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
| ||
|
Date: Tue, 20 Nov 2018 09:43:13 +0800 From: Aaron Lu <aaron.lu@...el.com> To: Tariq Toukan <tariqt@...lanox.com> Cc: "linux-mm@...ck.org" <linux-mm@...ck.org>, "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>, "netdev@...r.kernel.org" <netdev@...r.kernel.org>, Andrew Morton <akpm@...ux-foundation.org>, Paweł Staszewski <pstaszewski@...are.pl>, Jesper Dangaard Brouer <brouer@...hat.com>, Eric Dumazet <eric.dumazet@...il.com>, Ilias Apalodimas <ilias.apalodimas@...aro.org>, Yoel Caspersen <yoel@...knet.dk>, Mel Gorman <mgorman@...hsingularity.net>, Saeed Mahameed <saeedm@...lanox.com>, Michal Hocko <mhocko@...e.com>, Vlastimil Babka <vbabka@...e.cz>, Dave Hansen <dave.hansen@...ux.intel.com>, Alexander Duyck <alexander.h.duyck@...ux.intel.com>, Ian Kumlien <ian.kumlien@...il.com> Subject: Re: [PATCH v2 RESEND 1/2] mm/page_alloc: free order-0 pages through PCP in page_frag_free() On Mon, Nov 19, 2018 at 03:00:53PM +0000, Tariq Toukan wrote: > > > On 19/11/2018 3:48 PM, Aaron Lu wrote: > > page_frag_free() calls __free_pages_ok() to free the page back to > > Buddy. This is OK for high order page, but for order-0 pages, it > > misses the optimization opportunity of using Per-Cpu-Pages and can > > cause zone lock contention when called frequently. > > > > Paweł Staszewski recently shared his result of 'how Linux kernel > > handles normal traffic'[1] and from perf data, Jesper Dangaard Brouer > > found the lock contention comes from page allocator: > > > > mlx5e_poll_tx_cq > > | > > --16.34%--napi_consume_skb > > | > > |--12.65%--__free_pages_ok > > | | > > | --11.86%--free_one_page > > | | > > | |--10.10%--queued_spin_lock_slowpath > > | | > > | --0.65%--_raw_spin_lock > > | > > |--1.55%--page_frag_free > > | > > --1.44%--skb_release_data > > > > Jesper explained how it happened: mlx5 driver RX-page recycle > > mechanism is not effective in this workload and pages have to go > > through the page allocator. The lock contention happens during > > mlx5 DMA TX completion cycle. And the page allocator cannot keep > > up at these speeds.[2] > > > > I thought that __free_pages_ok() are mostly freeing high order > > pages and thought this is an lock contention for high order pages > > but Jesper explained in detail that __free_pages_ok() here are > > actually freeing order-0 pages because mlx5 is using order-0 pages > > to satisfy its page pool allocation request.[3] > > > > The free path as pointed out by Jesper is: > > skb_free_head() > > -> skb_free_frag() > > -> page_frag_free() > > And the pages being freed on this path are order-0 pages. > > > > Fix this by doing similar things as in __page_frag_cache_drain() - > > send the being freed page to PCP if it's an order-0 page, or > > directly to Buddy if it is a high order page. > > > > With this change, Paweł hasn't noticed lock contention yet in > > his workload and Jesper has noticed a 7% performance improvement > > using a micro benchmark and lock contention is gone. Ilias' test > > on a 'low' speed 1Gbit interface on an cortex-a53 shows ~11% > > performance boost testing with 64byte packets and __free_pages_ok() > > disappeared from perf top. > > > > [1]: https://www.spinics.net/lists/netdev/msg531362.html > > [2]: https://www.spinics.net/lists/netdev/msg531421.html > > [3]: https://www.spinics.net/lists/netdev/msg531556.html > > > > Reported-by: Paweł Staszewski <pstaszewski@...are.pl> > > Analysed-by: Jesper Dangaard Brouer <brouer@...hat.com> > > Acked-by: Vlastimil Babka <vbabka@...e.cz> > > Acked-by: Mel Gorman <mgorman@...hsingularity.net> > > Acked-by: Jesper Dangaard Brouer <brouer@...hat.com> > > Acked-by: Ilias Apalodimas <ilias.apalodimas@...aro.org> > > Tested-by: Ilias Apalodimas <ilias.apalodimas@...aro.org> > > Acked-by: Alexander Duyck <alexander.h.duyck@...ux.intel.com> > > Acked-by: Tariq Toukan <tariqt@...lanox.com > > missing '>' sign in my email tag. Sorry about that, will fix this and resend. > > Signed-off-by: Aaron Lu <aaron.lu@...el.com> > > ---
Powered by blists - more mailing lists