overleaf/services/clsi/app/js/ContentCacheMetrics.js
Jakob Ackermann b456ea726d [misc] merge pdf caching into main (#226)
* wip generate directory for hash content

* cleanup, remove console logging

* add content caching module

* Return PDF stream ranges with compile response

* Return the PDF file size in the compile response

* PDF range endpoint

* [misc] WIP: pdf caching: preserve the m-time on static content files

* [misc] WIP: pdf caching: improve browser caching, emit caching headers

* [misc] WIP: pdf caching: do not emit very small chunks <1kB

* [misc] keep up with moving output files into a separate directory

* [OutputCacheManager] add global feature flag for enabling pdf caching

* [misc] add contentId into the URL for protecting PDF stream contents

* [misc] support PDF stream caching for anonymous users

* [misc] add per-request feature flag for enabling PDF stream caching

* [misc] enable pdf caching in CI and emit metrics at the end of run

* [misc] expose compile stats and timings to the frontend

* [misc] log an error in case saving output files fails

* [misc] add metrics for pdf bandwidth and pdf caching performance

* [misc] add a dark mode to the pdf caching for computing ranges only

* [misc] move pdf caching metrics into ContentCacheMetrics

* [misc] add a config option for the min chunk size of pdf ranges

Co-authored-by: Brian Gough <brian.gough@overleaf.com>
Co-authored-by: Eric Mc Sween <eric.mcsween@overleaf.com>
2021-05-13 14:07:54 +01:00

80 lines
2.5 KiB
JavaScript

const Metrics = require('./Metrics')
const ONE_MB = 1024 * 1024
function emitPdfStats(stats, timings) {
if (timings['compute-pdf-caching']) {
emitPdfCachingStats(stats, timings)
} else {
// How much bandwidth will the pdf incur when downloaded in full?
Metrics.summary('pdf-bandwidth', stats['pdf-size'])
}
}
function emitPdfCachingStats(stats, timings) {
if (!stats['pdf-size']) return // double check
// How large is the overhead of hashing up-front?
const fraction =
timings.compileE2E - timings['compute-pdf-caching'] !== 0
? timings.compileE2E /
(timings.compileE2E - timings['compute-pdf-caching'])
: 1
Metrics.summary('overhead-compute-pdf-ranges', fraction * 100 - 100)
// How does the hashing scale to pdf size in MB?
Metrics.timing(
'compute-pdf-caching-relative-to-pdf-size',
timings['compute-pdf-caching'] / (stats['pdf-size'] / ONE_MB)
)
if (stats['pdf-caching-total-ranges-size']) {
// How does the hashing scale to total ranges size in MB?
Metrics.timing(
'compute-pdf-caching-relative-to-total-ranges-size',
timings['compute-pdf-caching'] /
(stats['pdf-caching-total-ranges-size'] / ONE_MB)
)
// How fast is the hashing per range on average?
Metrics.timing(
'compute-pdf-caching-relative-to-ranges-count',
timings['compute-pdf-caching'] / stats['pdf-caching-n-ranges']
)
// How many ranges are new?
Metrics.summary(
'new-pdf-ranges-relative-to-total-ranges',
(stats['pdf-caching-n-new-ranges'] / stats['pdf-caching-n-ranges']) * 100
)
}
// How much content is cacheable?
Metrics.summary(
'cacheable-ranges-to-pdf-size',
(stats['pdf-caching-total-ranges-size'] / stats['pdf-size']) * 100
)
const sizeWhenDownloadedInFull =
// All of the pdf
stats['pdf-size'] -
// These ranges are potentially cached.
stats['pdf-caching-total-ranges-size'] +
// These ranges are not cached.
stats['pdf-caching-new-ranges-size']
// How much bandwidth can we save when downloading the pdf in full?
Metrics.summary(
'pdf-bandwidth-savings',
100 - (sizeWhenDownloadedInFull / stats['pdf-size']) * 100
)
// How much bandwidth will the pdf incur when downloaded in full?
Metrics.summary('pdf-bandwidth', sizeWhenDownloadedInFull)
// How much space do the ranges use?
// This will accumulate the ranges size over time, skipping already written ranges.
Metrics.summary('pdf-ranges-disk-size', stats['pdf-caching-new-ranges-size'])
}
module.exports = {
emitPdfStats
}