Serverless Package Build Failed - Disk Quota Exceeded

TL;DR - Runpod deploy failed with Disk Quota Exceeded error even though volume has sufficient disk space. Details 1. I pushed a new release from my repository to submit a new build to runpod severless. 2. When building the package, runpod failed with the following error
2025-11-17 21:37:57 [INFO] #14 ERROR: error writing layer blob: rpc error: code = Unknown desc = close /runpod-volume/registry.runpod.net/REPO_NAME-main-dockerfile/ingest/784301177dee4429ca0632a250b9c5a261c51ba7ceb483c433ad14f65281598b/ref: disk quota exceeded: unknown
2025-11-17 21:37:57 [INFO] #14 ERROR: error writing layer blob: rpc error: code = Unknown desc = close /runpod-volume/registry.runpod.net/REPO_NAME-main-dockerfile/ingest/784301177dee4429ca0632a250b9c5a261c51ba7ceb483c433ad14f65281598b/ref: disk quota exceeded: unknown
3. I verified that my disk have sufficient space. I also increased it but the issue persist. 4. Here is the build ID for reference -> e5a888dd-a3a8-479e-862f-7d816cf61096 5. This was never an issue before, we did not add new packages to requirements.txt. Qusetion: What is the issue here? This is during the build phase, when runpod detects a new release from my repo.
16 Replies
Poddy
Poddy4d ago
riverfog7
riverfog74d ago
do you embed models to your docker image?
hangry6890
hangry6890OP4d ago
No I don't embed model in docker image. My model is stored in Volume and loaded in directly.
riverfog7
riverfog74d ago
do you know the size of the resulting docker image? like about 10 gigs
hangry6890
hangry6890OP4d ago
How can I check that? Do I have to build it locally?
riverfog7
riverfog74d ago
yeah you have to build it if you wanna check
riverfog7
riverfog74d ago
disk quota exceeded: unknown - Runpod
I've been routinely pushing updates to my serverless, and everything has been working fine until today. Now, I’m encountering the following error during the image push: ``` error writing layer blob: rpc error: code = Unknown desc = close /runpod-volume/registry.runpod.net/[redacted-project-path]/ingest/[hash...]/ref: disk quota exceeded: unkn...
riverfog7
riverfog74d ago
its on runpod's side ig make a ticket at the support page @hangry6890 https://contact.runpod.io/hc/en-us/requests/new
hangry6890
hangry6890OP4d ago
I got the same out of disk space error when I build locally, and the error seems related to the base image provided by Runpod. runpod/pytorch:2.8.0-py3.11-cuda12.8.1-cudnn-devel-ubuntu22.04 <- This image is almost 10GB large Note: I still have tons of disk space left but still see this error. I use that image as the base image to build on-top of, and that takes up the most space Error Message
------
> [1/6] FROM docker.io/runpod/pytorch:2.8.0-py3.11-cuda12.8.1-cudnn-devel-ubuntu22.04@sha256:cb154fcca15d1d6ce858cfa672b76505e30861ef981d28ec94bd44168767d853:
------
Dockerfile:2
--------------------
1 | # Use Runpod's CUDA-enabled base image
2 | >>> FROM runpod/pytorch:2.8.0-py3.11-cuda12.8.1-cudnn-devel-ubuntu22.04
3 |
4 | WORKDIR /app
--------------------
ERROR: failed to solve: failed to register layer: write /usr/local/lib/python3.11/dist-packages/triton/_C/libtriton.so: no space left on device
------
> [1/6] FROM docker.io/runpod/pytorch:2.8.0-py3.11-cuda12.8.1-cudnn-devel-ubuntu22.04@sha256:cb154fcca15d1d6ce858cfa672b76505e30861ef981d28ec94bd44168767d853:
------
Dockerfile:2
--------------------
1 | # Use Runpod's CUDA-enabled base image
2 | >>> FROM runpod/pytorch:2.8.0-py3.11-cuda12.8.1-cudnn-devel-ubuntu22.04
3 |
4 | WORKDIR /app
--------------------
ERROR: failed to solve: failed to register layer: write /usr/local/lib/python3.11/dist-packages/triton/_C/libtriton.so: no space left on device
riverfog7
riverfog74d ago
might be the default container size limit
Poddy
Poddy4d ago
@hangry6890
Escalated To Zendesk
The thread has been escalated to Zendesk!
Unknown User
Unknown User4d ago
Message Not Public
Sign In & Join Server To View
riverfog7
riverfog74d ago
I mean the local build failing default docker desktop container size limit exists
Unknown User
Unknown User4d ago
Message Not Public
Sign In & Join Server To View
hangry6890
hangry6890OP4d ago
TL;DR - We're still facing the same problem on Runpod deploy after image build works locally. Details - Updated base image to use FROM pytorch/pytorch:2.8.0-cuda12.8-cudnn9-runtime - Verified build works locally and it has a size of 8.24GB - However, Runpod still have the same issue - This is the build id -> 82c83ef1-b44c-4529-96b7-410a7e169c30 - Opened zendesk ticket #27234 Error message on Runpod
2025-11-17 23:26:35 [ERROR] ERROR: (*service).Write failed: rpc error: code = Unknown desc = close /runpod-volume/registry.runpod.net/REPO_NAME-main-dockerfile/ingest/be3d24e8c953f430df66c1ebc9b2ee4bb48c3537603f4281dde5ad1b271fd27d/ref: disk quota exceeded
2025-11-17 23:26:35 [ERROR] ERROR: (*service).Write failed: rpc error: code = Unknown desc = close /runpod-volume/registry.runpod.net/REPO_NAME-main-dockerfile/ingest/be3d24e8c953f430df66c1ebc9b2ee4bb48c3537603f4281dde5ad1b271fd27d/ref: disk quota exceeded
@Jason , @riverfog7
riverfog7
riverfog73d ago
Its on runpod side

Did you find this page helpful?