From 01466be7b9769bca7d209c60eb92a4dee9a738b9 Mon Sep 17 00:00:00 2001
From: "Raphael S. Carvalho" <raphaelsc@scylladb.com>
Date: Wed, 5 Apr 2023 16:31:09 -0300
Subject: [PATCH] sstables: Store raw token into summary entries

Scylla stores a dht::token into each summary entry, for convenience.

But that costs us 16 bytes for each summary entry. That's because
dht::token has a kind field in addition to data, both 64 bits.

With 1kk partitions, each averaging 4k bytes, summary may end up
with ~90k summary entries. So dht::token only will add ~1.5M to the
memory footprint of summary.

We know summary samples index keys, therefore all tokens in all
summary entries cannot have any token kind other than 'key'.
Therefore, we can save 8 bytes for each summary entry by storing
a 64-bit raw token and converting it back into token whenever
needed.

Memory footprint of summary entries in a summary goes from
	sizeof(summary_entry) * entries.size(): 1771520
to
	sizeof(summary_entry) * entries.size(): 1417216

which is explained by the 8 bytes reduction per summary entry.

Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
---
 sstables/sstables.cc    |  4 ++--
 sstables/types.hh       | 14 ++++++++++++--
 tools/scylla-sstable.cc |  2 +-
 3 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/sstables/sstables.cc b/sstables/sstables.cc
index e14cfef07e..6dbdf8e2b0 100644
--- a/sstables/sstables.cc
+++ b/sstables/sstables.cc
@@ -554,7 +554,7 @@ future<> parse(const schema& schema, sstable_version_types v, random_access_read
         // position is little-endian encoded
         auto position = seastar::read_le<uint64_t>(buf.get());
         auto token = schema.get_partitioner().get_token(key_view(key_data));
-        s.entries.push_back({ token, key_data, position });
+        s.entries.push_back(summary_entry{ token, key_data, position });
     }
     // Delete last element which isn't part of the on-disk format.
     s.positions.pop_back();
@@ -1689,7 +1689,7 @@ void maybe_add_summary_entry(summary& s, const dht::token& token, bytes_view key
         auto entry_size = 8 + 2 + key.size();  // offset + key_size.size + key.size
         state.next_data_offset_to_write_summary += state.summary_byte_cost * entry_size;
         auto key_data = s.add_summary_data(key);
-        s.entries.push_back({ token, key_data, index_offset });
+        s.entries.push_back(summary_entry{ token, key_data, index_offset });
     }
 }
 
diff --git a/sstables/types.hh b/sstables/types.hh
index f35f56e16c..92e285f9ee 100644
--- a/sstables/types.hh
+++ b/sstables/types.hh
@@ -126,16 +126,26 @@ inline std::ostream& operator<<(std::ostream& o, indexable_element e) {
 
 class summary_entry {
 public:
-    dht::token token;
+    int64_t raw_token;
     bytes_view key;
     uint64_t position;
 
+    explicit summary_entry(dht::token token, bytes_view key, uint64_t position)
+            : raw_token(dht::token::to_int64(token))
+            , key(key)
+            , position(position) {
+    }
+
     key_view get_key() const {
         return key_view{key};
     }
 
+    dht::token get_token() const {
+        return dht::token::from_int64(raw_token);
+    }
+
     decorated_key_view get_decorated_key() const {
-        return decorated_key_view(token, get_key());
+        return decorated_key_view(get_token(), get_key());
     }
 
     bool operator==(const summary_entry& x) const {
diff --git a/tools/scylla-sstable.cc b/tools/scylla-sstable.cc
index a47640b97e..e51cfc6b0d 100644
--- a/tools/scylla-sstable.cc
+++ b/tools/scylla-sstable.cc
@@ -980,7 +980,7 @@ void dump_summary_operation(schema_ptr schema, reader_permit permit, const std::
 
             auto pkey = e.get_key().to_partition_key(*schema);
             writer.Key("key");
-            writer.DataKey(*schema, pkey, e.token);
+            writer.DataKey(*schema, pkey, e.get_token());
             writer.Key("position");
             writer.Uint64(e.position);