open-consul/agent/consul/health_endpoint.go

268 lines
7.8 KiB
Go
Raw Normal View History

2014-01-08 21:52:09 +00:00
package consul
import (
2014-01-08 21:56:34 +00:00
"fmt"
New ACLs (#4791) This PR is almost a complete rewrite of the ACL system within Consul. It brings the features more in line with other HashiCorp products. Obviously there is quite a bit left to do here but most of it is related docs, testing and finishing the last few commands in the CLI. I will update the PR description and check off the todos as I finish them over the next few days/week. Description At a high level this PR is mainly to split ACL tokens from Policies and to split the concepts of Authorization from Identities. A lot of this PR is mostly just to support CRUD operations on ACLTokens and ACLPolicies. These in and of themselves are not particularly interesting. The bigger conceptual changes are in how tokens get resolved, how backwards compatibility is handled and the separation of policy from identity which could lead the way to allowing for alternative identity providers. On the surface and with a new cluster the ACL system will look very similar to that of Nomads. Both have tokens and policies. Both have local tokens. The ACL management APIs for both are very similar. I even ripped off Nomad's ACL bootstrap resetting procedure. There are a few key differences though. Nomad requires token and policy replication where Consul only requires policy replication with token replication being opt-in. In Consul local tokens only work with token replication being enabled though. All policies in Nomad are globally applicable. In Consul all policies are stored and replicated globally but can be scoped to a subset of the datacenters. This allows for more granular access management. Unlike Nomad, Consul has legacy baggage in the form of the original ACL system. The ramifications of this are: A server running the new system must still support other clients using the legacy system. A client running the new system must be able to use the legacy RPCs when the servers in its datacenter are running the legacy system. The primary ACL DC's servers running in legacy mode needs to be a gate that keeps everything else in the entire multi-DC cluster running in legacy mode. So not only does this PR implement the new ACL system but has a legacy mode built in for when the cluster isn't ready for new ACLs. Also detecting that new ACLs can be used is automatic and requires no configuration on the part of administrators. This process is detailed more in the "Transitioning from Legacy to New ACL Mode" section below.
2018-10-19 16:04:07 +00:00
"sort"
2017-05-05 10:36:35 +00:00
"github.com/armon/go-metrics"
pkg refactor command/agent/* -> agent/* command/consul/* -> agent/consul/* command/agent/command{,_test}.go -> command/agent{,_test}.go command/base/command.go -> command/base.go command/base/* -> command/* commands.go -> command/commands.go The script which did the refactor is: ( cd $GOPATH/src/github.com/hashicorp/consul git mv command/agent/command.go command/agent.go git mv command/agent/command_test.go command/agent_test.go git mv command/agent/flag_slice_value{,_test}.go command/ git mv command/agent . git mv command/base/command.go command/base.go git mv command/base/config_util{,_test}.go command/ git mv commands.go command/ git mv consul agent rmdir command/base/ gsed -i -e 's|package agent|package command|' command/agent{,_test}.go gsed -i -e 's|package agent|package command|' command/flag_slice_value{,_test}.go gsed -i -e 's|package base|package command|' command/base.go command/config_util{,_test}.go gsed -i -e 's|package main|package command|' command/commands.go gsed -i -e 's|base.Command|BaseCommand|' command/commands.go gsed -i -e 's|agent.Command|AgentCommand|' command/commands.go gsed -i -e 's|\tCommand:|\tBaseCommand:|' command/commands.go gsed -i -e 's|base\.||' command/commands.go gsed -i -e 's|command\.||' command/commands.go gsed -i -e 's|command|c|' main.go gsed -i -e 's|range Commands|range command.Commands|' main.go gsed -i -e 's|Commands: Commands|Commands: command.Commands|' main.go gsed -i -e 's|base\.BoolValue|BoolValue|' command/operator_autopilot_set.go gsed -i -e 's|base\.DurationValue|DurationValue|' command/operator_autopilot_set.go gsed -i -e 's|base\.StringValue|StringValue|' command/operator_autopilot_set.go gsed -i -e 's|base\.UintValue|UintValue|' command/operator_autopilot_set.go gsed -i -e 's|\bCommand\b|BaseCommand|' command/base.go gsed -i -e 's|BaseCommand Options|Command Options|' command/base.go gsed -i -e 's|base.Command|BaseCommand|' command/*.go gsed -i -e 's|c\.Command|c.BaseCommand|g' command/*.go gsed -i -e 's|\tCommand:|\tBaseCommand:|' command/*_test.go gsed -i -e 's|base\.||' command/*_test.go gsed -i -e 's|\bCommand\b|AgentCommand|' command/agent{,_test}.go gsed -i -e 's|cmd.AgentCommand|cmd.BaseCommand|' command/agent.go gsed -i -e 's|cli.AgentCommand = new(Command)|cli.Command = new(AgentCommand)|' command/agent_test.go gsed -i -e 's|exec.AgentCommand|exec.Command|' command/agent_test.go gsed -i -e 's|exec.BaseCommand|exec.Command|' command/agent_test.go gsed -i -e 's|NewTestAgent|agent.NewTestAgent|' command/agent_test.go gsed -i -e 's|= TestConfig|= agent.TestConfig|' command/agent_test.go gsed -i -e 's|: RetryJoin|: agent.RetryJoin|' command/agent_test.go gsed -i -e 's|\.\./\.\./|../|' command/config_util_test.go gsed -i -e 's|\bverifyUniqueListeners|VerifyUniqueListeners|' agent/config{,_test}.go command/agent.go gsed -i -e 's|\bserfLANKeyring\b|SerfLANKeyring|g' agent/{agent,keyring,testagent}.go command/agent.go gsed -i -e 's|\bserfWANKeyring\b|SerfWANKeyring|g' agent/{agent,keyring,testagent}.go command/agent.go gsed -i -e 's|\bNewAgent\b|agent.New|g' command/agent{,_test}.go gsed -i -e 's|\bNewAgent|New|' agent/{acl_test,agent,testagent}.go gsed -i -e 's|\bAgent\b|agent.&|g' command/agent{,_test}.go gsed -i -e 's|\bBool\b|agent.&|g' command/agent{,_test}.go gsed -i -e 's|\bConfig\b|agent.&|g' command/agent{,_test}.go gsed -i -e 's|\bDefaultConfig\b|agent.&|g' command/agent{,_test}.go gsed -i -e 's|\bDevConfig\b|agent.&|g' command/agent{,_test}.go gsed -i -e 's|\bMergeConfig\b|agent.&|g' command/agent{,_test}.go gsed -i -e 's|\bReadConfigPaths\b|agent.&|g' command/agent{,_test}.go gsed -i -e 's|\bParseMetaPair\b|agent.&|g' command/agent{,_test}.go gsed -i -e 's|\bSerfLANKeyring\b|agent.&|g' command/agent{,_test}.go gsed -i -e 's|\bSerfWANKeyring\b|agent.&|g' command/agent{,_test}.go gsed -i -e 's|circonus\.agent|circonus|g' command/agent{,_test}.go gsed -i -e 's|logger\.agent|logger|g' command/agent{,_test}.go gsed -i -e 's|metrics\.agent|metrics|g' command/agent{,_test}.go gsed -i -e 's|// agent.Agent|// agent|' command/agent{,_test}.go gsed -i -e 's|a\.agent\.Config|a.Config|' command/agent{,_test}.go gsed -i -e 's|agent\.AppendSliceValue|AppendSliceValue|' command/{configtest,validate}.go gsed -i -e 's|consul/consul|agent/consul|' GNUmakefile gsed -i -e 's|\.\./test|../../test|' agent/consul/server_test.go # fix imports f=$(grep -rl 'github.com/hashicorp/consul/command/agent' * | grep '\.go') gsed -i -e 's|github.com/hashicorp/consul/command/agent|github.com/hashicorp/consul/agent|' $f goimports -w $f f=$(grep -rl 'github.com/hashicorp/consul/consul' * | grep '\.go') gsed -i -e 's|github.com/hashicorp/consul/consul|github.com/hashicorp/consul/agent/consul|' $f goimports -w $f goimports -w command/*.go main.go )
2017-06-09 22:28:28 +00:00
"github.com/hashicorp/consul/agent/consul/state"
"github.com/hashicorp/consul/agent/structs"
bexpr "github.com/hashicorp/go-bexpr"
"github.com/hashicorp/go-memdb"
2014-01-08 21:52:09 +00:00
)
// Health endpoint is used to query the health information
type Health struct {
srv *Server
}
// ChecksInState is used to get all the checks in a given state
func (h *Health) ChecksInState(args *structs.ChecksInStateRequest,
reply *structs.IndexedHealthChecks) error {
2014-04-19 00:17:12 +00:00
if done, err := h.srv.forward("Health.ChecksInState", args, args, reply); done {
2014-01-08 21:52:09 +00:00
return err
}
filter, err := bexpr.CreateFilter(args.Filter, nil, reply.HealthChecks)
if err != nil {
return err
}
return h.srv.blockingQuery(
&args.QueryOptions,
&reply.QueryMeta,
2017-04-21 00:46:29 +00:00
func(ws memdb.WatchSet, state *state.Store) error {
var index uint64
var checks structs.HealthChecks
var err error
if len(args.NodeMetaFilters) > 0 {
index, checks, err = state.ChecksInStateByNodeMeta(ws, args.State, args.NodeMetaFilters)
} else {
index, checks, err = state.ChecksInState(ws, args.State)
}
if err != nil {
return err
}
reply.Index, reply.HealthChecks = index, checks
if err := h.srv.filterACL(args.Token, reply); err != nil {
return err
}
raw, err := filter.Execute(reply.HealthChecks)
if err != nil {
return err
}
reply.HealthChecks = raw.(structs.HealthChecks)
return h.srv.sortNodesByDistanceFrom(args.Source, reply.HealthChecks)
})
2014-01-08 21:52:09 +00:00
}
// NodeChecks is used to get all the checks for a node
func (h *Health) NodeChecks(args *structs.NodeSpecificRequest,
reply *structs.IndexedHealthChecks) error {
2014-04-19 00:17:12 +00:00
if done, err := h.srv.forward("Health.NodeChecks", args, args, reply); done {
2014-01-08 21:52:09 +00:00
return err
}
filter, err := bexpr.CreateFilter(args.Filter, nil, reply.HealthChecks)
if err != nil {
return err
}
return h.srv.blockingQuery(
&args.QueryOptions,
&reply.QueryMeta,
2017-04-21 00:46:29 +00:00
func(ws memdb.WatchSet, state *state.Store) error {
index, checks, err := state.NodeChecks(ws, args.Node)
if err != nil {
return err
}
reply.Index, reply.HealthChecks = index, checks
if err := h.srv.filterACL(args.Token, reply); err != nil {
return err
}
raw, err := filter.Execute(reply.HealthChecks)
if err != nil {
return err
}
reply.HealthChecks = raw.(structs.HealthChecks)
return nil
})
2014-01-08 21:52:09 +00:00
}
// ServiceChecks is used to get all the checks for a service
func (h *Health) ServiceChecks(args *structs.ServiceSpecificRequest,
reply *structs.IndexedHealthChecks) error {
2014-01-08 21:56:34 +00:00
// Reject if tag filtering is on
if args.TagFilter {
return fmt.Errorf("Tag filtering is not supported")
}
// Potentially forward
2014-04-19 00:17:12 +00:00
if done, err := h.srv.forward("Health.ServiceChecks", args, args, reply); done {
2014-01-08 21:52:09 +00:00
return err
}
filter, err := bexpr.CreateFilter(args.Filter, nil, reply.HealthChecks)
if err != nil {
return err
}
return h.srv.blockingQuery(
&args.QueryOptions,
&reply.QueryMeta,
2017-04-21 00:46:29 +00:00
func(ws memdb.WatchSet, state *state.Store) error {
var index uint64
var checks structs.HealthChecks
var err error
if len(args.NodeMetaFilters) > 0 {
index, checks, err = state.ServiceChecksByNodeMeta(ws, args.ServiceName, args.NodeMetaFilters)
} else {
index, checks, err = state.ServiceChecks(ws, args.ServiceName)
}
if err != nil {
return err
}
reply.Index, reply.HealthChecks = index, checks
if err := h.srv.filterACL(args.Token, reply); err != nil {
return err
}
raw, err := filter.Execute(reply.HealthChecks)
if err != nil {
return err
}
reply.HealthChecks = raw.(structs.HealthChecks)
return h.srv.sortNodesByDistanceFrom(args.Source, reply.HealthChecks)
})
2014-01-08 21:52:09 +00:00
}
// ServiceNodes returns all the nodes registered as part of a service including health info
func (h *Health) ServiceNodes(args *structs.ServiceSpecificRequest, reply *structs.IndexedCheckServiceNodes) error {
2014-04-19 00:17:12 +00:00
if done, err := h.srv.forward("Health.ServiceNodes", args, args, reply); done {
return err
}
// Verify the arguments
if args.ServiceName == "" {
return fmt.Errorf("Must provide service name")
}
// Determine the function we'll call
2018-03-22 02:54:44 +00:00
var f func(memdb.WatchSet, *state.Store, *structs.ServiceSpecificRequest) (uint64, structs.CheckServiceNodes, error)
switch {
case args.Connect:
2018-03-22 02:54:44 +00:00
f = h.serviceNodesConnect
case args.TagFilter:
2018-03-22 02:54:44 +00:00
f = h.serviceNodesTagFilter
default:
2018-03-22 02:54:44 +00:00
f = h.serviceNodesDefault
}
// If we're doing a connect query, we need read access to the service
// we're trying to find proxies for, so check that.
if args.Connect {
// Fetch the ACL token, if any.
New ACLs (#4791) This PR is almost a complete rewrite of the ACL system within Consul. It brings the features more in line with other HashiCorp products. Obviously there is quite a bit left to do here but most of it is related docs, testing and finishing the last few commands in the CLI. I will update the PR description and check off the todos as I finish them over the next few days/week. Description At a high level this PR is mainly to split ACL tokens from Policies and to split the concepts of Authorization from Identities. A lot of this PR is mostly just to support CRUD operations on ACLTokens and ACLPolicies. These in and of themselves are not particularly interesting. The bigger conceptual changes are in how tokens get resolved, how backwards compatibility is handled and the separation of policy from identity which could lead the way to allowing for alternative identity providers. On the surface and with a new cluster the ACL system will look very similar to that of Nomads. Both have tokens and policies. Both have local tokens. The ACL management APIs for both are very similar. I even ripped off Nomad's ACL bootstrap resetting procedure. There are a few key differences though. Nomad requires token and policy replication where Consul only requires policy replication with token replication being opt-in. In Consul local tokens only work with token replication being enabled though. All policies in Nomad are globally applicable. In Consul all policies are stored and replicated globally but can be scoped to a subset of the datacenters. This allows for more granular access management. Unlike Nomad, Consul has legacy baggage in the form of the original ACL system. The ramifications of this are: A server running the new system must still support other clients using the legacy system. A client running the new system must be able to use the legacy RPCs when the servers in its datacenter are running the legacy system. The primary ACL DC's servers running in legacy mode needs to be a gate that keeps everything else in the entire multi-DC cluster running in legacy mode. So not only does this PR implement the new ACL system but has a legacy mode built in for when the cluster isn't ready for new ACLs. Also detecting that new ACLs can be used is automatic and requires no configuration on the part of administrators. This process is detailed more in the "Transitioning from Legacy to New ACL Mode" section below.
2018-10-19 16:04:07 +00:00
rule, err := h.srv.ResolveToken(args.Token)
if err != nil {
return err
}
if rule != nil && !rule.ServiceRead(args.ServiceName) {
// Just return nil, which will return an empty response (tested)
return nil
}
}
filter, err := bexpr.CreateFilter(args.Filter, nil, reply.Nodes)
if err != nil {
return err
}
err = h.srv.blockingQuery(
&args.QueryOptions,
&reply.QueryMeta,
2017-04-21 00:46:29 +00:00
func(ws memdb.WatchSet, state *state.Store) error {
2018-03-22 02:54:44 +00:00
index, nodes, err := f(ws, state, args)
if err != nil {
return err
}
reply.Index, reply.Nodes = index, nodes
if len(args.NodeMetaFilters) > 0 {
reply.Nodes = nodeMetaFilter(args.NodeMetaFilters, reply.Nodes)
}
if err := h.srv.filterACL(args.Token, reply); err != nil {
return err
}
raw, err := filter.Execute(reply.Nodes)
if err != nil {
return err
}
reply.Nodes = raw.(structs.CheckServiceNodes)
return h.srv.sortNodesByDistanceFrom(args.Source, reply.Nodes)
})
// Provide some metrics
if err == nil {
// For metrics, we separate Connect-based lookups from non-Connect
key := "service"
if args.Connect {
key = "connect"
}
metrics.IncrCounterWithLabels([]string{"health", key, "query"}, 1,
[]metrics.Label{{Name: "service", Value: args.ServiceName}})
// DEPRECATED (singular-service-tag) - remove this when backwards RPC compat
// with 1.2.x is not required.
if args.ServiceTag != "" {
metrics.IncrCounterWithLabels([]string{"health", key, "query-tag"}, 1,
[]metrics.Label{{Name: "service", Value: args.ServiceName}, {Name: "tag", Value: args.ServiceTag}})
}
if len(args.ServiceTags) > 0 {
New ACLs (#4791) This PR is almost a complete rewrite of the ACL system within Consul. It brings the features more in line with other HashiCorp products. Obviously there is quite a bit left to do here but most of it is related docs, testing and finishing the last few commands in the CLI. I will update the PR description and check off the todos as I finish them over the next few days/week. Description At a high level this PR is mainly to split ACL tokens from Policies and to split the concepts of Authorization from Identities. A lot of this PR is mostly just to support CRUD operations on ACLTokens and ACLPolicies. These in and of themselves are not particularly interesting. The bigger conceptual changes are in how tokens get resolved, how backwards compatibility is handled and the separation of policy from identity which could lead the way to allowing for alternative identity providers. On the surface and with a new cluster the ACL system will look very similar to that of Nomads. Both have tokens and policies. Both have local tokens. The ACL management APIs for both are very similar. I even ripped off Nomad's ACL bootstrap resetting procedure. There are a few key differences though. Nomad requires token and policy replication where Consul only requires policy replication with token replication being opt-in. In Consul local tokens only work with token replication being enabled though. All policies in Nomad are globally applicable. In Consul all policies are stored and replicated globally but can be scoped to a subset of the datacenters. This allows for more granular access management. Unlike Nomad, Consul has legacy baggage in the form of the original ACL system. The ramifications of this are: A server running the new system must still support other clients using the legacy system. A client running the new system must be able to use the legacy RPCs when the servers in its datacenter are running the legacy system. The primary ACL DC's servers running in legacy mode needs to be a gate that keeps everything else in the entire multi-DC cluster running in legacy mode. So not only does this PR implement the new ACL system but has a legacy mode built in for when the cluster isn't ready for new ACLs. Also detecting that new ACLs can be used is automatic and requires no configuration on the part of administrators. This process is detailed more in the "Transitioning from Legacy to New ACL Mode" section below.
2018-10-19 16:04:07 +00:00
// Sort tags so that the metric is the same even if the request
// tags are in a different order
sort.Strings(args.ServiceTags)
labels := []metrics.Label{{Name: "service", Value: args.ServiceName}}
for _, tag := range args.ServiceTags {
labels = append(labels, metrics.Label{Name: "tag", Value: tag})
}
metrics.IncrCounterWithLabels([]string{"health", key, "query-tags"}, 1, labels)
}
if len(reply.Nodes) == 0 {
metrics.IncrCounterWithLabels([]string{"health", key, "not-found"}, 1,
[]metrics.Label{{Name: "service", Value: args.ServiceName}})
}
}
return err
}
2018-03-22 02:54:44 +00:00
// The serviceNodes* functions below are the various lookup methods that
// can be used by the ServiceNodes endpoint.
func (h *Health) serviceNodesConnect(ws memdb.WatchSet, s *state.Store, args *structs.ServiceSpecificRequest) (uint64, structs.CheckServiceNodes, error) {
return s.CheckConnectServiceNodes(ws, args.ServiceName)
}
func (h *Health) serviceNodesTagFilter(ws memdb.WatchSet, s *state.Store, args *structs.ServiceSpecificRequest) (uint64, structs.CheckServiceNodes, error) {
// DEPRECATED (singular-service-tag) - remove this when backwards RPC compat
// with 1.2.x is not required.
// Agents < v1.3.0 populate the ServiceTag field. In this case,
// use ServiceTag instead of the ServiceTags field.
if args.ServiceTag != "" {
return s.CheckServiceTagNodes(ws, args.ServiceName, []string{args.ServiceTag})
}
return s.CheckServiceTagNodes(ws, args.ServiceName, args.ServiceTags)
2018-03-22 02:54:44 +00:00
}
func (h *Health) serviceNodesDefault(ws memdb.WatchSet, s *state.Store, args *structs.ServiceSpecificRequest) (uint64, structs.CheckServiceNodes, error) {
return s.CheckServiceNodes(ws, args.ServiceName)
}