Re: [PATCH] net: use __GFP_NORETRY for high order allocations

2014-02-25 Thread David Miller
From: ebied...@xmission.com (Eric W. Biederman) Date: Fri, 07 Feb 2014 16:22:56 -0800 > David Miller writes: > >> From: Eric Dumazet >> Date: Thu, 06 Feb 2014 10:42:42 -0800 >> >>> From: Eric Dumazet >>> >>> sock_alloc_send_pskb() & sk_page_frag_refill() >>> have a loop trying high order allo

Re: [PATCH] net: use __GFP_NORETRY for high order allocations

2014-02-07 Thread Eric W. Biederman
David Miller writes: > From: Eric Dumazet > Date: Thu, 06 Feb 2014 10:42:42 -0800 > >> From: Eric Dumazet >> >> sock_alloc_send_pskb() & sk_page_frag_refill() >> have a loop trying high order allocations to prepare >> skb with low number of fragments as this increases performance. >> >> Probl

Re: [PATCH] net: use __GFP_NORETRY for high order allocations

2014-02-06 Thread David Miller
From: Eric Dumazet Date: Thu, 06 Feb 2014 10:42:42 -0800 > From: Eric Dumazet > > sock_alloc_send_pskb() & sk_page_frag_refill() > have a loop trying high order allocations to prepare > skb with low number of fragments as this increases performance. > > Problem is that under memory pressure/fr

Re: [PATCH] net: use __GFP_NORETRY for high order allocations

2014-02-06 Thread Eric W. Biederman
Eric Dumazet writes: > From: Eric Dumazet > > sock_alloc_send_pskb() & sk_page_frag_refill() > have a loop trying high order allocations to prepare > skb with low number of fragments as this increases performance. > > Problem is that under memory pressure/fragmentation, this can > trigger OOM wh

Re: [PATCH] net: use __GFP_NORETRY for high order allocations

2014-02-06 Thread Eric Dumazet
On Thu, 2014-02-06 at 18:03 -0800, Eric W. Biederman wrote: > Eric Dumazet writes: > > > From: Eric Dumazet > > > > sock_alloc_send_pskb() & sk_page_frag_refill() > > have a loop trying high order allocations to prepare > > skb with low number of fragments as this increases performance. > > > >

Re: [PATCH] net: use __GFP_NORETRY for high order allocations

2014-02-06 Thread David Rientjes
On Thu, 6 Feb 2014, Joe Perches wrote: > > If they absolutely require local memory to > > currnet's cpu node then that would make sense, > > I presumed THISNODE would be used only with NORETRY > Unfortunately, that would avoid attempting to defragment or reclaim remotely for the order-3 alloc

Re: [PATCH] net: use __GFP_NORETRY for high order allocations

2014-02-06 Thread Joe Perches
On Thu, 2014-02-06 at 13:03 -0800, David Rientjes wrote: > On Thu, 6 Feb 2014, Joe Perches wrote: > > > On Thu, 2014-02-06 at 10:42 -0800, Eric Dumazet wrote: > > > sock_alloc_send_pskb() & sk_page_frag_refill() > > > have a loop trying high order allocations to prepare > > > skb with low number o

Re: [PATCH] net: use __GFP_NORETRY for high order allocations

2014-02-06 Thread David Rientjes
On Thu, 6 Feb 2014, Joe Perches wrote: > On Thu, 2014-02-06 at 10:42 -0800, Eric Dumazet wrote: > > sock_alloc_send_pskb() & sk_page_frag_refill() > > have a loop trying high order allocations to prepare > > skb with low number of fragments as this increases performance. > > > > Problem is that u

Re: [PATCH] net: use __GFP_NORETRY for high order allocations

2014-02-06 Thread Eric Dumazet
On Thu, 2014-02-06 at 12:24 -0800, Joe Perches wrote: > Perhaps add __GFP_THISNODE too ? Why ? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Ple

Re: [PATCH] net: use __GFP_NORETRY for high order allocations

2014-02-06 Thread Joe Perches
On Thu, 2014-02-06 at 10:42 -0800, Eric Dumazet wrote: > sock_alloc_send_pskb() & sk_page_frag_refill() > have a loop trying high order allocations to prepare > skb with low number of fragments as this increases performance. > > Problem is that under memory pressure/fragmentation, this can > trigg

[PATCH] net: use __GFP_NORETRY for high order allocations

2014-02-06 Thread Eric Dumazet
From: Eric Dumazet sock_alloc_send_pskb() & sk_page_frag_refill() have a loop trying high order allocations to prepare skb with low number of fragments as this increases performance. Problem is that under memory pressure/fragmentation, this can trigger OOM while the intent was only to try the hi