* Page-pin packet memory for cuda
Bring back recyclers and pin offset buffers
* Add packet recycler to streamer
* Add set_pinnable to sigverify vecs to pin them
* Add packets reset test
* Add test for recycler and reduce the gc lock critical section
* Add comments/tests to cuda_runtime
* Add recycler to recv_blobs path.
* Add trace/names for debug and PacketsRecycler to bench-streamer
* Predict realloc and unpin beforehand.
* Add helper to reserve and pin
* Cap buffered packets length
* Call cuda wrapper functions
Use more chunks to avoid duplicate signature failures:
Duplicate signatures can occur because bank.clear_signatures()
can occur before the bank has actually committed the signatures
to the status cache and then error out on the next set of transactions.
* Use Rc to prevent clone of Packets
* Fix min => max in banking_stage threads.
Coalesce packet buffers better since a larger batch will
be faster through banking and sigverify.
Deconstruct batches into banking_stage from sigverify since
sigverify likes to accumulate batches but then a single banking_stage
thread will be stuck with a large batch. Maximize parallelism by
creating more chunks of work for banking_stage.
* Remove unused PohServiceConfig::Step
* Clarify variable name
* Poh::hash() now takes an iteration counter
* man -> max
* Inline functions with single call site
* Move PohServiceConfig into GenesisBlock
* Add plumbing to enable real PoH on testnets
* Batch hashes to improve PoH hash rate
* Ensure a constant hashes_per_tick
* Remove PohEntry mixin field
* Poh/PohEntry no longer maintains tick_height
* Ensure a constant hashes_per_tick
* ci/localnet-sanity.sh: Use real PoH
* Rework Poh/PohService to keep PohRecorder unlocked as much as possible while hashing
* Move append_vec bench to the crate with append_vec
* Use black_box to tell the compiler not to optimize away test data
```
pub fn black_box<T>(dummy: T) -> T {
unsafe {
let ret = std::ptr::read_volatile(&dummy);
std::mem::forget(dummy);
ret
}
}
```
* Revert "Use black_box to tell the compiler not to optimize away test data"
This reverts commit 5610b8ee957f1d8bf6e270e392859e8b23b1e472.
* Use black_box to tell the compiler not to optimize away test data
* Create bench directories
* move core tests to core
* remove window
* fix up flaky tests
* test_entryfication needs a singly-threaded banking_stage
* move core benches to core
* remove unnecessary dependencies
* remove core as a member for now, test it like runtime
* stop running tests twice
* remove duplicate runs of tests in perf
* Mostly implement key-value store and add integration points
Essential key-value store functionality is implemented, needs more work to be integrated, tested, and activated.
Behind the `kvstore` feature.
sakridge
carllin
TristanDebrunner
Michael Vines
Pankaj Garg
Rob Walker
sakridge
Sagar Dhawan
Greg Fitzgerald
Mark