netdev - Re: [PATCH net-next 1/3] net: napi: add hard irqs deferral feature

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

Message-Id: <20200502.164527.1751947884056966917.davem@davemloft.net>
Date:   Sat, 02 May 2020 16:45:27 -0700 (PDT)
From:   David Miller <davem@...emloft.net>
To:     eric.dumazet@...il.com
Cc:     jwi@...ux.ibm.com, edumazet@...gle.com, netdev@...r.kernel.org,
        lrizzo@...gle.com
Subject: Re: [PATCH net-next 1/3] net: napi: add hard irqs deferral feature

From: Eric Dumazet <eric.dumazet@...il.com>
Date: Sat, 2 May 2020 09:24:19 -0700

> Doing the unmap stuff can be costly in IOMMU world, and freeing skb
> can be also expensive.  Add to this that TCP stack might be called
> back (via skb->destructor()) to add more packets to the
> qdisc/device.
> 
> So using effectively the budget as a limit might help in some stress
> situations, by not re-enabling NIC interrupts, even before
> napi_defer_hard_irqs addition.

Even with this logic, TX budgeting should be consuming some fraction of
the budget compared to RX processing.  Even if TX work isn't free, it's
much cheaper than RX.