netdev - [PATCHv2 net-next 00/15]: TCP rexmit changes

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Date:	Sun, 21 Sep 2008 00:47:43 +0300
From:	"Ilpo Järvinen" <ilpo.jarvinen@...sinki.fi>
To:	David Miller <davem@...emloft.net>
Cc:	netdev@...r.kernel.org
Subject: [PATCHv2 net-next 00/15]: TCP rexmit changes

John Heffner noted ages ago that TCP does O(n^2) processing
during recovery. SACKtag part was solved earlier, making
duplicate ACKs to avoid scanning the write queue unnecessarily.
This change is intented to (mostly) solve the periods when
cumulative ACKs occur during a recovery, ie., basically when
the situation starts to resolve.

v2 fixes !tp->lost_out detection in case we went already more
than 2^31 from the previous retransmit_high.

I played again with it a bit, this time I also went to see the
counters using systemtap and afaict the counters matched what
I expected to see (fwd-rexmits and some other cases related to
collapse/fragment weren't covered by my simple transfer).

--
 i.

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html