From: Jamal Hadi Salim <jhs@mojatatu.com>
To: Eric Dumazet <eric.dumazet@gmail.com>,
John Fastabend <john.fastabend@gmail.com>
Cc: Eric Dumazet <edumazet@google.com>,
"David S. Miller" <davem@davemloft.net>,
netdev <netdev@vger.kernel.org>,
Alexei Starovoitov <ast@plumgrid.com>,
Eric Dumazet <edumazet@gmail.com>
Subject: Re: [PATCH net-next 6/6] net_sched: act: remove spinlock in fast path
Date: Fri, 03 Jul 2015 07:25:43 -0400 [thread overview]
Message-ID: <55967137.7080806@mojatatu.com> (raw)
In-Reply-To: <1435870750.11970.37.camel@edumazet-glaptop2.roam.corp.google.com>
On 07/02/15 16:59, Eric Dumazet wrote:
> On Thu, 2015-07-02 at 09:35 -0700, John Fastabend wrote:
>
> Point is to not dirty cache line for every packet ?
>
> Doing the test means we attempt dirtying only ~HZ times per second,
> which really matters to handle millions of packets per second.
>
> My tests show a good enough performance, not sure we want a percpu thing
> for this lastuse field.
>
Does it harm to always set gact->tcf_tm.lastuse ?
cheers,
jamal
next prev parent reply other threads:[~2015-07-03 11:25 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-07-02 13:07 [PATCH net-next 0/6] net_sched: act: lockless operation Eric Dumazet
2015-07-02 13:07 ` [PATCH net-next 1/6] net: sched: extend percpu stats helpers Eric Dumazet
2015-07-02 15:19 ` John Fastabend
2015-07-03 10:44 ` Jamal Hadi Salim
2015-07-02 13:07 ` [PATCH net-next 2/6] net: sched: add percpu stats to actions Eric Dumazet
2015-07-02 15:31 ` John Fastabend
2015-07-03 10:48 ` Jamal Hadi Salim
2015-07-02 13:07 ` [PATCH net-next 3/6] net_sched: act: make tcfg_pval non zero Eric Dumazet
2015-07-02 15:33 ` John Fastabend
2015-07-02 16:58 ` Alexei Starovoitov
2015-07-03 10:49 ` Jamal Hadi Salim
2015-07-04 7:18 ` Eric Dumazet
2015-07-02 13:07 ` [PATCH net-next 4/6] net_sched: act: use a separate packet counters for gact_determ() Eric Dumazet
2015-07-02 15:44 ` John Fastabend
2015-07-03 10:50 ` Jamal Hadi Salim
2015-07-02 13:07 ` [PATCH net-next 5/6] net_sched: act: read tcfg_ptype once Eric Dumazet
2015-07-02 15:47 ` John Fastabend
2015-07-03 10:57 ` Jamal Hadi Salim
2015-07-02 13:07 ` [PATCH net-next 6/6] net_sched: act: remove spinlock in fast path Eric Dumazet
2015-07-02 16:35 ` John Fastabend
2015-07-02 20:59 ` Eric Dumazet
2015-07-03 11:25 ` Jamal Hadi Salim [this message]
2015-07-03 12:08 ` Eric Dumazet
2015-07-03 17:21 ` John Fastabend
2015-07-02 17:13 ` Alexei Starovoitov
2015-07-03 11:07 ` Jamal Hadi Salim
2015-07-04 5:45 ` Eric Dumazet
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=55967137.7080806@mojatatu.com \
--to=jhs@mojatatu.com \
--cc=ast@plumgrid.com \
--cc=davem@davemloft.net \
--cc=edumazet@gmail.com \
--cc=edumazet@google.com \
--cc=eric.dumazet@gmail.com \
--cc=john.fastabend@gmail.com \
--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).