perf(transport): auto-tune stream receive window #1868
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This commit adds a basic smoke test using the `test-ficture` simulator, asserting that on a connection with unlimited bandwidth and 50ms round-trip-time Neqo can eventually achieve > 1 Gbit/s throughput. Showcases the potential a future stream flow-control auto-tuning algorithm can have. See mozilla#733.
Previously the stream send and receive window had a hard limit at 1MB. On high latency and/or high bandwidth connections, 1 MB is not enough to exhaust the available bandwidth. Sample scenario: ``` delay_s = 0.05 window_bits = 1 * 1024 * 1024 * 8 bandwidth_bits_s = window_bits / delay_s bandwidth_mbits_s = bandwidth_bits_s / 1024 / 1024 # 160.0 ``` In other words, on a 50 ms connection a 1 MB window can at most achieve 160 Mbit/s. This commit introduces an auto-tuning algorithm for the stream receive window, increasing the window towards the bandwidth-delay product of the connection.
Failed Interop TestsQUIC Interop Runner, client vs. server, differences relative to 922d266. neqo-latest as client
neqo-latest as server
All resultsSucceeded Interop TestsQUIC Interop Runner, client vs. server neqo-latest as client
neqo-latest as server
Unsupported Interop TestsQUIC Interop Runner, client vs. server neqo-latest as client
neqo-latest as server
|
This commit adds a basic smoke test using the `test-fixture` simulator, asserting the expected bandwidth on a 1 gbit link. Given mozilla#733, the current expected bandwidth is limited by the fixed sized stream receive buffer (1MiB).
A `Node` (e.g. a `Client`, `Server` or `TailDrop` router) can be in 3 states:
``` rust
enum NodeState {
/// The node just produced a datagram. It should be activated again as soon as possible.
Active,
/// The node is waiting.
Waiting(Instant),
/// The node became idle.
Idle,
}
```
`NodeHolder::ready()` determines whether a `Node` is ready to be processed
again. When `NodeState::Waiting`, it should only be ready when `t <= now`, i.e.
the waiting time has passed, not `t >= now`.
``` rust
impl NodeHolder {
fn ready(&self, now: Instant) -> bool {
match self.state {
Active => true,
Waiting(t) => t <= now, // not >=
Idle => false,
}
}
}
```
The previous behavior lead to wastefull non-ready `Node`s being processed and
thus a large test runtime when e.g. simulating a gbit
connection (mozilla#2203).
Codecov ReportAttention: Patch coverage is
Additional details and impacted files@@ Coverage Diff @@
## main #1868 +/- ##
========================================
Coverage 93.33% 93.34%
========================================
Files 114 114
Lines 36896 37177 +281
Branches 36896 37177 +281
========================================
+ Hits 34438 34703 +265
- Misses 1675 1680 +5
- Partials 783 794 +11 ☔ View full report in Codecov by Sentry. |
mxinden
changed the title
mxinden
commented
Dec 31, 2024
neqo-transport/src/send_stream.rs
Outdated
| pub const SEND_BUFFER_SIZE: usize = 0x10_0000; // 1 MiB | ||
| const MAX_SEND_BUFFER_SIZE: usize = 10 * 1024 * 1024; |
There was a problem hiding this comment.
Previously Neqo would buffer at most 1 MB of send data. Now Neqo buffers up to 10 MB. In other words, it supports an up to 10 MB large send window, depending on the receive window updates of the receiver.
Thus, while this pull request is focused on increasing receive (download) throughput, this patch might as well have an impact on send (upload) throughput on high bandwidth-delay product connections.
Concrete const value up for discussion. On a 50 ms connection a 10 MB window can achieve 1.6 Gbit/s.
mxinden
commented
Dec 31, 2024
| @@ -494,10 +494,10 @@ impl TxBuffer { | |||
|
|
|||
| /// Attempt to add some or all of the passed-in buffer to the `TxBuffer`. | |||
| pub fn send(&mut self, buf: &[u8]) -> usize { | |||
| let can_buffer = min(SEND_BUFFER_SIZE - self.buffered(), buf.len()); | |||
| let can_buffer = min(MAX_SEND_BUFFER_SIZE - self.buffered(), buf.len()); | |||
There was a problem hiding this comment.
Note that while we increase the send buffer up to MAX_SEND_BUFFER_SIZE, it is never shrunk. My rational:
- The majority of streams are short lived. In other words, even if a stream reaches a send buffer of
MAX_SEND_BUFFER_SIZE, the buffer is soon de-allocated. - For long lived buffers reaching
MAX_SEND_BUFFER_SIZE, my assumption is, thatMAX_SEND_BUFFER_SIZEis chosen conservative enough, that the additional allocation doesn't hurt. - Intuitively any shrinking heuristic likely leads to more memory churn, rather than decreasing resident memory.
Thoughts?
mxinden
commented
Dec 31, 2024
Comment on lines
+382
to
+409
| // Auto-tune max_active, i.e. the flow control window. | ||
| // | ||
| // If the sending rate ( window_bytes used / elapsed ) exceeds the rate | ||
| // allowed by the maximum flow control window and the current rtt ( | ||
| // max_active / rtt ), try to increase the maximum flow control window ( | ||
| // max_active ). | ||
| if let Some(max_allowed_sent_at) = self.max_allowed_sent_at { | ||
| let elapsed = now.duration_since(max_allowed_sent_at); | ||
| let window_bytes_used = self.max_active - (self.max_allowed - self.retired); | ||
|
|
||
| // Same as `elapsed / rtt < window_bytes_used / max_active` | ||
| // without floating point division. | ||
| if elapsed.as_micros() * u128::from(self.max_active) | ||
| < rtt.as_micros() * u128::from(window_bytes_used) | ||
| { | ||
| let prev_max_active = self.max_active; | ||
| // Try doubling the flow control window. | ||
| // | ||
| // Note that the flow control window should grow at least as | ||
| // fast as the congestion control window, in order to not | ||
| // unnecessarily limit throughput. | ||
| self.max_active = min(2 * self.max_active, MAX_RECV_WINDOW_SIZE); | ||
| qdebug!( | ||
| "Increasing max stream receive window: previous max_active: {} MiB new max_active: {} MiB last update: {:?} rtt: {rtt:?} stream_id: {}", | ||
| prev_max_active / 1024 / 1024, self.max_active / 1024 / 1024, now-self.max_allowed_sent_at.unwrap(), self.subject, | ||
| ); | ||
| } | ||
| } |
There was a problem hiding this comment.
Auto-tuning is executed right before sending a window update.
A window update is sent either:
- When
WINDOW_UPDATE_FRACTIONis reached, seefn should_send_flowc_updateabove. - The remote sends a
STREAM_DATA_BLOCKED.
mxinden
commented
Dec 31, 2024
Comment on lines
+382
to
+409
| // Auto-tune max_active, i.e. the flow control window. | ||
| // | ||
| // If the sending rate ( window_bytes used / elapsed ) exceeds the rate | ||
| // allowed by the maximum flow control window and the current rtt ( | ||
| // max_active / rtt ), try to increase the maximum flow control window ( | ||
| // max_active ). | ||
| if let Some(max_allowed_sent_at) = self.max_allowed_sent_at { | ||
| let elapsed = now.duration_since(max_allowed_sent_at); | ||
| let window_bytes_used = self.max_active - (self.max_allowed - self.retired); | ||
|
|
||
| // Same as `elapsed / rtt < window_bytes_used / max_active` | ||
| // without floating point division. | ||
| if elapsed.as_micros() * u128::from(self.max_active) | ||
| < rtt.as_micros() * u128::from(window_bytes_used) | ||
| { | ||
| let prev_max_active = self.max_active; | ||
| // Try doubling the flow control window. | ||
| // | ||
| // Note that the flow control window should grow at least as | ||
| // fast as the congestion control window, in order to not | ||
| // unnecessarily limit throughput. | ||
| self.max_active = min(2 * self.max_active, MAX_RECV_WINDOW_SIZE); | ||
| qdebug!( | ||
| "Increasing max stream receive window: previous max_active: {} MiB new max_active: {} MiB last update: {:?} rtt: {rtt:?} stream_id: {}", | ||
| prev_max_active / 1024 / 1024, self.max_active / 1024 / 1024, now-self.max_allowed_sent_at.unwrap(), self.subject, | ||
| ); | ||
| } | ||
| } |
There was a problem hiding this comment.
Note that this is not the exact algorithm suggested by @martinthomson in #733 (comment).
The algorithm proposed in this pull request adopts Martin's trigger mechanism, namely to increase the window based on the perceived BDP.
Therefore, I suggest that if the rate at which self.retired increases (that is, the change in that value, divided by the time elapsed) exceeds some function of self.max_active / path.rtt,
It does not adopt the increase mechanism, i.e. to increase by the amount of retired data. Instead, the window is simply doubled.
then we can increase self.max_active by the amount that self.retired has increased.
The rational is documented above.
// Try doubling the flow control window.
//
// Note that the flow control window should grow at least as
// fast as the congestion control window, in order to not
// unnecessarily limit throughput.
mxinden
requested review from
KershawChang,
martinthomson and
larseggert
as code owners
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Previously the stream send and receive window had a hard limit at 1MB. On high latency and/or high bandwidth connections (i.e. large bandwidth-delay product), 1 MB is not enough to exhaust the available bandwidth.
Sample scenario:
In other words, on a 50 ms connection a 1 MB window can at most achieve 160 Mbit/s.
This commit introduces an auto-tuning algorithm for the stream receive window, increasing the window towards the bandwidth-delay product of the connection.
Fixes #733.