diff --git a/.gitignore b/.gitignore index f76be949f..00b4b8a4d 100644 --- a/.gitignore +++ b/.gitignore @@ -6,3 +6,4 @@ .generate_exes .get_deps bin/ +**/.test/ diff --git a/Makefile b/Makefile index 29d918a9a..912d88c95 100644 --- a/Makefile +++ b/Makefile @@ -18,6 +18,9 @@ CMDS := controller apiserver pilot-elasticsearch pilot-cassandra GOPATH ?= /tmp/go GOFLAGS ?= "-a" +# Path of the Navigator Cassandra Pilot for integration tests +TEST_ASSET_NAVIGATOR_PILOT_CASSANDRA ?= "${CURDIR}/navigator-pilot-cassandra_linux_amd64" + help: # all - runs verify, build and docker_build targets # test - runs go_test target @@ -32,7 +35,7 @@ help: all: verify build docker_build -test: go_test +test: go_test test_integration .run_e2e: ${HACK_DIR}/prepare-e2e.sh @@ -44,7 +47,7 @@ build: $(CMDS) generate: .generate_files -verify: .hack_verify dep_verify go_verify helm_verify +verify: .hack_verify dep_verify go_verify helm_verify test_integration .hack_verify: @echo Running repo-infra verify scripts @@ -90,7 +93,7 @@ $(CMDS): go_build: $(CMDS) go_test: - go test -v $$(go list ./... | grep -v '/vendor/') + go test -v $$(go list ./... | grep -v -e '/vendor/' -e 'github.com/jetstack/navigator/test/') go_fmt: ./hack/verify-lint.sh @@ -105,3 +108,11 @@ go_fmt: # Helm targets helm_verify: helm lint contrib/charts/* + +.download_integration_test_binaries: + $(HACK_DIR)/download-integration-test-binaries.sh + touch .download_integration_test_binaries + +test_integration: .download_integration_test_binaries apiserver pilot-cassandra + TEST_ASSET_NAVIGATOR_PILOT_CASSANDRA=$(TEST_ASSET_NAVIGATOR_PILOT_CASSANDRA) \ + go test $(GO_TEST_ARGS) -v ./test/integration/... diff --git a/docs/cassandra.rst b/docs/cassandra.rst index 179f605c1..0dfd1befc 100644 --- a/docs/cassandra.rst +++ b/docs/cassandra.rst @@ -25,6 +25,8 @@ All the C* nodes (pods) in a ``nodepool`` have the same configuration and the fo .. include:: configure-scheduler.rst +.. _availability-zones-cassandra: + Cassandra Across Multiple Availability Zones -------------------------------------------- @@ -240,6 +242,37 @@ Navigator will add C* nodes, one at a time, until the desired number of nodes is You can look at ``CassandraCluster.Status.NodePools[].ReadyReplicas`` to see the current number of healthy C* nodes in each ``nodepool``. +Pilots and Cassandra Docker Images +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +By default, Navigator will use the `Cassandra Docker images from DockerHub `_. +It will use an image with a tag matching the supplied ``CassandraCluster.Spec.Version`` field. +If you prefer to use your own container image you should configure the ``CassandraCluster.Spec.Image`` fields. + +Navigator installs a ``navigator-pilot-cassandra`` executable into each Pod at the path ``/pilot``. +This ``pilot`` process connects to the API server to: +get extra configuration settings, +report the status of this C* node, and to +perform leader election of a single pilot in the cluster. + +The ``pilot`` overrides the following keys in the default ``/etc/cassandra/cassandra.yaml`` file: + +* ``cluster_name``: This will be set to match the name of the corresponding ``CassandraCluster`` resource in the API server. +* ``listen_address`` / ``listen_interface`` / ``broadcast_address`` / ``rpc_address`` / ``broadcast_rpc_address``: These keys and the corresponding values will be removed from the default configuration. + This ensures that Cassandra process listens and communicates using the IP address currently associated with the fully qualified domain name of the Pod. + This is important if the Pod is moved to another node and is assigned a different IP address. + Removing these settings from the Configuration file ensures that Cassandra uses the most recent IP address that Kubernetes has assigned to the Pod and that other C* nodes in the cluster are notified of the change of IP address. +* ``seed_provider``: This is set to ``io.jetstack.cassandra.KubernetesSeedProvider`` which allows Cassandra to look up the seed IP addresses from a Kubernetes service. + The ``seed_provider.*.seeds`` sub key will be removed. + This is to avoid the risk of nodes mistakenly joining the cluster as seeds if the seed provider service is temporarily unavailable. + +The ``pilot`` also overwrites ``cassandra-rackdc.properties`` with values derived from the ``CassandraCluster.Spec.Nodepools`` (see :ref:`availability-zones-cassandra`). + +Finally the ``pilot`` executes ``/usr/bin/cassandra`` directly. + +.. note:: + The default entry point (e.g. `/docker-entrypoint.sh `_ is ignored. + Supported Versions ------------------ diff --git a/docs/quick-start/cassandra-cluster.yaml b/docs/quick-start/cassandra-cluster.yaml index 29ca9bdfa..20a9a7763 100644 --- a/docs/quick-start/cassandra-cluster.yaml +++ b/docs/quick-start/cassandra-cluster.yaml @@ -31,3 +31,5 @@ spec: pilotImage: repository: "quay.io/jetstack/navigator-pilot-cassandra" tag: "v0.1.0" + securityContext: + runAsUser: 999 diff --git a/hack/download-integration-test-binaries.sh b/hack/download-integration-test-binaries.sh new file mode 100755 index 000000000..1eff7ddf2 --- /dev/null +++ b/hack/download-integration-test-binaries.sh @@ -0,0 +1,29 @@ +#!/bin/bash + +set -o errexit +set -o nounset +set -o pipefail +set -o xtrace + +# Close stdin +exec 0<&- + +ROOT_DIR="$(git rev-parse --show-toplevel)" + +ETCD_VERSION=v3.2.10 +ETCD_URL="https://storage.googleapis.com/etcd" + +KUBE_VERSION_URL="https://storage.googleapis.com/kubernetes-release/release/stable-1.10.txt" +KUBE_VERSION=$(curl --fail --silent "${KUBE_VERSION_URL}") +KUBE_BIN_URL="https://storage.googleapis.com/kubernetes-release/release/${KUBE_VERSION}/bin/linux/amd64" + +ASSETS_DIR="${ROOT_DIR}/vendor/sigs.k8s.io/testing_frameworks/integration/assets/bin" + +mkdir -p "${ASSETS_DIR}" + +curl --fail --silent ${ETCD_URL}/${ETCD_VERSION}/etcd-${ETCD_VERSION}-linux-amd64.tar.gz | \ + tar --extract --gzip --directory="${ASSETS_DIR}" --strip-components=1 '*/etcd' +curl --fail --silent --output "${ASSETS_DIR}/kube-apiserver" "${KUBE_BIN_URL}/kube-apiserver" +curl --fail --silent --output "${ASSETS_DIR}/kubectl" "${KUBE_BIN_URL}/kubectl" + +chmod +x ${ASSETS_DIR}/* diff --git a/hack/testdata/cass-cluster-test.template.yaml b/hack/testdata/cass-cluster-test.template.yaml index 39f300636..00518ccd1 100644 --- a/hack/testdata/cass-cluster-test.template.yaml +++ b/hack/testdata/cass-cluster-test.template.yaml @@ -24,3 +24,5 @@ spec: repository: "${NAVIGATOR_IMAGE_REPOSITORY}/navigator-pilot-cassandra" tag: "${NAVIGATOR_IMAGE_TAG}" pullPolicy: "${NAVIGATOR_IMAGE_PULLPOLICY}" + securityContext: + runAsUser: 999 diff --git a/internal/test/util/testfs/testfs.go b/internal/test/util/testfs/testfs.go new file mode 100644 index 000000000..3aef2e5a4 --- /dev/null +++ b/internal/test/util/testfs/testfs.go @@ -0,0 +1,53 @@ +package testfs + +import ( + "fmt" + "io/ioutil" + "os" + "path" + "path/filepath" + "testing" + + "github.com/stretchr/testify/require" +) + +type TestFs struct { + t *testing.T + d string +} + +func New(t *testing.T) *TestFs { + d := fmt.Sprintf(".test/%s", t.Name()) + d, err := filepath.Abs(d) + require.NoError(t, err) + err = os.RemoveAll(d) + if err != nil && !os.IsNotExist(err) { + t.Fatalf("Error while removing old test directory: %s", err) + } + + err = os.MkdirAll(d, os.ModePerm) + require.NoError(t, err) + + return &TestFs{ + t: t, + d: d, + } +} + +func (tfs *TestFs) TempPath(name string) string { + outPath := path.Join(tfs.d, name) + tmpFile, err := ioutil.TempFile(tfs.d, name) + require.NoError(tfs.t, err) + err = tmpFile.Close() + require.NoError(tfs.t, err) + err = os.Rename(tmpFile.Name(), outPath) + require.NoError(tfs.t, err) + return outPath +} + +func (tfs *TestFs) TempDir(name string) string { + outPath := path.Join(tfs.d, name) + err := os.MkdirAll(outPath, os.ModePerm) + require.NoError(tfs.t, err) + return outPath +} diff --git a/pkg/config/config.go b/pkg/config/config.go new file mode 100644 index 000000000..5af4cda5e --- /dev/null +++ b/pkg/config/config.go @@ -0,0 +1,59 @@ +package config + +import ( + "os" + "path/filepath" + + "github.com/pkg/errors" + "github.com/spf13/viper" + shutil "github.com/termie/go-shutil" +) + +const ( + BackupSuffix = ".navigator_original" +) + +type config struct { + *viper.Viper +} + +type Interface interface { + WriteConfig() error + Set(key string, value interface{}) + AllSettings() map[string]interface{} +} + +var _ Interface = &config{} + +func newFrom(path, format string) (Interface, error) { + path, err := filepath.Abs(path) + if err != nil { + return nil, errors.Wrap(err, "unable to read absolute path") + } + backupPath := path + BackupSuffix + err = shutil.CopyFile(path, backupPath, false) + if err != nil && !os.IsNotExist(err) { + return nil, errors.Wrap(err, "unable to create backup file") + } + c := &config{viper.New()} + c.SetConfigFile(path) + c.SetConfigType(format) + f, err := os.Open(path) + if err != nil && !os.IsNotExist(err) { + return nil, errors.Wrap(err, "unable to open file") + } + defer f.Close() + err = c.ReadConfig(f) + if err != nil { + return nil, errors.Wrap(err, "unable to read file") + } + return c, nil +} + +func NewFromYaml(path string) (Interface, error) { + return newFrom(path, "yaml") +} + +func NewFromProperties(path string) (Interface, error) { + return newFrom(path, "properties") +} diff --git a/pkg/config/config_test.go b/pkg/config/config_test.go new file mode 100644 index 000000000..343ec4692 --- /dev/null +++ b/pkg/config/config_test.go @@ -0,0 +1,47 @@ +package config_test + +import ( + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + shutil "github.com/termie/go-shutil" + + "github.com/jetstack/navigator/internal/test/util/testfs" + "github.com/jetstack/navigator/pkg/config" +) + +func TestRoundTrip(t *testing.T) { + tfs := testfs.New(t) + + inPath := tfs.TempPath("config.yaml") + err := shutil.CopyFile("testdata/config1.yaml", inPath, false) + require.NoError(t, err) + + c1, err := config.NewFromYaml(inPath) + require.NoError(t, err) + + err = c1.WriteConfig() + require.NoError(t, err) + + c2, err := config.NewFromYaml(inPath) + require.NoError(t, err) + + assert.Equal(t, c1.AllSettings(), c2.AllSettings()) +} + +func TestBackup(t *testing.T) { + tfs := testfs.New(t) + path := tfs.TempPath("conf1.yaml") + _, err := config.NewFromYaml(path) + require.NoError(t, err) + assert.FileExists(t, path+".navigator_original") +} + +func TestNoSource(t *testing.T) { + tfs := testfs.New(t) + dir := tfs.TempDir("conf1") + path := dir + "/conf1.yaml" + _, err := config.NewFromYaml(path) + require.NoError(t, err) +} diff --git a/pkg/config/testdata/config1.yaml b/pkg/config/testdata/config1.yaml new file mode 100644 index 000000000..ddb2ecd7b --- /dev/null +++ b/pkg/config/testdata/config1.yaml @@ -0,0 +1,3 @@ +foo: +- bar +- baz diff --git a/pkg/controllers/cassandra/nodepool/resource.go b/pkg/controllers/cassandra/nodepool/resource.go index 1d6786447..d98fee3cb 100644 --- a/pkg/controllers/cassandra/nodepool/resource.go +++ b/pkg/controllers/cassandra/nodepool/resource.go @@ -23,8 +23,6 @@ const ( cassDataVolumeName = "cassandra-data" cassDataVolumeMountPath = "/var/lib/cassandra" - cassSnitch = "GossipingPropertyFileSnitch" - // See https://jolokia.org/reference/html/agents.html#jvm-agent jolokiaHost = "127.0.0.1" jolokiaPort = 8778 @@ -106,6 +104,9 @@ func StatefulSetForCluster( jolokiaPort, jolokiaContext, ), + "--cassandra-cluster-name", cluster.Name, + "--cassandra-rack", ptr.DerefString(np.Rack), + "--cassandra-dc", ptr.DerefString(np.Datacenter), }, Image: fmt.Sprintf( "%s:%s", @@ -196,38 +197,6 @@ func StatefulSetForCluster( Name: "HEAP_NEWSIZE", Value: "100M", }, - // Deliberately set to a single space to force Cassandra to do a host name lookup. - // See https://github.com/apache/cassandra/blob/cassandra-3.11.2/conf/cassandra.yaml#L592 - { - Name: "CASSANDRA_LISTEN_ADDRESS", - Value: " ", - }, - { - Name: "CASSANDRA_BROADCAST_ADDRESS", - Value: " ", - }, - { - Name: "CASSANDRA_RPC_ADDRESS", - Value: " ", - }, - // Set a non-existent default seed. - // The Kubernetes Seed Provider will fall back to a default seed host if it can't look up seeds via the CASSANDRA_SERVICE. - // And if the CASSANDRA_SEEDS environment variable is not set, it defaults to localhost. - // Which could cause confusion if a non-seed node is temporarily unable to lookup the seed nodes from the service. - // We want the list of seeds to be strictly controlled by the service. - // See: - // https://github.com/docker-library/cassandra/blame/master/3.11/docker-entrypoint.sh#L31 and - // https://github.com/apache/cassandra/blob/cassandra-3.11.2/conf/cassandra.yaml#L416 and - // https://github.com/kubernetes/examples/blob/cabf8b8e4739e576837111e156763d19a64a3591/cassandra/java/src/main/java/io/k8s/cassandra/KubernetesSeedProvider.java#L69 and - // https://github.com/kubernetes/examples/blob/cabf8b8e4739e576837111e156763d19a64a3591/cassandra/go/main.go#L51 - { - Name: "CASSANDRA_SEEDS", - Value: "black-hole-dns-name", - }, - { - Name: "CASSANDRA_ENDPOINT_SNITCH", - Value: cassSnitch, - }, { Name: "CASSANDRA_SERVICE", Value: util.SeedsServiceName(cluster), @@ -236,14 +205,6 @@ func StatefulSetForCluster( Name: "CASSANDRA_CLUSTER_NAME", Value: cluster.Name, }, - { - Name: "CASSANDRA_DC", - Value: ptr.DerefString(np.Datacenter), - }, - { - Name: "CASSANDRA_RACK", - Value: ptr.DerefString(np.Rack), - }, { Name: "JVM_OPTS", Value: fmt.Sprintf( diff --git a/pkg/pilot/cassandra/v3/options.go b/pkg/pilot/cassandra/v3/options.go index bfd7d0a0c..60be493ac 100644 --- a/pkg/pilot/cassandra/v3/options.go +++ b/pkg/pilot/cassandra/v3/options.go @@ -18,9 +18,11 @@ import ( ) const ( - defaultResyncPeriod = time.Second * 30 - defaultConfigDir = "/etc/pilot" - defaultJolokiaURL = "http://127.0.0.1:8778/jolokia/" + defaultResyncPeriod = time.Second * 30 + defaultConfigDir = "/etc/pilot" + defaultJolokiaURL = "http://127.0.0.1:8778/jolokia/" + defaultCassandraPath = "/usr/sbin/cassandra" + defaultCassandraConfigPath = "/etc/cassandra" ) // PilotOptions are the options required to run this Pilot. This can be used to @@ -44,6 +46,21 @@ type PilotOptions struct { // JolokiaURL is the base URL of the Jolokia REST API server. JolokiaURL string + // CassandraClusterName is the cluster_name that will be written to cassandra.yaml + CassandraClusterName string + + // CassandraPath is the path to the cassandra executable + CassandraPath string + + // CassandraConfigPath is the path to the Cassandra configuration directory + CassandraConfigPath string + + // CassandraRack is the Cassandra rack name + CassandraRack string + + // CassandraConfigPath is the Cassandra DC name + CassandraDC string + // GenericPilotOptions contains options for the genericpilot GenericPilotOptions *genericpilot.Options @@ -74,6 +91,11 @@ func (o *PilotOptions) AddFlags(flags *pflag.FlagSet) { flags.DurationVar(&o.ResyncPeriod, "resync-period", defaultResyncPeriod, "Re-sync period for control loops operated by the pilot") flags.StringVar(&o.ConfigDir, "config-dir", defaultConfigDir, "Base directory for additional Pilot configuration") flags.StringVar(&o.JolokiaURL, "jolokia-url", defaultJolokiaURL, "The base URL of the Jolokia REST API server") + flags.StringVar(&o.CassandraClusterName, "cassandra-cluster-name", "", "The cluster_name value that will be written to cassandra.yaml") + flags.StringVar(&o.CassandraPath, "cassandra-path", defaultCassandraPath, "The path to the cassandra executable") + flags.StringVar(&o.CassandraConfigPath, "cassandra-config-path", defaultCassandraConfigPath, "The path to cassandra.yaml") + flags.StringVar(&o.CassandraRack, "cassandra-rack", "", "The Cassandra rack name.") + flags.StringVar(&o.CassandraDC, "cassandra-dc", "", "The Cassandra DC name.") } func (o *PilotOptions) Complete() error { diff --git a/pkg/pilot/cassandra/v3/pilot.go b/pkg/pilot/cassandra/v3/pilot.go index 817d9c0e9..520d62cd6 100644 --- a/pkg/pilot/cassandra/v3/pilot.go +++ b/pkg/pilot/cassandra/v3/pilot.go @@ -2,23 +2,32 @@ package v3 import ( "fmt" - "io/ioutil" "os" "os/exec" - "strings" + "path" "k8s.io/client-go/tools/cache" "github.com/golang/glog" + "github.com/pkg/errors" "github.com/jetstack/navigator/pkg/apis/navigator/v1alpha1" "github.com/jetstack/navigator/pkg/cassandra/nodetool" clientset "github.com/jetstack/navigator/pkg/client/clientset/versioned" listersv1alpha1 "github.com/jetstack/navigator/pkg/client/listers/navigator/v1alpha1" + "github.com/jetstack/navigator/pkg/config" "github.com/jetstack/navigator/pkg/pilot/genericpilot" "github.com/jetstack/navigator/pkg/pilot/genericpilot/hook" ) +const ( + cassSnitch = "GossipingPropertyFileSnitch" + cassSeedProvider = "io.jetstack.cassandra.KubernetesSeedProvider" + + CassandraYaml = "cassandra.yaml" + CassandraRackDcProperties = "cassandra-rackdc.properties" +) + type Pilot struct { Options *PilotOptions @@ -42,24 +51,6 @@ func NewPilot(opts *PilotOptions) (*Pilot, error) { pilotInformerSynced: pilotInformer.Informer().HasSynced, nodeTool: opts.nodeTool, } - - // hack to test the seedprovider, this should use whatever pattern is decided upon here: - // https://github.com/jetstack/navigator/issues/251 - cfgPath := "/etc/cassandra/cassandra.yaml" - read, err := ioutil.ReadFile(cfgPath) - if err != nil { - return nil, err - } - - newContents := strings.Replace(string(read), - "org.apache.cassandra.locator.SimpleSeedProvider", - "io.jetstack.cassandra.KubernetesSeedProvider", -1) - - err = ioutil.WriteFile(cfgPath, []byte(newContents), 0) - if err != nil { - return nil, err - } - return p, nil } @@ -71,11 +62,15 @@ func (p *Pilot) WaitForCacheSync(stopCh <-chan struct{}) error { } func (p *Pilot) Hooks() *hook.Hooks { - return &hook.Hooks{} + return &hook.Hooks{ + PreStart: []hook.Interface{ + hook.New("WriteConfig", p.WriteConfig), + }, + } } func (p *Pilot) CmdFunc(pilot *v1alpha1.Pilot) (*exec.Cmd, error) { - cmd := exec.Command("/docker-entrypoint.sh") + cmd := exec.Command(p.Options.CassandraPath, "-f") cmd.Stdout = os.Stdout cmd.Stderr = os.Stderr return cmd, nil @@ -129,3 +124,64 @@ func (p *Pilot) LivenessCheck() error { _, err := p.nodeTool.Status() return err } + +func (p *Pilot) writeCassandraYaml(pilot *v1alpha1.Pilot) error { + cfg, err := config.NewFromYaml( + path.Join(p.Options.CassandraConfigPath, "cassandra.yaml"), + ) + if err != nil { + return err + } + var null *struct{} + cfg.Set("cluster_name", p.Options.CassandraClusterName) + cfg.Set("listen_address", null) + cfg.Set("broadcast_address", null) + cfg.Set("rpc_address", null) + cfg.Set("endpoint_snitch", cassSnitch) + cfg.Set( + "seed_provider", + []map[string]interface{}{{ + "class_name": cassSeedProvider, + "parameters": []interface{}{ + map[string]interface{}{ + "seeds": "", + }, + }, + }}, + ) + return cfg.WriteConfig() +} + +func (p *Pilot) writeCassandraRackDcProperties(pilot *v1alpha1.Pilot) error { + cfg, err := config.NewFromProperties( + path.Join(p.Options.CassandraConfigPath, "cassandra-rackdc.properties"), + ) + if err != nil { + return err + } + cfg.Set("rack", p.Options.CassandraRack) + cfg.Set("dc", p.Options.CassandraDC) + return cfg.WriteConfig() +} + +// WriteConfig creates Navigator compatible Cassandra configuration files. +// Look for original cassandra.yaml +// Back it up. +// Unmarshall it as an unstructured map of strings. +// Remove keys +// Set SeedProvider key +// Write it back to the original path. +// Write the properties file. (backing up the original (if present)) +func (p *Pilot) WriteConfig(pilot *v1alpha1.Pilot) (err error) { + err = p.writeCassandraYaml(pilot) + if err != nil { + return errors.Wrap(err, "unable to write cassandra.yaml") + } + + err = p.writeCassandraRackDcProperties(pilot) + if err != nil { + return errors.Wrap(err, "unable to write cassandra-rackdc.properties") + } + + return nil +} diff --git a/pkg/pilot/cassandra/v3/pilot_test.go b/pkg/pilot/cassandra/v3/pilot_test.go index 591f8944c..16feacb07 100644 --- a/pkg/pilot/cassandra/v3/pilot_test.go +++ b/pkg/pilot/cassandra/v3/pilot_test.go @@ -1,8 +1,14 @@ package v3 import ( + "io/ioutil" "testing" + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + shutil "github.com/termie/go-shutil" + + "github.com/jetstack/navigator/internal/test/util/testfs" "github.com/jetstack/navigator/pkg/api/version" "github.com/jetstack/navigator/pkg/apis/navigator/v1alpha1" "github.com/jetstack/navigator/pkg/cassandra/nodetool" @@ -87,3 +93,61 @@ func TestPilotSyncFunc(t *testing.T) { ) } } + +func TestWriteConfig(t *testing.T) { + t.Run( + "create cassandra.yaml", + func(t *testing.T) { + tfs := testfs.New(t) + etc := tfs.TempDir("etc") + cassConfigPath := etc + "/cassandra" + err := shutil.CopyTree("testdata", cassConfigPath, nil) + require.NoError(t, err) + + pilotResource := &v1alpha1.Pilot{} + p := &Pilot{ + Options: &PilotOptions{ + CassandraConfigPath: cassConfigPath, + }, + } + + err = p.WriteConfig(pilotResource) + require.NoError(t, err) + + cassConfig, err := ioutil.ReadFile(cassConfigPath + "/cassandra.yaml") + require.NoError(t, err) + assert.Contains(t, string(cassConfig), cassSnitch) + assert.Contains(t, string(cassConfig), cassSeedProvider) + }, + ) + t.Run( + "create cassandra-rackdc.properties", + func(t *testing.T) { + tfs := testfs.New(t) + etc := tfs.TempDir("etc") + cassConfigPath := etc + "/cassandra" + err := shutil.CopyTree("testdata", cassConfigPath, nil) + require.NoError(t, err) + + expectedRack := "rack-name-foo" + expectedDC := "dc-bar" + + pilotResource := &v1alpha1.Pilot{} + p := &Pilot{ + Options: &PilotOptions{ + CassandraConfigPath: cassConfigPath, + CassandraRack: expectedRack, + CassandraDC: expectedDC, + }, + } + + err = p.WriteConfig(pilotResource) + require.NoError(t, err) + + cassConfig, err := ioutil.ReadFile(cassConfigPath + "/cassandra-rackdc.properties") + require.NoError(t, err) + assert.Contains(t, string(cassConfig), expectedRack) + assert.Contains(t, string(cassConfig), expectedDC) + }, + ) +} diff --git a/pkg/pilot/cassandra/v3/testdata/cassandra-rackdc.properties b/pkg/pilot/cassandra/v3/testdata/cassandra-rackdc.properties new file mode 100644 index 000000000..2ea604384 --- /dev/null +++ b/pkg/pilot/cassandra/v3/testdata/cassandra-rackdc.properties @@ -0,0 +1,27 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +# These properties are used with GossipingPropertyFileSnitch and will +# indicate the rack and dc for this node +dc=dc1 +rack=rack1 + +# Add a suffix to a datacenter name. Used by the Ec2Snitch and Ec2MultiRegionSnitch +# to append a string to the EC2 region name. +#dc_suffix= + +# Uncomment the following line to make this snitch prefer the internal ip when possible, as the Ec2MultiRegionSnitch does. +# prefer_local=true diff --git a/pkg/pilot/cassandra/v3/testdata/cassandra.yaml b/pkg/pilot/cassandra/v3/testdata/cassandra.yaml new file mode 100644 index 000000000..68237459a --- /dev/null +++ b/pkg/pilot/cassandra/v3/testdata/cassandra.yaml @@ -0,0 +1,1237 @@ +# Cassandra storage config YAML + +# NOTE: +# See http://wiki.apache.org/cassandra/StorageConfiguration for +# full explanations of configuration directives +# /NOTE + +# The name of the cluster. This is mainly used to prevent machines in +# one logical cluster from joining another. +cluster_name: 'Test Cluster' + +# This defines the number of tokens randomly assigned to this node on the ring +# The more tokens, relative to other nodes, the larger the proportion of data +# that this node will store. You probably want all nodes to have the same number +# of tokens assuming they have equal hardware capability. +# +# If you leave this unspecified, Cassandra will use the default of 1 token for legacy compatibility, +# and will use the initial_token as described below. +# +# Specifying initial_token will override this setting on the node's initial start, +# on subsequent starts, this setting will apply even if initial token is set. +# +# If you already have a cluster with 1 token per node, and wish to migrate to +# multiple tokens per node, see http://wiki.apache.org/cassandra/Operations +num_tokens: 256 + +# Triggers automatic allocation of num_tokens tokens for this node. The allocation +# algorithm attempts to choose tokens in a way that optimizes replicated load over +# the nodes in the datacenter for the replication strategy used by the specified +# keyspace. +# +# The load assigned to each node will be close to proportional to its number of +# vnodes. +# +# Only supported with the Murmur3Partitioner. +# allocate_tokens_for_keyspace: KEYSPACE + +# initial_token allows you to specify tokens manually. While you can use it with +# vnodes (num_tokens > 1, above) -- in which case you should provide a +# comma-separated list -- it's primarily used when adding nodes to legacy clusters +# that do not have vnodes enabled. +# initial_token: + +# See http://wiki.apache.org/cassandra/HintedHandoff +# May either be "true" or "false" to enable globally +hinted_handoff_enabled: true + +# When hinted_handoff_enabled is true, a black list of data centers that will not +# perform hinted handoff +# hinted_handoff_disabled_datacenters: +# - DC1 +# - DC2 + +# this defines the maximum amount of time a dead host will have hints +# generated. After it has been dead this long, new hints for it will not be +# created until it has been seen alive and gone down again. +max_hint_window_in_ms: 10800000 # 3 hours + +# Maximum throttle in KBs per second, per delivery thread. This will be +# reduced proportionally to the number of nodes in the cluster. (If there +# are two nodes in the cluster, each delivery thread will use the maximum +# rate; if there are three, each will throttle to half of the maximum, +# since we expect two nodes to be delivering hints simultaneously.) +hinted_handoff_throttle_in_kb: 1024 + +# Number of threads with which to deliver hints; +# Consider increasing this number when you have multi-dc deployments, since +# cross-dc handoff tends to be slower +max_hints_delivery_threads: 2 + +# Directory where Cassandra should store hints. +# If not set, the default directory is $CASSANDRA_HOME/data/hints. +# hints_directory: /var/lib/cassandra/hints + +# How often hints should be flushed from the internal buffers to disk. +# Will *not* trigger fsync. +hints_flush_period_in_ms: 10000 + +# Maximum size for a single hints file, in megabytes. +max_hints_file_size_in_mb: 128 + +# Compression to apply to the hint files. If omitted, hints files +# will be written uncompressed. LZ4, Snappy, and Deflate compressors +# are supported. +#hints_compression: +# - class_name: LZ4Compressor +# parameters: +# - + +# Maximum throttle in KBs per second, total. This will be +# reduced proportionally to the number of nodes in the cluster. +batchlog_replay_throttle_in_kb: 1024 + +# Authentication backend, implementing IAuthenticator; used to identify users +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthenticator, +# PasswordAuthenticator}. +# +# - AllowAllAuthenticator performs no checks - set it to disable authentication. +# - PasswordAuthenticator relies on username/password pairs to authenticate +# users. It keeps usernames and hashed passwords in system_auth.roles table. +# Please increase system_auth keyspace replication factor if you use this authenticator. +# If using PasswordAuthenticator, CassandraRoleManager must also be used (see below) +authenticator: AllowAllAuthenticator + +# Authorization backend, implementing IAuthorizer; used to limit access/provide permissions +# Out of the box, Cassandra provides org.apache.cassandra.auth.{AllowAllAuthorizer, +# CassandraAuthorizer}. +# +# - AllowAllAuthorizer allows any action to any user - set it to disable authorization. +# - CassandraAuthorizer stores permissions in system_auth.role_permissions table. Please +# increase system_auth keyspace replication factor if you use this authorizer. +authorizer: AllowAllAuthorizer + +# Part of the Authentication & Authorization backend, implementing IRoleManager; used +# to maintain grants and memberships between roles. +# Out of the box, Cassandra provides org.apache.cassandra.auth.CassandraRoleManager, +# which stores role information in the system_auth keyspace. Most functions of the +# IRoleManager require an authenticated login, so unless the configured IAuthenticator +# actually implements authentication, most of this functionality will be unavailable. +# +# - CassandraRoleManager stores role data in the system_auth keyspace. Please +# increase system_auth keyspace replication factor if you use this role manager. +role_manager: CassandraRoleManager + +# Validity period for roles cache (fetching granted roles can be an expensive +# operation depending on the role manager, CassandraRoleManager is one example) +# Granted roles are cached for authenticated sessions in AuthenticatedUser and +# after the period specified here, become eligible for (async) reload. +# Defaults to 2000, set to 0 to disable caching entirely. +# Will be disabled automatically for AllowAllAuthenticator. +roles_validity_in_ms: 2000 + +# Refresh interval for roles cache (if enabled). +# After this interval, cache entries become eligible for refresh. Upon next +# access, an async reload is scheduled and the old value returned until it +# completes. If roles_validity_in_ms is non-zero, then this must be +# also. +# Defaults to the same value as roles_validity_in_ms. +# roles_update_interval_in_ms: 2000 + +# Validity period for permissions cache (fetching permissions can be an +# expensive operation depending on the authorizer, CassandraAuthorizer is +# one example). Defaults to 2000, set to 0 to disable. +# Will be disabled automatically for AllowAllAuthorizer. +permissions_validity_in_ms: 2000 + +# Refresh interval for permissions cache (if enabled). +# After this interval, cache entries become eligible for refresh. Upon next +# access, an async reload is scheduled and the old value returned until it +# completes. If permissions_validity_in_ms is non-zero, then this must be +# also. +# Defaults to the same value as permissions_validity_in_ms. +# permissions_update_interval_in_ms: 2000 + +# Validity period for credentials cache. This cache is tightly coupled to +# the provided PasswordAuthenticator implementation of IAuthenticator. If +# another IAuthenticator implementation is configured, this cache will not +# be automatically used and so the following settings will have no effect. +# Please note, credentials are cached in their encrypted form, so while +# activating this cache may reduce the number of queries made to the +# underlying table, it may not bring a significant reduction in the +# latency of individual authentication attempts. +# Defaults to 2000, set to 0 to disable credentials caching. +credentials_validity_in_ms: 2000 + +# Refresh interval for credentials cache (if enabled). +# After this interval, cache entries become eligible for refresh. Upon next +# access, an async reload is scheduled and the old value returned until it +# completes. If credentials_validity_in_ms is non-zero, then this must be +# also. +# Defaults to the same value as credentials_validity_in_ms. +# credentials_update_interval_in_ms: 2000 + +# The partitioner is responsible for distributing groups of rows (by +# partition key) across nodes in the cluster. You should leave this +# alone for new clusters. The partitioner can NOT be changed without +# reloading all data, so when upgrading you should set this to the +# same partitioner you were already using. +# +# Besides Murmur3Partitioner, partitioners included for backwards +# compatibility include RandomPartitioner, ByteOrderedPartitioner, and +# OrderPreservingPartitioner. +# +partitioner: org.apache.cassandra.dht.Murmur3Partitioner + +# Directories where Cassandra should store data on disk. Cassandra +# will spread data evenly across them, subject to the granularity of +# the configured compaction strategy. +# If not set, the default directory is $CASSANDRA_HOME/data/data. +# data_file_directories: +# - /var/lib/cassandra/data + +# commit log. when running on magnetic HDD, this should be a +# separate spindle than the data directories. +# If not set, the default directory is $CASSANDRA_HOME/data/commitlog. +# commitlog_directory: /var/lib/cassandra/commitlog + +# Enable / disable CDC functionality on a per-node basis. This modifies the logic used +# for write path allocation rejection (standard: never reject. cdc: reject Mutation +# containing a CDC-enabled table if at space limit in cdc_raw_directory). +cdc_enabled: false + +# CommitLogSegments are moved to this directory on flush if cdc_enabled: true and the +# segment contains mutations for a CDC-enabled table. This should be placed on a +# separate spindle than the data directories. If not set, the default directory is +# $CASSANDRA_HOME/data/cdc_raw. +# cdc_raw_directory: /var/lib/cassandra/cdc_raw + +# Policy for data disk failures: +# +# die +# shut down gossip and client transports and kill the JVM for any fs errors or +# single-sstable errors, so the node can be replaced. +# +# stop_paranoid +# shut down gossip and client transports even for single-sstable errors, +# kill the JVM for errors during startup. +# +# stop +# shut down gossip and client transports, leaving the node effectively dead, but +# can still be inspected via JMX, kill the JVM for errors during startup. +# +# best_effort +# stop using the failed disk and respond to requests based on +# remaining available sstables. This means you WILL see obsolete +# data at CL.ONE! +# +# ignore +# ignore fatal errors and let requests fail, as in pre-1.2 Cassandra +disk_failure_policy: stop + +# Policy for commit disk failures: +# +# die +# shut down gossip and Thrift and kill the JVM, so the node can be replaced. +# +# stop +# shut down gossip and Thrift, leaving the node effectively dead, but +# can still be inspected via JMX. +# +# stop_commit +# shutdown the commit log, letting writes collect but +# continuing to service reads, as in pre-2.0.5 Cassandra +# +# ignore +# ignore fatal errors and let the batches fail +commit_failure_policy: stop + +# Maximum size of the native protocol prepared statement cache +# +# Valid values are either "auto" (omitting the value) or a value greater 0. +# +# Note that specifying a too large value will result in long running GCs and possbily +# out-of-memory errors. Keep the value at a small fraction of the heap. +# +# If you constantly see "prepared statements discarded in the last minute because +# cache limit reached" messages, the first step is to investigate the root cause +# of these messages and check whether prepared statements are used correctly - +# i.e. use bind markers for variable parts. +# +# Do only change the default value, if you really have more prepared statements than +# fit in the cache. In most cases it is not neccessary to change this value. +# Constantly re-preparing statements is a performance penalty. +# +# Default value ("auto") is 1/256th of the heap or 10MB, whichever is greater +prepared_statements_cache_size_mb: + +# Maximum size of the Thrift prepared statement cache +# +# If you do not use Thrift at all, it is safe to leave this value at "auto". +# +# See description of 'prepared_statements_cache_size_mb' above for more information. +# +# Default value ("auto") is 1/256th of the heap or 10MB, whichever is greater +thrift_prepared_statements_cache_size_mb: + +# Maximum size of the key cache in memory. +# +# Each key cache hit saves 1 seek and each row cache hit saves 2 seeks at the +# minimum, sometimes more. The key cache is fairly tiny for the amount of +# time it saves, so it's worthwhile to use it at large numbers. +# The row cache saves even more time, but must contain the entire row, +# so it is extremely space-intensive. It's best to only use the +# row cache if you have hot rows or static rows. +# +# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup. +# +# Default value is empty to make it "auto" (min(5% of Heap (in MB), 100MB)). Set to 0 to disable key cache. +key_cache_size_in_mb: + +# Duration in seconds after which Cassandra should +# save the key cache. Caches are saved to saved_caches_directory as +# specified in this configuration file. +# +# Saved caches greatly improve cold-start speeds, and is relatively cheap in +# terms of I/O for the key cache. Row cache saving is much more expensive and +# has limited use. +# +# Default is 14400 or 4 hours. +key_cache_save_period: 14400 + +# Number of keys from the key cache to save +# Disabled by default, meaning all keys are going to be saved +# key_cache_keys_to_save: 100 + +# Row cache implementation class name. Available implementations: +# +# org.apache.cassandra.cache.OHCProvider +# Fully off-heap row cache implementation (default). +# +# org.apache.cassandra.cache.SerializingCacheProvider +# This is the row cache implementation availabile +# in previous releases of Cassandra. +# row_cache_class_name: org.apache.cassandra.cache.OHCProvider + +# Maximum size of the row cache in memory. +# Please note that OHC cache implementation requires some additional off-heap memory to manage +# the map structures and some in-flight memory during operations before/after cache entries can be +# accounted against the cache capacity. This overhead is usually small compared to the whole capacity. +# Do not specify more memory that the system can afford in the worst usual situation and leave some +# headroom for OS block level cache. Do never allow your system to swap. +# +# Default value is 0, to disable row caching. +row_cache_size_in_mb: 0 + +# Duration in seconds after which Cassandra should save the row cache. +# Caches are saved to saved_caches_directory as specified in this configuration file. +# +# Saved caches greatly improve cold-start speeds, and is relatively cheap in +# terms of I/O for the key cache. Row cache saving is much more expensive and +# has limited use. +# +# Default is 0 to disable saving the row cache. +row_cache_save_period: 0 + +# Number of keys from the row cache to save. +# Specify 0 (which is the default), meaning all keys are going to be saved +# row_cache_keys_to_save: 100 + +# Maximum size of the counter cache in memory. +# +# Counter cache helps to reduce counter locks' contention for hot counter cells. +# In case of RF = 1 a counter cache hit will cause Cassandra to skip the read before +# write entirely. With RF > 1 a counter cache hit will still help to reduce the duration +# of the lock hold, helping with hot counter cell updates, but will not allow skipping +# the read entirely. Only the local (clock, count) tuple of a counter cell is kept +# in memory, not the whole counter, so it's relatively cheap. +# +# NOTE: if you reduce the size, you may not get you hottest keys loaded on startup. +# +# Default value is empty to make it "auto" (min(2.5% of Heap (in MB), 50MB)). Set to 0 to disable counter cache. +# NOTE: if you perform counter deletes and rely on low gcgs, you should disable the counter cache. +counter_cache_size_in_mb: + +# Duration in seconds after which Cassandra should +# save the counter cache (keys only). Caches are saved to saved_caches_directory as +# specified in this configuration file. +# +# Default is 7200 or 2 hours. +counter_cache_save_period: 7200 + +# Number of keys from the counter cache to save +# Disabled by default, meaning all keys are going to be saved +# counter_cache_keys_to_save: 100 + +# saved caches +# If not set, the default directory is $CASSANDRA_HOME/data/saved_caches. +# saved_caches_directory: /var/lib/cassandra/saved_caches + +# commitlog_sync may be either "periodic" or "batch." +# +# When in batch mode, Cassandra won't ack writes until the commit log +# has been fsynced to disk. It will wait +# commitlog_sync_batch_window_in_ms milliseconds between fsyncs. +# This window should be kept short because the writer threads will +# be unable to do extra work while waiting. (You may need to increase +# concurrent_writes for the same reason.) +# +# commitlog_sync: batch +# commitlog_sync_batch_window_in_ms: 2 +# +# the other option is "periodic" where writes may be acked immediately +# and the CommitLog is simply synced every commitlog_sync_period_in_ms +# milliseconds. +commitlog_sync: periodic +commitlog_sync_period_in_ms: 10000 + +# The size of the individual commitlog file segments. A commitlog +# segment may be archived, deleted, or recycled once all the data +# in it (potentially from each columnfamily in the system) has been +# flushed to sstables. +# +# The default size is 32, which is almost always fine, but if you are +# archiving commitlog segments (see commitlog_archiving.properties), +# then you probably want a finer granularity of archiving; 8 or 16 MB +# is reasonable. +# Max mutation size is also configurable via max_mutation_size_in_kb setting in +# cassandra.yaml. The default is half the size commitlog_segment_size_in_mb * 1024. +# This should be positive and less than 2048. +# +# NOTE: If max_mutation_size_in_kb is set explicitly then commitlog_segment_size_in_mb must +# be set to at least twice the size of max_mutation_size_in_kb / 1024 +# +commitlog_segment_size_in_mb: 32 + +# Compression to apply to the commit log. If omitted, the commit log +# will be written uncompressed. LZ4, Snappy, and Deflate compressors +# are supported. +# commitlog_compression: +# - class_name: LZ4Compressor +# parameters: +# - + +# any class that implements the SeedProvider interface and has a +# constructor that takes a Map of parameters will do. +seed_provider: + # Addresses of hosts that are deemed contact points. + # Cassandra nodes use this list of hosts to find each other and learn + # the topology of the ring. You must change this if you are running + # multiple nodes! + - class_name: org.apache.cassandra.locator.SimpleSeedProvider + parameters: + # seeds is actually a comma-delimited list of addresses. + # Ex: ",," + - seeds: "127.0.0.1" + +# For workloads with more data than can fit in memory, Cassandra's +# bottleneck will be reads that need to fetch data from +# disk. "concurrent_reads" should be set to (16 * number_of_drives) in +# order to allow the operations to enqueue low enough in the stack +# that the OS and drives can reorder them. Same applies to +# "concurrent_counter_writes", since counter writes read the current +# values before incrementing and writing them back. +# +# On the other hand, since writes are almost never IO bound, the ideal +# number of "concurrent_writes" is dependent on the number of cores in +# your system; (8 * number_of_cores) is a good rule of thumb. +concurrent_reads: 32 +concurrent_writes: 32 +concurrent_counter_writes: 32 + +# For materialized view writes, as there is a read involved, so this should +# be limited by the less of concurrent reads or concurrent writes. +concurrent_materialized_view_writes: 32 + +# Maximum memory to use for sstable chunk cache and buffer pooling. +# 32MB of this are reserved for pooling buffers, the rest is used as an +# cache that holds uncompressed sstable chunks. +# Defaults to the smaller of 1/4 of heap or 512MB. This pool is allocated off-heap, +# so is in addition to the memory allocated for heap. The cache also has on-heap +# overhead which is roughly 128 bytes per chunk (i.e. 0.2% of the reserved size +# if the default 64k chunk size is used). +# Memory is only allocated when needed. +# file_cache_size_in_mb: 512 + +# Flag indicating whether to allocate on or off heap when the sstable buffer +# pool is exhausted, that is when it has exceeded the maximum memory +# file_cache_size_in_mb, beyond which it will not cache buffers but allocate on request. + +# buffer_pool_use_heap_if_exhausted: true + +# The strategy for optimizing disk read +# Possible values are: +# ssd (for solid state disks, the default) +# spinning (for spinning disks) +# disk_optimization_strategy: ssd + +# Total permitted memory to use for memtables. Cassandra will stop +# accepting writes when the limit is exceeded until a flush completes, +# and will trigger a flush based on memtable_cleanup_threshold +# If omitted, Cassandra will set both to 1/4 the size of the heap. +# memtable_heap_space_in_mb: 2048 +# memtable_offheap_space_in_mb: 2048 + +# memtable_cleanup_threshold is deprecated. The default calculation +# is the only reasonable choice. See the comments on memtable_flush_writers +# for more information. +# +# Ratio of occupied non-flushing memtable size to total permitted size +# that will trigger a flush of the largest memtable. Larger mct will +# mean larger flushes and hence less compaction, but also less concurrent +# flush activity which can make it difficult to keep your disks fed +# under heavy write load. +# +# memtable_cleanup_threshold defaults to 1 / (memtable_flush_writers + 1) +# memtable_cleanup_threshold: 0.11 + +# Specify the way Cassandra allocates and manages memtable memory. +# Options are: +# +# heap_buffers +# on heap nio buffers +# +# offheap_buffers +# off heap (direct) nio buffers +# +# offheap_objects +# off heap objects +memtable_allocation_type: heap_buffers + +# Total space to use for commit logs on disk. +# +# If space gets above this value, Cassandra will flush every dirty CF +# in the oldest segment and remove it. So a small total commitlog space +# will tend to cause more flush activity on less-active columnfamilies. +# +# The default value is the smaller of 8192, and 1/4 of the total space +# of the commitlog volume. +# +# commitlog_total_space_in_mb: 8192 + +# This sets the number of memtable flush writer threads per disk +# as well as the total number of memtables that can be flushed concurrently. +# These are generally a combination of compute and IO bound. +# +# Memtable flushing is more CPU efficient than memtable ingest and a single thread +# can keep up with the ingest rate of a whole server on a single fast disk +# until it temporarily becomes IO bound under contention typically with compaction. +# At that point you need multiple flush threads. At some point in the future +# it may become CPU bound all the time. +# +# You can tell if flushing is falling behind using the MemtablePool.BlockedOnAllocation +# metric which should be 0, but will be non-zero if threads are blocked waiting on flushing +# to free memory. +# +# memtable_flush_writers defaults to two for a single data directory. +# This means that two memtables can be flushed concurrently to the single data directory. +# If you have multiple data directories the default is one memtable flushing at a time +# but the flush will use a thread per data directory so you will get two or more writers. +# +# Two is generally enough to flush on a fast disk [array] mounted as a single data directory. +# Adding more flush writers will result in smaller more frequent flushes that introduce more +# compaction overhead. +# +# There is a direct tradeoff between number of memtables that can be flushed concurrently +# and flush size and frequency. More is not better you just need enough flush writers +# to never stall waiting for flushing to free memory. +# +#memtable_flush_writers: 2 + +# Total space to use for change-data-capture logs on disk. +# +# If space gets above this value, Cassandra will throw WriteTimeoutException +# on Mutations including tables with CDC enabled. A CDCCompactor is responsible +# for parsing the raw CDC logs and deleting them when parsing is completed. +# +# The default value is the min of 4096 mb and 1/8th of the total space +# of the drive where cdc_raw_directory resides. +# cdc_total_space_in_mb: 4096 + +# When we hit our cdc_raw limit and the CDCCompactor is either running behind +# or experiencing backpressure, we check at the following interval to see if any +# new space for cdc-tracked tables has been made available. Default to 250ms +# cdc_free_space_check_interval_ms: 250 + +# A fixed memory pool size in MB for for SSTable index summaries. If left +# empty, this will default to 5% of the heap size. If the memory usage of +# all index summaries exceeds this limit, SSTables with low read rates will +# shrink their index summaries in order to meet this limit. However, this +# is a best-effort process. In extreme conditions Cassandra may need to use +# more than this amount of memory. +index_summary_capacity_in_mb: + +# How frequently index summaries should be resampled. This is done +# periodically to redistribute memory from the fixed-size pool to sstables +# proportional their recent read rates. Setting to -1 will disable this +# process, leaving existing index summaries at their current sampling level. +index_summary_resize_interval_in_minutes: 60 + +# Whether to, when doing sequential writing, fsync() at intervals in +# order to force the operating system to flush the dirty +# buffers. Enable this to avoid sudden dirty buffer flushing from +# impacting read latencies. Almost always a good idea on SSDs; not +# necessarily on platters. +trickle_fsync: false +trickle_fsync_interval_in_kb: 10240 + +# TCP port, for commands and data +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +storage_port: 7000 + +# SSL port, for encrypted communication. Unused unless enabled in +# encryption_options +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +ssl_storage_port: 7001 + +# Address or interface to bind to and tell other Cassandra nodes to connect to. +# You _must_ change this if you want multiple nodes to be able to communicate! +# +# Set listen_address OR listen_interface, not both. +# +# Leaving it blank leaves it up to InetAddress.getLocalHost(). This +# will always do the Right Thing _if_ the node is properly configured +# (hostname, name resolution, etc), and the Right Thing is to use the +# address associated with the hostname (it might not be). +# +# Setting listen_address to 0.0.0.0 is always wrong. +# +listen_address: localhost + +# Set listen_address OR listen_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# listen_interface: eth0 + +# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address +# you can specify which should be chosen using listen_interface_prefer_ipv6. If false the first ipv4 +# address will be used. If true the first ipv6 address will be used. Defaults to false preferring +# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. +# listen_interface_prefer_ipv6: false + +# Address to broadcast to other Cassandra nodes +# Leaving this blank will set it to the same value as listen_address +# broadcast_address: 1.2.3.4 + +# When using multiple physical network interfaces, set this +# to true to listen on broadcast_address in addition to +# the listen_address, allowing nodes to communicate in both +# interfaces. +# Ignore this property if the network configuration automatically +# routes between the public and private networks such as EC2. +# listen_on_broadcast_address: false + +# Internode authentication backend, implementing IInternodeAuthenticator; +# used to allow/disallow connections from peer nodes. +# internode_authenticator: org.apache.cassandra.auth.AllowAllInternodeAuthenticator + +# Whether to start the native transport server. +# Please note that the address on which the native transport is bound is the +# same as the rpc_address. The port however is different and specified below. +start_native_transport: true +# port for the CQL native transport to listen for clients on +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +native_transport_port: 9042 +# Enabling native transport encryption in client_encryption_options allows you to either use +# encryption for the standard port or to use a dedicated, additional port along with the unencrypted +# standard native_transport_port. +# Enabling client encryption and keeping native_transport_port_ssl disabled will use encryption +# for native_transport_port. Setting native_transport_port_ssl to a different value +# from native_transport_port will use encryption for native_transport_port_ssl while +# keeping native_transport_port unencrypted. +# native_transport_port_ssl: 9142 +# The maximum threads for handling requests when the native transport is used. +# This is similar to rpc_max_threads though the default differs slightly (and +# there is no native_transport_min_threads, idle threads will always be stopped +# after 30 seconds). +# native_transport_max_threads: 128 +# +# The maximum size of allowed frame. Frame (requests) larger than this will +# be rejected as invalid. The default is 256MB. If you're changing this parameter, +# you may want to adjust max_value_size_in_mb accordingly. This should be positive and less than 2048. +# native_transport_max_frame_size_in_mb: 256 + +# The maximum number of concurrent client connections. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections: -1 + +# The maximum number of concurrent client connections per source ip. +# The default is -1, which means unlimited. +# native_transport_max_concurrent_connections_per_ip: -1 + +# Whether to start the thrift rpc server. +start_rpc: false + +# The address or interface to bind the Thrift RPC service and native transport +# server to. +# +# Set rpc_address OR rpc_interface, not both. +# +# Leaving rpc_address blank has the same effect as on listen_address +# (i.e. it will be based on the configured hostname of the node). +# +# Note that unlike listen_address, you can specify 0.0.0.0, but you must also +# set broadcast_rpc_address to a value other than 0.0.0.0. +# +# For security reasons, you should not expose this port to the internet. Firewall it if needed. +rpc_address: localhost + +# Set rpc_address OR rpc_interface, not both. Interfaces must correspond +# to a single address, IP aliasing is not supported. +# rpc_interface: eth1 + +# If you choose to specify the interface by name and the interface has an ipv4 and an ipv6 address +# you can specify which should be chosen using rpc_interface_prefer_ipv6. If false the first ipv4 +# address will be used. If true the first ipv6 address will be used. Defaults to false preferring +# ipv4. If there is only one address it will be selected regardless of ipv4/ipv6. +# rpc_interface_prefer_ipv6: false + +# port for Thrift to listen for clients on +rpc_port: 9160 + +# RPC address to broadcast to drivers and other Cassandra nodes. This cannot +# be set to 0.0.0.0. If left blank, this will be set to the value of +# rpc_address. If rpc_address is set to 0.0.0.0, broadcast_rpc_address must +# be set. +# broadcast_rpc_address: 1.2.3.4 + +# enable or disable keepalive on rpc/native connections +rpc_keepalive: true + +# Cassandra provides two out-of-the-box options for the RPC Server: +# +# sync +# One thread per thrift connection. For a very large number of clients, memory +# will be your limiting factor. On a 64 bit JVM, 180KB is the minimum stack size +# per thread, and that will correspond to your use of virtual memory (but physical memory +# may be limited depending on use of stack space). +# +# hsha +# Stands for "half synchronous, half asynchronous." All thrift clients are handled +# asynchronously using a small number of threads that does not vary with the amount +# of thrift clients (and thus scales well to many clients). The rpc requests are still +# synchronous (one thread per active request). If hsha is selected then it is essential +# that rpc_max_threads is changed from the default value of unlimited. +# +# The default is sync because on Windows hsha is about 30% slower. On Linux, +# sync/hsha performance is about the same, with hsha of course using less memory. +# +# Alternatively, can provide your own RPC server by providing the fully-qualified class name +# of an o.a.c.t.TServerFactory that can create an instance of it. +rpc_server_type: sync + +# Uncomment rpc_min|max_thread to set request pool size limits. +# +# Regardless of your choice of RPC server (see above), the number of maximum requests in the +# RPC thread pool dictates how many concurrent requests are possible (but if you are using the sync +# RPC server, it also dictates the number of clients that can be connected at all). +# +# The default is unlimited and thus provides no protection against clients overwhelming the server. You are +# encouraged to set a maximum that makes sense for you in production, but do keep in mind that +# rpc_max_threads represents the maximum number of client requests this server may execute concurrently. +# +# rpc_min_threads: 16 +# rpc_max_threads: 2048 + +# uncomment to set socket buffer sizes on rpc connections +# rpc_send_buff_size_in_bytes: +# rpc_recv_buff_size_in_bytes: + +# Uncomment to set socket buffer size for internode communication +# Note that when setting this, the buffer size is limited by net.core.wmem_max +# and when not setting it it is defined by net.ipv4.tcp_wmem +# See also: +# /proc/sys/net/core/wmem_max +# /proc/sys/net/core/rmem_max +# /proc/sys/net/ipv4/tcp_wmem +# /proc/sys/net/ipv4/tcp_wmem +# and 'man tcp' +# internode_send_buff_size_in_bytes: + +# Uncomment to set socket buffer size for internode communication +# Note that when setting this, the buffer size is limited by net.core.wmem_max +# and when not setting it it is defined by net.ipv4.tcp_wmem +# internode_recv_buff_size_in_bytes: + +# Frame size for thrift (maximum message length). +thrift_framed_transport_size_in_mb: 15 + +# Set to true to have Cassandra create a hard link to each sstable +# flushed or streamed locally in a backups/ subdirectory of the +# keyspace data. Removing these links is the operator's +# responsibility. +incremental_backups: false + +# Whether or not to take a snapshot before each compaction. Be +# careful using this option, since Cassandra won't clean up the +# snapshots for you. Mostly useful if you're paranoid when there +# is a data format change. +snapshot_before_compaction: false + +# Whether or not a snapshot is taken of the data before keyspace truncation +# or dropping of column families. The STRONGLY advised default of true +# should be used to provide data safety. If you set this flag to false, you will +# lose data on truncation or drop. +auto_snapshot: true + +# Granularity of the collation index of rows within a partition. +# Increase if your rows are large, or if you have a very large +# number of rows per partition. The competing goals are these: +# +# - a smaller granularity means more index entries are generated +# and looking up rows withing the partition by collation column +# is faster +# - but, Cassandra will keep the collation index in memory for hot +# rows (as part of the key cache), so a larger granularity means +# you can cache more hot rows +column_index_size_in_kb: 64 + +# Per sstable indexed key cache entries (the collation index in memory +# mentioned above) exceeding this size will not be held on heap. +# This means that only partition information is held on heap and the +# index entries are read from disk. +# +# Note that this size refers to the size of the +# serialized index information and not the size of the partition. +column_index_cache_size_in_kb: 2 + +# Number of simultaneous compactions to allow, NOT including +# validation "compactions" for anti-entropy repair. Simultaneous +# compactions can help preserve read performance in a mixed read/write +# workload, by mitigating the tendency of small sstables to accumulate +# during a single long running compactions. The default is usually +# fine and if you experience problems with compaction running too +# slowly or too fast, you should look at +# compaction_throughput_mb_per_sec first. +# +# concurrent_compactors defaults to the smaller of (number of disks, +# number of cores), with a minimum of 2 and a maximum of 8. +# +# If your data directories are backed by SSD, you should increase this +# to the number of cores. +#concurrent_compactors: 1 + +# Throttles compaction to the given total throughput across the entire +# system. The faster you insert data, the faster you need to compact in +# order to keep the sstable count down, but in general, setting this to +# 16 to 32 times the rate you are inserting data is more than sufficient. +# Setting this to 0 disables throttling. Note that this account for all types +# of compaction, including validation compaction. +compaction_throughput_mb_per_sec: 16 + +# When compacting, the replacement sstable(s) can be opened before they +# are completely written, and used in place of the prior sstables for +# any range that has been written. This helps to smoothly transfer reads +# between the sstables, reducing page cache churn and keeping hot rows hot +sstable_preemptive_open_interval_in_mb: 50 + +# Throttles all outbound streaming file transfers on this node to the +# given total throughput in Mbps. This is necessary because Cassandra does +# mostly sequential IO when streaming data during bootstrap or repair, which +# can lead to saturating the network connection and degrading rpc performance. +# When unset, the default is 200 Mbps or 25 MB/s. +# stream_throughput_outbound_megabits_per_sec: 200 + +# Throttles all streaming file transfer between the datacenters, +# this setting allows users to throttle inter dc stream throughput in addition +# to throttling all network stream traffic as configured with +# stream_throughput_outbound_megabits_per_sec +# When unset, the default is 200 Mbps or 25 MB/s +# inter_dc_stream_throughput_outbound_megabits_per_sec: 200 + +# How long the coordinator should wait for read operations to complete +read_request_timeout_in_ms: 5000 +# How long the coordinator should wait for seq or index scans to complete +range_request_timeout_in_ms: 10000 +# How long the coordinator should wait for writes to complete +write_request_timeout_in_ms: 2000 +# How long the coordinator should wait for counter writes to complete +counter_write_request_timeout_in_ms: 5000 +# How long a coordinator should continue to retry a CAS operation +# that contends with other proposals for the same row +cas_contention_timeout_in_ms: 1000 +# How long the coordinator should wait for truncates to complete +# (This can be much longer, because unless auto_snapshot is disabled +# we need to flush first so we can snapshot before removing the data.) +truncate_request_timeout_in_ms: 60000 +# The default timeout for other, miscellaneous operations +request_timeout_in_ms: 10000 + +# How long before a node logs slow queries. Select queries that take longer than +# this timeout to execute, will generate an aggregated log message, so that slow queries +# can be identified. Set this value to zero to disable slow query logging. +slow_query_log_timeout_in_ms: 500 + +# Enable operation timeout information exchange between nodes to accurately +# measure request timeouts. If disabled, replicas will assume that requests +# were forwarded to them instantly by the coordinator, which means that +# under overload conditions we will waste that much extra time processing +# already-timed-out requests. +# +# Warning: before enabling this property make sure to ntp is installed +# and the times are synchronized between the nodes. +cross_node_timeout: false + +# Set keep-alive period for streaming +# This node will send a keep-alive message periodically with this period. +# If the node does not receive a keep-alive message from the peer for +# 2 keep-alive cycles the stream session times out and fail +# Default value is 300s (5 minutes), which means stalled stream +# times out in 10 minutes by default +# streaming_keep_alive_period_in_secs: 300 + +# phi value that must be reached for a host to be marked down. +# most users should never need to adjust this. +# phi_convict_threshold: 8 + +# endpoint_snitch -- Set this to a class that implements +# IEndpointSnitch. The snitch has two functions: +# +# - it teaches Cassandra enough about your network topology to route +# requests efficiently +# - it allows Cassandra to spread replicas around your cluster to avoid +# correlated failures. It does this by grouping machines into +# "datacenters" and "racks." Cassandra will do its best not to have +# more than one replica on the same "rack" (which may not actually +# be a physical location) +# +# CASSANDRA WILL NOT ALLOW YOU TO SWITCH TO AN INCOMPATIBLE SNITCH +# ONCE DATA IS INSERTED INTO THE CLUSTER. This would cause data loss. +# This means that if you start with the default SimpleSnitch, which +# locates every node on "rack1" in "datacenter1", your only options +# if you need to add another datacenter are GossipingPropertyFileSnitch +# (and the older PFS). From there, if you want to migrate to an +# incompatible snitch like Ec2Snitch you can do it by adding new nodes +# under Ec2Snitch (which will locate them in a new "datacenter") and +# decommissioning the old ones. +# +# Out of the box, Cassandra provides: +# +# SimpleSnitch: +# Treats Strategy order as proximity. This can improve cache +# locality when disabling read repair. Only appropriate for +# single-datacenter deployments. +# +# GossipingPropertyFileSnitch +# This should be your go-to snitch for production use. The rack +# and datacenter for the local node are defined in +# cassandra-rackdc.properties and propagated to other nodes via +# gossip. If cassandra-topology.properties exists, it is used as a +# fallback, allowing migration from the PropertyFileSnitch. +# +# PropertyFileSnitch: +# Proximity is determined by rack and data center, which are +# explicitly configured in cassandra-topology.properties. +# +# Ec2Snitch: +# Appropriate for EC2 deployments in a single Region. Loads Region +# and Availability Zone information from the EC2 API. The Region is +# treated as the datacenter, and the Availability Zone as the rack. +# Only private IPs are used, so this will not work across multiple +# Regions. +# +# Ec2MultiRegionSnitch: +# Uses public IPs as broadcast_address to allow cross-region +# connectivity. (Thus, you should set seed addresses to the public +# IP as well.) You will need to open the storage_port or +# ssl_storage_port on the public IP firewall. (For intra-Region +# traffic, Cassandra will switch to the private IP after +# establishing a connection.) +# +# RackInferringSnitch: +# Proximity is determined by rack and data center, which are +# assumed to correspond to the 3rd and 2nd octet of each node's IP +# address, respectively. Unless this happens to match your +# deployment conventions, this is best used as an example of +# writing a custom Snitch class and is provided in that spirit. +# +# You can use a custom Snitch by setting this to the full class name +# of the snitch, which will be assumed to be on your classpath. +endpoint_snitch: SimpleSnitch + +# controls how often to perform the more expensive part of host score +# calculation +dynamic_snitch_update_interval_in_ms: 100 +# controls how often to reset all host scores, allowing a bad host to +# possibly recover +dynamic_snitch_reset_interval_in_ms: 600000 +# if set greater than zero and read_repair_chance is < 1.0, this will allow +# 'pinning' of replicas to hosts in order to increase cache capacity. +# The badness threshold will control how much worse the pinned host has to be +# before the dynamic snitch will prefer other replicas over it. This is +# expressed as a double which represents a percentage. Thus, a value of +# 0.2 means Cassandra would continue to prefer the static snitch values +# until the pinned host was 20% worse than the fastest. +dynamic_snitch_badness_threshold: 0.1 + +# request_scheduler -- Set this to a class that implements +# RequestScheduler, which will schedule incoming client requests +# according to the specific policy. This is useful for multi-tenancy +# with a single Cassandra cluster. +# NOTE: This is specifically for requests from the client and does +# not affect inter node communication. +# org.apache.cassandra.scheduler.NoScheduler - No scheduling takes place +# org.apache.cassandra.scheduler.RoundRobinScheduler - Round robin of +# client requests to a node with a separate queue for each +# request_scheduler_id. The scheduler is further customized by +# request_scheduler_options as described below. +request_scheduler: org.apache.cassandra.scheduler.NoScheduler + +# Scheduler Options vary based on the type of scheduler +# +# NoScheduler +# Has no options +# +# RoundRobin +# throttle_limit +# The throttle_limit is the number of in-flight +# requests per client. Requests beyond +# that limit are queued up until +# running requests can complete. +# The value of 80 here is twice the number of +# concurrent_reads + concurrent_writes. +# default_weight +# default_weight is optional and allows for +# overriding the default which is 1. +# weights +# Weights are optional and will default to 1 or the +# overridden default_weight. The weight translates into how +# many requests are handled during each turn of the +# RoundRobin, based on the scheduler id. +# +# request_scheduler_options: +# throttle_limit: 80 +# default_weight: 5 +# weights: +# Keyspace1: 1 +# Keyspace2: 5 + +# request_scheduler_id -- An identifier based on which to perform +# the request scheduling. Currently the only valid option is keyspace. +# request_scheduler_id: keyspace + +# Enable or disable inter-node encryption +# JVM defaults for supported SSL socket protocols and cipher suites can +# be replaced using custom encryption options. This is not recommended +# unless you have policies in place that dictate certain settings, or +# need to disable vulnerable ciphers or protocols in case the JVM cannot +# be updated. +# FIPS compliant settings can be configured at JVM level and should not +# involve changing encryption settings here: +# https://docs.oracle.com/javase/8/docs/technotes/guides/security/jsse/FIPS.html +# *NOTE* No custom encryption options are enabled at the moment +# The available internode options are : all, none, dc, rack +# +# If set to dc cassandra will encrypt the traffic between the DCs +# If set to rack cassandra will encrypt the traffic between the racks +# +# The passwords used in these options must match the passwords used when generating +# the keystore and truststore. For instructions on generating these files, see: +# http://download.oracle.com/javase/6/docs/technotes/guides/security/jsse/JSSERefGuide.html#CreateKeystore +# +server_encryption_options: + internode_encryption: none + keystore: conf/.keystore + keystore_password: cassandra + truststore: conf/.truststore + truststore_password: cassandra + # More advanced defaults below: + # protocol: TLS + # algorithm: SunX509 + # store_type: JKS + # cipher_suites: [TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA,TLS_DHE_RSA_WITH_AES_128_CBC_SHA,TLS_DHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA] + # require_client_auth: false + # require_endpoint_verification: false + +# enable or disable client/server encryption. +client_encryption_options: + enabled: false + # If enabled and optional is set to true encrypted and unencrypted connections are handled. + optional: false + keystore: conf/.keystore + keystore_password: cassandra + # require_client_auth: false + # Set trustore and truststore_password if require_client_auth is true + # truststore: conf/.truststore + # truststore_password: cassandra + # More advanced defaults below: + # protocol: TLS + # algorithm: SunX509 + # store_type: JKS + # cipher_suites: [TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA,TLS_DHE_RSA_WITH_AES_128_CBC_SHA,TLS_DHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA] + +# internode_compression controls whether traffic between nodes is +# compressed. +# Can be: +# +# all +# all traffic is compressed +# +# dc +# traffic between different datacenters is compressed +# +# none +# nothing is compressed. +internode_compression: dc + +# Enable or disable tcp_nodelay for inter-dc communication. +# Disabling it will result in larger (but fewer) network packets being sent, +# reducing overhead from the TCP protocol itself, at the cost of increasing +# latency if you block for cross-datacenter responses. +inter_dc_tcp_nodelay: false + +# TTL for different trace types used during logging of the repair process. +tracetype_query_ttl: 86400 +tracetype_repair_ttl: 604800 + +# By default, Cassandra logs GC Pauses greater than 200 ms at INFO level +# This threshold can be adjusted to minimize logging if necessary +# gc_log_threshold_in_ms: 200 + +# If unset, all GC Pauses greater than gc_log_threshold_in_ms will log at +# INFO level +# UDFs (user defined functions) are disabled by default. +# As of Cassandra 3.0 there is a sandbox in place that should prevent execution of evil code. +enable_user_defined_functions: false + +# Enables scripted UDFs (JavaScript UDFs). +# Java UDFs are always enabled, if enable_user_defined_functions is true. +# Enable this option to be able to use UDFs with "language javascript" or any custom JSR-223 provider. +# This option has no effect, if enable_user_defined_functions is false. +enable_scripted_user_defined_functions: false + +# Enables materialized view creation on this node. +# Materialized views are considered experimental and are not recommended for production use. +enable_materialized_views: true + +# The default Windows kernel timer and scheduling resolution is 15.6ms for power conservation. +# Lowering this value on Windows can provide much tighter latency and better throughput, however +# some virtualized environments may see a negative performance impact from changing this setting +# below their system default. The sysinternals 'clockres' tool can confirm your system's default +# setting. +windows_timer_interval: 1 + + +# Enables encrypting data at-rest (on disk). Different key providers can be plugged in, but the default reads from +# a JCE-style keystore. A single keystore can hold multiple keys, but the one referenced by +# the "key_alias" is the only key that will be used for encrypt opertaions; previously used keys +# can still (and should!) be in the keystore and will be used on decrypt operations +# (to handle the case of key rotation). +# +# It is strongly recommended to download and install Java Cryptography Extension (JCE) +# Unlimited Strength Jurisdiction Policy Files for your version of the JDK. +# (current link: http://www.oracle.com/technetwork/java/javase/downloads/jce8-download-2133166.html) +# +# Currently, only the following file types are supported for transparent data encryption, although +# more are coming in future cassandra releases: commitlog, hints +transparent_data_encryption_options: + enabled: false + chunk_length_kb: 64 + cipher: AES/CBC/PKCS5Padding + key_alias: testing:1 + # CBC IV length for AES needs to be 16 bytes (which is also the default size) + # iv_length: 16 + key_provider: + - class_name: org.apache.cassandra.security.JKSKeyProvider + parameters: + - keystore: conf/.keystore + keystore_password: cassandra + store_type: JCEKS + key_password: cassandra + + +##################### +# SAFETY THRESHOLDS # +##################### + +# When executing a scan, within or across a partition, we need to keep the +# tombstones seen in memory so we can return them to the coordinator, which +# will use them to make sure other replicas also know about the deleted rows. +# With workloads that generate a lot of tombstones, this can cause performance +# problems and even exaust the server heap. +# (http://www.datastax.com/dev/blog/cassandra-anti-patterns-queues-and-queue-like-datasets) +# Adjust the thresholds here if you understand the dangers and want to +# scan more tombstones anyway. These thresholds may also be adjusted at runtime +# using the StorageService mbean. +tombstone_warn_threshold: 1000 +tombstone_failure_threshold: 100000 + +# Log WARN on any multiple-partition batch size exceeding this value. 5kb per batch by default. +# Caution should be taken on increasing the size of this threshold as it can lead to node instability. +batch_size_warn_threshold_in_kb: 5 + +# Fail any multiple-partition batch exceeding this value. 50kb (10x warn threshold) by default. +batch_size_fail_threshold_in_kb: 50 + +# Log WARN on any batches not of type LOGGED than span across more partitions than this limit +unlogged_batch_across_partitions_warn_threshold: 10 + +# Log a warning when compacting partitions larger than this value +compaction_large_partition_warning_threshold_mb: 100 + +# GC Pauses greater than gc_warn_threshold_in_ms will be logged at WARN level +# Adjust the threshold based on your application throughput requirement +# By default, Cassandra logs GC Pauses greater than 200 ms at INFO level +gc_warn_threshold_in_ms: 1000 + +# Maximum size of any value in SSTables. Safety measure to detect SSTable corruption +# early. Any value size larger than this threshold will result into marking an SSTable +# as corrupted. This should be positive and less than 2048. +# max_value_size_in_mb: 256 + +# Back-pressure settings # +# If enabled, the coordinator will apply the back-pressure strategy specified below to each mutation +# sent to replicas, with the aim of reducing pressure on overloaded replicas. +back_pressure_enabled: false +# The back-pressure strategy applied. +# The default implementation, RateBasedBackPressure, takes three arguments: +# high ratio, factor, and flow type, and uses the ratio between incoming mutation responses and outgoing mutation requests. +# If below high ratio, outgoing mutations are rate limited according to the incoming rate decreased by the given factor; +# if above high ratio, the rate limiting is increased by the given factor; +# such factor is usually best configured between 1 and 10, use larger values for a faster recovery +# at the expense of potentially more dropped mutations; +# the rate limiting is applied according to the flow type: if FAST, it's rate limited at the speed of the fastest replica, +# if SLOW at the speed of the slowest one. +# New strategies can be added. Implementors need to implement org.apache.cassandra.net.BackpressureStrategy and +# provide a public constructor accepting a Map. +back_pressure_strategy: + - class_name: org.apache.cassandra.net.RateBasedBackPressure + parameters: + - high_ratio: 0.90 + factor: 5 + flow: FAST + +# Coalescing Strategies # +# Coalescing multiples messages turns out to significantly boost message processing throughput (think doubling or more). +# On bare metal, the floor for packet processing throughput is high enough that many applications won't notice, but in +# virtualized environments, the point at which an application can be bound by network packet processing can be +# surprisingly low compared to the throughput of task processing that is possible inside a VM. It's not that bare metal +# doesn't benefit from coalescing messages, it's that the number of packets a bare metal network interface can process +# is sufficient for many applications such that no load starvation is experienced even without coalescing. +# There are other benefits to coalescing network messages that are harder to isolate with a simple metric like messages +# per second. By coalescing multiple tasks together, a network thread can process multiple messages for the cost of one +# trip to read from a socket, and all the task submission work can be done at the same time reducing context switching +# and increasing cache friendliness of network message processing. +# See CASSANDRA-8692 for details. + +# Strategy to use for coalescing messages in OutboundTcpConnection. +# Can be fixed, movingaverage, timehorizon, disabled (default). +# You can also specify a subclass of CoalescingStrategies.CoalescingStrategy by name. +# otc_coalescing_strategy: DISABLED + +# How many microseconds to wait for coalescing. For fixed strategy this is the amount of time after the first +# message is received before it will be sent with any accompanying messages. For moving average this is the +# maximum amount of time that will be waited as well as the interval at which messages must arrive on average +# for coalescing to be enabled. +# otc_coalescing_window_us: 200 + +# Do not try to coalesce messages if we already got that many messages. This should be more than 2 and less than 128. +# otc_coalescing_enough_coalesced_messages: 8 + +# How many milliseconds to wait between two expiration runs on the backlog (queue) of the OutboundTcpConnection. +# Expiration is done if messages are piling up in the backlog. Droppable messages are expired to free the memory +# taken by expired messages. The interval should be between 0 and 1000, and in most installations the default value +# will be appropriate. A smaller value could potentially expire messages slightly sooner at the expense of more CPU +# time and queue contention while iterating the backlog of messages. +# An interval of 0 disables any wait time, which is the behavior of former Cassandra versions. +# +# otc_backlog_expiration_interval_ms: 200 diff --git a/pkg/pilot/genericpilot/genericpilot.go b/pkg/pilot/genericpilot/genericpilot.go index 61662944b..3462572ad 100644 --- a/pkg/pilot/genericpilot/genericpilot.go +++ b/pkg/pilot/genericpilot/genericpilot.go @@ -111,10 +111,12 @@ func (g *GenericPilot) runController(stopCh <-chan struct{}) <-chan error { func (g *GenericPilot) runElector(stopCh <-chan struct{}) <-chan error { out := make(chan error, 1) - go func() { - defer close(out) - out <- g.elector.Run() - }() + if g.Options.LeaderElect { + go func() { + defer close(out) + out <- g.elector.Run() + }() + } return out } diff --git a/pkg/pilot/genericpilot/options.go b/pkg/pilot/genericpilot/options.go index 17e61edde..d6f456de1 100644 --- a/pkg/pilot/genericpilot/options.go +++ b/pkg/pilot/genericpilot/options.go @@ -44,6 +44,7 @@ type Options struct { PilotName string // PilotNamespace is the namespace the corresponding Pilot exists within PilotNamespace string + LeaderElect bool LeaderElectionConfigMap string // CmdFunc returns an *exec.Cmd for a given Pilot resource for the pilot @@ -179,5 +180,7 @@ func (o *Options) Pilot() (*GenericPilot, error) { func (o *Options) AddFlags(flags *pflag.FlagSet) { flags.StringVar(&o.PilotName, "pilot-name", "", "The name of this Pilot. If not specified, an auto-detected name will be used.") flags.StringVar(&o.PilotNamespace, "pilot-namespace", "", "The namespace the corresponding Pilot resource for this Pilot exists within.") + flags.BoolVar(&o.LeaderElect, "leader-elect", true, ""+ + "If true, navigator will perform leader election between pilots.") flags.StringVar(&o.LeaderElectionConfigMap, "leader-election-config-map", "", "The name of the ConfigMap to use for leader election") } diff --git a/test/integration/pilot_test.go b/test/integration/pilot_test.go new file mode 100644 index 000000000..8310aafda --- /dev/null +++ b/test/integration/pilot_test.go @@ -0,0 +1,183 @@ +package integration_test + +import ( + "os" + "os/exec" + "path/filepath" + "syscall" + "testing" + "time" + + "github.com/onsi/gomega/gbytes" + "github.com/pkg/errors" + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + "sigs.k8s.io/testing_frameworks/integration" + + "github.com/jetstack/navigator/internal/test/util/testfs" +) + +func MakeKubeConfig(f *integration.ControlPlane, path string) error { + ctl := f.KubeCtl() + ctl.Opts = []string{"--kubeconfig", path} + + _, _, err := ctl.Run( + "config", + "set-credentials", + "user1", + ) + if err != nil { + return errors.Wrap(err, "unable to create user") + } + + _, _, err = ctl.Run( + "config", + "set-cluster", + "integration1", + "--server", + f.APIURL().String(), + "--certificate-authority", + filepath.Join(f.APIServer.CertDir, "apiserver.crt"), + ) + if err != nil { + return errors.Wrap(err, "unable to create cluster") + } + + _, _, err = ctl.Run( + "config", + "set-context", + "default", + "--cluster", "integration1", + "--user", "user1", + ) + if err != nil { + return errors.Wrap(err, "unable to create context") + } + + _, _, err = ctl.Run( + "config", + "use-context", + "default", + ) + if err != nil { + return errors.Wrap(err, "unable to use context") + } + return nil +} + +func TestPilotCassandra(t *testing.T) { + cp := &integration.ControlPlane{ + APIServer: &integration.APIServer{ + Args: []string{ + "--etcd-servers={{ if .EtcdURL }}{{ .EtcdURL.String }}{{ end }}", + "--cert-dir={{ .CertDir }}", + "--insecure-port={{ if .URL }}{{ .URL.Port }}{{ end }}", + "--insecure-bind-address={{ if .URL }}{{ .URL.Hostname }}{{ end }}", + "--secure-port=0", + "--feature-gates=CustomResourceSubresources=true", + "-v=4", "--alsologtostderr", + }, + // Out: os.Stdout, + // Err: os.Stderr, + }, + } + err := cp.Start() + require.NoError(t, err) + defer func() { + err := cp.Stop() + if err != nil { + t.Fatal(err) + } + }() + cli := cp.KubeCtl() + + crdPath, err := filepath.Abs("testdata/pilot_crd.yaml") + require.NoError(t, err) + stdout, stderr, err := cli.Run( + "apply", + "--filename", + crdPath, + ) + t.Log("stdout", stdout) + t.Log("stderr", stderr) + require.NoError(t, err) + + stdout, stderr, err = cli.Run( + "create", + "namespace", + "ns1", + ) + t.Log("stdout", stdout) + t.Log("stderr", stderr) + require.NoError(t, err) + pilotResourcePath, err := filepath.Abs("testdata/pilot.yaml") + require.NoError(t, err) + stdout, stderr, err = cli.Run( + "apply", + "--filename", + pilotResourcePath, + ) + t.Log("stdout", stdout) + t.Log("stderr", stderr) + require.NoError(t, err) + + tfs := testfs.New(t) + + kubeConfig := tfs.TempPath("kube.config") + cassConfig := tfs.TempDir("etc_cassandra") + pilotConfigDir := tfs.TempDir("etc/pilot") + cassPath, err := filepath.Abs("testdata/fake_cassandra") + require.NoError(t, err) + err = MakeKubeConfig(cp, kubeConfig) + require.NoError(t, err) + + pilotPath, pilotPathFound := os.LookupEnv("TEST_ASSET_NAVIGATOR_PILOT_CASSANDRA") + if !pilotPathFound { + t.Fatal( + "Please set environment variable TEST_ASSET_NAVIGATOR_PILOT_CASSANDRA " + + "with the path to the navigator-pilot-cassandra binary under test.") + } + + cmd := exec.Command( + pilotPath, + "--pilot-name", "pilot1", + "--pilot-namespace", "ns1", + "--kubeconfig", kubeConfig, + "--v=4", "--alsologtostderr", + "--leader-elect=false", + "--cassandra-config-path", cassConfig, + "--cassandra-path", cassPath, + "--cassandra-rack", "rack-for-test", + "--cassandra-dc", "dc-for-test", + "--config-dir", pilotConfigDir, + ) + startDetectStream := gbytes.NewBuffer() + ready := startDetectStream.Detect("FAKE CASSANDRA") + cmd.Stdout = startDetectStream + cmd.Stderr = os.Stderr + + err = cmd.Start() + require.NoError(t, err) + defer func() { + // XXX: Pilot doesn't respond to SIGKILL + err := cmd.Process.Signal(os.Interrupt) + require.NoError(t, err) + err = cmd.Wait() + if exiterr, ok := err.(*exec.ExitError); ok { + if status, ok := exiterr.Sys().(syscall.WaitStatus); ok { + if status.ExitStatus() == 255 { + // XXX Pilot should return 0 if it exits cleanly after a signal. + return + } + } + } + require.NoError(t, err) + }() + select { + case <-ready: + case <-time.After(time.Second * 5): + t.Fatal("timeout waiting for process to start") + } + assert.FileExists(t, cassConfig+"/cassandra.yaml") + assert.FileExists(t, cassConfig+"/cassandra-rackdc.properties") +} diff --git a/test/integration/testdata/cassandra.yaml b/test/integration/testdata/cassandra.yaml new file mode 100644 index 000000000..f98310056 --- /dev/null +++ b/test/integration/testdata/cassandra.yaml @@ -0,0 +1,2 @@ +foo: + bar: org.apache.cassandra.locator.SimpleSeedProvider diff --git a/test/integration/testdata/fake_cassandra b/test/integration/testdata/fake_cassandra new file mode 100755 index 000000000..d8961b756 --- /dev/null +++ b/test/integration/testdata/fake_cassandra @@ -0,0 +1,8 @@ +#!/usr/bin/sh +set -o errexit +set -o pipefail + +while true; do + echo "FAKE CASSANDRA" + sleep 1 +done diff --git a/test/integration/testdata/pilot.yaml b/test/integration/testdata/pilot.yaml new file mode 100644 index 000000000..ed07fecdb --- /dev/null +++ b/test/integration/testdata/pilot.yaml @@ -0,0 +1,11 @@ +apiVersion: navigator.jetstack.io/v1alpha1 +kind: Pilot +metadata: + name: pilot1 + namespace: ns1 + ownerReferences: + - apiVersion: navigator.jetstack.io/v1alpha1 + kind: CassandraCluster + name: cluster1 + uid: 23c88696-cf7b-11e7-9ec9-0a580a200927 + controller: true diff --git a/test/integration/testdata/pilot_crd.yaml b/test/integration/testdata/pilot_crd.yaml new file mode 100644 index 000000000..50e8ab31e --- /dev/null +++ b/test/integration/testdata/pilot_crd.yaml @@ -0,0 +1,17 @@ +apiVersion: apiextensions.k8s.io/v1beta1 +kind: CustomResourceDefinition +metadata: + name: pilots.navigator.jetstack.io +spec: + group: navigator.jetstack.io + version: v1alpha1 + scope: Namespaced + names: + plural: pilots + singular: pilot + kind: Pilot + # categories is a list of grouped resources the custom resource belongs to. + categories: + - all + subresources: + status: {}