similar to: [Xen-ia64-devel] RE: RE: Linux PG_arch_1 conflict

>From: Isaku Yamahata >Sent: 2006年3月14日 12:43 >> > >> >What do you think of the followings? Too hacky? >> > >> > >> >extern struct address_space xen_ia64_foreign_dummy_mapping; >> >#define PageForeign(page) \ >> > (page->mapping == &xen_ia64_foreign_dummy_mapping) >> > >> >#define SetPageForeign(page,

> http://lists.xensource.com/archives/html/xen-devel/2005-12/msg00238.html > > > > > > The issue is that PG_arch_1 is reserved for arch-specific > > usage, the paravirtualization changes for Xenlinux utilize > > it (to mark foreign pages) because it was otherwise unused > > in Linux/x86. But Xen is no longer an arch. > > > > Grep''ing

Xenlinux uses a special architecture-dependent bit in the page table, called PG_arch_1 to indicate that a page is "foreign" (PG_foreign). It also apparently uses it to determine if a page is pinned (PG_pinned). Linux/ia64 (and apparently Linux/ppc and Linux/ppc64) use the PG_arch_1 bit for other purposes. On Linux/ia64, it is used to determine if the instruction cache needs to be

While, as discussed, the performance impact of this option is certainly higher than on native Linux, the option should not be entirely disallowed if people want to sacrifice performance for less lowmem pressure. Signed-off-by: Jan Beulich <jbeulich@novell.com> Index: sle10-sp1-2007-01-10/arch/i386/Kconfig =================================================================== ---

On 2016/3/15 14:51, Minchan Kim wrote: > On Tue, Mar 15, 2016 at 03:40:53PM +0900, Sergey Senozhatsky wrote: >> On (03/11/16 16:30), Minchan Kim wrote: >>> -static void *location_to_obj(struct page *page, unsigned long obj_idx) >>> +static void objidx_to_page_and_ofs(struct size_class *class, >>> + struct page *first_page, >>> + unsigned long

On 2016/3/15 14:51, Minchan Kim wrote: > On Tue, Mar 15, 2016 at 03:40:53PM +0900, Sergey Senozhatsky wrote: >> On (03/11/16 16:30), Minchan Kim wrote: >>> -static void *location_to_obj(struct page *page, unsigned long obj_idx) >>> +static void objidx_to_page_and_ofs(struct size_class *class, >>> + struct page *first_page, >>> + unsigned long

On (03/11/16 16:30), Minchan Kim wrote: > -static void *location_to_obj(struct page *page, unsigned long obj_idx) > +static void objidx_to_page_and_ofs(struct size_class *class, > + struct page *first_page, > + unsigned long obj_idx, > + struct page **obj_page, > + unsigned long *ofs_in_page) this looks big; 5 params, function "returning" both page and

On (03/11/16 16:30), Minchan Kim wrote: > -static void *location_to_obj(struct page *page, unsigned long obj_idx) > +static void objidx_to_page_and_ofs(struct size_class *class, > + struct page *first_page, > + unsigned long obj_idx, > + struct page **obj_page, > + unsigned long *ofs_in_page) this looks big; 5 params, function "returning" both page and

After way to many months here is the fifth version of the guest page hinting patches. Compared to version four a few improvements have been added: - Avoid page_host_discards() calls outside of page-states.h - The discard list is now implemented via the page_free_discarded hook and architecture specific code. - PG_state_change page flag has been replaced with architecture specficic

After way to many months here is the fifth version of the guest page hinting patches. Compared to version four a few improvements have been added: - Avoid page_host_discards() calls outside of page-states.h - The discard list is now implemented via the page_free_discarded hook and architecture specific code. - PG_state_change page flag has been replaced with architecture specficic

Greetings, after Carsten pitched CMM2 on the kvm mini summit here is a repost of version 5 of the guest page hinting patches. The code is still the same but has been adapted to the latest git level. -- blue skies, Martin. "Reality continues to ruin my life." - Calvin.

Greetings, after Carsten pitched CMM2 on the kvm mini summit here is a repost of version 5 of the guest page hinting patches. The code is still the same but has been adapted to the latest git level. -- blue skies, Martin. "Reality continues to ruin my life." - Calvin.

On 11/13/2013 06:21 AM, Michael Dalton wrote: > Commit 2613af0ed18a ("virtio_net: migrate mergeable rx buffers to page frag > allocators") changed the mergeable receive buffer size from PAGE_SIZE to > MTU-size, introducing a single-stream regression for benchmarks with large > average packet size. There is no single optimal buffer size for all workloads. > For workloads

On 11/13/2013 06:21 AM, Michael Dalton wrote: > Commit 2613af0ed18a ("virtio_net: migrate mergeable rx buffers to page frag > allocators") changed the mergeable receive buffer size from PAGE_SIZE to > MTU-size, introducing a single-stream regression for benchmarks with large > average packet size. There is no single optimal buffer size for all workloads. > For workloads

Recently, I got many reports about perfermance degradation in embedded system(Android mobile phone, webOS TV and so on) and failed to fork easily. The problem was fragmentation caused by zram and GPU driver pages. Their pages cannot be migrated so compaction cannot work well, either so reclaimer ends up shrinking all of working set pages. It made system very slow and even to fail to fork easily.

Recently, I got many reports about perfermance degradation in embedded system(Android mobile phone, webOS TV and so on) and failed to fork easily. The problem was fragmentation caused by zram and GPU driver pages. Their pages cannot be migrated so compaction cannot work well, either so reclaimer ends up shrinking all of working set pages. It made system very slow and even to fail to fork easily.

Recently, I got many reports about perfermance degradation in embedded system(Android mobile phone, webOS TV and so on) and failed to fork easily. The problem was fragmentation caused by zram and GPU driver pages. Their pages cannot be migrated so compaction cannot work well, either so reclaimer ends up shrinking all of working set pages. It made system very slow and even to fail to fork easily.

Recently, I got many reports about perfermance degradation in embedded system(Android mobile phone, webOS TV and so on) and failed to fork easily. The problem was fragmentation caused by zram and GPU driver pages. Their pages cannot be migrated so compaction cannot work well, either so reclaimer ends up shrinking all of working set pages. It made system very slow and even to fail to fork easily.

This patch is cleaned up of the patch which was sent as http://lists.xensource.com/archives/html/xen-devel/2007-06/msg00324.html # HG changeset patch # User yamahata@valinux.co.jp # Date 1181545986 -32400 # Node ID 69e2dd4e06c405a92717c5f1818f5096e1dc0bcd # Parent d5e0eb7dd069c0ffc1854da81aa143ccfb0ad66e make dma address conversion logic of gnttab dma arch specific. gnttab_dma_map_page() and

skb_page_frag_refill currently permits only order-0 page allocs unless GFP_WAIT is used. Change skb_page_frag_refill to attempt higher-order page allocations whether or not GFP_WAIT is used. If memory cannot be allocated, the allocator will fall back to successively smaller page allocs (down to order-0 page allocs). This change brings skb_page_frag_refill in line with the existing page allocation