We've recently marked the ngtsc test as flaky for the Windows
job. We should not attempt running tests 3 times locally. This
negatively impacts the debugging/developer workflow.
Instead, flaky test attempts can still be made on CI. Using the
default attempt count of 3.
PR Close#50852
Currently when `yarn benchmarks run-compare` is used, the local
repository could be converted to a shallow clone. This is not
a problem but might result in confusion. We avoid this by
not performing a shallow fetch when a comparison is initiated.
The performance gains seem neglegible.
PR Close#50851
This PR fixes GC memory numbers reported by benchpress,
where previously reported amount was always 0.
This is due to the fact that Chrome browser reports GC
events as a single X event now, instead of a B / E pair
of events.
PR Close#50760
Prior to this commit, the renderer destroy method was being called before the animation complete. This is problematic when using `REMOVE_STYLES_ON_COMPONENT_DESTROY` as it causes the styles to be removed too early.
This commit, updates this destroy logic to be call the render destroy once the animations complete.
This has been reported internally in:
- http://b/271251353#comment12
- http://b/282004950#comment5
PR Close#50677
We already collect and report benchmark results for comparison runs, but
for normal benchmark runs we should do the same to make the results
more discoverable (and not in the middle of Bazel output).
PR Close#50816
Exposes the function used to transform an input on `ComponentFactory.inputs` and `ComponentMirror.inputs`. We'll need this to support input transforms in `elements`.
PR Close#50713
The previous API design for the runtime deps tracker was done with only local compilation in mind. Now if we want to use it for JIT as well then some new requirements come along which are addressed by this commit as follows:
- JIT scopes need distinct sets for directive and pipes. Thus the ScopeData interface is modified to include these info.
- JIT needs access to scopes for various operations. So methods `getNgModuleScope` and `getStandaloneComponentScope` are added to the tracker's public api.
- Test bed needs to clear the scope cache for its override mechanism. So method `clearScopeCacheFor` is added to the tracker's public api for this reason.
PR Close#50606
The types and interfaces re;ated to the runtime deps tracker are added. Also an empty implementation is added to be completed in follow up PRs (after the interfaces are confirmed in this PR).
The added files are not used anywhere, so the change should not affect anything in anyway.
PR Close#50606
The existing microbenchmarks are not widely known
and are not used to drive design / coding decissions.
At the same time those test add to the maintanance cost:
- use hand-written instructions;
- plug into runtime internals and are fragile;
- require development of mocks for the runtime internals.
Those tests are removed since they are costly to maintain
and, at the same, don't provide enough value.
PR Close#50786
An internal compiler option named `supportTestBed` is now available for use by the
Angular CLI. This option currently controls the extraction and emit of Angular class
metadata. This emitted information is only needed in AOT mode when using certain
TestBed APIs. However, AOT mode is currently not available for unit testing within
the Angular CLI. As a result, the metadata is not used within CLI generation applications
and in particular production applications. Without this option, the CLI needs to
manually perform a code transform to remove the metadata and also replicate TypeScript's
import eliding. This is can be a complicated operation and must be continually kept
up to date with any changes to both the Angular compiler and TypeScript. The introduction
of this new option alleviates these concerns.
PR Close#50604
Pawel and myself have investigated benchpress for quite some
time now, and I believe we have the most up-to-date understanding
in the team- so it would make sense to add us to the owners.
PR Close#50769
Paul Gschwendtner