Skip to content

Commit ea5b309

Browse files
committed
autofix
1 parent 6e23941 commit ea5b309

File tree

1 file changed

+4
-2
lines changed

1 file changed

+4
-2
lines changed

src/blog/tanstack-start-ssr-performance-600-percent.md

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -71,6 +71,7 @@ autocannon -d 30 -c 100 --warmup [ -d 2 -c 20 ] http://localhost:3000/bench/link
7171
### CPU profiling with `@platformatic/flame`
7272

7373
To record a CPU profile of the server under load, we use [`@platformatic/flame`](https://github.com/platformatic/flame) to start the server:
74+
7475
```sh
7576
flame run ./dist/server.mjs
7677
```
@@ -98,7 +99,6 @@ Our benchmarks were stable enough to produce very similar results on a range of
9899

99100
The exact benchmark code is available in [our repository](https://github.com/TanStack/router/tree/main/e2e/react-start/flamegraph-bench).
100101

101-
102102
## Finding 1: `URL` is expensive in server hot paths
103103

104104
### The mechanism
@@ -135,7 +135,6 @@ See: [#6442](https://github.com/TanStack/router/pull/6442), [#6447](https://gith
135135

136136
Like every PR in this series, this was profiling the impacted method before and after the change. For example we can see in the example below that the `buildLocation` method went from being one of the major bottlenecks of a navigation to being a very small part of the overall cost:
137137

138-
139138
| | |
140139
| ------ | --------------------------------------------------------------------------------------------------------------------------------------- |
141140
| Before | ![CPU profiling of buildLocation before the changes](/blog-assets/tanstack-start-ssr-performance-600-percent/before-build-location.png) |
@@ -267,12 +266,15 @@ To be clear: TanStack Start was not broken before these changes. Under normal tr
267266
The following graphs show event-loop utilization against throughput for each feature-focused endpoint, before and after the optimizations. Lower utilization at the same req/s means more headroom; higher req/s at the same utilization means more capacity.
268267

269268
#### links-100
269+
270270
![Event-loop utilization vs throughput for links-100, before and after](/blog-assets/tanstack-start-ssr-performance-600-percent/links-after.png)
271271

272272
#### layouts-26-with-params
273+
273274
![Event-loop utilization vs throughput for nested routes, before and after](/blog-assets/tanstack-start-ssr-performance-600-percent/nested-after.png)
274275

275276
#### empty (baseline)
277+
276278
![Event-loop utilization vs throughput for minimal route, before and after](/blog-assets/tanstack-start-ssr-performance-600-percent/nothing-after.png)
277279

278280
### Flamegraph evidence slots

0 commit comments

Comments
 (0)