[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <9c4b954f-fa3c-7818-ef01-16eae542cd53@kernel.org>
Date: Tue, 3 Oct 2023 08:29:39 -0600
From: David Ahern <dsahern@...nel.org>
To: Paolo Abeni <pabeni@...hat.com>, Eric Dumazet <edumazet@...gle.com>,
"David S . Miller" <davem@...emloft.net>, Jakub Kicinski <kuba@...nel.org>
Cc: Neal Cardwell <ncardwell@...gle.com>, Yuchung Cheng <ycheng@...gle.com>,
netdev@...r.kernel.org, eric.dumazet@...il.com
Subject: Re: [PATCH net-next 4/4] tcp_metrics: optimize
tcp_metrics_flush_all()
On 10/3/23 2:04 AM, Paolo Abeni wrote:
>> I have found cond_resched() can occur some unnecessary overhead if
>> called too often. Wrap in `if (need_resched)`?
>
> Interesting. I could not find any significant overhead with code
> inspection - it should be a matter of 2 conditionals instead of one -
> Any idea why?
I would need to go through the ftrace output. I think it is really use
case dependent and for this one and the way tcp_metrics_nl_cmd_del is
called just cond_resched is ok.
Powered by blists - more mailing lists