Slow performance on EU-SE-1 pods with network storage
Performance for last two days on pods deployed on EU has been quite bad. I use mostly comfyui for image generation and I noticed it takes three times as long to execute my workflows compared to before. In some cases the generation just flat out fails. I tried using A40s and A5000 GPUs with same results.
Also transferring files from PC to pods seems quite slow (using runpodctl)
None of this was an issue like 2 days ago
Last used pod id: ID: 7k71ur7lgq3f5x
Can someone look into it from the team?
11 Replies
Same for me. I also submitted ticket.
Same issue. Even simple operations are getting stuck in D state and failing to complete.
Me too, can't even load up my machine
@Choowkee
Escalated To Zendesk
The thread has been escalated to Zendesk!
Hey is it solved?
I'm also facing the same issue. Network storage in eu-se-1 is super slow since last couple of days. Loading models from vol takes 10mins+ when run the first time which leads to timeouts
seems like they got the same as you @Rishabh Jalan , slow NS is it?
Yeah .there is an message at the incident also
Same issue. They not resolving the issue rather by saying restart the machines. Unprofessional behavior from Runpod side
Sent a ticket via email as well to signal boost the issue. Support asking me to try and deploy my network volume on a different server - when thats impossible - was quite an interesting response 😄
oh now my pod wont even deploy, stuck on "waiting for logs..."
Solution
Seems perfo is back to normal ,marking as solved