New feature: per-VIP / per-backend runtime counters
* New GetVPPLBCounters RPC serving an in-process snapshot refreshed
by a 5s scrape loop (internal/vpp/lbstats.go). Each cycle pulls
the LB plugin's four SimpleCounters (next, first, untracked,
no-server) plus the FIB /net/route/to CombinedCounter for every
VIP and every backend host prefix via a single DumpStats call.
* FIB stats-index discovery via ip_route_lookup (internal/vpp/
fibstats.go); per-worker reduction happens in the collector.
* Prometheus collector exports vip_packets_total (kind label),
vip_route_{packets,bytes}_total, and backend_route_{packets,
bytes}_total. Metrics source interface extended with VIPStats /
BackendRouteStats; vpp.Client publishes snapshots via
atomic.Pointer and clears them on disconnect.
* New 'show vpp lb counters' CLI command. The 'show vpp lbstate'
and 'sync vpp lbstate' commands are restructured under 'show
vpp lb {state,counters}' / 'sync vpp lb state' to make room
for the new verb.
New feature: src-ip-sticky frontends
* New frontend YAML key 'src-ip-sticky' (bool). Plumbed through
config.Frontend, desiredVIP, and the lb_add_del_vip_v2 call.
* Reflected in gRPC FrontendInfo.src_ip_sticky and VPPLBVIP.
src_ip_sticky, and shown in 'show vpp lb state' output.
* Scraped back from VPP by parsing 'show lb vips verbose' through
cli_inband — lb_vip_details does not expose the flag. The same
scrape also recovers the LB pool index for each VIP, which the
stats-segment counters are keyed on. This is a documented
temporary workaround until VPP ships an lb_vip_v2_dump.
* src_ip_sticky cannot be mutated on a live VIP, so a flipped flag
triggers a tear-down-and-recreate in reconcileVIP (ASes deleted
with flush, VIP deleted, then re-added). Flip is logged.
New feature: frontend state aggregation and events
* New health.FrontendState (unknown/up/down) and FrontendTransition
types. A frontend is 'up' iff at least one backend has a nonzero
effective weight, 'unknown' iff no backend has real state yet,
and 'down' otherwise.
* Checker tracks per-frontend aggregate state, recomputing after
each backend transition and emitting a frontend-transition Event
on change. Reload drops entries for removed frontends.
* checker.Event gains an optional FrontendTransition pointer;
backend- vs. frontend-transition events are demultiplexed on
that field.
* WatchEvents now sends an initial snapshot of frontend state on
connect (mirroring the existing backend snapshot), subscribes
once to the checker stream, and fans out to backend/frontend
handlers based on the client's filter flags. The proto
FrontendEvent message grows name + transition fields.
* New Checker.FrontendState accessor.
Refactor: pure health helpers
* Moved the priority-failover selector and the (pool idx, active
pool, state, cfg weight) → (vpp weight, flush) mapping out of
internal/vpp/lbsync.go into a new internal/health/weights.go so
the checker can reuse them for frontend-state computation
without importing internal/vpp.
* New functions: health.ActivePoolIndex, BackendEffectiveWeight,
EffectiveWeights, ComputeFrontendState. lbsync.go now calls
these directly; vpp.EffectiveWeights is a thin wrapper over
health.EffectiveWeights retained for the gRPC observability
path. Fully unit-tested in internal/health/weights_test.go.
maglevc polish
* --color default is now mode-aware: on in the interactive shell,
off in one-shot mode so piped output is script-safe. Explicit
--color=true/false still overrides.
* New stripHostMask helper drops /32 and /128 from VIP display;
non-host prefixes pass through unchanged.
* Counter table column order fixed (first before next) and
packets/bytes columns renamed to fib-packets/fib-bytes to
clarify they come from the FIB, not the LB plugin.
Docs
* config-guide: document src-ip-sticky, including the VIP
recreate-on-change caveat.
* user-guide, maglevc.1, maglevd.8: updated command tree, new
counters command, color defaults, and the src-ip-sticky field.
304 lines
9.1 KiB
Protocol Buffer
304 lines
9.1 KiB
Protocol Buffer
syntax = "proto3";
|
|
|
|
package maglev;
|
|
|
|
option go_package = "git.ipng.ch/ipng/vpp-maglev/internal/grpcapi";
|
|
|
|
// Maglev exposes the state of backend health for all frontends.
|
|
service Maglev {
|
|
rpc ListFrontends(ListFrontendsRequest) returns (ListFrontendsResponse);
|
|
rpc GetFrontend(GetFrontendRequest) returns (FrontendInfo);
|
|
rpc ListBackends(ListBackendsRequest) returns (ListBackendsResponse);
|
|
rpc GetBackend(GetBackendRequest) returns (BackendInfo);
|
|
rpc PauseBackend(BackendRequest) returns (BackendInfo);
|
|
rpc ResumeBackend(BackendRequest) returns (BackendInfo);
|
|
rpc EnableBackend(BackendRequest) returns (BackendInfo);
|
|
rpc DisableBackend(BackendRequest) returns (BackendInfo);
|
|
rpc ListHealthChecks(ListHealthChecksRequest) returns (ListHealthChecksResponse);
|
|
rpc GetHealthCheck(GetHealthCheckRequest) returns (HealthCheckInfo);
|
|
rpc SetFrontendPoolBackendWeight(SetWeightRequest) returns (FrontendInfo);
|
|
rpc WatchEvents(WatchRequest) returns (stream Event);
|
|
rpc CheckConfig(CheckConfigRequest) returns (CheckConfigResponse);
|
|
rpc ReloadConfig(ReloadConfigRequest) returns (ReloadConfigResponse);
|
|
rpc GetVPPInfo(GetVPPInfoRequest) returns (VPPInfo);
|
|
rpc GetVPPLBState(GetVPPLBStateRequest) returns (VPPLBState);
|
|
rpc SyncVPPLBState(SyncVPPLBStateRequest) returns (SyncVPPLBStateResponse);
|
|
rpc GetVPPLBCounters(GetVPPLBCountersRequest) returns (VPPLBCounters);
|
|
}
|
|
|
|
// ---- requests ---------------------------------------------------------------
|
|
|
|
message ListFrontendsRequest {}
|
|
|
|
message GetFrontendRequest {
|
|
string name = 1;
|
|
}
|
|
|
|
message ListBackendsRequest {}
|
|
|
|
message GetBackendRequest {
|
|
string name = 1;
|
|
}
|
|
|
|
message BackendRequest {
|
|
string name = 1;
|
|
}
|
|
|
|
message ListHealthChecksRequest {}
|
|
|
|
message GetHealthCheckRequest {
|
|
string name = 1;
|
|
}
|
|
|
|
message CheckConfigRequest {}
|
|
|
|
message CheckConfigResponse {
|
|
bool ok = 1;
|
|
string parse_error = 2; // set when YAML cannot be read or parsed
|
|
string semantic_error = 3; // set when YAML is valid but semantically incorrect
|
|
}
|
|
|
|
message ReloadConfigRequest {}
|
|
|
|
message ReloadConfigResponse {
|
|
bool ok = 1;
|
|
string parse_error = 2; // set when YAML cannot be read or parsed
|
|
string semantic_error = 3; // set when YAML is valid but semantically incorrect
|
|
string reload_error = 4; // set when config is valid but the reload itself failed
|
|
}
|
|
|
|
message GetVPPInfoRequest {}
|
|
|
|
message VPPInfo {
|
|
string version = 1;
|
|
string build_date = 2;
|
|
string build_directory = 3;
|
|
uint32 pid = 4;
|
|
int64 boottime_ns = 5; // unix timestamp (ns) when VPP started (from /sys/boottime)
|
|
int64 connecttime_ns = 6; // unix timestamp (ns) when maglevd connected to VPP
|
|
}
|
|
|
|
// ---- VPP load-balancer state ------------------------------------------------
|
|
|
|
message GetVPPLBStateRequest {}
|
|
|
|
// VPPLBConf mirrors VPP's lb_conf_get_reply: global LB plugin settings.
|
|
message VPPLBConf {
|
|
string ip4_src_address = 1;
|
|
string ip6_src_address = 2;
|
|
uint32 sticky_buckets_per_core = 3;
|
|
uint32 flow_timeout = 4;
|
|
}
|
|
|
|
// VPPLBAS is one application server attached to a VIP.
|
|
message VPPLBAS {
|
|
string address = 1;
|
|
uint32 weight = 2; // 0-100
|
|
uint32 flags = 3; // VPP AS flags (bit 0 = used, bit 1 = flushed)
|
|
uint32 num_buckets = 4;
|
|
int64 in_use_since_ns = 5; // unix timestamp (ns), 0 if never used
|
|
}
|
|
|
|
// VPPLBVIP mirrors VPP's lb_vip_details plus the attached application servers.
|
|
// Note: srv_type, dscp, and target_port are intentionally omitted — maglevd
|
|
// only supports GRE encap, so NAT/L3DSR-specific fields don't apply.
|
|
message VPPLBVIP {
|
|
string prefix = 1; // CIDR, e.g. 192.0.2.1/32
|
|
uint32 protocol = 2; // 6=TCP, 17=UDP, 255=any
|
|
uint32 port = 3; // 0 = all-port VIP
|
|
string encap = 4; // gre4|gre6|l3dsr|nat4|nat6
|
|
uint32 flow_table_length = 5;
|
|
repeated VPPLBAS application_servers = 6;
|
|
bool src_ip_sticky = 7; // source-IP based sticky session (scraped via cli_inband)
|
|
}
|
|
|
|
message VPPLBState {
|
|
VPPLBConf conf = 1;
|
|
repeated VPPLBVIP vips = 2;
|
|
}
|
|
|
|
// SyncVPPLBStateRequest triggers a reconciliation between the maglev config
|
|
// and the VPP load-balancer dataplane. When frontend_name is set, only that
|
|
// frontend's VIP is synced (SyncLBStateVIP) and no VIPs are removed. When
|
|
// unset, a full reconciliation runs (SyncLBStateAll), which will also remove
|
|
// stale VIPs from VPP.
|
|
message SyncVPPLBStateRequest {
|
|
optional string frontend_name = 1;
|
|
}
|
|
|
|
message SyncVPPLBStateResponse {}
|
|
|
|
// ---- VPP load-balancer runtime counters ------------------------------------
|
|
|
|
// GetVPPLBCountersRequest asks maglevd for the most recent per-VIP and
|
|
// per-backend counter snapshot. The data is served from an in-process
|
|
// cache that is refreshed every ~5 seconds server-side; the call itself
|
|
// is cheap and does not hit VPP.
|
|
message GetVPPLBCountersRequest {}
|
|
|
|
// VPPLBVIPCounters is the point-in-time counter row for a single VIP.
|
|
// The four lb_* fields are the LB plugin's SimpleCounters (packets only);
|
|
// packets / bytes come from the VPP FIB's combined counter at the VIP's
|
|
// host prefix (/net/route/to).
|
|
message VPPLBVIPCounters {
|
|
string prefix = 1; // CIDR, e.g. 192.0.2.1/32
|
|
string protocol = 2; // tcp | udp | any
|
|
uint32 port = 3;
|
|
uint64 next_packet = 4; // "/packet from existing sessions"
|
|
uint64 first_packet = 5; // "/first session packet"
|
|
uint64 untracked_packet = 6; // "/untracked packet"
|
|
uint64 no_server = 7; // "/no server configured"
|
|
uint64 packets = 8; // /net/route/to (FIB, summed across workers)
|
|
uint64 bytes = 9; // /net/route/to (FIB, summed across workers)
|
|
}
|
|
|
|
// VPPLBBackendCounters is the FIB combined counter for a single backend's
|
|
// host prefix, summed across worker threads.
|
|
message VPPLBBackendCounters {
|
|
string backend = 1; // backend name from config
|
|
string address = 2; // backend IP address
|
|
uint64 packets = 3;
|
|
uint64 bytes = 4;
|
|
}
|
|
|
|
message VPPLBCounters {
|
|
repeated VPPLBVIPCounters vips = 1;
|
|
repeated VPPLBBackendCounters backends = 2;
|
|
}
|
|
|
|
message SetWeightRequest {
|
|
string frontend = 1;
|
|
string pool = 2;
|
|
string backend = 3;
|
|
int32 weight = 4; // 0-100
|
|
}
|
|
|
|
// WatchRequest controls which event types are streamed. All fields default to
|
|
// true (i.e. an empty request subscribes to everything at info level).
|
|
message WatchRequest {
|
|
optional bool log = 1; // include log events (default: true)
|
|
string log_level = 2; // minimum log level: debug|info|warn|error (default: info)
|
|
optional bool backend = 3; // include backend transition events (default: true)
|
|
optional bool frontend = 4; // include frontend events (default: true)
|
|
}
|
|
|
|
// ---- responses --------------------------------------------------------------
|
|
|
|
message ListFrontendsResponse {
|
|
repeated string frontend_names = 1;
|
|
}
|
|
|
|
message PoolBackendInfo {
|
|
string name = 1;
|
|
int32 weight = 2; // configured weight from YAML (0-100)
|
|
int32 effective_weight = 3; // state-aware weight after pool-failover logic
|
|
}
|
|
|
|
message PoolInfo {
|
|
string name = 1;
|
|
repeated PoolBackendInfo backends = 2;
|
|
}
|
|
|
|
message FrontendInfo {
|
|
string name = 1;
|
|
string address = 2;
|
|
string protocol = 3;
|
|
uint32 port = 4;
|
|
repeated PoolInfo pools = 5;
|
|
string description = 6;
|
|
bool src_ip_sticky = 7; // VPP LB uses src-IP-based stickiness for this VIP
|
|
}
|
|
|
|
message ListBackendsResponse {
|
|
repeated string backend_names = 1;
|
|
}
|
|
|
|
message ListHealthChecksResponse {
|
|
repeated string names = 1;
|
|
}
|
|
|
|
message HTTPCheckParams {
|
|
string path = 1;
|
|
string host = 2;
|
|
int32 response_code_min = 3;
|
|
int32 response_code_max = 4;
|
|
string response_regexp = 5;
|
|
string server_name = 6;
|
|
bool insecure_skip_verify = 7;
|
|
}
|
|
|
|
message TCPCheckParams {
|
|
bool ssl = 1;
|
|
string server_name = 2;
|
|
bool insecure_skip_verify = 3;
|
|
}
|
|
|
|
message HealthCheckInfo {
|
|
string name = 1;
|
|
string type = 2;
|
|
uint32 port = 3;
|
|
string probe_ipv4_src = 4;
|
|
string probe_ipv6_src = 5;
|
|
int64 interval_ns = 6;
|
|
int64 fast_interval_ns = 7;
|
|
int64 down_interval_ns = 8;
|
|
int64 timeout_ns = 9;
|
|
int32 rise = 10;
|
|
int32 fall = 11;
|
|
HTTPCheckParams http = 12;
|
|
TCPCheckParams tcp = 13;
|
|
}
|
|
|
|
message BackendInfo {
|
|
string name = 1;
|
|
string address = 2;
|
|
string state = 3;
|
|
repeated TransitionRecord transitions = 4;
|
|
bool enabled = 5;
|
|
string healthcheck = 6;
|
|
}
|
|
|
|
message TransitionRecord {
|
|
string from = 1;
|
|
string to = 2;
|
|
int64 at_unix_ns = 3;
|
|
}
|
|
|
|
// ---- event stream -----------------------------------------------------------
|
|
|
|
// LogAttr is a single key/value attribute from a structured log record.
|
|
message LogAttr {
|
|
string key = 1;
|
|
string value = 2;
|
|
}
|
|
|
|
// LogEvent carries a single structured log record.
|
|
message LogEvent {
|
|
int64 at_unix_ns = 1;
|
|
string level = 2;
|
|
string msg = 3;
|
|
repeated LogAttr attrs = 4;
|
|
}
|
|
|
|
// BackendEvent is emitted on every backend state transition.
|
|
message BackendEvent {
|
|
string backend_name = 1;
|
|
TransitionRecord transition = 2;
|
|
}
|
|
|
|
// FrontendEvent is emitted when a frontend's aggregate state changes.
|
|
// Frontends have three states: unknown, up, down. See docs/healthchecks.md.
|
|
message FrontendEvent {
|
|
string frontend_name = 1;
|
|
TransitionRecord transition = 2;
|
|
}
|
|
|
|
// Event is the envelope returned by WatchEvents.
|
|
message Event {
|
|
oneof event {
|
|
LogEvent log = 1;
|
|
BackendEvent backend = 2;
|
|
FrontendEvent frontend = 3;
|
|
}
|
|
}
|