From: Yunsheng Lin <linyunsheng@huawei.com> To: Alexander H Duyck <alexander.duyck@gmail.com>, David Howells <dhowells@redhat.com>, <netdev@vger.kernel.org> Cc: "David S. Miller" <davem@davemloft.net>, Eric Dumazet <edumazet@google.com>, Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>, Willem de Bruijn <willemdebruijn.kernel@gmail.com>, David Ahern <dsahern@kernel.org>, Matthew Wilcox <willy@infradead.org>, Jens Axboe <axboe@kernel.dk>, <linux-mm@kvack.org>, <linux-kernel@vger.kernel.org>, Jeroen de Borst <jeroendb@google.com>, Catherine Sullivan <csully@google.com>, Shailend Chand <shailend@google.com>, Felix Fietkau <nbd@nbd.name>, John Crispin <john@phrozen.org>, Sean Wang <sean.wang@mediatek.com>, Mark Lee <Mark-MC.Lee@mediatek.com>, Lorenzo Bianconi <lorenzo@kernel.org>, Matthias Brugger <matthias.bgg@gmail.com>, AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>, Keith Busch <kbusch@kernel.org>, Jens Axboe <axboe@fb.com>, Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>, Chaitanya Kulkarni <kch@nvidia.com>, Andrew Morton <akpm@linux-foundation.org>, <linux-arm-kernel@lists.infradead.org>, <linux-mediatek@lists.infradead.org>, <linux-nvme@lists.infradead.org> Subject: Re: [PATCH net-next 03/12] mm: Make the page_frag_cache allocator alignment param a pow-of-2 Date: Thu, 30 Nov 2023 17:00:52 +0800 [thread overview] Message-ID: <e841d2f4-b221-9099-8312-6b859ccb98de@huawei.com> (raw) In-Reply-To: <51161740e832334594960ed43430b868a6f892c3.camel@gmail.com> On 2023/5/27 23:54, Alexander H Duyck wrote: > On Wed, 2023-05-24 at 16:33 +0100, David Howells wrote: >> Make the page_frag_cache allocator's alignment parameter a power of 2 >> rather than a mask and give a warning if it isn't. >> >> This means that it's consistent with {napi,netdec}_alloc_frag_align() and >> allows __{napi,netdev}_alloc_frag_align() to be removed. I am trying to rmove the page frag implemetation in vhost_net_page_frag_refill() by using page_frag_alloc_align(), and I ended up having a simiar patch as this one. >> > > This goes against the original intention of these functions. One of the > reasons why this is being used is because when somebody enables > something like 2K jumbo frames they don't necessarily want to have to > allocate 4K SLABs. Instead they can just add a bit of overhead and get > almost twice the utilization out of an order 3 page. > > The requirement should only be cache alignment, not power of 2 > alignment. This isn't meant to be a slab allocator. We are just > sectioning up pages to handle mixed workloads. In the case of > networking we can end up getting everything from 60B packets, to 1514B > in the standard cases. That was why we started sectioning up pages in > the first place so putting a power of 2 requirement on it doens't fit > our use case at all and is what we were trying to get away from with > the SLAB allocators. It seems that is_power_of_2() checking in this patch does not excluding the non-align case if we are passing 'align' being 1, which means we still can support the 'everything from 60B packets, to 1514B' case. > > . >
WARNING: multiple messages have this Message-ID (diff)
From: Yunsheng Lin <linyunsheng@huawei.com> To: Alexander H Duyck <alexander.duyck@gmail.com>, David Howells <dhowells@redhat.com>, <netdev@vger.kernel.org> Cc: "David S. Miller" <davem@davemloft.net>, Eric Dumazet <edumazet@google.com>, Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>, Willem de Bruijn <willemdebruijn.kernel@gmail.com>, David Ahern <dsahern@kernel.org>, Matthew Wilcox <willy@infradead.org>, Jens Axboe <axboe@kernel.dk>, <linux-mm@kvack.org>, <linux-kernel@vger.kernel.org>, Jeroen de Borst <jeroendb@google.com>, Catherine Sullivan <csully@google.com>, Shailend Chand <shailend@google.com>, Felix Fietkau <nbd@nbd.name>, John Crispin <john@phrozen.org>, Sean Wang <sean.wang@mediatek.com>, Mark Lee <Mark-MC.Lee@mediatek.com>, Lorenzo Bianconi <lorenzo@kernel.org>, Matthias Brugger <matthias.bgg@gmail.com>, AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>, Keith Busch <kbusch@kernel.org>, Jens Axboe <axboe@fb.com>, Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>, Chaitanya Kulkarni <kch@nvidia.com>, Andrew Morton <akpm@linux-foundation.org>, <linux-arm-kernel@lists.infradead.org>, <linux-mediatek@lists.infradead.org>, <linux-nvme@lists.infradead.org> Subject: Re: [PATCH net-next 03/12] mm: Make the page_frag_cache allocator alignment param a pow-of-2 Date: Thu, 30 Nov 2023 17:00:52 +0800 [thread overview] Message-ID: <e841d2f4-b221-9099-8312-6b859ccb98de@huawei.com> (raw) In-Reply-To: <51161740e832334594960ed43430b868a6f892c3.camel@gmail.com> On 2023/5/27 23:54, Alexander H Duyck wrote: > On Wed, 2023-05-24 at 16:33 +0100, David Howells wrote: >> Make the page_frag_cache allocator's alignment parameter a power of 2 >> rather than a mask and give a warning if it isn't. >> >> This means that it's consistent with {napi,netdec}_alloc_frag_align() and >> allows __{napi,netdev}_alloc_frag_align() to be removed. I am trying to rmove the page frag implemetation in vhost_net_page_frag_refill() by using page_frag_alloc_align(), and I ended up having a simiar patch as this one. >> > > This goes against the original intention of these functions. One of the > reasons why this is being used is because when somebody enables > something like 2K jumbo frames they don't necessarily want to have to > allocate 4K SLABs. Instead they can just add a bit of overhead and get > almost twice the utilization out of an order 3 page. > > The requirement should only be cache alignment, not power of 2 > alignment. This isn't meant to be a slab allocator. We are just > sectioning up pages to handle mixed workloads. In the case of > networking we can end up getting everything from 60B packets, to 1514B > in the standard cases. That was why we started sectioning up pages in > the first place so putting a power of 2 requirement on it doens't fit > our use case at all and is what we were trying to get away from with > the SLAB allocators. It seems that is_power_of_2() checking in this patch does not excluding the non-align case if we are passing 'align' being 1, which means we still can support the 'everything from 60B packets, to 1514B' case. > > . > _______________________________________________ linux-arm-kernel mailing list linux-arm-kernel@lists.infradead.org http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2023-11-30 9:01 UTC|newest] Thread overview: 69+ messages / expand[flat|nested] mbox.gz Atom feed top 2023-05-24 15:32 [PATCH net-next 00/12] splice, net: Replace sendpage with sendmsg(MSG_SPLICE_PAGES), part 3 David Howells 2023-05-24 15:33 ` [PATCH net-next 01/12] mm: Move the page fragment allocator from page_alloc.c into its own file David Howells 2023-05-24 15:33 ` [PATCH net-next 02/12] mm: Provide a page_frag_cache allocator cleanup function David Howells 2023-05-24 15:33 ` David Howells 2023-05-24 15:33 ` [PATCH net-next 03/12] mm: Make the page_frag_cache allocator alignment param a pow-of-2 David Howells 2023-05-24 15:33 ` David Howells 2023-05-27 15:54 ` Alexander H Duyck 2023-05-27 15:54 ` Alexander H Duyck 2023-11-30 9:00 ` Yunsheng Lin [this message] 2023-11-30 9:00 ` Yunsheng Lin 2023-06-16 15:28 ` David Howells 2023-06-16 15:28 ` David Howells 2023-06-16 16:06 ` Alexander Duyck 2023-06-16 16:06 ` Alexander Duyck 2023-05-24 15:33 ` [PATCH net-next 04/12] mm: Make the page_frag_cache allocator use multipage folios David Howells 2023-05-24 15:33 ` David Howells 2023-05-26 11:56 ` Yunsheng Lin 2023-05-26 11:56 ` Yunsheng Lin 2023-05-27 15:47 ` Alexander H Duyck 2023-05-27 15:47 ` Alexander H Duyck 2023-06-06 8:25 ` David Howells 2023-06-06 8:25 ` David Howells 2023-06-06 14:59 ` Alexander Duyck 2023-06-06 14:59 ` Alexander Duyck 2023-05-26 12:47 ` David Howells 2023-05-26 12:47 ` David Howells 2023-05-26 14:06 ` Mika Penttilä 2023-05-26 14:06 ` Mika Penttilä 2023-05-27 0:50 ` Jakub Kicinski 2023-05-27 0:50 ` Jakub Kicinski 2023-05-24 15:33 ` [PATCH net-next 05/12] mm: Make the page_frag_cache allocator handle __GFP_ZERO itself David Howells 2023-05-24 15:33 ` David Howells 2023-05-27 0:57 ` Jakub Kicinski 2023-05-27 0:57 ` Jakub Kicinski 2023-05-27 15:54 ` Alexander Duyck 2023-05-27 15:54 ` Alexander Duyck 2023-05-24 15:33 ` [PATCH net-next 06/12] mm: Make the page_frag_cache allocator use per-cpu David Howells 2023-05-24 15:33 ` David Howells 2023-05-27 1:02 ` Jakub Kicinski 2023-05-27 1:02 ` Jakub Kicinski 2023-05-24 15:33 ` [PATCH net-next 07/12] net: Clean up users of netdev_alloc_cache and napi_frag_cache David Howells 2023-05-24 15:33 ` [PATCH net-next 08/12] net: Copy slab data for sendmsg(MSG_SPLICE_PAGES) David Howells 2023-05-24 15:33 ` [PATCH net-next 09/12] tls/sw: Support MSG_SPLICE_PAGES David Howells 2023-05-27 1:08 ` Jakub Kicinski 2023-05-30 22:26 ` Bug in short splice to socket? David Howells 2023-05-31 0:32 ` Jakub Kicinski 2023-06-01 11:01 ` David Laight 2023-06-01 13:09 ` Linus Torvalds 2023-06-01 13:19 ` Linus Torvalds 2023-06-01 14:34 ` David Howells 2023-06-01 15:12 ` Linus Torvalds 2023-06-05 11:03 ` David Laight 2023-06-05 15:52 ` David Howells 2023-06-01 17:14 ` David Howells 2023-06-02 4:20 ` Jakub Kicinski 2023-06-02 8:23 ` David Howells 2023-06-02 11:28 ` Linus Torvalds 2023-06-02 11:44 ` David Howells 2023-06-02 12:11 ` Linus Torvalds 2023-06-02 16:39 ` Jakub Kicinski 2023-06-02 16:53 ` Linus Torvalds 2023-06-02 17:05 ` Linus Torvalds 2023-06-02 17:38 ` Jakub Kicinski 2023-06-02 20:38 ` David Howells 2023-06-02 20:50 ` David Howells 2023-05-24 15:33 ` [PATCH net-next 10/12] tls/sw: Convert tls_sw_sendpage() to use MSG_SPLICE_PAGES David Howells 2023-05-27 1:13 ` Jakub Kicinski 2023-05-24 15:33 ` [PATCH net-next 11/12] tls/device: Support MSG_SPLICE_PAGES David Howells 2023-05-24 15:33 ` [PATCH net-next 12/12] tls/device: Convert tls_device_sendpage() to use MSG_SPLICE_PAGES David Howells
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=e841d2f4-b221-9099-8312-6b859ccb98de@huawei.com \ --to=linyunsheng@huawei.com \ --cc=Mark-MC.Lee@mediatek.com \ --cc=akpm@linux-foundation.org \ --cc=alexander.duyck@gmail.com \ --cc=angelogioacchino.delregno@collabora.com \ --cc=axboe@fb.com \ --cc=axboe@kernel.dk \ --cc=csully@google.com \ --cc=davem@davemloft.net \ --cc=dhowells@redhat.com \ --cc=dsahern@kernel.org \ --cc=edumazet@google.com \ --cc=hch@lst.de \ --cc=jeroendb@google.com \ --cc=john@phrozen.org \ --cc=kbusch@kernel.org \ --cc=kch@nvidia.com \ --cc=kuba@kernel.org \ --cc=linux-arm-kernel@lists.infradead.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mediatek@lists.infradead.org \ --cc=linux-mm@kvack.org \ --cc=linux-nvme@lists.infradead.org \ --cc=lorenzo@kernel.org \ --cc=matthias.bgg@gmail.com \ --cc=nbd@nbd.name \ --cc=netdev@vger.kernel.org \ --cc=pabeni@redhat.com \ --cc=sagi@grimberg.me \ --cc=sean.wang@mediatek.com \ --cc=shailend@google.com \ --cc=willemdebruijn.kernel@gmail.com \ --cc=willy@infradead.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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.