diff --git a/Documentation/benchmarks/README.md b/Documentation/benchmarks/README.md
index dff7d9953..f1b998894 100644
--- a/Documentation/benchmarks/README.md
+++ b/Documentation/benchmarks/README.md
@@ -5,3 +5,9 @@ etcd benchmarks will be published regularly and tracked for each release below:
 - [etcd v2.1.0-alpha](./etcd-2-1-0-alpha-benchmarks.md)
 - [etcd v2.2.0-rc](./etcd-2-2-0-rc-benchmarks.md)
 - [etcd v3 demo](./etcd-3-demo-benchmarks.md)
+
+# Memory Usage Benchmarks
+
+It records expected memory usage in different scenarios.
+
+- [etcd v2.2.0-rc](./etcd-2-2-0-rc-memory-benchmarks.md)
diff --git a/Documentation/benchmarks/etcd-2-2-0-rc-memory-benchmarks.md b/Documentation/benchmarks/etcd-2-2-0-rc-memory-benchmarks.md
new file mode 100644
index 000000000..a8d9f1408
--- /dev/null
+++ b/Documentation/benchmarks/etcd-2-2-0-rc-memory-benchmarks.md
@@ -0,0 +1,47 @@
+## Physical machine
+
+GCE n1-standard-2 machine type
+
+- 1x dedicated local SSD mounted under /var/lib/etcd
+- 1x dedicated slow disk for the OS
+- 7.5 GB memory
+- 2x CPUs
+
+## etcd
+
+```
+etcd Version: 2.2.0-rc.0+git
+Git SHA: 103cb5c
+Go Version: go1.5
+Go OS/Arch: linux/amd64
+```
+
+## Testing
+
+Start 3-member etcd cluster, each of which uses 2 cores.
+
+The length of key name is always 64 bytes, which is a reasonable length of average key bytes.
+
+## Memory Maximal Usage
+
+- etcd may use maximal memory if one follower is dead and the leader keeps sending snapshots.
+- `max RSS` is the maximal memory usage recorded in 3 runs.
+
+| value bytes | key number  | data size(MB) | max RSS(MB) | max RSS/data rate on leader |
+|-------------|-------------|---------------|-------------|-----------------------------|
+| 128  | 50000  | 6 | 433 | 72x |
+| 128  | 100000 | 12 | 659 | 54x |
+| 128  | 200000 | 24 | 1466 | 61x |
+| 1024 | 50000  | 48 | 1253 | 26x |
+| 1024 | 100000 | 96 | 2344 | 24x |
+| 1024 | 200000 | 192 | 4361 | 22x |
+
+## Data Size Threshold
+
+- When etcd reaches data size threshold, it may trigger leader election easily and drop part of proposals.
+- At most cases, etcd cluster should work smoothly if it doesn't hit the threshold. If it doesn't work well due to insufficient resources, you need to decrease its data size.
+
+| value bytes | key number limitation | suggested data size threshold(MB) | consumed RSS(MB) |
+|-------------|-----------------------|-----------------------------------|------------------|
+| 128 | 400K | 48 | 2400 |
+| 1024 | 300K | 292 | 6500 |