When this option is enabled, the layout task will print an error when
display list items draw outside their owning Flow's position rect. This
will make it easier to detect layout errors before they break rendering.
This is a command-line option for the moment, because we violate this
rule quite a bit still. Once all bugs causing this are fixed, we can be
more aggressive about enabling the option.
This is quite a bit cleaner than abusing the rust debug functionality.
If we start collecting too many debugging options in the servo
executable we could opt to organize them into a single option.
Fixes#2263.
This is a grab bag of performance improvements that significantly improve style recalculation, layout, and painting on a few static pages.
Let me know if you'd like me to split this PR up.
r? @glennw
This is quite a bit cleaner than abusing the rust debug functionality.
If we start collecting too many debugging options in the servo
executable we could opt to organize them into a single option.
Fixes#2263.
When this option is enabled, the layout task will print an error when
display list items draw outside their owning Flow's position rect. This
will make it easier to detect layout errors before they break rendering.
This is a command-line option for the moment, because we violate this
rule quite a bit still. Once all bugs causing this are fixed, we can be
more aggressive about enabling the option.
construction to avoid cloning and moving flows so much.
Besides amounting to a 5%-10% win on a page with a lot of text, this
simplifies and refactors the text layout code.
The flow tree is currently dumped for debugging purposes early on in
the flow process, so many values are still zero. If we wait to dump it
until later, the output will more accurately reflect the real flow tree.
The flow tree is currently dumped for debugging purposes early on in
the flow process, so many values are still zero. If we wait to dump it
until later, the output will more accurately reflect the real flow tree.
This also adds some extra debugging infrastructure which I found useful tracking
this bug down. A regression in the br reftests is also uncovered by this patch,
which I'll work on fixing next.
EDIT: nevermind. no regression, I just tested that before a rebase.
r? @pcwalton
This also adds some extra debugging infrastructure which I found useful tracking
this bug down. A regression in the br reftests is also uncovered by this patch,
which I'll work on fixing next.
r? @pcwalton
Seems to be a 38% layout win on a site I tested with a lot of text.
Other browser engines typically do not duplicate the information in the font style struct. `FontStyle` actually predates @SimonSapin's CSS selector matching library. It's time to get rid of it!
r? @glennw
r? @Ms2ger, @jdm
The parser is now a JS-managed object and we use hooks in html5ever to trace its internal state. This should be memory-safe even if arbitrary JavaScript can run during a parse. Please let me know if you think of a reason it wouldn't be!
I think the likely outcome of a garbage collection during parsing is a dynamic `RefCell` borrow failure, but I'm going to look into that after this lands. It should be safe to trace the parser while it's mutably borrowed, as long as it's not shared between threads, so we can probably switch to `UnsafeCell`.
