Birbla

Discussion summary

A PostgreSQL performance comparison across 23 EC2 instance types was discussed, with suggestions to include Azure, GCP, AMD instances, and optimized read types. Participants also considered design adjustments for heavy write loads and comparisons with Aurora PostgreSQL.

What the discussion says

  • Include more cloud providers like Azure and GCP.
  • Add AMD instance types such as M8a, R8a, C8a.
  • Compare default PostgreSQL with Aurora PostgreSQL.
  • Consider performance with heavy write workloads.
  • Include optimized read instance types like r8gd, m8gd.
“Gotta get the AMD instances in there.”
— Rafuino
“Would love to see a comparison between Aurora PostgreSQL and self-host PostgreSQL.”
— ballislife30

Comments

Hacker News

Interesting, is there something like this for azure

by crudgen

Gotta get the AMD instances in there. Not seeing M8a, R8a, C8a, for example

by Rafuino

An info badge next to rps would be nice, I'm trying to guess what r is. Rows? Records? Requests?

by TurdF3rguson

What are your thoughts on how design changes if writes become much heavier, ie. when recording agent operations?

by handfuloflight

I'd be very curious to see you add the Optimized Reads instance types, e.g. r8gd or m8gd, to your benchmark. They add a local NVMe-based SSD block storage that serves as a cache in front of the network-based disks among other use cases. They have been a huge win for us for a read-heavy workload where the dataset is significantly larger than memory.

Edit: Apologies, on a closer read, I realize you were not testing RDS but managing Postgres on EC2 directly.

by mattlong

Would love to see a comparison between Aurora PostgreSQL and self-host PostgreSQL on the same EC2 instance type.

by ballislife30

Would be interesting to see huge pages and io2 impact.

I did a smaller version on Azure and disk latency had a massive impact much more so than max IOPs (although their crappy storage offering needed like 64-128 iodepth to get advertised iops).

Results seem mostly in line with expectations. Iirc vcpu is threads so on arm64 you get 4 smt1 cores vs Intel/AMD you get 2 smt2 cores.

by nijave

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • Superbase?
    by sysguru2046
  • Interesting, is there something like this for azure
    by crudgen
  • Gotta get the AMD instances in there. Not seeing M8a, R8a, C8a, for example
    by Rafuino
  • An info badge next to rps would be nice, I'm trying to guess what r is. Rows? Records? Requests?
    by TurdF3rguson
  • What are your thoughts on how design changes if writes become much heavier, ie. when recording agent operations?
    by handfuloflight
  • I'd be very curious to see you add the Optimized Reads instance types, e.g. r8gd or m8gd, to your benchmark. They add a local NVMe-based SSD block storage that serves as a cache in front of the network-based disks among other use cases. They have been a huge win for us for a read-heavy workload where the dataset is significantly larger than memory.

    Edit: Apologies, on a closer read, I realize you were not testing RDS but managing Postgres on EC2 directly.

    by mattlong
  • Would love to see a comparison between Aurora PostgreSQL and self-host PostgreSQL on the same EC2 instance type.
    by ballislife30
  • Would be interesting to see huge pages and io2 impact.

    I did a smaller version on Azure and disk latency had a massive impact much more so than max IOPs (although their crappy storage offering needed like 64-128 iodepth to get advertised iops).

    Results seem mostly in line with expectations. Iirc vcpu is threads so on arm64 you get 4 smt1 cores vs Intel/AMD you get 2 smt2 cores.

    by nijave