Skip to main content

TLDR

Assumptions​

  • The AKalculator Algorithm is not perfect yet.

  • Default Configuration

    • Every Kafka config is set to its default, unless mentioned explicitly in these pages
    • All traffic is assumed to be evenly distributed
    • Replication Factor is set to 3
    • Brokers are evenly split across availability zones
  • Cloud Regions

    • AKalculator uses the US East region in all clouds
      • AWS: us-east (N. Virginia)
      • GCP: us-east1
      • Azure: East US (not East US 2)
  • CPU

    • 1 vCPU allows a broker to handle 5 MiB/s Produce and 15 MiB/s Consume (at the same time)
  • Traffic

    • 75% of consume traffic reads from the tail of the log
      • all tail reads are served from pagecache and do not touch the disk
    • 25% of consume traffic is historical
      • historical reads hit the disk when tiered storage is disabled, and do not touch the disk when tiered storage is enabled
  • IOPS

    • Write/Read IOPS are all assumed as 128 KiB per IO
  • Storage Configuration

    • configures a 60 minute local.retention.ms
    • uses SSDs
    • assumes zero compacted topics
  • Partition Count

    • The calculator assumes that the cluster has 1000 partitions
  • Disk Size

    • max disk size is 16 TiB
    • max allowed disk usage is 50% (i.e, 50% free space capacity is kept)
  • Cluster Size

    • clusters are between 3<->200 brokers in size

🤗 Comments Welcome!

Leave feedback, report bugs or just complain at: