featurebase/dax/workerjob.go
Travis Turner 8fca15e936
RetryWithTx (#2348)
* First pass at RetryWithTx

* Refactor RetryWithTx to take a writable bool (instead of reads, writes)

* Implment DirectiveMethodDiff

This commit adds support for a Directive to contain only the diffs (as
opposed to the full Directive).

* Update controller tests to allow for DirectiveMethodDiff (over Full)

* Update RetryWithTx to retry on duplicate key constraint.

If two concurrent processes call IngestShard() for the same shard, both
were trying to insert the same job into the jobs table. That resulted in
a duplicate key error from the database. We want to include that error
in the list of errors for which RetryWithTx should retry.

* Remove unused method: Directive.TranslatePartitions()

* Replace query in a loop with a single query

We had a query which was looking to see if a job already existed. That
query was inside a loop, and could potentially generate 256 queries (for
example). This commit replaces that logic so that we use a single query
wiht an `IN ()` clause.

* Convert to directive version-by-address

This commit uses a separate directive version per address. It moves the
version get/increment back inside the buildDirective method so that if
two concurrent processes are building a directive for the same address,
one of them will get rolled back trying to commit the version update.

* Migration for directive version by address

* Add a comment about DirectiveVersion lock/unlock logic

* Remove AddLastWins

* fix linter

* handle error in walkdir

* fix test failures from removing AddLastWins
2023-03-30 20:54:37 -05:00

204 lines
4.4 KiB
Go

package dax
import (
"sort"
"strings"
)
// Job is a generic identifier used to represent a specific role assigned to a
// worker.
type Job string
// Job allows a Job to implement the Jobber interface.
func (j Job) Job() Job {
return j
}
// Jobs is a slice of Job.
type Jobs []Job
type Jobber interface {
Job() Job
}
// WorkerInfo represents a Worker and the Jobs to which it has been assigned.
type WorkerInfo struct {
Address Address
Jobs []Job
}
// WorkerInfos is a sortable slice of WorkerInfo.
type WorkerInfos []WorkerInfo
func (w WorkerInfos) Len() int { return len(w) }
func (w WorkerInfos) Less(i, j int) bool { return w[i].Address < w[j].Address }
func (w WorkerInfos) Swap(i, j int) { w[i], w[j] = w[j], w[i] }
// WorkerDiff represents the changes made to a Worker following the latest
// event.
type WorkerDiff struct {
Address Address
AddedJobs []Job
RemovedJobs []Job
}
// Add adds w2 to w. It panics if w and w2 don't have the same worker
// ID. Any job that is added and then removed or removed and then
// added cancels out and won't be present after add is called.
func (w *WorkerDiff) Add(w2 WorkerDiff) {
if w.Address != w2.Address {
panic("can't add worker diffs from different workers")
}
a1 := NewSet(w.AddedJobs...)
a2 := NewSet(w2.AddedJobs...)
r1 := NewSet(w.RemovedJobs...)
r2 := NewSet(w2.RemovedJobs...)
// final Added is (a1 - r2) + (a2 - r1)
// this is because anything that is removed and then added, or added and
// then removed cancels out
added := a1.Minus(r2).Plus(a2.Minus(r1))
// final removed is (r1 - a2) + (r2 - a1)
removed := r1.Minus(a2).Plus(r2.Minus(a1))
w.AddedJobs = added.Sorted()
w.RemovedJobs = removed.Sorted()
}
// WorkerDiffs is a sortable slice of WorkerDiff.
type WorkerDiffs []WorkerDiff
func (w WorkerDiffs) Len() int { return len(w) }
func (w WorkerDiffs) Less(i, j int) bool { return w[i].Address < w[j].Address }
func (w WorkerDiffs) Swap(i, j int) { w[i], w[j] = w[j], w[i] }
func (w WorkerDiffs) Apply(o WorkerDiffs) WorkerDiffs {
out := make(WorkerDiffs, len(w))
// m is a map which makes it easy for us to match on Address between the two
// WorkerDiffs; i.e. without doing nested loops.
m := make(map[Address]int)
for i := range w {
out[i] = w[i]
m[out[i].Address] = i
}
for i := range o {
oAddr := o[i].Address
if idx, ok := m[oAddr]; ok {
// merge these
out[idx].Add(o[i])
continue
}
// Append any items from o which don't exist in w.
out = append(out, o[i])
}
sort.Sort(out)
return out
}
// Set is a set of stringy items.
type Set[K ~string] map[K]struct{}
func NewSet[K ~string](stuff ...K) Set[K] {
s := make(map[K]struct{})
for _, thing := range stuff {
s[thing] = struct{}{}
}
return Set[K](s)
}
// Count returns the number of items in the set.
func (s Set[K]) Count() int {
return len(s)
}
// Contains returns true if k is in the set.
func (s Set[K]) Contains(k K) bool {
_, ok := s[k]
return ok
}
// Add adds k to the set.
func (s Set[K]) Add(k K) {
s[k] = struct{}{}
}
// Remove removes k from the set.
func (s Set[K]) Remove(k K) {
delete(s, k)
}
// RemoveByPrefix removes all items from Set that have the given prefix.
func (s Set[K]) RemoveByPrefix(prefix string) []K {
ret := make([]K, 0)
for k := range s {
if strings.HasPrefix(string(k), prefix) {
ret = append(ret, k)
delete(s, k)
}
}
return ret
}
// Slice returns a slice containing each member of the set in an undefined order.
func (s Set[K]) Slice() []K {
ret := make([]K, 0, len(s))
for k := range s {
ret = append(ret, k)
}
return ret
}
// Copy creates a copy of the set.
func (s Set[K]) Copy() Set[K] {
ret := make(map[K]struct{})
for k, v := range s {
ret[k] = v
}
return ret
}
// Minus returns the a copy of s without any members which are also in s2.
func (s Set[K]) Minus(s2 Set[K]) Set[K] {
ret := make(map[K]struct{})
for k := range s {
if _, ok := s2[k]; !ok {
ret[k] = struct{}{}
}
}
return ret
}
// Plus returns a copy of s that also contains all members of s2.
func (s Set[K]) Plus(s2 Set[K]) Set[K] {
ret := s.Copy()
for k := range s2 {
ret[k] = struct{}{}
}
return ret
}
// Merge adds the members of s2 to s.
func (s Set[K]) Merge(s2 Set[K]) {
for k, v := range s2 {
s[k] = v
}
}
// Sorted returns Set[K] as a sorted slice of K.
func (s Set[K]) Sorted() []K {
js := make([]K, 0, len(s))
for j := range s {
js = append(js, j)
}
sort.Slice(js, func(i, j int) bool {
return js[i] < js[j]
})
return js
}