era: speed up index reading (#6305)

This commit is contained in:
Jacek Sieka 2024-05-22 10:21:04 +02:00 committed by GitHub
parent 708b23f084
commit e0f8ea752b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 16 deletions

View File

@ -92,41 +92,43 @@ proc appendRecord(f: IoHandle, index: Index): Result[int64, string] =
f.appendIndex(index.startSlot, index.offsets) f.appendIndex(index.startSlot, index.offsets)
proc readIndex*(f: IoHandle): Result[Index, string] = proc readIndex*(f: IoHandle): Result[Index, string] =
var
buf: seq[byte]
pos: int
let let
startPos = ? f.getFilePos().mapErr(toString) startPos = ? f.getFilePos().mapErr(toString)
fileSize = ? f.getFileSize().mapErr(toString) fileSize = ? f.getFileSize().mapErr(toString)
header = ? f.readHeader() header = ? f.readRecord(buf)
if header.typ != E2Index: return err("not an index") if header.typ != E2Index: return err("not an index")
if header.len < 16: return err("index entry too small") if buf.len < 16: return err("index entry too small")
if header.len mod 8 != 0: return err("index length invalid") if buf.len mod 8 != 0: return err("index length invalid")
var buf: array[8, byte]
? f.readFileExact(buf)
let let
slot = uint64.fromBytesLE(buf) slot = uint64.fromBytesLE(buf.toOpenArray(pos, pos + 7))
count = header.len div 8 - 2 count = buf.len div 8 - 2
pos += 8
# technically not an error, but we'll throw this sanity check in here..
if slot > int32.high().uint64: return err("fishy slot")
var offsets = newSeqUninitialized[int64](count) var offsets = newSeqUninitialized[int64](count)
for i in 0..<count: for i in 0..<count:
? f.readFileExact(buf)
let let
offset = uint64.fromBytesLE(buf) offset = uint64.fromBytesLE(buf.toOpenArray(pos, pos + 7))
absolute = absolute =
if offset == 0: 0'i64 if offset == 0: 0'i64
else: else:
# Wrapping math is actually convenient here # Wrapping math is actually convenient here
cast[int64](cast[uint64](startPos) + offset) cast[int64](cast[uint64](startPos) + offset)
if absolute < 0 or absolute > fileSize: return err("Invalid offset") if absolute < 0 or absolute > fileSize: return err("invalid offset")
offsets[i] = absolute offsets[i] = absolute
pos += 8
? f.readFileExact(buf) if uint64(count) != uint64.fromBytesLE(buf.toOpenArray(pos, pos + 7)):
if uint64(count) != uint64.fromBytesLE(buf): return err("invalid count") return err("invalid count")
# technically not an error, but we'll throw this sanity check in here..
if slot > int32.high().uint64: return err("fishy slot")
ok(Index(startSlot: Slot(slot), offsets: offsets)) ok(Index(startSlot: Slot(slot), offsets: offsets))