---
title: "Analysis for Deluge Benchmarks - Static Network Dissemination Experiment"
output:
  bookdown::html_notebook2:
    number_sections: TRUE
    toc: TRUE
date: "2025-01-15"
---

This document contains the analysis for the Deluge benchmarks.

```{r message=FALSE}
library(tidyverse)

devtools::load_all()
```

# Parse/Load Data

This is data that's been pre-parsed from an experiment [log source](https://github.com/codex-storage/bittorrent-benchmarks/blob/1ee8ea8a35a2c0fccea6e7c955183c4ed03eebb3/benchmarks/logging/sources.py#L27).

```{r}
experiments <- read_all_experiments('./data/g1739826980')
```

```{r}
COUNT_DISTINCT = list(
  'codex_static_dissemination' = FALSE,
  'deluge_static_dissemination' = TRUE
)
```


Computes the benchmark statistics from raw download logs.

```{r}
benchmarks <- lapply(experiments, function(experiment) {
  print(glue::glue('Process {experiment$experiment_id}'))
  download_time_stats <- tryCatch({
    meta <- experiment$meta
    completion <- experiment |>
      download_times(
        piece_count_distinct = COUNT_DISTINCT[[meta$experiment_type]]) |>
      completion_time_stats(meta)
    
    if (is.null(completion)) {
      NULL
    } else {
      completion |> mutate(
        experiment_type = meta$experiment_type,
        network_size = meta$nodes$network_size,
        seeders = meta$seeders,
        leechers = network_size - meta$seeders,
        file_size = meta$file_size
      )
    }
  }, error = function(e) { print(e); NULL })
}) |> 
  drop_nulls() |>
  bind_rows() |>
  arrange(file_size, network_size, seeders, leechers) |>
  mutate(
    # This factor conversion is horrible but needed so things are sorted properly in the plot.
    file_size = factor(rlang::parse_bytes(as.character(file_size)),
                        levels = rlang::parse_bytes(as.character(
                          unique(file_size[order(file_size, decreasing = TRUE)])))),
    seeder_ratio = seeders/network_size
  ) |>
  relocate(file_size, network_size, seeders, leechers)
```

# Results

First, we present the raw data in tabular format:

```{r}
benchmarks
```

We then plot the median by network size, and facet it by seeder ratio and file size to see if looks sane:

```{r fig.width = 10, warning=FALSE, message=FALSE}
ggplot(benchmarks, aes(col = experiment_type, fill = experiment_type)) +
  geom_ribbon(aes(ymin = p25, ymax = p75, x = network_size),
              fill = scales::alpha('blue', 0.5), col = 'lightgray') +
  geom_point(aes(x = network_size, y = p25), col = 'darkgray', size=10.0, shape='-') +
  geom_point(aes(x = network_size, y = p75), col = 'darkgray', size=10.0, shape='-') +
  geom_line(aes(x = network_size, y = median)) +
  geom_point(aes(x = network_size, y = median)) +
  ylab('median download time (seconds)') +
  xlab('network size') +
  theme_minimal(base_size=15) +
  facet_grid(
    file_size ~ seeder_ratio,
    scales = 'free_y',
    labeller = labeller(
      file_size = as_labeller(function(x) x),
      seeder_ratio = as_labeller(function(x) {
        paste0("seeder ratio: ", scales::percent(as.numeric(x)))
      }))
  ) +
  scale_color_discrete(name = 'experiment type') +
  guides(fill = 'none') +
  ylim(c(0,NA))
```