snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-23 02:27:40 +08:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

Update performance

Browse Source
This commit is contained in:
Mathilde Boivin 2020-03-26 19:22:59 +01:00
parent c15deb41b0
commit 7297396162
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
README.md
View File

@ -175,19 +175,19 @@ Now that your MeiliSearch server is up and running, you can learn more about how
## Performances ## Performances
When processing a dataset composed of _100 353_ documents with _352_ attributes each and _3_ of them indexed, which means more than _300 000_ fields indexed for _35 million_ stored, MeiliSearch is able to carry out more than _2.8k req/sec_ with an average response time of _9 ms_ on an Intel i7-7700 (8) @ 4.2GHz. When processing a dataset composed of 5M books composed of a title and an author name, MeiliSearch is able to carry out more than 553 req/sec with an average response time of 21 ms on an Intel i7-7700 (8) @ 4.2GHz.
Requests are made using [wrk](https://github.com/wg/wrk) and scripted to simulate real users' queries. Requests are made using [wrk](https://github.com/wg/wrk) and scripted to simulate real users' queries.
``` ```
Running 10s test @ http://localhost:2230 Running 10s test @ http://1.2.3.4:7700
2 threads and 25 connections 2 threads and 10 connections
Thread Stats Avg Stdev Max +/- Stdev Thread Stats Avg Stdev Max +/- Stdev
Latency 9.52ms 7.61ms 99.25ms 84.58% Latency 21.45ms 15.64ms 214.10ms 85.95%
Req/Sec 1.41k 119.11 1.78k 64.50% Req/Sec 256.48 37.66 330.00 69.50%
28080 requests in 10.01s, 7.42MB read 5132 requests in 10.05s, 2.31MB read
Requests/sec: 2806.46 Requests/sec: 510.46
Transfer/sec: 759.17KB Transfer/sec: 234.77KB
``` ```
We also indexed a dataset containing about _12 millions_ cities names in _24 minutes_ on a _8 cores_, _64 GB of RAM_, and a _300 GB NMVe_ SSD machine.<br/> We also indexed a dataset containing about _12 millions_ cities names in _24 minutes_ on a _8 cores_, _64 GB of RAM_, and a _300 GB NMVe_ SSD machine.<br/>