| 1 | // SPDX-License-Identifier: GPL-3.0-or-later |
| 2 | |
| 3 | // Package vnoderegistry tracks v2 vnode HOST_DEFINE metadata shared across jobs. |
| 4 | package vnoderegistry |
| 5 | |
| 6 | import ( |
| 7 | "fmt" |
| 8 | "maps" |
| 9 | "slices" |
| 10 | "sort" |
| 11 | "strconv" |
| 12 | "strings" |
| 13 | "sync" |
| 14 | |
| 15 | "github.com/netdata/netdata/go/plugins/pkg/netdataapi" |
| 16 | "github.com/netdata/netdata/go/plugins/plugin/framework/chartemit" |
| 17 | ) |
| 18 | |
| 19 | const maxReportedMetadataStatesPerGUID = 64 |
| 20 | |
| 21 | // Owner identifies one runtime owner of a vnode GUID. |
| 22 | // |
| 23 | // Jobruntime v2 uses stable per-job/per-scope owner IDs so a job can release |
| 24 | // registry ownership after it has emitted cleanup for the corresponding scope. |
| 25 | type Owner string |
| 26 | |
| 27 | // Registration reports the result of registering vnode metadata for an owner. |
| 28 | type Registration struct { |
| 29 | // Info is the metadata retained by the registry after registration. |
| 30 | Info netdataapi.HostInfo |
| 31 | |
| 32 | // Previous is set when an existing GUID's metadata was updated. |
| 33 | Previous netdataapi.HostInfo |
| 34 | |
| 35 | // NeedDefine is true when this registration created or updated the registry entry. |
| 36 | NeedDefine bool |
| 37 | |
| 38 | // OwnerAdded is true when this call added a new owner record. |
| 39 | OwnerAdded bool |
| 40 | |
| 41 | // MetadataUpdated is true when Info replaced previously retained metadata. |
| 42 | MetadataUpdated bool |
| 43 | |
| 44 | // UpdateFirstSeen is true only for the first occurrence of a distinct metadata |
| 45 | // transition. Callers should use this to avoid log spam. |
| 46 | UpdateFirstSeen bool |
| 47 | |
| 48 | revision uint64 |
| 49 | previousRevision uint64 |
| 50 | } |
| 51 | |
| 52 | type Registry struct { |
| 53 | mu sync.Mutex |
| 54 | entries map[string]*entry |
| 55 | } |
| 56 | |
| 57 | type entry struct { |
| 58 | info netdataapi.HostInfo |
| 59 | revision uint64 |
| 60 | owners map[Owner]struct{} |
| 61 | reportedStates map[string]struct{} |
| 62 | reportedOrder []string |
| 63 | } |
| 64 | |
| 65 | // New returns an empty concurrency-safe vnode registry. |
| 66 | func New() *Registry { |
| 67 | return &Registry{entries: make(map[string]*entry)} |
| 68 | } |
| 69 | |
| 70 | // Register records that owner emits metrics under info.GUID. |
| 71 | // |
| 72 | // New metadata for an existing GUID replaces the retained metadata. This keeps |
| 73 | // runtime vnode updates simple: callers should log MetadataUpdated as a warning |
| 74 | // because repeated conflicting writers can still cause metadata flip-flop. |
| 75 | func (r *Registry) Register(owner Owner, info netdataapi.HostInfo) (Registration, error) { |
| 76 | if r == nil { |
| 77 | return Registration{}, fmt.Errorf("vnoderegistry: nil registry") |
| 78 | } |
| 79 | owner = Owner(strings.TrimSpace(string(owner))) |
| 80 | if owner == "" { |
| 81 | return Registration{}, fmt.Errorf("vnoderegistry: owner is required") |
| 82 | } |
| 83 | info, err := chartemit.PrepareHostInfo(info) |
| 84 | if err != nil { |
| 85 | return Registration{}, fmt.Errorf("vnoderegistry: %w", err) |
| 86 | } |
| 87 | |
| 88 | r.mu.Lock() |
| 89 | defer r.mu.Unlock() |
| 90 | |
| 91 | if r.entries == nil { |
| 92 | r.entries = make(map[string]*entry) |
| 93 | } |
| 94 | |
| 95 | ent, ok := r.entries[info.GUID] |
| 96 | if !ok { |
| 97 | ent = &entry{ |
| 98 | info: cloneHostInfo(info), |
| 99 | revision: 1, |
| 100 | owners: map[Owner]struct{}{owner: {}}, |
| 101 | reportedStates: make(map[string]struct{}), |
| 102 | } |
| 103 | r.entries[info.GUID] = ent |
| 104 | return Registration{ |
| 105 | Info: cloneHostInfo(ent.info), |
| 106 | NeedDefine: true, |
| 107 | OwnerAdded: true, |
| 108 | revision: ent.revision, |
| 109 | }, nil |
| 110 | } |
| 111 | |
| 112 | _, hadOwner := ent.owners[owner] |
| 113 | ent.owners[owner] = struct{}{} |
| 114 | |
| 115 | result := Registration{ |
| 116 | Info: cloneHostInfo(ent.info), |
| 117 | OwnerAdded: !hadOwner, |
| 118 | revision: ent.revision, |
| 119 | } |
| 120 | if hostInfoEqual(ent.info, info) { |
| 121 | return result, nil |
| 122 | } |
| 123 | |
| 124 | previous := cloneHostInfo(ent.info) |
| 125 | previousRevision := ent.revision |
| 126 | ent.info = cloneHostInfo(info) |
| 127 | ent.revision++ |
| 128 | result.Info = cloneHostInfo(ent.info) |
| 129 | result.Previous = previous |
| 130 | result.revision = ent.revision |
| 131 | result.previousRevision = previousRevision |
| 132 | result.NeedDefine = true |
| 133 | result.MetadataUpdated = true |
| 134 | |
| 135 | updateKey := hostInfoFingerprint(info) |
| 136 | if markReportedState(ent, updateKey) { |
| 137 | result.UpdateFirstSeen = true |
| 138 | } |
| 139 | return result, nil |
| 140 | } |
| 141 | |
| 142 | // Rollback undoes a registration that has not been emitted successfully. |
| 143 | // |
| 144 | // Rollback is best-effort: if another registration changed the same GUID after |
| 145 | // reg, the metadata restore is skipped to avoid undoing a later writer. |
| 146 | func (r *Registry) Rollback(owner Owner, reg Registration) { |
| 147 | if r == nil { |
| 148 | return |
| 149 | } |
| 150 | owner = Owner(strings.TrimSpace(string(owner))) |
| 151 | guid := strings.TrimSpace(reg.Info.GUID) |
| 152 | if owner == "" || guid == "" { |
| 153 | return |
| 154 | } |
| 155 | |
| 156 | r.mu.Lock() |
| 157 | defer r.mu.Unlock() |
| 158 | |
| 159 | ent, ok := r.entries[guid] |
| 160 | if !ok { |
| 161 | return |
| 162 | } |
| 163 | if reg.OwnerAdded { |
| 164 | delete(ent.owners, owner) |
| 165 | } |
| 166 | if reg.MetadataUpdated && ent.revision == reg.revision && hostInfoEqual(ent.info, reg.Info) { |
| 167 | ent.info = cloneHostInfo(reg.Previous) |
| 168 | ent.revision = reg.previousRevision |
| 169 | } |
| 170 | if len(ent.owners) == 0 { |
| 171 | delete(r.entries, guid) |
| 172 | } |
| 173 | } |
| 174 | |
| 175 | // Release removes one owner record for guid. It returns true when the GUID entry |
| 176 | // was removed because no owners remain. |
| 177 | func (r *Registry) Release(owner Owner, guid string) bool { |
| 178 | if r == nil { |
| 179 | return false |
| 180 | } |
| 181 | owner = Owner(strings.TrimSpace(string(owner))) |
| 182 | guid = strings.TrimSpace(guid) |
| 183 | if owner == "" || guid == "" { |
| 184 | return false |
| 185 | } |
| 186 | |
| 187 | r.mu.Lock() |
| 188 | defer r.mu.Unlock() |
| 189 | |
| 190 | ent, ok := r.entries[guid] |
| 191 | if !ok { |
| 192 | return false |
| 193 | } |
| 194 | delete(ent.owners, owner) |
| 195 | if len(ent.owners) > 0 { |
| 196 | return false |
| 197 | } |
| 198 | delete(r.entries, guid) |
| 199 | return true |
| 200 | } |
| 201 | |
| 202 | // Lookup returns the retained metadata for guid. |
| 203 | func (r *Registry) Lookup(guid string) (netdataapi.HostInfo, bool) { |
| 204 | if r == nil { |
| 205 | return netdataapi.HostInfo{}, false |
| 206 | } |
| 207 | guid = strings.TrimSpace(guid) |
| 208 | if guid == "" { |
| 209 | return netdataapi.HostInfo{}, false |
| 210 | } |
| 211 | |
| 212 | r.mu.Lock() |
| 213 | defer r.mu.Unlock() |
| 214 | |
| 215 | ent, ok := r.entries[guid] |
| 216 | if !ok { |
| 217 | return netdataapi.HostInfo{}, false |
| 218 | } |
| 219 | return cloneHostInfo(ent.info), true |
| 220 | } |
| 221 | |
| 222 | // Owners returns the sorted owner IDs currently registered for guid. |
| 223 | func (r *Registry) Owners(guid string) []Owner { |
| 224 | if r == nil { |
| 225 | return nil |
| 226 | } |
| 227 | guid = strings.TrimSpace(guid) |
| 228 | if guid == "" { |
| 229 | return nil |
| 230 | } |
| 231 | |
| 232 | r.mu.Lock() |
| 233 | defer r.mu.Unlock() |
| 234 | |
| 235 | ent, ok := r.entries[guid] |
| 236 | if !ok { |
| 237 | return nil |
| 238 | } |
| 239 | owners := make([]Owner, 0, len(ent.owners)) |
| 240 | for owner := range ent.owners { |
| 241 | owners = append(owners, owner) |
| 242 | } |
| 243 | slices.Sort(owners) |
| 244 | return owners |
| 245 | } |
| 246 | |
| 247 | // Len returns the number of retained GUID entries. |
| 248 | func (r *Registry) Len() int { |
| 249 | if r == nil { |
| 250 | return 0 |
| 251 | } |
| 252 | r.mu.Lock() |
| 253 | defer r.mu.Unlock() |
| 254 | return len(r.entries) |
| 255 | } |
| 256 | |
| 257 | func cloneHostInfo(info netdataapi.HostInfo) netdataapi.HostInfo { |
| 258 | return netdataapi.HostInfo{ |
| 259 | GUID: info.GUID, |
| 260 | Hostname: info.Hostname, |
| 261 | Labels: maps.Clone(info.Labels), |
| 262 | } |
| 263 | } |
| 264 | |
| 265 | func hostInfoEqual(left, right netdataapi.HostInfo) bool { |
| 266 | return left.GUID == right.GUID && |
| 267 | left.Hostname == right.Hostname && |
| 268 | maps.Equal(left.Labels, right.Labels) |
| 269 | } |
| 270 | |
| 271 | func hostInfoFingerprint(info netdataapi.HostInfo) string { |
| 272 | var b strings.Builder |
| 273 | writeHostInfoFingerprint(&b, info) |
| 274 | return b.String() |
| 275 | } |
| 276 | |
| 277 | func writeHostInfoFingerprint(b *strings.Builder, info netdataapi.HostInfo) { |
| 278 | writeFingerprintPart(b, info.GUID) |
| 279 | writeFingerprintPart(b, info.Hostname) |
| 280 | |
| 281 | keys := make([]string, 0, len(info.Labels)) |
| 282 | for key := range info.Labels { |
| 283 | keys = append(keys, key) |
| 284 | } |
| 285 | sort.Strings(keys) |
| 286 | for _, key := range keys { |
| 287 | writeFingerprintPart(b, key) |
| 288 | writeFingerprintPart(b, info.Labels[key]) |
| 289 | } |
| 290 | } |
| 291 | |
| 292 | func writeFingerprintPart(b *strings.Builder, value string) { |
| 293 | b.WriteString(strconv.Itoa(len(value))) |
| 294 | b.WriteByte(':') |
| 295 | b.WriteString(value) |
| 296 | b.WriteByte('\xff') |
| 297 | } |
| 298 | |
| 299 | func markReportedState(ent *entry, key string) bool { |
| 300 | if ent.reportedStates == nil { |
| 301 | ent.reportedStates = make(map[string]struct{}) |
| 302 | } |
| 303 | if _, seen := ent.reportedStates[key]; seen { |
| 304 | return false |
| 305 | } |
| 306 | if len(ent.reportedOrder) >= maxReportedMetadataStatesPerGUID { |
| 307 | evicted := ent.reportedOrder[0] |
| 308 | copy(ent.reportedOrder, ent.reportedOrder[1:]) |
| 309 | ent.reportedOrder = ent.reportedOrder[:len(ent.reportedOrder)-1] |
| 310 | delete(ent.reportedStates, evicted) |
| 311 | } |
| 312 | ent.reportedStates[key] = struct{}{} |
| 313 | ent.reportedOrder = append(ent.reportedOrder, key) |
| 314 | return true |
| 315 | } |