mirror of
https://github.com/apple/swift-nio-http2
synced 2026-11-22 04:30:43 +00:00
Motivation: The OutboundFlowControlBuffer is responsible for managing DATA and HEADERS frames for all streams in order to ensure that we obey HTTP/2 flow control rules, even when users don't. This object is therefore on the data path for the vast majority of frames, and is extremely performance sensitive. Unfortunately, the current algorithm has some nasty performance cliffs. Right now it has the awkward property of making flushes take an amount of time linear in the number of streams on the connection, not the number of streams that had had frames sent on them. The result is that connections with highly parallel numbers of streams see extremely poor performance when flushing, a problem that is exacerbated if other parts of the HTTP/2 stack fail to coalesce those flushes. We can clean this up in a few ways, but the easiest way is to just keep track of which streams have done I/O since the last flush. While we're there, we can make a few other optimisations to ensure we only flush data on streams we are actually processing, to further reduce the risk of wasting our time processing unnecessary work. Modifications: - Add a Set to keep track of where we've done writes since the last flush. - Streams whose flow control window goes to zero stop being writable. - Cheaper and more accurate calculation of zero-length writes, which avoids the possibility of awkward stalls with zero-length DATA frames and END_STREAM. - Stop doing math about the number of flushed bytes, we don't use that information any more. Results: An approximately 10% performance gain on the 100 concurrent streams server-only benchmark. The relative performance gain shifts with the number of active streams, but it should be positive in all cases.
58 lines
1.8 KiB
Bash
Executable File
58 lines
1.8 KiB
Bash
Executable File
#!/bin/bash
|
|
##===----------------------------------------------------------------------===##
|
|
##
|
|
## This source file is part of the SwiftNIO open source project
|
|
##
|
|
## Copyright (c) 2020 Apple Inc. and the SwiftNIO project authors
|
|
## Licensed under Apache License v2.0
|
|
##
|
|
## See LICENSE.txt for license information
|
|
## See CONTRIBUTORS.txt for the list of SwiftNIO project authors
|
|
##
|
|
## SPDX-License-Identifier: Apache-2.0
|
|
##
|
|
##===----------------------------------------------------------------------===##
|
|
|
|
set +ex
|
|
|
|
# Benchmarks known to behave well under cachegrind.
|
|
# When adding new benchmarks, consider adding them to this list.
|
|
CACHEGRIND_BENCHES=( server_only_10k_requests_100_concurrent server_only_10k_requests_1_concurrent )
|
|
|
|
function run_bench {
|
|
BRANCH="$1"
|
|
|
|
echo "Running against $BRANCH"
|
|
git checkout "$BRANCH"
|
|
swift build -c release -Xswiftc -g -Xswiftc -DCACHEGRIND > /dev/null
|
|
|
|
for BENCH in "${CACHEGRIND_BENCHES[@]}"; do
|
|
valgrind --tool=cachegrind --cachegrind-out-file="cachegrind.out.$BENCH.$BRANCH" ./.build/x86_64-unknown-linux-gnu/release/NIOHTTP2PerformanceTester "$BENCH" > /dev/null
|
|
done
|
|
}
|
|
|
|
function compare {
|
|
BASE_BRANCH="$1"
|
|
TARGET_BRANCH="$2"
|
|
|
|
for BENCH in "${CACHEGRIND_BENCHES[@]}"; do
|
|
BASE_TOTAL=$(cg_annotate "cachegrind.out.$BENCH.$BASE_BRANCH" | grep "PROGRAM TOTALS" | awk '{ print $1 }')
|
|
TARGET_TOTAL=$(cg_annotate "cachegrind.out.$BENCH.$TARGET_BRANCH" | grep "PROGRAM TOTALS" | awk '{ print $1 }')
|
|
|
|
echo "Bench $BENCH result changed: base $BASE_TOTAL, target $TARGET_TOTAL"
|
|
done
|
|
}
|
|
|
|
if ! command -v valgrind &> /dev/null; then
|
|
echo "Valgrind not installed, please install valgrind and re-run"
|
|
exit 1
|
|
fi
|
|
|
|
BASE_BRANCH="$1"
|
|
TARGET_BRANCH="$2"
|
|
|
|
run_bench "$BASE_BRANCH"
|
|
run_bench "$TARGET_BRANCH"
|
|
compare "$BASE_BRANCH" "$TARGET_BRANCH"
|
|
|