[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20150412.213333.176696352108729674.davem@davemloft.net>
Date: Sun, 12 Apr 2015 21:33:33 -0400 (EDT)
From: David Miller <davem@...emloft.net>
To: eric.dumazet@...il.com
Cc: netdev@...r.kernel.org
Subject: Re: [PATCH net-next] tcp/dccp: get rid of central timewait timer
From: Eric Dumazet <eric.dumazet@...il.com>
Date: Fri, 10 Apr 2015 12:19:34 -0700
> From: Eric Dumazet <edumazet@...gle.com>
>
> Using a timer wheel for timewait sockets was nice ~15 years ago when
> memory was expensive and machines had a single processor.
>
> This does not scale, code is ugly and source of huge latencies
> (Typically 30 ms have been seen, cpus spinning on death_lock spinlock.)
>
> We can afford to use an extra 64 bytes per timewait sock and spread
> timewait load to all cpus to have better behavior.
>
> Tested:
...
> Signed-off-by: Eric Dumazet <edumazet@...gle.com>
First of all, I had to munge your commit message by hand. All of
those ping output lines that start with '---' tell 'git am' "commit
message ends here" so most of your test results got removed. I added
them back by hand.
Second of all, this doesn't compile:
net/ipv4/tcp_minisocks.c: In function ‘tcp_time_wait’:
net/ipv4/tcp_minisocks.c:283:27: warning: passing argument 2 of ‘inet_twsk_alloc’ from incompatible pointer type
tw = inet_twsk_alloc(sk, &tcp_death_row.tw_count, state);
^
In file included from include/linux/tcp.h:24:0,
from include/net/tcp.h:24,
from net/ipv4/tcp_minisocks.c:26:
include/net/inet_timewait_sock.h:108:28: note: expected ‘struct inet_timewait_death_row *’ but argument is of type ‘struct atomic_t *’
struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
^
Powered by blists - more mailing lists