Question

我在VMWare ESXi 6.7中运行4节点Cassandra集群，我使用ycsb测试4节点Cassandra集群。结果完全不符合预期，我只是通过4节点集群获得20000 ops / sec。有些人可以让我知道下面的Cassandra基准测试的配置是我的配置文件。

cluster_name: 'test-cluster'
num_tokens: 256
hinted_handoff_enabled: true
max_hint_window_in_ms: 10800000 # 3 hours
hinted_handoff_throttle_in_kb: 1024
max_hints_delivery_threads: 2
hints_directory: /mnt/hints
hints_flush_period_in_ms: 10000
max_hints_file_size_in_mb: 128
batchlog_replay_throttle_in_kb: 1024
authenticator: AllowAllAuthenticator
authorizer: AllowAllAuthorizer
role_manager: CassandraRoleManager
roles_validity_in_ms: 2000
permissions_validity_in_ms: 2000
partitioner: org.apache.cassandra.dht.Murmur3Partitioner
data_file_directories:
    - /mnt/cassandra-data
commitlog_directory: /mnt/commitlog
disk_failure_policy: stop
commit_failure_policy: stop
key_cache_size_in_mb: 0
key_cache_save_period: 14400
row_cache_size_in_mb: 0
row_cache_save_period: 0
counter_cache_size_in_mb:
counter_cache_save_period: 7200
saved_caches_directory: /mnt/saved-cache
commitlog_sync: periodic
commitlog_sync_period_in_ms: 100
commitlog_segment_size_in_mb: 32
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: "<ip1>,<ip2>,<ip3>"
          - seeds: "192.168.50.235,192.168.50.254"
concurrent_reads: 64
concurrent_writes: 32
concurrent_counter_writes: 32
concurrent_materialized_view_writes: 32
memtable_allocation_type: heap_buffers
memtable_flush_writers: 4
index_summary_capacity_in_mb:
index_summary_resize_interval_in_minutes: 60
trickle_fsync: true
trickle_fsync_interval_in_kb: 256
storage_port: 7000
ssl_storage_port: 7001
listen_address: 192.168.50.235
start_native_transport: true
native_transport_port: 9042
start_rpc: false
rpc_address: localhost
rpc_port: 9160
rpc_keepalive: true
rpc_server_type: sync
thrift_framed_transport_size_in_mb: 15
incremental_backups: false
snapshot_before_compaction: false
auto_snapshot: true
tombstone_warn_threshold: 1000
tombstone_failure_threshold: 100000
column_index_size_in_kb: 64
batch_size_warn_threshold_in_kb: 5
batch_size_fail_threshold_in_kb: 50
unlogged_batch_across_partitions_warn_threshold: 10
compaction_throughput_mb_per_sec: 0
compaction_large_partition_warning_threshold_mb: 100
sstable_preemptive_open_interval_in_mb: 50
read_request_timeout_in_ms: 5000
range_request_timeout_in_ms: 10000
write_request_timeout_in_ms: 2000
counter_write_request_timeout_in_ms: 5000
cas_contention_timeout_in_ms: 1000
truncate_request_timeout_in_ms: 60000
request_timeout_in_ms: 10000
cross_node_timeout: false
endpoint_snitch: GossipingPropertyFileSnitch
dynamic_snitch_update_interval_in_ms: 100 
dynamic_snitch_reset_interval_in_ms: 600000
dynamic_snitch_badness_threshold: 0.1
request_scheduler: org.apache.cassandra.scheduler.NoScheduler
server_encryption_options:
    internode_encryption: none
    keystore: conf/.keystore
    keystore_password: cassandra
    truststore: conf/.truststore
    truststore_password: cassandra
client_encryption_options:
    enabled: false
    optional: false
    keystore: conf/.keystore
    keystore_password: cassandra

internode_compression: all
inter_dc_tcp_nodelay: false
tracetype_query_ttl: 86400
tracetype_repair_ttl: 604800
gc_warn_threshold_in_ms: 1000
enable_user_defined_functions: false
enable_scripted_user_defined_functions: false
enable_materialized_views: true
windows_timer_interval: 1

Answer 1

实际上是1个节点，单个磁盘在4个cassandra实例之间存在竞争。确保每个实例都有自己的磁盘（没有数据库可以比其磁盘运行更快）。如果想在单个主机上运行4个cassandra实例，请使用ccm或仅绑定到自己接口的4个不同实例，而不是使用虚拟化来降低它的速度。

ycsb在对cassandra进行基准测试时非常糟糕，尝试使用带有cassandra的cassandra-stress。当推送超过100k时，Theres还限制了单个客户端可以在需要开始使用多个客户端（单独系统）的地方。

对Cassandra 4节点集群进行基准测试的配置是什么

1 个答案: