From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A463D406271 for ; Mon, 11 May 2026 15:47:47 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778514467; cv=none; b=VReULoS1dnJChkxVXzP2K/19tHS6QMe7daoQ8ZqTyC3pxlvxvVY/POoNSGaUsoKR7cJlpK51O5HJZ9L7yujz6LtGBo+AGoFnPsO7e0ViHO9azHkfs6uJGumbCNMo/xAIv0svLda13oPU9gm3Y/rdbb+VdB8CmxNI0QBYUpxmb2Y= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1778514467; c=relaxed/simple; bh=wg3sj4YnE54AHzo71NUx2gXbPJJaa+jjk+3YhaTtn2k=; h=Date:From:To:Cc:Subject:Message-ID:References:MIME-Version: Content-Type:Content-Disposition:In-Reply-To; b=PHfKfXZtgPfhi+8SDmOrgDrgkUKWVvz7y+ssLCnkVHofQZP/2rTbiO4RfxRUHq8TCrdWPAyTKMZlBMLoe9NY6FSY0y30b7OujJquFR6+13Ajisc0YcMlQIq9NVQuustwRv21nYevruxCk7n/64aBsZQMubxyXd6NqKtUdiDNAMI= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=BvNpoFXI; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="BvNpoFXI" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 4EF42C2BCB0; Mon, 11 May 2026 15:47:46 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1778514467; bh=wg3sj4YnE54AHzo71NUx2gXbPJJaa+jjk+3YhaTtn2k=; h=Date:From:To:Cc:Subject:References:In-Reply-To:From; b=BvNpoFXI3fi7jwGkY+pWzGB1wYn05cTBMtf2Kpj7RTyHJq6h1pPue8F7RwO173Ngr 6m+0uZ3W3Jhh6O9cOYnEzxy16U8y0930otjA13SJtsp2NtE0ypnPQG/FoQn8jWsPtR KpaMT5d1UWpJbbz86jxDsUPw+jiEmn/icj+xqoNKm1LVpvBr7lVZ3gP0aYQr13Qxjo XiY8SaGpgfLwCDroE0/qJJWHdmPl4SxZYcRJK5APgHS7fNNJbf2+HAzi+s4aFRUcyU GQTiCzqc48IPD0rhu89keicVmyV6tExe2QBPCdpAAeHvs30A98+RE1gP4qya7zfhnr 99uBaZ7+MwEbw== Date: Mon, 11 May 2026 16:47:43 +0100 From: Simon Horman To: Aleksandr Loktionov Cc: intel-wired-lan@lists.osuosl.org, anthony.l.nguyen@intel.com, netdev@vger.kernel.org Subject: Re: [PATCH iwl-next 7/8] ixgbe: limit ITR decrease in latency mode to prevent ACK overdrive Message-ID: <20260511154743.GD27589@horms.kernel.org> References: <20260508031226.3601800-1-aleksandr.loktionov@intel.com> <20260508031226.3601800-8-aleksandr.loktionov@intel.com> Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20260508031226.3601800-8-aleksandr.loktionov@intel.com> On Fri, May 08, 2026 at 05:12:25AM +0200, Aleksandr Loktionov wrote: > From: Alexander Duyck > > When operating in latency mode and the computed ITR is lower than the > current setting, the algorithm can reduce the interrupt rate too > aggressively in a single step. For a TCP workload this means the ACK > stream (a latency-sensitive, low-packet-rate workload) can drive the > moderation down to very high interrupt rates, starving CPU time from > the sender side. > > After the speed-based ITR calculation is complete, check whether the > result is in latency mode and would decrease below the current setting. > If so, limit the decrease to at most IXGBE_ITR_ADAPTIVE_MIN_INC (2 us) > per update. This ensures the number of interrupts grows by no more > than 2x per adjustment step for latency-class workloads, dialling in > smoothly rather than overshooting. > > Signed-off-by: Alexander Duyck > Signed-off-by: Aleksandr Loktionov Reviewed-by: Simon Horman > --- > drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 11 +++++++++++ > 1 file changed, 11 insertions(+) > > diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c > index aea76b3..ba7b013 100644 > --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c > +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c > @@ -2888,6 +2888,17 @@ static void ixgbe_update_itr(struct ixgbe_q_vector *q_vector, > break; > } > > + /* In the case of a latency specific workload only allow us to > + * reduce the ITR by at most 2us. By doing this we should dial > + * in so that our number of interrupts is no more than 2x the number > + * of packets for the least busy workload. So for example in the case > + * of a TCP workload the ACK packets being received would set the > + * interrupt rate as they are a latency specific workload. > + */ > + if ((itr & IXGBE_ITR_ADAPTIVE_LATENCY) && itr < ring_container->itr) > + itr = max_t(unsigned int, itr, > + ring_container->itr - IXGBE_ITR_ADAPTIVE_MIN_INC); nit: I expect this could be min(). And if it could, it should. > + > clear_counts: > /* write back value */ > ring_container->itr = itr; > -- > 2.52.0 >