# Unexpected High Disk Utilization on All Frozen Nodes After Adding New Node in Elastic Cloud

**URL:** <https://discuss.elastic.co/t/unexpected-high-disk-utilization-on-all-frozen-nodes-after-adding-new-node-in-elastic-cloud/378910>\
**Category:** Elasticsearch\
**Tags:** elastic-stack-monitoring, elastic-stack-alerting\
**Created:** [June 5, 2025, 11:40am UTC](https://discuss.elastic.co/t/unexpected-high-disk-utilization-on-all-frozen-nodes-after-adding-new-node-in-elastic-cloud/378910 "2025-06-05T11:40:33Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![SourabhK1](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/sourabhk1/32/142111_2.png) [@SourabhK1](https://discuss.elastic.co/u/SourabhK1)\
**Post date:** [June 5, 2025, 11:40am UTC](https://discuss.elastic.co/t/unexpected-high-disk-utilization-on-all-frozen-nodes-after-adding-new-node-in-elastic-cloud/378910/1 "2025-06-05T11:40:33Z")

</div>

We’re using frozen tier in Elastic Cloud with searchable snapshots (fully mounted).  
Initially had 3 frozen nodes (~99.4% used disk capacity), and hit the 9000 shard limit.  
Added a 4th frozen node to increase capacity (12,000 shards total).

After the node joined, shards rebalanced equally on all 4 frozen nodes, but all 4 nodes now show ~99.4% disk usage—including the new one, almost immediately.

Only ~120 shards were pending before scale-up.  
Is this high disk usage due to blob cache behavior, or something else we should investigate?

Looking to understand if this is expected in Elastic Cloud or a potential misconfiguration.

Thanks!

---

<div class="post-metadata">

**Author:** ![Tortoise](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/tortoise/32/147587_2.png) [@Tortoise](https://discuss.elastic.co/u/Tortoise)\
**Post date:** [June 6, 2025, 5:28am UTC](https://discuss.elastic.co/t/unexpected-high-disk-utilization-on-all-frozen-nodes-after-adding-new-node-in-elastic-cloud/378910/2 "2025-06-06T05:28:14Z")

</div>

Hello @SourabhK1

Welcome to the community.

> **[Searchable snapshots | Elastic Docs](https://www.elastic.co/docs/deploy-manage/tools/snapshot-and-restore/searchable-snapshots)**
>
> Searchable snapshots let you use snapshots to search infrequently accessed and read-only data in a very cost-effective fashion. The cold and frozen data...

As per this URL you can check the defaults set on your environment generally it is 90% default. So when you add a new frozen node the disk space will be shown by default 90% occupied :

 ![image](https://us1.discourse-cdn.com/elastic/original/3X/c/3/c3c79bcd7298555cdaf4ca3bd5d6648ae0c3f4d6.png)

Thanks!!

---

<div class="post-metadata">

**Author:** ![SourabhK1](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/sourabhk1/32/142111_2.png) [@SourabhK1](https://discuss.elastic.co/u/SourabhK1)\
**Post date:** [June 6, 2025, 5:06pm UTC](https://discuss.elastic.co/t/unexpected-high-disk-utilization-on-all-frozen-nodes-after-adding-new-node-in-elastic-cloud/378910/3 "2025-06-06T17:06:36Z")

</div>

@Tortoise Thank you. This is something relevant.