In several places in gossip code, the entire crds table is scanned only
to filter out nodes' contact infos. Currently on mainnet, crds table is
of size ~70k, while there are only ~470 nodes. So the full table scan is
inefficient. Instead we may maintain an index of only nodes' contact
infos.
Based on run-time profiles, the majority time of new_pull_requests is
spent building bloom filters, in hashing and bit-vec ops.
This commit builds crds filters in parallel using rayon constructs. The
added benchmark shows ~5x speedup (4-core machine, 8 threads).
* Save/restore Tower
* Avoid unwrap()
* Rebase cleanups
* Forcibly pass test
* Correct reconcilation of votes after validator resume
* d b g
* Add more tests
* fsync and fix test
* Add test
* Fix fmt
* Debug
* Fix tests...
* save
* Clarify error message and code cleaning around it
* Move most of code out of tower save hot codepath
* Proper comment for the lack of fsync on tower
* Clean up
* Clean up
* Simpler type alias
* Manage tower-restored ancestor slots without banks
* Add comment
* Extract long code blocks...
* Add comment
* Simplify returned tuple...
* Tweak too aggresive log
* Fix typo...
* Add test
* Update comment
* Improve test to require non-empty stray restored slots
* Measure tower save and dump all tower contents
* Log adjust and add threshold related assertions
* cleanup adjust
* Properly lower stray restored slots priority...
* Rust fmt
* Fix test....
* Clarify comments a bit and add TowerError::TooNew
* Further clean-up arround TowerError
* Truly create ancestors by excluding last vote slot
* Add comment for stray_restored_slots
* Add comment for stray_restored_slots
* Use BTreeSet
* Consider root_slot into post-replay adjustment
* Tweak logging
* Add test for stray_restored_ancestors
* Reorder some code
* Better names for unit tests
* Add frozen_abi to SavedTower
* Fold long lines
* Tweak stray ancestors and too old slot history
* Re-adjust error conditon of too old slot history
* Test normal ancestors is checked before stray ones
* Fix conflict, update tests, adjust behavior a bit
* Fix test
* Address review comments
* Last touch!
* Immediately after creating cleaning pr
* Revert stray slots
* Revert comment...
* Report error as metrics
* Revert not to panic! and ignore unfixable test...
* Normalize lockouts.root_slot more strictly
* Add comments for panic! and more assertions
* Proper initialize root without vote account
* Clarify code and comments based on review feedback
* Fix rebase
* Further simplify based on assured tower root
* Reorder code for more readability
Co-authored-by: Michael Vines <mvines@gmail.com>
filter_crds_values checks every crds filter against every hash value:
https://github.com/solana-labs/solana/blob/ee646aa7/core/src/crds_gossip_pull.rs#L432
which can be inefficient if the filter's bit-mask only matches small
portion of the entire crds table.
This commit shards crds values into separate tables based on shard_bits
first bits of their hash prefix. Given a (mask, mask_bits) filter,
filtering crds can be done by inspecting only relevant shards.
If CrdsFilter.mask_bits <= shard_bits, then precisely only the crds
values which match (mask, mask_bits) bit pattern are traversed.
If CrdsFilter.mask_bits > shard_bits, then approximately only
1/2^shard_bits of crds values are inspected.
Benchmarking on a gce cluster of 20 nodes, I see ~10% improvement in
generate_pull_responses metric, but with larger clusters, crds table and
2^mask_bits are both larger, so the impact should be more significant.
* Make Message::new_with_payer the default constructor
* Remove Transaction::new_[un]signed_instructions
These guess the fee-payer instead of stating it explicitly
* Pass blocktree into execute_batch, if persist_transaction_status
* Add validator arg to enable persistent transaction status store
* Pass blocktree into banking_stage, if persist_transaction_status
* Add validator params to bash scripts
* Expose actual transaction statuses outside Bank; add tests
* Fix benches
* Offload transaction status writes to a separate thread
* Enable persistent transaction status along with rpc service
* nudge
* Review comments
* credit_only_credits_forwarding
* whack transfer_now()
* fixup
* bench should retry the airdrop TX
* fixup
* try to make bench-exchange a bit more robust, informative
* Stabilize some banking stage tests
Fixes#5660
* Fix CI...
* clean up
* Fix ci
* Address review nits
* Use bank.max_tick_height due to off-by-one for no PohRecord's clearing bank
* Fix CI...
* Use bank.max_tick_height() instead for clarity
* Refactor blocktree processor args and support full leader cache
* Add entry callback option
* Rename num_threads to override_num_threads
* Add test for entry callback
* Refactor cached leader schedule changes
* Add tests for blocktree process options
* Refactor test
* @mvines feedback
Summary of Changes:
This change adds functionality to randomize tx execution for every entry. It does this by implementing OrderedIterator that iterates tx slice as per the order specified. The order is generated randomly for every entry.
* Insert data shreds in blocktree and database
* Integrate data shreds with rest of the code base
* address review comments, and some clippy fixes
* Fixes to some tests
* more test fixes
* ignore some local cluster tests
* ignore replicator local cluster tests
* 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.