
}