On Mon, 5 Nov 2018 14:28:36 +0800
Aaron Lu <aaron...@intel.com> wrote:
> On Sat, Nov 03, 2018 at 01:53:25PM +0100, Jesper Dangaard Brouer wrote:
> >
> > On Fri, 2 Nov 2018 22:20:24 +0800 Aaron Lu <aaron...@intel.com> wrote:
> >
> > > On Fri, Nov 02, 2018 at 12:40:37PM +0100, Jesper Dangaard Brouer wrote:
> > > > On Fri, 2 Nov 2018 13:23:56 +0800
> > > > Aaron Lu <aaron...@intel.com> wrote:
> > > >
> > > > > On Thu, Nov 01, 2018 at 08:23:19PM +0000, Saeed Mahameed wrote:
> > > > > > On Thu, 2018-11-01 at 23:27 +0800, Aaron Lu wrote:
> > > > > > > On Thu, Nov 01, 2018 at 10:22:13AM +0100, Jesper Dangaard Brouer
> > > > > > > wrote:
> > > > > > > ... ...
> > > > > > > > Section copied out:
> > > > > > > >
> > > > > > > > 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
> > > > > > > >
> > > > > > >
> > > > > > > This callchain looks like it is freeing higher order pages than
> > > > > > > order
> > > > > > > 0:
> > > > > > > __free_pages_ok is only called for pages whose order are bigger
> > > > > > > than
> > > > > > > 0.
> > > > > >
> > > > > > mlx5 rx uses only order 0 pages, so i don't know where these high
> > > > > > order
> > > > > > tx SKBs are coming from..
> > > > >
> > > > > Perhaps here:
> > > > > __netdev_alloc_skb(), __napi_alloc_skb(), __netdev_alloc_frag() and
> > > > > __napi_alloc_frag() will all call page_frag_alloc(), which will use
> > > > > __page_frag_cache_refill() to get an order 3 page if possible, or fall
> > > > > back to an order 0 page if order 3 page is not available.
> > > > >
> > > > > I'm not sure if your workload will use the above code path though.
> > > >
> > > > TL;DR: this is order-0 pages (code-walk trough proof below)
> > > >
> > > > To Aaron, the network stack *can* call __free_pages_ok() with order-0
> > > > pages, via:
> > > >
> > > > static void skb_free_head(struct sk_buff *skb)
> > > > {
> > > > unsigned char *head = skb->head;
> > > >
> > > > if (skb->head_frag)
> > > > skb_free_frag(head);
> > > > else
> > > > kfree(head);
> > > > }
> > > >
> > > > static inline void skb_free_frag(void *addr)
> > > > {
> > > > page_frag_free(addr);
> > > > }
> > > >
> > > > /*
> > > > * Frees a page fragment allocated out of either a compound or order 0
> > > > page.
> > > > */
> > > > void page_frag_free(void *addr)
> > > > {
> > > > struct page *page = virt_to_head_page(addr);
> > > >
> > > > if (unlikely(put_page_testzero(page)))
> > > > __free_pages_ok(page, compound_order(page));
> > > > }
> > > > EXPORT_SYMBOL(page_frag_free);
> > >
> > > I think here is a problem - order 0 pages are freed directly to buddy,
> > > bypassing per-cpu-pages. This might be the reason lock contention
> > > appeared on free path.
> >
> > OMG - you just found a significant issue with the network stacks
> > interaction with the page allocator! This explains why I could not get
> > the PCP (Per-Cpu-Pages) system to have good performance, in my
> > performance networking benchmarks. As we are basically only using the
> > alloc side of PCP, and not the free side.
>
> Exactly.
>
> > We have spend years adding different driver level recycle tricks to
> > avoid this code path getting activated, exactly because it is rather
> > slow and problematic that we hit this zone->lock.
>
> I can see when this code path is hit, it causes unnecessary taking of
> zone lock for order-0 pages and cause lock contention.
>
> >
> > > Can someone apply below diff and see if lock contention is gone?
> >
> > I have also applied and tested this patch, and yes the lock contention
> > is gone. As mentioned is it rather difficult to hit this code path, as
> > the driver page recycle mechanism tries to hide/avoid it, but mlx5 +
> > page_pool + CPU-map recycling have a known weakness that bypass the
> > driver page recycle scheme (that I've not fixed yet). I observed a 7%
> > speedup for this micro benchmark.
>
> Good to know this, I will prepare a formal patch.
I wonder if this code is still missing something. I was looking at
using put_devmap_managed_page() infrastructure, but I realized that
page_frag_free() is also skipping this code path. I guess, I can add
it later when I show/proof (performance wise) that this is a good idea
(as we currently don't have any users).
> > > diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> > > index e2ef1c17942f..65c0ae13215a 100644
> > > --- a/mm/page_alloc.c
> > > +++ b/mm/page_alloc.c
> > > @@ -4554,8 +4554,14 @@ void page_frag_free(void *addr)
> > > {
> > > struct page *page = virt_to_head_page(addr);
> > >
> > > - if (unlikely(put_page_testzero(page)))
> > > - __free_pages_ok(page, compound_order(page));
> > > + if (unlikely(put_page_testzero(page))) {
> > > + unsigned int order = compound_order(page);
> > > +
> > > + if (order == 0)
> > > + free_unref_page(page);
> > > + else
> > > + __free_pages_ok(page, order);
> > > + }
> > > }
> > > EXPORT_SYMBOL(page_frag_free);
> >
> > Thank you Aaron for spotting this!!!
>
> Which is impossible without your analysis :-)
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
