# What happens when all nodes are over water mark for disk based allocation?

**URL:** <https://discuss.elastic.co/t/what-happens-when-all-nodes-are-over-water-mark-for-disk-based-allocation/47312>\
**Category:** Elasticsearch\
**Created:** [April 13, 2016, 9:31pm UTC](https://discuss.elastic.co/t/what-happens-when-all-nodes-are-over-water-mark-for-disk-based-allocation/47312 "2016-04-13T21:31:58Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![Caleb\_Phillips](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/caleb_phillips/32/1540_2.png) [@Caleb\_Phillips](https://discuss.elastic.co/u/Caleb_Phillips)\
**Post date:** [April 13, 2016, 9:31pm UTC](https://discuss.elastic.co/t/what-happens-when-all-nodes-are-over-water-mark-for-disk-based-allocation/47312/1 "2016-04-13T21:31:58Z")

</div>

My guess is that there would be trouble creating new indices, but would existing indices continue to function as long as there were no allocation events?

---

<div class="post-metadata">

**Author:** ![warkolm](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/warkolm/32/39224_2.png) [@warkolm](https://discuss.elastic.co/u/warkolm)\
**Post date:** [April 13, 2016, 9:35pm UTC](https://discuss.elastic.co/t/what-happens-when-all-nodes-are-over-water-mark-for-disk-based-allocation/47312/2 "2016-04-13T21:35:04Z")

</div>

Yeah, it won't allocate new shards but won't un-allocate existing ones.

---

<div class="post-metadata">

**Author:** ![Caleb\_Phillips](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/caleb_phillips/32/1540_2.png) [@Caleb\_Phillips](https://discuss.elastic.co/u/Caleb_Phillips)\
**Post date:** [April 13, 2016, 9:50pm UTC](https://discuss.elastic.co/t/what-happens-when-all-nodes-are-over-water-mark-for-disk-based-allocation/47312/3 "2016-04-13T21:50:09Z")

</div>

Thanks, Mark.

Is there any setting that will prevent ES from writing to already allocated shards if disk space passes a certain percentage?

---

<div class="post-metadata">

**Author:** ![warkolm](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/warkolm/32/39224_2.png) [@warkolm](https://discuss.elastic.co/u/warkolm)\
**Post date:** [April 13, 2016, 9:50pm UTC](https://discuss.elastic.co/t/what-happens-when-all-nodes-are-over-water-mark-for-disk-based-allocation/47312/4 "2016-04-13T21:50:57Z")

</div>

Nope.

---

<div class="post-metadata">

**Author:** ![Caleb\_Phillips](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/caleb_phillips/32/1540_2.png) [@Caleb\_Phillips](https://discuss.elastic.co/u/Caleb_Phillips)\
**Post date:** [April 13, 2016, 10:11pm UTC](https://discuss.elastic.co/t/what-happens-when-all-nodes-are-over-water-mark-for-disk-based-allocation/47312/5 "2016-04-13T22:11:20Z")

</div>

Thanks for the quick responses

---

<div class="post-metadata">

**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\
**Post date:** [July 5, 2017, 10:59pm UTC](https://discuss.elastic.co/t/what-happens-when-all-nodes-are-over-water-mark-for-disk-based-allocation/47312/6 "2017-07-05T22:59:28Z")

</div>