Check System Stats

AttentionThis page documents an earlier version. Go to the latest (v2.1)version.

Host resource usage

To check the CPU, Memory and Disk usage on a Linux machine you can run:

  1. $ sudo echo -n "CPUs: ";cat /proc/cpuinfo | grep processor | wc -l; echo -n "Mem: ";free -h | grep Mem | tr -s " " | cut -d" " -f 2; echo -n "Disk: "; df -h / | grep -v Filesystem;
  1. CPUs: 72
  2. Mem: 251G
  3. Disk: /dev/sda2 160G 13G 148G 8% /
  4. 10.1.12.104
  5. CPUs: 88
  6. Mem: 251G
  7. Disk: /dev/sda2 208G 22G 187G 11% /
  8. 10.1.12.105
  9. CPUs: 88
  10. Mem: 251G
  11. Disk: /dev/sda2 208G 5.1G 203G 3% /

Generally, common tools like top or iostat may be useful.

Auditd

If top reports high CPU usage for the auditd process, it may have some rules auditing some system calls frequently used Yugabyte which can significantly affect performance.You can try temporarily disabling audit by running (on each Yugabyte node):

  1. $ auditctl -e 0

and check if this improves peformance.

To re-enable it afterwards run:

  1. $ auditctl -e 1

Yugabyte processes state

YugabyteDB provides web endpoints where the current state of each process is aggregated.This includes logs, gflags as well as memory, disk, and network usage metrics.Additionally, it provides dedicated metrics endpoints for CQL and, respectively, Redis requests.

DescriptionURL
Master Web Page<node-ip>:7000
TServer Web Page<node-ip>:9000
Redis Metrics<node-ip>:11000/metrics
CQL Metrics<node-ip>:12000/metrics

Note that, when running yb-ctl locally with default settings, it will create three local ips 127.0.0.1, 127.0.0.2, and 127.0.0.3, one for each YugabyteDB node.