我正在对 cassandra 集群进行基准测试,因此使用 cassandra-stress 工具。能够在复制因子为 2、CL 为仲裁、线程率为 40、在 2 个节点上并从 11.43.600.66 运行压力的表中插入 1M 条记录。
./cassandra-stress user profile= demo.yaml n=1000000 ops(insert=1,likelyquery0=2) cl= quorum -node 11.43.600.66,11.43.600.65 -rate threads=40
**demo.yaml script:**
columnspec:
- name: user_name
size: gaussian(20..45)
population: gaussian(10000..50000)
- name: system_name
size: gaussian(20..45)
population: gaussian(50..60)
- name: time
size: uniform(15..25)
population: uniform(100000..1000000)
- name: request_uri
size: gaussian(50..80)
population: gaussian(100..150)
insert:
partitions: fixed(1)
select: fixed(1)/1000
batchtype: UNLOGGED
我试图了解 nodetool cfstats、cfhistograms 与 OpsCenter 的结果。来自 Opscenter 的写入和读取请求延迟 (ms/op) 的表级指标是:
cfhistograms 结果以计算写入和读取延迟。延迟以微秒为
单位 cfstats 以毫秒为单位
a) As per the results of cfhistograms and cfstats
Write Latency: 0.0117ms = 11.7 micros
Read Latency: 0.0943ms = 94.3 micros
This would approximately match the results at 50% as
Write Latency: 10micros
Read Latency: 103micros
问题 1:cfstats 和 cfhistograms 显示结果的百分比是多少?我总是会考虑 95%,但 95% 的 cfstats 结果与此处的 cfhistograms 不匹配。我考虑有什么问题吗?
b) From OpsCenter results:
Write Latency: 1.6ms/op = 1600 micros
Read Latency: 1.9ms/op = 1900 micros
问题2:为什么与cfhistograms和opscenter的结果不匹配?是否像写的 opscenter y 轴值,读请求延迟必须在 micros/op 而不是 ms/op 中?
版本:
Cassandra 2.1.8.689
OpsCenter 5.2.2
如果我错了,请告诉我..!!
谢谢