Weviate Serverless Disk Usage Too High

Support
1

Description

Our “serverless” cluster is failing to insert new records due to disk usage being to high.

put object: import into index record: put local object: shard=“C3Alih6pvtKv”: store is read-only due to: disk usage too high. Set to read-only at 90.38%, threshold set to 90.00%"

Server Setup Information

  • Weaviate Server Version: 1.28.4
  • Deployment Method: serverless
  • Multi Node? Number of Running Nodes: serverless
  • Client Language and Version: curl
  • Multitenancy?: no

Any additional Information

I am confused as to what serverless offering does as it seems to me it does it not scale well at all with errors like this.

2

hi @pdp !!

This can happen on recently created clusters, where the disk usage is not known yet.

Now, when you start ingesting objects, and do it aggressively, the auto scaler will not have enough time to kick in.

Once we provision enough disk, it can support more aggressive imports as it has more room and data to work with.

For any issues related to clusters hosted at our cloud, the best place for support is from our Console, where you will be instructed on how to create a support ticket.

This will help us get access to your cluster and fix it faster.

Let me know if that helps!

Thanks!

3

Hey, thanks for the reply.

I did reach out to the support team but nothing yet.

Is it normal for the cluster to be in this state for 4 hours?

4

Hi @pdp !!

It is not normal. Sorry for the inconvenience.

if you create a new cluster in our cloud and want to perform an aggressive ingestion in a short period of time, you can reach out to us so we can allocate enough resources beforehand, so you migration/ingestion can go smoothly.

Please, let me know if you got a response already from the support line.

Thanks!