For all code paths (gossip push, pull, purge, etc) that remove or
override a crds value, it is necessary to record hash of values purged
from crds table, in order to exclude them from subsequent pull-requests;
otherwise the next pull request will likely return outdated values,
wasting bandwidth:
https://github.com/solana-labs/solana/blob/ed51cde37/core/src/crds_gossip_pull.rs#L486-L491
Currently this is done all over the place in multiple modules, and this
has caused bugs in the past where purged values were not recorded.
This commit encapsulated this bookkeeping into crds module, so that any
code path which removes or overrides a crds value, also records the hash
of purged value in-place.
It is crucial that VersionedCrdsValue::insert_timestamp does not go
backward in time:
https://github.com/solana-labs/solana/blob/ec37a843a/core/src/crds.rs#L67-L79
Otherwise methods such as get_votes and get_epoch_slots_since will
break, which will break their downstream flow, including vote-listener
and optimistic confirmation:
https://github.com/solana-labs/solana/blob/ec37a843a/core/src/cluster_info.rs#L1197-L1215https://github.com/solana-labs/solana/blob/ec37a843a/core/src/cluster_info.rs#L1274-L1298
For that, Crds::new_versioned is intended to be called "atomically" with
Crds::insert_verioned (as the comment already says so):
https://github.com/solana-labs/solana/blob/ec37a843a/core/src/crds.rs#L126-L129
However, currently this is violated in the code. For example,
filter_pull_responses creates VersionedCrdsValues (with the current
timestamp), then acquires an exclusive lock on gossip, then
process_pull_responses writes those values to the crds table:
https://github.com/solana-labs/solana/blob/ec37a843a/core/src/cluster_info.rs#L2375-L2392
Depending on the workload and lock contention, the insert_timestamps may
well be in the past when these values finally are inserted into gossip.
To avoid such scenarios, this commit:
* removes Crds::new_versioned and Crd::insert_versioned.
* makes VersionedCrdsValue constructor private, only invoked in
Crds::insert, so that insert_timestamp is populated right before
insert.
This will improve insert_timestamp monotonicity as long as Crds::insert
is not called with a stalled timestamp. Following commits may further
improve this by calling timestamp() inside Crds::insert, and/or
switching to std::time::Instant which guarantees monotonicity.
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.