servo

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

We’ve analysed the runtime performance of Servo and Chromium in the cases of loading four websites, as of the versions below:

“servo.1” — f8933a57353aeca14a6cbc60b3cb0cf98cab6c5d (2024-10-06)
“servo.2” — 7015e0fb5f1a63ed13a5b07b056036e6e7adbc16 (2024-10-22)
“servo.3” — bac1101163a436096fe0b71bed79094658bba3b2 (2024-10-30)
“chromium” — Google Chrome 128.0.6613.113 (Official Build), as shipped with NixOS 24.11.20240905.8ce7f9f

We found the newer versions of Servo (servo.2 and servo.3) to be significantly faster than the older version (servo.1), thanks to several performance improvements we landed last month. For example, taking the average change across the pages under test with a two-CPU configuration, First Contentful Paint times are 23% lower, and overall rendering times are 38% lower.

servo.3 continues to outperform Chromium in First Contentful Paint for three of the four pages under test. We still lag behind Chromium (chromium) in FCP for www.baidu.com, but are now only 81% slower, down from 97% slower.

servo.3 performs less favourably in overall rendering time, but improves over servo.1 and servo.2. We now outperform Chromium (chromium) in all CPU configurations for one of the four pages under test (zh.wikipedia.org), and outperform it for some CPU configurations in two others (servo.org and www.baidu.com).

All of the code and data used to write this report is in this file including:

perf-analysis-tools — our tooling
- perf-analysis-tools/run-all-benchmarks.sh — how we ran the benchmarks
- convert-pftrace-to-json.sh — converts Chrome tracing files to JSON
- analyse-cpu-results.sh — computes summaries for each sample within a CPU configuration
- generate-report-tables.sh — collates summaries into tables for this report
*/summary.txt — summary results (generated by our tooling)
Data for each engine under test
- *.servo.1 — data for the first version of Servo (servo.1)
- *.servo.2 — data for the second version of Servo (servo.2)
- *.servo.3 — data for the third version of Servo (servo.3)
- *.chromium — data for Chromium (chromium)
- */*.html — Servo HTML traces
- */*.pftrace — Chrome tracing files
Data for each page under test
- servo.org.* — data for https://servo.org/
- www.amazon.com.* — data for https://www.amazon.com/dp/B07S9XZYN2
- zh.wikipedia.org.* — data for https://zh.wikipedia.org/wiki/Servo
- www.baidu.com.* — data for https://www.baidu.com/

Methodology

This report further automates the collection and analysis of data over our previous report, since there are now 64 configurations (four engines × four pages × four CPU configurations) that are each run 30 times. Changes to our procedures include:

Merging the mitmproxy recordings, so the replay only needs to be started once
Fixing intermittent xdotool failures caused by races in benchmark-servo.sh
Parameterising our CPU isolation script over Linux cpu ids
Writing scripts to run benchmarks across the 64 configurations
Making those scripts set up the correct CPU isolation automatically
Making measurement resumable at sample boundaries (every 30 runs)

Note that the times in this report are not directly comparable with those in the previous report, due to some minor changes in measurement procedure, such as increasing the time we run each browser from 5 seconds to 10 seconds. The results for servo.1 are the best representation of how Servo performed at the time of the previous report.

That said, due to time constraints, our methodology is otherwise unchanged from the previous report. Notably, there are several unresolved limitations in our collection and interpretation of data, which we’ll discuss below.

The test scenarios in this report only cover cold page loads, without any caching or further user interaction.

Times are not cut off after the page is “fully loaded”, which may distort results due to layout operations after page load.

In § User-facing paint metrics, we don’t have Largest Contentful Paint (LCP) data, since this metric is not yet implemented in Servo.

In § Raw events, much of the LayoutPerform time in Servo is also recorded in ParseHTML, yielding unreasonable ParseHTML times, and ScriptEvaluate times in Servo are unreasonably small compared to similar events in Chromium.

In § Rendering phases model, the Rasterise phase for Chromium is incomplete, since it only includes Layerize events, and Parse and Script phase times are heavily distorted between Servo and Chromium.

Test environment

Our test environment is as follows:

AMD 7950X (amd64)
NixOS 24.11.20240905.8ce7f9f running X11
Linux 6.11.0-rc6, linuxPackages_testing from NixOS (as above)
Servo is built with ./mach build --profile production-stripped
Chromium is google-chrome from NixOS (as above)
- NIXPKGS_ALLOW_UNFREE=1 nix run --impure github:NixOS/nixpkgs/8ce7f9f78bdbe659a8d7c1fe376b89b3a43e4cdc\#google-chrome
servo/perf-analysis-tools as of 01d5b4152dae0

The workloads are run in a shell created as follows:

$ newgrp mitmproxy
$ nix-shell ~/path/to/servo/shell.nix --run zsh

CPU isolation is handled in § Measurement procedure.

Measurement procedure

To ensure that the windows are kept offscreen, we use the following i3 config:

$ cat ~/.config/i3/config
for_window [instance="^servo$" class="^servo$"] floating enable
for_window [instance="^google-chrome [(]" class="^Google-chrome$"] floating enable
assign [instance="^servo$" class="^servo$"] 7
assign [instance="^google-chrome [(]" class="^Google-chrome$"] 7

To ensure that the benchmarking scripts can set up the CPU isolation automatically, we use the following sudoers(5) config:

$ cat /etc/sudoers
%wheel  ALL=(ALL:ALL)    NOPASSWD: /path/to/perf-analysis-tools/isolate-cpu-for-shell.sh

We run the benchmarks as follows:

$ cd perf-analysis-tools

$ cat run-all-benchmarks.sh
#!/usr/bin/env zsh
set -euo pipefail -o bsdecho
sudo ./isolate-cpu-for-shell.sh $$ 14 15
./run-benchmarks-for-cpu.sh ../report3/2cpu
sudo ./isolate-cpu-for-shell.sh $$ {12..15}
./run-benchmarks-for-cpu.sh ../report3/4cpu
sudo ./isolate-cpu-for-shell.sh $$ {10..15}
./run-benchmarks-for-cpu.sh ../report3/6cpu
sudo ./isolate-cpu-for-shell.sh $$ {8..15}
./run-benchmarks-for-cpu.sh ../report3/8cpu

$ ./run-all-benchmarks.sh

This in turn sets up the CPU isolation for each CPU configuration and runs the benchmarks:

$ cat run-benchmarks-for-cpu.sh
#!/usr/bin/env zsh
set -euo pipefail -o bsdecho
sample_dir=$1
./run-benchmarks-for-site.sh servo.org https://servo.org/ "$sample_dir"
./run-benchmarks-for-site.sh www.amazon.com https://www.amazon.com/dp/B07S9XZYN2 "$sample_dir"
./run-benchmarks-for-site.sh zh.wikipedia.org https://zh.wikipedia.org/wiki/Servo "$sample_dir"
./run-benchmarks-for-site.sh www.baidu.com https://www.baidu.com/ "$sample_dir"

This in turn runs the benchmarks for each site:

#!/usr/bin/env zsh
set -euo pipefail -o bsdecho
key=$1
url=$2
sample_dir=$3
./benchmark-servo.sh ~/code/servo/servo.20241006.f8933a57353aeca14a6cbc60b3cb0cf98cab6c5d/servo "$url" 30 "$sample_dir/$key.servo.1"
./benchmark-servo.sh ~/code/servo/servo.20241022.7015e0fb5f1a63ed13a5b07b056036e6e7adbc16/servo "$url" 30 "$sample_dir/$key.servo.2"
./benchmark-servo.sh ~/code/servo/servo.20241030.bac1101163a436096fe0b71bed79094658bba3b2/servo "$url" 30 "$sample_dir/$key.servo.3"
./benchmark-chromium.sh google-chrome-stable "$url" 30 "$sample_dir/$key.chromium"

This in turn runs the benchmarks for each engine.

Analysis procedure

We first convert the Chromium traces from Perfetto format to JSON format:

$ ./convert-pftrace-to-json.sh /path/to/traceconv

Then we compute summaries for each sample within a CPU configuration:

$ for i in ?cpu; do ./analyse-cpu-results.sh $i; done

Then we collate those summaries and generate the tables:

$ ./generate-report-tables.sh

User-facing paint metrics

The paint metrics (FP and FCP) are standard web platform concepts that should be comparable between Chromium and Servo. In Chromium, their duration is measured from the markAsMainFrame event. In Servo, they are measured from the start of the first event associated with the page URL, which is always a ScriptParseHTML event.

The results are as follows.

FP (synthetic)

servo.org

	2cpu	4cpu	6cpu	8cpu
servo.1	401.3ms	393.6ms	385.9ms	373.0ms
servo.2	321.3ms	359.7ms	359.6ms	302.8ms
servo.3	314.9ms	350.5ms	301.4ms	309.1ms
chromium	686.5ms	467.9ms	436.0ms	429.1ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
servo.1	1.063s	1.178s	1.268s	1.174s
servo.2	973.5ms	1.090s	1.201s	1.209s
servo.3	974.1ms	1.139s	1.210s	1.211s
chromium	537.0ms	321.9ms	284.0ms	275.2ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
servo.1	334.9ms	302.6ms	288.6ms	299.9ms
servo.2	146.4ms	124.3ms	134.0ms	127.2ms
servo.3	139.8ms	132.0ms	123.5ms	124.5ms
chromium	666.1ms	396.1ms	402.3ms	403.4ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
servo.1	741.3ms	711.1ms	788.4ms	793.6ms
servo.2	692.4ms	712.0ms	686.0ms	689.3ms
servo.3	696.7ms	691.2ms	691.2ms	678.5ms
chromium	791.4ms	805.6ms	799.4ms	788.2ms

FCP (synthetic)

servo.org

	2cpu	4cpu	6cpu	8cpu
servo.1	401.3ms	393.6ms	385.9ms	373.0ms
servo.2	321.3ms	359.7ms	359.6ms	302.8ms
servo.3	314.9ms	350.5ms	301.4ms	309.1ms
chromium	686.5ms	467.9ms	436.0ms	429.1ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
servo.1	1.063s	1.178s	1.268s	1.174s
servo.2	973.5ms	1.090s	1.201s	1.209s
servo.3	974.1ms	1.139s	1.210s	1.211s
chromium	537.0ms	321.9ms	284.0ms	275.2ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
servo.1	334.9ms	302.6ms	288.6ms	299.9ms
servo.2	146.4ms	124.3ms	134.0ms	127.2ms
servo.3	139.8ms	132.0ms	123.5ms	124.5ms
chromium	666.1ms	396.1ms	402.3ms	403.4ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
servo.1	741.3ms	711.1ms	788.4ms	793.6ms
servo.2	692.4ms	712.0ms	686.0ms	689.3ms
servo.3	696.7ms	691.2ms	691.2ms	678.5ms
chromium	791.4ms	805.6ms	799.4ms	788.2ms

Raw events

For a detailed discussion of these events, see this section in our previous report.

The results are as follows, but the Servo and Chromium results are not comparable.

Compositing (real)

servo.org

	2cpu	4cpu	6cpu	8cpu
servo.1	53.92ms	53.27ms	52.92ms	53.66ms
servo.2	53.72ms	55.37ms	53.80ms	52.00ms
servo.3	51.15ms	55.20ms	54.44ms	51.60ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
servo.1	26.51ms	76.70ms	76.55ms	74.21ms
servo.2	82.79ms	76.54ms	75.68ms	75.92ms
servo.3	84.53ms	79.57ms	77.20ms	74.21ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
servo.1	41.18ms	40.38ms	40.17ms	39.61ms
servo.2	40.96ms	41.86ms	40.79ms	40.04ms
servo.3	26.82ms	42.33ms	40.70ms	40.14ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
servo.1	8.364ms	6.094ms	6.065ms	3.165ms
servo.2	5.268ms	30.14ms	4.472ms	29.48ms
servo.3	9.122ms	30.11ms	7.166ms	29.94ms

LayoutPerform (real)

servo.org

	2cpu	4cpu	6cpu	8cpu
servo.1	128.5ms	118.0ms	116.3ms	116.2ms
servo.2	57.93ms	51.04ms	49.21ms	48.93ms
servo.3	28.65ms	21.55ms	20.57ms	19.79ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
servo.1	5.666s	4.871s	4.844s	3.760s
servo.2	5.971s	5.724s	4.105s	3.424s
servo.3	5.311s	5.010s	4.312s	3.346s

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
servo.1	262.5ms	238.1ms	228.8ms	228.7ms
servo.2	163.9ms	160.1ms	140.7ms	147.9ms
servo.3	149.4ms	168.2ms	149.3ms	199.1ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
servo.1	179.3ms	161.4ms	162.8ms	150.5ms
servo.2	50.05ms	106.5ms	40.26ms	52.91ms
servo.3	30.84ms	39.48ms	38.87ms	54.77ms

ScriptEvaluate (real)

servo.org

	2cpu	4cpu	6cpu	8cpu
servo.1	356.9μs	354.2μs	354.2μs	355.0μs
servo.2	352.2μs	361.2μs	359.5μs	359.7μs
servo.3	356.5μs	359.2μs	355.9μs	356.1μs

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
servo.1	229.8ms	181.2ms	202.7ms	182.0ms
servo.2	196.7ms	152.8ms	177.0ms	151.0ms
servo.3	187.2ms	149.1ms	180.6ms	141.3ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
servo.1	654.2μs	675.0μs	663.1μs	658.3μs
servo.2	637.0μs	674.9μs	639.7μs	636.4μs
servo.3	731.9μs	677.6μs	648.4μs	636.1μs

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
servo.1	9.680ms	9.287ms	9.204ms	9.166ms
servo.2	9.629ms	9.133ms	9.168ms	9.022ms
servo.3	9.764ms	9.211ms	9.167ms	9.074ms

ScriptParseHTML (real)

servo.org

	2cpu	4cpu	6cpu	8cpu
servo.1	90.71ms	86.90ms	86.40ms	86.17ms
servo.2	22.59ms	20.51ms	20.03ms	19.89ms
servo.3	16.15ms	14.28ms	13.96ms	13.64ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
servo.1	825.2ms	831.2ms	805.1ms	808.7ms
servo.2	837.2ms	780.5ms	724.0ms	731.0ms
servo.3	744.0ms	676.7ms	736.3ms	704.1ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
servo.1	250.6ms	226.0ms	219.3ms	213.1ms
servo.2	45.03ms	36.73ms	37.76ms	35.55ms
servo.3	43.08ms	36.81ms	35.29ms	35.99ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
servo.1	84.62ms	83.58ms	83.57ms	83.41ms
servo.2	86.24ms	85.47ms	85.62ms	85.30ms
servo.3	83.20ms	83.02ms	82.92ms	82.61ms

EvaluateScript (real)

servo.org

	2cpu	4cpu	6cpu	8cpu
chromium	4.919ms	4.415ms	4.408ms	4.384ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
chromium	166.1ms	107.2ms	99.11ms	96.07ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
chromium	9.789ms	6.957ms	6.893ms	6.982ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
chromium	73.95ms	129.1ms	46.14ms	124.0ms

FunctionCall (real)

servo.org

	2cpu	4cpu	6cpu	8cpu
chromium	1.116ms	1.102ms	1.110ms	1.100ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
chromium	912.5ms	651.6ms	611.6ms	611.4ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
chromium	118.6ms	90.91ms	89.47ms	88.44ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
chromium	28.56ms	70.39ms	12.72ms	68.94ms

Layerize (real)

servo.org

	2cpu	4cpu	6cpu	8cpu
chromium	228.0μs	269.0μs	261.0μs	268.0μs

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
chromium	9.156ms	9.024ms	9.179ms	8.352ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
chromium	3.358ms	3.146ms	3.171ms	2.895ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
chromium	472.0μs	372.0μs	322.0μs	403.0μs

Layout (real)

servo.org

	2cpu	4cpu	6cpu	8cpu
chromium	50.03ms	42.30ms	41.29ms	40.29ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
chromium	152.3ms	105.2ms	99.62ms	96.77ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
chromium	140.6ms	124.5ms	123.5ms	123.0ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
chromium	26.51ms	24.25ms	22.96ms	23.41ms

Paint (real)

servo.org

	2cpu	4cpu	6cpu	8cpu
chromium	918.0μs	1.139ms	1.137ms	1.151ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
chromium	22.33ms	20.18ms	16.53ms	17.70ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
chromium	12.52ms	13.06ms	13.13ms	12.97ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
chromium	855.0μs	878.0μs	724.0μs	880.0μs

ParseHTML (real)

servo.org

	2cpu	4cpu	6cpu	8cpu
chromium	7.442ms	5.406ms	5.400ms	5.573ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
chromium	190.1ms	133.3ms	122.6ms	117.2ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
chromium	8.332ms	5.448ms	5.090ms	5.113ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
chromium	34.92ms	26.98ms	24.57ms	24.79ms

PrePaint (real)

servo.org

	2cpu	4cpu	6cpu	8cpu
chromium	624.0μs	762.0μs	743.0μs	748.0μs

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
chromium	21.91ms	18.63ms	16.29ms	17.02ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
chromium	4.945ms	4.943ms	4.938ms	4.457ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
chromium	746.0μs	754.0μs	563.0μs	763.0μs

TimerFire (real)

servo.org

	2cpu	4cpu	6cpu	8cpu
chromium	444.0μs	451.0μs	450.0μs	455.0μs

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
chromium	575.7ms	418.3ms	402.6ms	393.1ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
chromium	29.84ms	25.52ms	24.89ms	23.27ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
chromium	8.511ms	6.742ms	4.359ms	6.372ms

UpdateLayoutTree (real)

servo.org

	2cpu	4cpu	6cpu	8cpu
chromium	14.87ms	14.85ms	14.44ms	14.72ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
chromium	129.6ms	86.65ms	84.23ms	83.08ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
chromium	24.13ms	18.37ms	18.53ms	17.83ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
chromium	4.689ms	6.415ms	4.720ms	6.196ms

Rendering phases model

For a detailed discussion of this model, see this section in our previous report.

The results are as follows, but we do not consider them very meaningful.

Parse (synthetic)

servo.org

	2cpu	4cpu	6cpu	8cpu
servo.1	90.71ms	86.90ms	86.40ms	86.17ms
servo.2	22.59ms	20.51ms	20.03ms	19.89ms
servo.3	16.15ms	14.28ms	13.96ms	13.64ms
chromium	7.318ms	5.303ms	5.296ms	5.475ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
servo.1	825.2ms	831.2ms	805.1ms	808.7ms
servo.2	837.2ms	780.5ms	724.0ms	731.0ms
servo.3	744.0ms	676.7ms	736.3ms	704.1ms
chromium	190.1ms	133.3ms	122.6ms	117.2ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
servo.1	250.6ms	226.0ms	219.3ms	213.1ms
servo.2	45.03ms	36.73ms	37.76ms	35.55ms
servo.3	43.08ms	36.81ms	35.29ms	35.99ms
chromium	8.332ms	5.448ms	5.090ms	5.113ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
servo.1	84.62ms	83.58ms	83.57ms	83.41ms
servo.2	86.24ms	85.47ms	85.62ms	85.30ms
servo.3	83.20ms	83.02ms	82.92ms	82.61ms
chromium	34.92ms	26.98ms	24.57ms	24.79ms

Script (synthetic)

servo.org

	2cpu	4cpu	6cpu	8cpu
servo.1	356.9μs	354.2μs	354.2μs	355.0μs
servo.2	352.2μs	361.2μs	359.5μs	359.7μs
servo.3	356.5μs	359.2μs	355.9μs	356.1μs
chromium	6.171ms	5.588ms	5.556ms	5.537ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
servo.1	229.8ms	181.2ms	202.7ms	182.0ms
servo.2	196.7ms	152.8ms	177.0ms	151.0ms
servo.3	187.2ms	149.1ms	180.6ms	141.3ms
chromium	1.145s	831.6ms	762.2ms	761.7ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
servo.1	654.2μs	675.0μs	663.1μs	658.3μs
servo.2	637.0μs	674.9μs	639.7μs	636.4μs
servo.3	731.9μs	677.6μs	648.4μs	636.1μs
chromium	130.6ms	100.9ms	98.53ms	97.29ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
servo.1	9.680ms	9.287ms	9.204ms	9.166ms
servo.2	9.629ms	9.133ms	9.168ms	9.022ms
servo.3	9.764ms	9.211ms	9.167ms	9.074ms
chromium	103.6ms	206.2ms	59.76ms	195.8ms

Layout (synthetic)

servo.org

	2cpu	4cpu	6cpu	8cpu
servo.1	128.5ms	118.0ms	116.3ms	116.2ms
servo.2	57.93ms	51.04ms	49.21ms	48.93ms
servo.3	28.65ms	21.55ms	20.57ms	19.79ms
chromium	80.82ms	59.30ms	58.29ms	57.53ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
servo.1	5.666s	4.871s	4.844s	3.760s
servo.2	5.971s	5.724s	4.105s	3.424s
servo.3	5.311s	5.010s	4.312s	3.346s
chromium	380.6ms	243.1ms	222.8ms	214.6ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
servo.1	262.5ms	238.1ms	228.8ms	228.7ms
servo.2	163.9ms	160.1ms	140.7ms	147.9ms
servo.3	149.4ms	168.2ms	149.3ms	199.1ms
chromium	189.1ms	162.6ms	161.7ms	160.3ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
servo.1	179.3ms	161.4ms	162.8ms	150.5ms
servo.2	50.05ms	106.5ms	40.26ms	52.91ms
servo.3	30.84ms	39.48ms	38.87ms	54.77ms
chromium	33.17ms	32.69ms	28.97ms	31.56ms

Rasterise (synthetic)

servo.org

	2cpu	4cpu	6cpu	8cpu
servo.1	53.92ms	53.27ms	52.92ms	53.66ms
servo.2	53.72ms	55.37ms	53.80ms	52.00ms
servo.3	51.15ms	55.20ms	54.44ms	51.60ms
chromium	228.0μs	269.0μs	261.0μs	268.0μs

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
servo.1	26.51ms	76.70ms	76.55ms	74.21ms
servo.2	82.79ms	76.54ms	75.68ms	75.92ms
servo.3	84.53ms	79.57ms	77.20ms	74.21ms
chromium	9.156ms	9.024ms	9.179ms	8.352ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
servo.1	41.18ms	40.38ms	40.17ms	39.61ms
servo.2	40.96ms	41.86ms	40.79ms	40.04ms
servo.3	26.82ms	42.33ms	40.70ms	40.14ms
chromium	3.358ms	3.146ms	3.171ms	2.895ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
servo.1	8.364ms	6.094ms	6.065ms	3.165ms
servo.2	5.268ms	30.14ms	4.472ms	29.48ms
servo.3	9.122ms	30.11ms	7.166ms	29.94ms
chromium	472.0μs	372.0μs	322.0μs	403.0μs

Overall rendering time model

To make the most of the data we have, we can take the union of all of the events above and call that the Renderer. Whenever Servo or Chromium is recording time in Renderer, they are busy with some phase of the rendering process for the page under test (or a generic task, like Compositing in Servo).

The results are as follows.

Renderer (synthetic)

servo.org

	2cpu	4cpu	6cpu	8cpu
servo.1	193.5ms	176.5ms	173.8ms	172.9ms
servo.2	115.4ms	111.1ms	107.1ms	106.9ms
servo.3	85.27ms	80.83ms	79.96ms	76.73ms
chromium	97.99ms	68.00ms	66.68ms	65.99ms

www.amazon.com

	2cpu	4cpu	6cpu	8cpu
servo.1	6.292s	5.322s	5.236s	4.151s
servo.2	6.413s	6.133s	4.665s	3.895s
servo.3	5.799s	5.607s	4.963s	3.783s
chromium	1.481s	1.035s	983.9ms	971.4ms

zh.wikipedia.org

	2cpu	4cpu	6cpu	8cpu
servo.1	334.7ms	306.4ms	296.1ms	294.4ms
servo.2	176.5ms	175.9ms	156.5ms	163.5ms
servo.3	202.7ms	183.6ms	165.5ms	214.5ms
chromium	347.5ms	267.2ms	265.8ms	262.3ms

www.baidu.com

	2cpu	4cpu	6cpu	8cpu
servo.1	279.2ms	251.4ms	252.6ms	236.7ms
servo.2	145.3ms	214.2ms	133.4ms	169.1ms
servo.3	141.9ms	153.4ms	153.5ms	167.8ms
chromium	139.9ms	245.2ms	97.19ms	232.6ms