Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Uses fold+reduce for handling duplicate pubkeys during index generation #34011

Merged
merged 2 commits into from
Nov 10, 2023
Merged

Uses fold+reduce for handling duplicate pubkeys during index generation #34011

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c0bf775
Uses fold+reduce for handling duplicate pubkeys during index generation
brooksprumo Nov 9, 2023
7512e9a
adds DuplicatePubkeysVisitedInfo
brooksprumo Nov 9, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
95 changes: 64 additions & 31 deletions accounts-db/src/accounts_db.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9397,51 +9397,84 @@ impl AccountsDb {
..GenerateIndexTimings::default()
};

// subtract data.len() from accounts_data_len for all old accounts that are in the index twice
let mut accounts_data_len_dedup_timer =
Measure::start("handle accounts data len duplicates");
let uncleaned_roots = Mutex::new(IntSet::default());
if pass == 0 {
let accounts_data_len_from_duplicates = unique_pubkeys_by_bin
#[derive(Debug, Default)]
struct DuplicatePubkeysVisitedInfo {
accounts_data_len_from_duplicates: u64,
uncleaned_roots: IntSet<Slot>,
}
impl DuplicatePubkeysVisitedInfo {
fn reduce(mut a: Self, mut b: Self) -> Self {
if a.uncleaned_roots.len() >= b.uncleaned_roots.len() {
a.merge(b);
a
} else {
b.merge(a);
b
}
}
fn merge(&mut self, other: Self) {
self.accounts_data_len_from_duplicates +=
other.accounts_data_len_from_duplicates;
self.uncleaned_roots.extend(other.uncleaned_roots);
}
}

// subtract data.len() from accounts_data_len for all old accounts that are in the index twice
let mut accounts_data_len_dedup_timer =
Measure::start("handle accounts data len duplicates");
let DuplicatePubkeysVisitedInfo {
accounts_data_len_from_duplicates,
uncleaned_roots,
} = unique_pubkeys_by_bin
.par_iter()
.map(|unique_keys| {
unique_keys
.par_chunks(4096)
.map(|pubkeys| {
let (count, uncleaned_roots_this_group) = self
.visit_duplicate_pubkeys_during_startup(
pubkeys,
&rent_collector,
&timings,
);
let mut uncleaned_roots = uncleaned_roots.lock().unwrap();
uncleaned_roots_this_group.into_iter().for_each(|slot| {
uncleaned_roots.insert(slot);
});
count
})
.sum::<u64>()
})
.sum();
.fold(
DuplicatePubkeysVisitedInfo::default,
|accum, pubkeys_by_bin| {
let intermediate = pubkeys_by_bin
.par_chunks(4096)
.fold(DuplicatePubkeysVisitedInfo::default, |accum, pubkeys| {
let (accounts_data_len_from_duplicates, uncleaned_roots) = self
.visit_duplicate_pubkeys_during_startup(
pubkeys,
&rent_collector,
&timings,
);
let intermediate = DuplicatePubkeysVisitedInfo {
accounts_data_len_from_duplicates,
uncleaned_roots,
};
DuplicatePubkeysVisitedInfo::reduce(accum, intermediate)
})
.reduce(
DuplicatePubkeysVisitedInfo::default,
DuplicatePubkeysVisitedInfo::reduce,
);
DuplicatePubkeysVisitedInfo::reduce(accum, intermediate)
},
)
.reduce(
DuplicatePubkeysVisitedInfo::default,
DuplicatePubkeysVisitedInfo::reduce,
);
accounts_data_len_dedup_timer.stop();
timings.accounts_data_len_dedup_time_us = accounts_data_len_dedup_timer.as_us();
timings.slots_to_clean = uncleaned_roots.len() as u64;

self.accounts_index
.add_uncleaned_roots(uncleaned_roots.into_iter());
Comment on lines +9460 to +9465
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Following from https://github.com/solana-labs/solana/pull/34011/files#r1389679091, those lines were moved here.

accounts_data_len.fetch_sub(accounts_data_len_from_duplicates, Ordering::Relaxed);
info!(
"accounts data len: {}",
accounts_data_len.load(Ordering::Relaxed)
);
}
accounts_data_len_dedup_timer.stop();
timings.accounts_data_len_dedup_time_us = accounts_data_len_dedup_timer.as_us();

let uncleaned_roots = uncleaned_roots.into_inner().unwrap();
timings.slots_to_clean = uncleaned_roots.len() as u64;

if pass == 0 {
// Need to add these last, otherwise older updates will be cleaned
for root in &slots {
self.accounts_index.add_root(*root);
}
self.accounts_index
.add_uncleaned_roots(uncleaned_roots.into_iter());
Comment on lines -9443 to -9444
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This was moved up into the block that makes uncleaned_roots. Same for the other "removed" lines just above here.


self.set_storage_count_and_alive_bytes(storage_info, &mut timings);
}
Expand Down