# Slow recovery speeds

**URL:** <https://discuss.elastic.co/t/slow-recovery-speeds/102277>\
**Category:** Elasticsearch\
**Created:** [September 29, 2017, 3:43pm UTC](https://discuss.elastic.co/t/slow-recovery-speeds/102277 "2017-09-29T15:43:15Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![avaneeshr](https://avatars.discourse-cdn.com/v4/letter/a/85f322/32.png) [@avaneeshr](https://discuss.elastic.co/u/avaneeshr)\
**Post date:** [September 29, 2017, 3:43pm UTC](https://discuss.elastic.co/t/slow-recovery-speeds/102277/1 "2017-09-29T15:43:15Z")

</div>

Hi all!  
ES v2.4.0  
I am using a AWS i3.4xlarge instance (NVMe SSDs) which is IO optimized and has high Network throughput  
Single node cluster- 16 cores, 120G memory, 10gbps network link  
I try to restore a snapshot from S3 repository (size: 320G, 3 shards) to this node  
I check the values in iotop and iftop, and they confirm that the recovery is restricted by the default 40mb max\_bytes\_per\_sec limit.

Then I add these settings to my cluster:

```
curl -XPUT 10.5.2.30:9200/_cluster/settings -d '{
"persistent" : {
"cluster.routing.allocation.node_concurrent_recoveries": 20,
"indices.recovery.max_bytes_per_sec": "100mb",
"indices.recovery.concurrent_streams": 5,
"indices.recovery.concurrent_small_file_streams": 5,
"indices.recovery.translog_ops": 5000,
"cluster.routing.allocation.node_initial_primaries_recoveries": 30}
}'

```

I restart the cluster and try to recover the snapshot.  
But I still get the exact same speeds - 40MBps write.

Where am I missing?

---

<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:** [October 27, 2017, 3:43pm UTC](https://discuss.elastic.co/t/slow-recovery-speeds/102277/2 "2017-10-27T15:43:25Z")

</div>

This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.