Re: [PATCH 0/2] xen/mm: Optimize init_heap_pages()

[Julien Grall <julien@xxxxxxx>]

On 09/06/2022 09:30, Julien Grall wrote:
> From: Julien Grall <jgrall@xxxxxxxxxx>
>
> Hi all,
>
> As part of the Live-Update work, we noticed that a big part Xen boot
> is spent to add pages in the heap. For instance, on when running Xen
> in a nested envionment on a c5.metal, it takes ~1.5s.
On IRC, Bertrand asked me how I measured the time taken here. I will 
share on xen-devel so everyone can use it. Note the patch is x86 
specific, but could be easily adapted for Arm.
diff --git a/xen/arch/x86/setup.c b/xen/arch/x86/setup.c
index 53a73010e029..d99b9f3abf5e 100644
--- a/xen/arch/x86/setup.c
+++ b/xen/arch/x86/setup.c
@@ -615,10 +615,16 @@ static inline bool using_2M_mapping(void)
            !l1_table_offset((unsigned long)__2M_rwdata_end);
 }

+extern uint64_t myticks;
+
 static void noreturn init_done(void)
 {
     void *va;
     unsigned long start, end;
+    uint64_t elapsed = tsc_ticks2ns(myticks);
+
+    printk("elapsed %lu ms %lu ns\n", elapsed / MILLISECS(1),
+           elapsed % MILLISECS(1));

     system_state = SYS_STATE_active;

diff --git a/xen/common/page_alloc.c b/xen/common/page_alloc.c
index ea59cd1a4aba..3e6504283f1e 100644
--- a/xen/common/page_alloc.c
+++ b/xen/common/page_alloc.c
@@ -1865,9 +1865,12 @@ static unsigned long avail_heap_pages(
     return free_pages;
 }

+uint64_t myticks;
+
 void __init end_boot_allocator(void)
 {
     unsigned int i;
+    uint64_t stsc = rdtsc_ordered();

     /* Pages that are free now go to the domain sub-allocator. */
     for ( i = 0; i < nr_bootmem_regions; i++ )
@@ -1892,6 +1895,8 @@ void __init end_boot_allocator(void)
     if ( !dma_bitsize && (num_online_nodes() > 1) )
         dma_bitsize = arch_get_dma_bitsize();

+    myticks = rdtsc_ordered() - stsc;
+
     printk("Domain heap initialised");
     if ( dma_bitsize )
         printk(" DMA width %u bits", dma_bitsize);

Cheers,

--
Julien Grall