# Is there some guide manual for a reasonable way to deployment topology ？

**URL:** <https://forums.foundationdb.org/t/is-there-some-guide-manual-for-a-reasonable-way-to-deployment-topology/2778>\
**Category:** Development\
**Created:** [July 6, 2021, 6:49am UTC](https://forums.foundationdb.org/t/is-there-some-guide-manual-for-a-reasonable-way-to-deployment-topology/2778 "2021-07-06T06:49:39Z")\
**Posts on this page:** 1\
**Showing post:** 3

<div class="post-metadata">

**Author:** ![alexmiller](https://sea1.discourse-cdn.com/foundationdb/user_avatar/forums.foundationdb.org/alexmiller/32/326_2.png) [@alexmiller](https://forums.foundationdb.org/u/alexmiller)\
**Post date:** [July 6, 2021, 11:05pm UTC](https://forums.foundationdb.org/t/is-there-some-guide-manual-for-a-reasonable-way-to-deployment-topology/2778/3 "2021-07-06T23:05:32Z")

</div>

There’s a family of threads about performance tuning:

- [Cluster tuning cookbook](https://forums.foundationdb.org/t/cluster-tuning-cookbook/520) and the threads linked therein
- [How to troubleshoot throughput performance degrade?](https://forums.foundationdb.org/t/how-to-troubleshoot-throughput-performance-degrade/1436/)

Note that both python\_performance.py and go-ycsb will test the amount of work that you can generate from only one client. It’s possible that the bottleneck in your benchmark is the client. [Why doesn't my cluster performance scale when I double the number of machines?](https://forums.foundationdb.org/t/why-doesnt-my-cluster-performance-scale-when-i-double-the-number-of-machines/640) has instructions on how to run `multitest` and benchmark fdb clusters using FDB in a way that runs across multiple client processes.

---

_[View the full topic](https://forums.foundationdb.org/t/is-there-some-guide-manual-for-a-reasonable-way-to-deployment-topology/2778)._