From: Eric Dumazet <dada1@cosmosbay.com>
To: David Miller <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Subject: Re: [PATCH] [NET] reduce sizeof(struct inet_peer), cleanup, change in peer_check_expire()
Date: Fri, 13 Oct 2006 05:56:43 +0200 [thread overview]
Message-ID: <452F0E7B.3010701@cosmosbay.com> (raw)
In-Reply-To: <20061012.151529.95506153.davem@davemloft.net>
David Miller a écrit :
> From: Eric Dumazet <dada1@cosmosbay.com>
> Date: Thu, 12 Oct 2006 22:14:12 +0200
>
>> 1) shrink struct inet_peer on 64 bits platforms.
>> ------------------------------------------------
>> I noticed sizeof(struct inet_peer) was 64+8 on x86_64
>>
>> As we dont really need 64 bits timestamps (we only care for garbage
>> collection), we can use 32bits ones and reduce sizeof(struct inet_peer) to 64
>> bytes : Because of SLAB_HWCACHE_ALIGN constraint, final allocation is 64 bytes
>> instead of 128 bytes per inet_peer structure.
>
> I'm not convinced this is %100 correct. There are wrapping
> cases that I think aren't covered.
>
> Consider an entry that lives long enough for the lower 32-bits
> of jiffies to wrap, then we kill it, but we won't purge it
> properly if the wrapped jiffie is close to dtime.
>
> I'm sure there are other similar cases as well.
Hum, if it was incorrect, I urge you to grep for tcp_time_stamp, and correct
this as soon as possible :)
2^31 is 2147483648
Thats a *lot* of timer ticks, an inet_peer entry should not stay in
unused_list for more than 10 minutes.
Even if the system is under stress for more than 30 days, and some entries
stay that long in unused list, they wont leak : either they are re-used,
either they are purged by cleanup_once(0); done in inet_getpeer().
Eric
next prev parent reply other threads:[~2006-10-13 3:56 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20051217071029.GY23384@wotan.suse.de>
[not found] ` <20051216.231517.68922847.davem@davemloft.net>
[not found] ` <43A3EE8A.5020907@cosmosbay.com>
[not found] ` <43CCBF3D.2070900@cosmosbay.com>
[not found] ` <4415A4C1.1030906@cosmosbay.com>
2006-10-12 20:14 ` [PATCH] [NET] reduce sizeof(struct inet_peer), cleanup, change in peer_check_expire() Eric Dumazet
2006-10-12 22:15 ` David Miller
2006-10-13 3:56 ` Eric Dumazet [this message]
2006-10-13 4:18 ` David Miller
2006-10-13 4:24 ` Eric Dumazet
2006-10-18 5:08 ` [PATCH] [NET] reduce sizeof(struct flow) Eric Dumazet
2006-10-18 5:17 ` YOSHIFUJI Hideaki / 吉藤英明
2006-10-18 5:30 ` Eric Dumazet
2006-10-18 5:27 ` David Miller
2006-10-18 5:42 ` Eric Dumazet
2006-10-18 6:53 ` David Miller
2006-10-18 8:20 ` Steven Whitehouse
2006-10-18 8:55 ` Eric Dumazet
2006-10-18 12:42 ` Steven Whitehouse
2006-10-18 13:32 ` Eric Dumazet
2006-10-19 3:50 ` David Miller
2006-10-19 5:13 ` Eric Dumazet
2006-10-20 13:55 ` [PATCH] [NET] reduce sizeof(struct flowi) by 20 bytes Eric Dumazet
2006-10-22 3:25 ` David Miller
2006-10-18 11:33 ` [PATCH] [NET] reduce sizeof(struct flow) Ingo Oeser
2006-10-20 7:18 ` [PATCH] [NET] can use __get_cpu_var() instead of per_cpu() in loopback driver Eric Dumazet
2006-10-20 7:32 ` David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=452F0E7B.3010701@cosmosbay.com \
--to=dada1@cosmosbay.com \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).