<p><span class="h-card" translate="no"><a href="https://mastodon.social/@wingo" class="u-url mention">@<span>wingo</span></a></span> <span class="h-card" translate="no"><a href="https://mastodon.social/@sayrer" class="u-url mention">@<span>sayrer</span></a></span> I think appendix p36 suggests that 6x there for vlarge in h2 is about 4GB heap. Meanwhile this random zgc presentation which shows latency improvement (<a href="https://cr.openjdk.org/~pliden/slides/ZGC-Jfokus-2018.pdf" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">cr.openjdk.org/~pliden/slides/</span><span class="invisible">ZGC-Jfokus-2018.pdf</span></a>) uses 128GB heaps. So they're just talking past each other entirely.</p>
