VPC, cassandra-stress script, and other smaller fixes

scylladb · Apr 24, 2024 · 7748692 · 7748692
2 parents 04a5b13 + b49fe39
commit 7748692
Show file tree

Hide file tree

Showing 10 changed files with 132 additions and 42 deletions.
diff --git a/output.tf b/output.tf
@@ -4,4 +4,29 @@ output "PublicIP" {
 output "CQL_PASS" {
   value     = data.scylladbcloud_cql_auth.scylla.password
   sensitive = true
-}
+}
+
+# Output the VPC peering connection ID
+output "scylladbcloud_vpc_peering_connection_id" {
+  value = scylladbcloud_vpc_peering.scylladbcloud.connection_id
+}
+
+// Output the private IP addresses of the nodes
+output "scylladbcloud_cluster_ips" {
+  value = scylladbcloud_cluster.scylladbcloud.node_private_ips
+}
+
+// Output the dns names of the nodes
+output "scylladbcloud_dns_names" {
+  value = scylladbcloud_cluster.scylladbcloud.node_dns_names
+}
+
+output "scylladbcloud_datacenter" {
+  value = scylladbcloud_cluster.scylladbcloud.datacenter
+}
+
+// Output the CQL password
+output "scylladbcloud_cql_password" {
+  value     = data.scylladbcloud_cql_auth.scylla.password # Get the CQL password for the cluster
+  sensitive = true                                        # Mark the output as sensitive so it won't be shown in logs or output
+}
diff --git a/profile/stress-0.yml b/profile/stress-0.yml
@@ -3,7 +3,7 @@ keyspace: pet_store_iot
 
 # Create the keyspace
 keyspace_definition: |
-  CREATE KEYSPACE pet_store_iot WITH replication = {'class': 'SimpleStrategy', 'replication_factor': 1};
+  CREATE KEYSPACE pet_store_iot WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1};
 
 # The name of the table
 table: sensor_data
@@ -21,10 +21,10 @@ table_definition: |
     AND compaction = {
       'class': 'TimeWindowCompactionStrategy',  
       'compaction_window_size': '1',    
-      'compaction_window_unit': 'DAYS', 
-      'max_sstable_age_days': '365',   
-      'timestamp_resolution': 'MICROSECONDS'
-    };
+      'compaction_window_unit': 'DAYS',    
+      'timestamp_resolution': 'MICROSECONDS' 
+    }
+    AND speculative_retry = 'NONE';
 
 # Define the columns for the table
 columnspec:
@@ -63,4 +63,4 @@ queries:
     fields: samerow
   add_sensor_data:
     cql: INSERT INTO sensor_data (device_id, sensor_type, bucket, timestamp, value) VALUES (?, ?, ?, ?, ?);
-    fields: samerow
+    fields: samerow
diff --git a/profile/stress-1.yml b/profile/stress-1.yml
@@ -3,7 +3,7 @@ keyspace: pet_store_iot
 
 # Create the keyspace
 keyspace_definition: |
-  CREATE KEYSPACE pet_store_iot WITH replication = {'class': 'SimpleStrategy', 'replication_factor': 1};
+  CREATE KEYSPACE pet_store_iot WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1};
 
 # The name of the table
 table: sensor_data
@@ -22,9 +22,9 @@ table_definition: |
       'class': 'TimeWindowCompactionStrategy',  
       'compaction_window_size': '1',    
       'compaction_window_unit': 'DAYS', 
-      'max_sstable_age_days': '365',   
       'timestamp_resolution': 'MICROSECONDS'
-    };
+    }
+    AND speculative_retry = 'NONE';
 
 # Define the columns for the table
 columnspec:
@@ -63,4 +63,4 @@ queries:
     fields: samerow
   add_sensor_data:
     cql: INSERT INTO sensor_data (device_id, sensor_type, bucket, timestamp, value) VALUES (?, ?, ?, ?, ?);
-    fields: samerow
+    fields: samerow
diff --git a/profile/stress-2.yml b/profile/stress-2.yml
@@ -3,7 +3,7 @@ keyspace: pet_store_iot
 
 # Create the keyspace
 keyspace_definition: |
-  CREATE KEYSPACE pet_store_iot WITH replication = {'class': 'SimpleStrategy', 'replication_factor': 1};
+  CREATE KEYSPACE pet_store_iot WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1};
 
 # The name of the table
 table: sensor_data
@@ -21,10 +21,10 @@ table_definition: |
     AND compaction = {
       'class': 'TimeWindowCompactionStrategy',  
       'compaction_window_size': '1',    
-      'compaction_window_unit': 'DAYS', 
-      'max_sstable_age_days': '365',   
+      'compaction_window_unit': 'DAYS',   
       'timestamp_resolution': 'MICROSECONDS'
-    };
+    }
+    AND speculative_retry = 'NONE';
 
 # Define the columns for the table
 columnspec:
@@ -63,4 +63,4 @@ queries:
     fields: samerow
   add_sensor_data:
     cql: INSERT INTO sensor_data (device_id, sensor_type, bucket, timestamp, value) VALUES (?, ?, ?, ?, ?);
-    fields: samerow
+    fields: samerow
diff --git a/profile/stress-3.yml b/profile/stress-3.yml
@@ -0,0 +1,66 @@
+# The name of the keyspace
+keyspace: pet_store_iot
+
+# Create the keyspace
+keyspace_definition: |
+  CREATE KEYSPACE pet_store_iot WITH replication = {'class': 'NetworkTopologyStrategy', 'replication_factor': 1};
+
+# The name of the table
+table: sensor_data
+
+# The CQL command to create the table
+table_definition: |
+  CREATE TABLE sensor_data (
+    device_id text,
+    sensor_type text,
+    bucket timestamp,
+    timestamp timestamp,
+    value double,
+    PRIMARY KEY ((device_id, sensor_type, bucket), timestamp)
+    ) WITH CLUSTERING ORDER BY (timestamp DESC)
+    AND compaction = {
+      'class': 'TimeWindowCompactionStrategy',  
+      'compaction_window_size': '1',    
+      'compaction_window_unit': 'DAYS',   
+      'timestamp_resolution': 'MICROSECONDS'
+    }
+    AND speculative_retry = 'NONE';
+
+# Define the columns for the table
+columnspec:
+  - name: device_id
+    size: FIXED(10)
+    population: uniform(1..10000)
+  - name: sensor_type
+    size: FIXED(10)
+    population: uniform(1..10)
+  - name: bucket
+    size: FIXED(10)
+    # Set the population of the bucket column to a sequence of timestamps from 1619798400 to the current time
+    population: seq(1640995200..1683013974)
+  - name: timestamp
+    size: FIXED(10)
+    # Set the population of the timestamp column to a sequence of timestamps from 1619798400 to the current time
+    population: seq(1640995200..1683013974)
+  - name: value
+    size: FIXED(10)
+    # Set the population of the value column to a Gaussian distribution with a mean of 50 and a standard deviation of 10
+    population: gaussian(10..50)
+
+# Define the insertion profile
+insert:
+  partitions: fixed(1)
+  batchtype: UNLOGGED
+  select: fixed(1)/1
+
+# Define the CQL queries for the stress test
+queries:
+  get_sensor_data:
+    cql: SELECT * FROM sensor_data WHERE device_id = ? AND sensor_type = ? AND bucket = ? AND timestamp >= ? AND timestamp <= ? LIMIT 100;
+    fields: samerow
+  get_latest_sensor_data:
+    cql: SELECT * FROM sensor_data WHERE device_id = ? AND sensor_type = ? AND bucket = ? LIMIT 1;
+    fields: samerow
+  add_sensor_data:
+    cql: INSERT INTO sensor_data (device_id, sensor_type, bucket, timestamp, value) VALUES (?, ?, ?, ?, ?);
+    fields: samerow
diff --git a/provider.tf b/provider.tf
@@ -1,5 +1,5 @@
 provider "aws" {
   region                   = var.scylla_cloud_region
   shared_credentials_files = ["${var.aws_creds}"]
-  profile                  = "DeveloperAccessRole"
-}
+  profile                  = "${var.aws_profile}"
+}
diff --git a/scylladb-cloud.tf b/scylladb-cloud.tf
@@ -39,24 +39,9 @@ resource "scylladbcloud_vpc_peering" "scylladbcloud" {
   cluster_id      = scylladbcloud_cluster.scylladbcloud.id
   datacenter      = scylladbcloud_cluster.scylladbcloud.datacenter
   peer_vpc_id     = aws_vpc.custom_vpc.id
-  peer_cidr_block = var.custom_vpc
+  peer_cidr_blocks = [var.custom_vpc]
   peer_region     = data.aws_region.current.name
   peer_account_id = data.aws_caller_identity.current.account_id
   allow_cql       = true
 }
 
-# Output the VPC peering connection ID
-output "scylladbcloud_vpc_peering_connection_id" {
-  value = scylladbcloud_vpc_peering.scylladbcloud.connection_id
-}
-
-// Output the private IP addresses of the nodes
-output "scylladbcloud_cluster_ips" {
-  value = scylladbcloud_cluster.scylladbcloud.node_private_ips
-}
-
-// Output the CQL password
-output "scylladbcloud_cql_password" {
-  value     = data.scylladbcloud_cql_auth.scylla.password # Get the CQL password for the cluster
-  sensitive = true                                        # Mark the output as sensitive so it won't be shown in logs or output
-}
diff --git a/scylladb-loaders.tf b/scylladb-loaders.tf
@@ -2,7 +2,7 @@
 # Create tags to identify the instances and sets timeouts for creating the instances.
 
 resource "aws_instance" "instance" {
-  count           = length(aws_subnet.public_subnet.*.id)
+  count           = var.loader_node_count
   ami             = var.ami_id
   instance_type   = var.instance_type
   subnet_id       = element(aws_subnet.public_subnet.*.id, count.index)
@@ -41,8 +41,9 @@ resource "aws_instance" "instance" {
     inline = [
       "sudo systemctl stop scylla-server |tee scylla.log",
       "echo '/usr/bin/cassandra-stress user profile=./stress.yml n=${var.num_of_ops} cl=local_quorum no-warmup \"ops(insert=1)\" -rate threads=${var.num_threads} fixed=450000/s -mode native cql3 user=${var.scylla_user} password=${local.scylla_pass} -log file=populating.log  -node ${local.scylla_ips}' > start.sh",
-      "echo '/usr/bin/cassandra-stress user profile=./stress.yml duration=24h no-warmup cl=local_quorum \"ops(insert=4,simple1=2)\" -rate threads=${var.num_threads} fixed=${var.throttle} -mode native cql3 user=${var.scylla_user} password=${local.scylla_pass} -log file=benchmarking.log -node ${local.scylla_ips}' > benchmark.sh",
+      "echo '/usr/bin/cassandra-stress user profile=./stress.yml duration=24h no-warmup cl=local_quorum \"ops(add_sensor_data=1,get_sensor_data=3)\" -rate threads=${var.num_threads} fixed=${var.throttle} -mode native cql3 user=${var.scylla_user} password=${local.scylla_pass} -log file=benchmarking.log -node ${local.scylla_ips}' > benchmark.sh",
       "sudo chmod +x start.sh benchmark.sh",
+      "echo '/home/scyllaadm/benchmark.sh' >> /home/scyllaadm/start.sh",
       "sudo mv /home/scyllaadm/cassandra-stress.service /etc/systemd/system/cassandra-stress.service ",
       "sudo mv /home/scyllaadm/cassandra-stress-benchmark.service /etc/systemd/system/cassandra-stress-benchmark.service ", "sudo systemctl daemon-reload ",
       "sudo systemctl start cassandra-stress.service",
@@ -67,7 +68,7 @@ resource "aws_eip" "eip" {
   count            = length(aws_instance.instance.*.id)               # Create an Elastic IP for each EC2 instance
   instance         = element(aws_instance.instance.*.id, count.index) # Associate the Elastic IP with the current EC2 instance
   public_ipv4_pool = "amazon"                                         # Use the Amazon pool for public IPv4 addresses
-  vpc              = true                                             # Create a VPC Elastic IP address
+  domain           = "vpc"                                            # Create a VPC Elastic IP address
 
   tags = { # Add tags to the Elastic IP resource
     "Name" = "${var.custom_name}-EIP-${count.index}"

diff --git a/service/cassandra-stress.service b/service/cassandra-stress.service
@@ -4,7 +4,7 @@ Description="Start Cassandra-stress to populate ScyllaDB"
 [Service]
 User=scyllaadm
 WorkingDirectory=/home/scyllaadm/
-ExecStart=/usr/bin/bash /home/scyllaadm/start.sh & wait && /usr/bin/bash /home/scyllaadm/benchmark.sh
+ExecStart=/usr/bin/bash /home/scyllaadm/start.sh
 Type=simple
 [Install]
-WantedBy=multi-user.target
+WantedBy=multi-user.target
diff --git a/variables.tf b/variables.tf
@@ -36,6 +36,12 @@ variable "aws_creds" {
   default     = "/home/user/.aws/credentials"
 }
 
+# AWS Profile to Use
+variable "aws_profile" {
+   description = "AWS Profile to Use"
+   type        = string
+   default     = "DeveloperAccessRole"
+}
 ################################################
 
 #
@@ -54,7 +60,7 @@ variable "num_threads" {
 variable "num_of_ops" {
   description = "Total number of operations to run"
   type        = string
-  default     = "1000M"
+  default     = "5M"
 }
 
 # Throttling for the Cassandra stress tool
@@ -71,9 +77,16 @@ variable "instance_type" {
   default     = "i4i.8xlarge"
 }
 
+# Number of Loader instances to create
+variable "loader_node_count" {
+  description = "Number of Loader instances to create"
+  type        = string
+  default     = "3"
+}
+
 # ScyllaDB Cloud instance type
 variable "scylla_node_type" {
-  description = "Type of ScyllaDB Cloud instance"
+  description = "Type of ScyllaDB Cloud instance (3,6,9,12,15,18,21)"
   type        = string
   default     = "i4i.4xlarge"
 }
@@ -121,6 +134,6 @@ variable "scylla_node_count" {
 }
 
 locals {
-  scylla_ips  = (join(",", [for s in scylladbcloud_cluster.scylladbcloud.node_private_ips : format("%s", s)]))
+  scylla_ips  = (join(",", [for s in scylladbcloud_cluster.scylladbcloud.node_dns_names : format("%s", s)]))
   scylla_pass = data.scylladbcloud_cql_auth.scylla.password
 }