Bug #359
Fwd: [PATCH] tcp: fix tcp_rcv_rtt_update() use of an unscaled RTT sample
| Status: | Closed | Start date: | ||
|---|---|---|---|---|
| Priority: | Normal | Due date: | ||
| Assignee: | % Done: | 0% |
||
| Category: | Linux Kernel | Spent time: | 0.50 hour | |
| Target version: | 1st Public Cerowrt release |
Description
---------- Forwarded message ----------
From: David Miller <davem@davemloft.net>
Date: Tue, Apr 10, 2012 at 11:47 AM
Subject: Re: [PATCH] tcp: fix tcp_rcv_rtt_update() use of an unscaled RTT sample
To: ncardwell@google.com
Cc: netdev@vger.kernel.org, nanditad@google.com, ycheng@google.com,
edumazet@google.com, therbert@google.com
From: Neal Cardwell <ncardwell@google.com>
Date: Tue, 10 Apr 2012 13:59:20 -0400
Fix a code path in tcp_rcv_rtt_update() that was comparing scaled and unscaled RTT samples.
The intent in the code was to only use the 'm' measurement if it was a new minimum. However, since 'm' had not yet been shifted left 3 bits but 'new_sample' had, this comparison would nearly always succeed, leading us to erroneously set our receive-side RTT estimate to the 'm' sample when that sample could be nearly 8x too high to use.
The overall effect is to often cause the receive-side RTT estimate to be significantly too large (up to 40% too large for brief periods in my tests).
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Applied, thanks.
History
Updated by Dave Täht about 1 year ago
- Target version set to 1st Public Cerowrt release
- Assignee set to Dave Täht
- Status changed from New to Closed
- Category set to Linux Kernel
Tested in cerowrt 3.3.2-6. Will probably be fixed in 3.3.3