Here is a AWS Aurora PostgreSQL 12 database.

The database is an r5.4xlarge and average load is ~16.

Over 3 hours, the average "Write IOPS" was 40,000 and the average "Read IOPS" was 15,000.

In the same period, the average "[Billed] Volume Write IOPS" was 400,000 and the average "[Billed] Volume Read IOPS" was 3,000,000. (I believe those are 5 min sums.)

Why are writes 2.5x reads, but for billed volume, writes are 1/8th reads?

Why is there a huge difference? Is that unusual? Does it indicate an I/O pathology?

enter image description here


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.