From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 76DDA46AF5; Sat, 5 Jul 2025 09:44:37 +0200 (CEST) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 0C9944028C; Sat, 5 Jul 2025 09:44:37 +0200 (CEST) Received: from frasgout.his.huawei.com (frasgout.his.huawei.com [185.176.79.56]) by mails.dpdk.org (Postfix) with ESMTP id 3C24440287 for ; Sat, 5 Jul 2025 09:44:35 +0200 (CEST) Received: from mail.maildlp.com (unknown [172.18.186.216]) by frasgout.his.huawei.com (SkyGuard) with ESMTP id 4bZ2Z75wyPz6L578; Sat, 5 Jul 2025 15:43:59 +0800 (CST) Received: from frapeml500008.china.huawei.com (unknown [7.182.85.71]) by mail.maildlp.com (Postfix) with ESMTPS id 951D21402F5; Sat, 5 Jul 2025 15:44:34 +0800 (CST) Received: from frapeml500007.china.huawei.com (7.182.85.172) by frapeml500008.china.huawei.com (7.182.85.71) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.1.2507.39; Sat, 5 Jul 2025 09:44:34 +0200 Received: from frapeml500007.china.huawei.com ([7.182.85.172]) by frapeml500007.china.huawei.com ([7.182.85.172]) with mapi id 15.01.2507.039; Sat, 5 Jul 2025 09:44:34 +0200 From: Konstantin Ananyev To: Konstantin Ananyev , =?iso-8859-1?Q?Morten_Br=F8rup?= , "thomas@monjalon.net" , Bruce Richardson CC: "dev@dpdk.org" Subject: RE: [RFC] ethdev: TX mbuf fast release optimization Thread-Topic: [RFC] ethdev: TX mbuf fast release optimization Thread-Index: AdvsIqk6dXfxyQ/IQSK9FKicZXvNKwA28pmQACBkzjA= Date: Sat, 5 Jul 2025 07:44:34 +0000 Message-ID: References: <98CBD80474FA8B44BF855DF32C47DC35E9FD87@smartserver.smartshare.dk> <395df6c41a554ee29b122d7f85950690@huawei.com> In-Reply-To: <395df6c41a554ee29b122d7f85950690@huawei.com> Accept-Language: en-GB, en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-originating-ip: [10.126.171.243] Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org > -----Original Message----- > From: Konstantin Ananyev > Sent: Friday, July 4, 2025 5:20 PM > To: Morten Br=F8rup ; thomas@monjalon.net; Bruc= e Richardson > Cc: dev@dpdk.org > Subject: RE: [RFC] ethdev: TX mbuf fast release optimization >=20 >=20 > > For TX mbuf fast release offload, I propose to add the mbuf mempool > > pointer to the ethdev tx queue configuration structure, > > so the ethdev TX burst operation doesn't need to fetch it from the > > first mbuf of each burst being fast free'd to the mempool. > > > > This modification of the struct rte_eth_txconf, and the requirement > > to set the mempool pointer if the RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE > > flag is set, will be an API+ABI change in 25.11. > > Should it be announced in the 25.07 release notes? > > > > Note: We could phase it in softly by letting the ethdev drivers > > check if the pointer has been set, and fall back to fetching it > > from mbuf[0] if not. > > > > /** > > * A structure used to configure a Tx ring of an Ethernet port. > > */ > > struct rte_eth_txconf { > > struct rte_eth_thresh tx_thresh; /**< Tx ring threshold registers. */ > > uint16_t tx_rs_thresh; /**< Drives the setting of RS bit on TXDs. */ > > uint16_t tx_free_thresh; /**< Start freeing Tx buffers if there are > > less free descriptors than this value. */ > > > > uint8_t tx_deferred_start; /**< Do not start queue with rte_eth_dev_st= art(). */ > > /** > > * Per-queue Tx offloads to be set using RTE_ETH_TX_OFFLOAD_* flags. > > * Only offloads set on tx_queue_offload_capa or tx_offload_capa > > * fields on rte_eth_dev_info structure are allowed to be set. > > */ > > uint64_t offloads; > > > > + /** > > + * Per-queue mempool to release the mbufs to; required for > > + * RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE offload. > > + */ > > + struct rte_mempool *mp; > > + >=20 > Even though I usually recommend to use MBUF_FAST_FREE - Correction, meant to say: I usually recommend not to use MBUF_FAST_FREE. The rest remains the same :) > that's probably a good change. > At least people will realize that they have to provide a single mempool > per TX queue when they enable FAST_FREE flag. > One naming suggestion I have - can we name it somehow more informative: > 'fast_free_mp' or so? > Also, we can update tx_queue_setup() to catch the situation when FAST_FRE= E > is set but mp is NULL, or visa-versa. > Again drivers can probably add extra check when debug is enabled, that > all mbufs are exactly from that mempool. >=20 >=20 > > uint64_t reserved_64s[2]; /**< Reserved for future fields */ > > void *reserved_ptrs[2]; /**< Reserved for future fields */ > > }; > >