# Literature review

### [Bottleneck Characterization of Dynamic Web Site Benchmarks](https://scholarship.rice.edu/bitstream/handle/1911/96296/TR02-391.pdf?sequence=1\&isAllowed=y)       (2002. Rice University Computer Science)

A performance evaluation of these benchmarks on commodity hardware identified bottleneck resources for each case.

* The online bookstore's bottleneck was the <mark style="background-color:orange;">database CPU</mark>
* front-end and the back-end a bottleneck. <mark style="color:orange;">With amounts of memory common by today’s standards</mark>, neither the main memory nor the disk proved to be a limiting factor in terms of performance for any of the benchmarks.

### [Measuring bottleneck link speed in packet-switched networks](https://reader.elsevier.com/reader/sd/pii/S0166531696900322?token=5E0B56BDEB848904778746A4A399472DAA413A0256147BBAB6622D552558242D52A373FCB70E3B159ACDFB8E803B22EB\&originRegion=eu-west-1\&originCreation=20230507211051) (2004.Computer Science Department, Boston University)

* For document transfer applications like <mark style="color:orange;">FTP, Gopher, and the World Wide Web, transfer time is directly related to available bandwidth</mark>. This depends on the path capacity between client and server and the competing traffic on that path. <mark style="background-color:orange;">If applications had access to these measurements, they could calculate path utilization and select the best path or server to reduce response time</mark>. This dynamic server selection would be particularly useful in mobile computing environments with frequently changing server availability.

### [Bottleneck Identification and Performance Modeling of OPC UA Communication Models](https://dl.acm.org/doi/abs/10.1145/3297663.3309670) (2019. ACM/SPEC International Conference on Performance Engineering)

* performance measurements with OPC UA client/server and pub/sub communication and created a CPU utilization prediction model based on linear regression that can be used to size hardware environments. We found that the <mark style="background-color:orange;">server CPU is the main bottleneck for OPC UA pub/sub communication</mark>, but allows a throughput of up to 40,000 signals per second on a Raspberry Pi Zero. We also found that the client/server session management <mark style="color:orange;">overhead can severely impact performance, if more than 20 clients access a single server.</mark>

<div align="right"><figure><img src="https://970977003-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9CSfXent0d8AWRVxR166%2Fuploads%2FBBj0LvidSV1Ewk0h5QQ7%2Fmodel.PNG?alt=media&#x26;token=0a6b13eb-5b3e-409f-bce5-daafe5776dab" alt="Modeling of OPC UA " width="339"><figcaption><p>ref: <a href="https://dl.acm.org/doi/abs/10.1145/3297663.3309670">https://dl.acm.org/doi/abs/10.1145/3297663.3309670</a></p></figcaption></figure></div>

&#x20;


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://phry-d-zpringchill.gitbook.io/an-empirical-study-of-factors-affecting-bottleneck/chapter-2/literature-review.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.