allow dctcp alpha to drop to zero
Subsystems (3)
PATCH 1/1 allow dctcp alpha to drop to zero
If alpha is strictly reduced by alpha >> dctcp_shift_g and if alpha is less than 1 << dctcp_shift_g, then alpha may never reach zero. For example, given shift_g=4 and alpha=15, alpha >> dctcp_shift_g yields 0 and alpha remains 15. The effect isn't noticeable in this case below cwnd=137, but could gradually drive uncongested flows with leftover alpha down to cwnd=137. A larger dctcp_shift_g would have a greater effect.
This change causes alpha=15 to drop to 0 instead of being decrementing by 1 as it would when alpha=16. However, it requires one less conditional to implement since it doesn't have to guard against subtracting 1 from 0U. A decay of 15 is not unreasonable since an equal or greater amount occurs at alpha >= 240.
--- net/ipv4/tcp_dctcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/ipv4/tcp_dctcp.c +1 -1
@@ -209,7 +209,7 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)/* alpha = (1 - g) * alpha + g * F */ - alpha -= alpha >> dctcp_shift_g; + alpha -=min_not_zero (alpha, alpha >> dctcp_shift_g);if (bytes_ecn) {/* If dctcp_shift_g == 1, a 32bit value would overflow * after 8 Mbytes.
Signature · 1 line
1.9.1
Quoted 7 lines · Andrew Shewmaker
If alpha is strictly reduced by alpha >>
dctcp_shift_gand if alpha is less than 1 <<dctcp_shift_g, then alpha may never reach zero. For example, given shift_g=4 and alpha=15, alpha >>dctcp_shift_gyields 0 and alpha remains 15. The effect isn't noticeable in this case below cwnd=137, but could gradually drive uncongested flows with leftover alpha down to cwnd=137. A largerdctcp_shift_gwould have a greater effect.
Quoted 7 lines
This change causes alpha=15 to drop to 0 instead of being decrementing by 1 as it would when alpha=16. However, it requires one less conditional to implement since it doesn't have to guard against subtracting 1 from 0U. A decay of 15 is not unreasonable since an equal or greater amount occurs at alpha >= 240.
Signed-off-by Andrew G. Shewmaker <[email protected]>
[ cwnd=137 is quite large so I don't think its important enough for -stable ].
Quoted 14 lines · Florian Westphal
Quoted 13 lines · Andrew Shewmaker
If alpha is strictly reduced by alpha >>
dctcp_shift_gand if alpha is less than 1 <<dctcp_shift_g, then alpha may never reach zero. For example, given shift_g=4 and alpha=15, alpha >>dctcp_shift_gyields 0 and alpha remains 15. The effect isn't noticeable in this case below cwnd=137, but could gradually drive uncongested flows with leftover alpha down to cwnd=137. A largerdctcp_shift_gwould have a greater effect.This change causes alpha=15 to drop to 0 instead of being decrementing by 1 as it would when alpha=16. However, it requires one less conditional to implement since it doesn't have to guard against subtracting 1 from 0U. A decay of 15 is not unreasonable since an equal or greater amount occurs at alpha >= 240.
Quoted 6 lines
Quoted 1 line
Signed-off-by Andrew G. Shewmaker <[email protected]>Acked-by Florian Westphal <[email protected]>[ cwnd=137 is quite large so I don't think its important enough for -stable ].
If my math is correct (please double check it), then my patch will make a difference in scenarios such as:
data center: ~20+ Gbps and 500 microsecond RTT
137 * 9000 * 8 / (500 * pow(10, -6)) / pow(10, 9) = 19.728 Gbps [pkt / W] * [bits / pkt] * [W / sec]
regional: ~33+ Mbps and 50 millisecond RTT
137 * 1500 * 8 / (50 * pow(10, -3)) / pow(10, 6) = 32.88 Mbps
international: ~11+ Mbps and 150 millisecond RTT
137 * 1500 * 8 / (150 * pow(10, -3)) / pow(10, 6) = 10.96 Mbps
Even if the broader internet does not ever configure ECN appropriately for use with DCTCP, I care about the latter two cases because I'm using an RTT-based congestion ratio in the same way as DCTCP uses its ECN-based congestion ratio. A tech report describing use of RTTs in this way, with some preliminary Mininet results, is available:
https://www.soe.ucsc.edu/research/technical-reports/UCSC-SOE-15-20
I plan on submitting some RFC patches to DCTCP based on my prototype soon.
Signature · 1 line
Andrew Shewmaker
From: Andrew Shewmaker <[email protected]>
Date: Sun, 18 Oct 2015 21:59:08 -0700
Quoted 7 lines
If alpha is strictly reduced by alpha >>
dctcp_shift_gand if alpha is less than 1 <<dctcp_shift_g, then alpha may never reach zero. For example, given shift_g=4 and alpha=15, alpha >>dctcp_shift_gyields 0 and alpha remains 15. The effect isn't noticeable in this case below cwnd=137, but could gradually drive uncongested flows with leftover alpha down to cwnd=137. A largerdctcp_shift_gwould have a greater effect.
Quoted 7 lines
This change causes alpha=15 to drop to 0 instead of being decrementing by 1 as it would when alpha=16. However, it requires one less conditional to implement since it doesn't have to guard against subtracting 1 from 0U. A decay of 15 is not unreasonable since an equal or greater amount occurs at alpha >= 240.
Signed-off-by Andrew G. Shewmaker <[email protected]>
Applied, thanks.