Age | Commit message (Collapse) | Author |
|
|
|
It can successfully parse SpeedMessage1.
Preliminary results: 750MB/s on Core2 2.4GHz.
This number is 2.5x proto2.
This isn't apples-to-apples, because
proto2 is parsing to a struct and we are
just doing stream parsing, but for apps
that are currently using proto2, this is the
improvement they would see if they could
move to stream-based processing.
Unfortunately perf-regression-test.py is
broken, and I'm not 100% sure why. It would
be nice to fix it first (to ensure that
there are no performance regressions for
the table-based decoder) but I'm really
impatient to get the JIT checked in.
|
|
This doesn't reflect any material change in
how I will be working on upb, and I have no
problem making this change. It's still open
source under the BSD license, and I'll still
be working on it well beyond the hours that
constitute a normal job.
|
|
This is a significant change to the upb_stream
protocol, and should hopefully be the last
significant change.
All callbacks are now registered ahead-of-time
instead of having delegated callbacks registered
at runtime, which makes it much easier to
aggressively optimize ahead-of-time (like with a
JIT).
Other impacts of this change:
- You no longer need to have loaded descriptor.proto
as a upb_def to load other descriptors! This means
the special-case code we used for bootstrapping is
no longer necessary, and we no longer need to link
the descriptor for descriptor.proto into upb.
- A client can now register any upb_value as what
will be delivered to their value callback, not
just a upb_fielddef*. This should allow for other
clients to get more bang out of the streaming
decoder.
This change unfortunately causes a bit of a performance
regression -- I think largely due to highly
suboptimal code that GCC generates when structs
are returned by value. See:
http://blog.reverberate.org/2011/03/19/when-a-compilers-slow-code-actually-bites-you/
On the other hand, once we have a JIT this should
no longer matter.
Performance numbers:
plain.parsestream_googlemessage1.upb_table: 374 -> 396 (5.88)
plain.parsestream_googlemessage2.upb_table: 616 -> 449 (-27.11)
plain.parsetostruct_googlemessage1.upb_table_byref: 268 -> 269 (0.37)
plain.parsetostruct_googlemessage1.upb_table_byval: 215 -> 204 (-5.12)
plain.parsetostruct_googlemessage2.upb_table_byref: 307 -> 281 (-8.47)
plain.parsetostruct_googlemessage2.upb_table_byval: 297 -> 272 (-8.42)
omitfp.parsestream_googlemessage1.upb_table: 423 -> 410 (-3.07)
omitfp.parsestream_googlemessage2.upb_table: 679 -> 483 (-28.87)
omitfp.parsetostruct_googlemessage1.upb_table_byref: 287 -> 282 (-1.74)
omitfp.parsetostruct_googlemessage1.upb_table_byval: 226 -> 219 (-3.10)
omitfp.parsetostruct_googlemessage2.upb_table_byref: 315 -> 298 (-5.40)
omitfp.parsetostruct_googlemessage2.upb_table_byval: 297 -> 287 (-3.37)
|
|
|
|
|
|
It is slower than the C decoder for now because it
falls off the fast path too often. But it can
successfully decode varints, fixed32 and fixed64.
|
|
upb_inttable() now supports a "compact" operation that will
decide on an array size and put all entries with small enough
keys into the array part for faster lookup.
Also exposed the upb_itof_ent structure and put a few useful
values there, so they are one fewer pointer chase away.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
One simplification to come.
|
|
"make descriptorgen" is now valgrind-clean again.
|
|
There is currently a memory leak when type definitions
form cycles. This will need to be dealt with.
|
|
|
|
This is in anticipation of making upb_msgdef's easy
to dup. This involved removing all traces of any
descriptors from the defs.
|
|
This should make it both easier to use and easier to
optimize, in exchange for a small amount of generality.
In practice, any remotely normal case is still very
natural.
|
|
|
|
Also delay deletion of subfields until the entire message is
deleted.
|
|
|
|
|
|
The cost is that a upb_msg will now always have an overhead
of 2*sizeof(void*). This is comparable to proto2 overhead.
The benefit is that upb_msg is now self-describing, and
read-only algorithms can now operate on a upb_msg regardless
of the memory-management scheme.
Also, upb_array and upb_string now know inherently if they
own their associated memory, and upb_array has a generic
pointer for memory management purposes like upb_msg does.
|
|
There is significant refactoring here, as well as some more trivial
name changes. upb_msg has become upb_msgdef, to reflect the fact
that a upb_msg is not *itself* a message, it describes a message.
There are other renamings, such as upb_parse_state -> upb_stream_parser.
More significantly, the upb_msg class and parser have been refactored
to reflect my recent realization about how memory management should
work. upb_msg now has no memory management, and a memory mangement
scheme (that works beautifully with multiple language runtimes) will
be layered on top of it.
This iteration has the new, read-only upb_msg. upb_mm_msg (a
memory-managed message class) will come in the next change.
|
|
|
|
was a lot of work.
|
|
|
|
|
|
|
|
|