qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Peter Lieven <pl@kamp.de>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>,
	"qemu-ppc@nongnu.org" <qemu-ppc@nongnu.org>,
	"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
	David Gibson <david@gibson.dropbear.id.au>
Subject: Re: [Qemu-devel] broken incoming migration
Date: Tue, 04 Jun 2013 17:10:18 +0200	[thread overview]
Message-ID: <51AE035A.5070301@kamp.de> (raw)
In-Reply-To: <51ADFC7A.7030009@redhat.com>

On 04.06.2013 16:40, Paolo Bonzini wrote:
> Il 04/06/2013 16:38, Peter Lieven ha scritto:
>> On 04.06.2013 16:14, Paolo Bonzini wrote:
>>> Il 04/06/2013 15:52, Peter Lieven ha scritto:
>>>> On 30.05.2013 16:41, Paolo Bonzini wrote:
>>>>> Il 30/05/2013 16:38, Peter Lieven ha scritto:
>>>>>>>> You could also scan the page for nonzero values before writing it.
>>>>>> i had this in mind, but then choosed the other approach.... turned
>>>>>> out to be a bad idea.
>>>>>>
>>>>>> alexey: i will prepare a patch later today, could you then please
>>>>>> verify it fixes your problem.
>>>>>>
>>>>>> paolo: would we still need the madvise or is it enough to not write
>>>>>> the zeroes?
>>>>> It should be enough to not write them.
>>>> Problem: checking the pages for zero allocates them. even at the source.
>>> It doesn't look like.  I tried this program and top doesn't show an
>>> increasing amount of reserved memory:
>>>
>>> #include <stdio.h>
>>> #include <stdlib.h>
>>> int main()
>>> {
>>>       char *x = malloc(500 << 20);
>>>       int i, j;
>>>       for (i = 0; i < 500; i += 10) {
>>>           for (j = 0; j < 10 << 20; j += 4096) {
>>>                *(volatile char*) (x + (i << 20) + j);
>>>           }
>>>           getchar();
>>>       }
>>> }
>> strange. we are talking about RSS size, right?
> None of the three top values change, and only VIRT is >500 MB.
>
>> is the malloc above using mmapped memory?
> Yes.
>
>> which kernel version do you use?
> 3.9.
>
>> what avoids allocating the memory for me is the following (with
>> whatever side effects it has ;-))
> This would also fail to migrate any page that is swapped out, breaking
> overcommit in a more subtle way. :)
>
> Paolo
the following does also not allocate memory, but qemu does...

#include <stdio.h>
#include <stdlib.h>
#include <assert.h>
#include <unistd.h>
#include <sys/resource.h>
#include <inttypes.h>
#include <string.h>
#include <sys/mman.h>
#include <errno.h>

#if defined __SSE2__
#include <emmintrin.h>
#define VECTYPE        __m128i
#define SPLAT(p)       _mm_set1_epi8(*(p))
#define ALL_EQ(v1, v2) (_mm_movemask_epi8(_mm_cmpeq_epi8(v1, v2)) == 0xFFFF)
#else
#define VECTYPE        unsigned long
#define SPLAT(p)       (*(p) * (~0UL / 255))
#define ALL_EQ(v1, v2) ((v1) == (v2))
#endif

#define BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR 8

/* Round number down to multiple */
#define QEMU_ALIGN_DOWN(n, m) ((n) / (m) * (m))

/* Round number up to multiple */
#define QEMU_ALIGN_UP(n, m) QEMU_ALIGN_DOWN((n) + (m) - 1, (m))

#define QEMU_VMALLOC_ALIGN (256 * 4096)

/* alloc shared memory pages */
void *qemu_anon_ram_alloc(size_t size)
{
     size_t align = QEMU_VMALLOC_ALIGN;
     size_t total = size + align - getpagesize();
     void *ptr = mmap(0, total, PROT_READ | PROT_WRITE,
                      MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
     size_t offset = QEMU_ALIGN_UP((uintptr_t)ptr, align) - (uintptr_t)ptr;

     if (ptr == MAP_FAILED) {
         fprintf(stderr, "Failed to allocate %zu B: %s\n",
                 size, strerror(errno));
         abort();
     }

     ptr += offset;
     total -= offset;

     if (offset > 0) {
         munmap(ptr - offset, offset);
     }
     if (total > size) {
         munmap(ptr + size, total - size);
     }

     return ptr;
}

static inline int
can_use_buffer_find_nonzero_offset(const void *buf, size_t len)
{
     return (len % (BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR
                    * sizeof(VECTYPE)) == 0
             && ((uintptr_t) buf) % sizeof(VECTYPE) == 0);
}

size_t buffer_find_nonzero_offset(const void *buf, size_t len)
{
     const VECTYPE *p = buf;
     const VECTYPE zero = (VECTYPE){0};
     size_t i;

     if (!len) {
         return 0;
     }

     assert(can_use_buffer_find_nonzero_offset(buf, len));

     for (i = 0; i < BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR; i++) {
         if (!ALL_EQ(p[i], zero)) {
             return i * sizeof(VECTYPE);
         }
     }

     for (i = BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR;
          i < len / sizeof(VECTYPE);
          i += BUFFER_FIND_NONZERO_OFFSET_UNROLL_FACTOR) {
         VECTYPE tmp0 = p[i + 0] | p[i + 1];
         VECTYPE tmp1 = p[i + 2] | p[i + 3];
         VECTYPE tmp2 = p[i + 4] | p[i + 5];
         VECTYPE tmp3 = p[i + 6] | p[i + 7];
         VECTYPE tmp01 = tmp0 | tmp1;
         VECTYPE tmp23 = tmp2 | tmp3;
         if (!ALL_EQ(tmp01 | tmp23, zero)) {
             break;
         }
     }

     return i * sizeof(VECTYPE);
}

int main()
{
      //char *x = malloc(1024 << 20);
      char *x = qemu_anon_ram_alloc(1024 << 20);

      int i, j;
      int ret = 0;
      struct rusage rusage;
      for (i = 0; i < 500; i ++) {
          for (j = 0; j < 10 << 20; j += 4096) {
               ret += buffer_find_nonzero_offset((char*) (x + (i << 20) + j), 4096);
          }
          getrusage( RUSAGE_SELF, &rusage );
          printf("read offset: %d kB, RSS size: %ld kB", ((i+1) << 10), rusage.ru_maxrss);
          getchar();
      }
      printf("%d zero pages\n", ret);
}

  parent reply	other threads:[~2013-06-04 15:10 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-05-30  7:44 [Qemu-devel] broken incoming migration Alexey Kardashevskiy
2013-05-30  7:49 ` Alexey Kardashevskiy
2013-05-30  7:49 ` Paolo Bonzini
2013-05-30  8:18   ` Alexey Kardashevskiy
2013-05-30  9:08     ` Peter Lieven
2013-05-30  9:31       ` Alexey Kardashevskiy
2013-05-30 13:00       ` Paolo Bonzini
2013-05-30 13:38         ` Alexey Kardashevskiy
2013-05-30 14:08           ` Paolo Bonzini
2013-05-30 14:38         ` Peter Lieven
2013-05-30 14:41           ` Paolo Bonzini
2013-06-04 13:52             ` Peter Lieven
2013-06-04 14:14               ` Paolo Bonzini
2013-06-04 14:38                 ` Peter Lieven
2013-06-04 14:40                   ` Paolo Bonzini
2013-06-04 14:48                     ` Peter Lieven
2013-06-04 15:17                       ` Paolo Bonzini
2013-06-04 19:15                         ` Peter Lieven
2013-06-05  3:37                           ` Alexey Kardashevskiy
2013-06-05  6:09                             ` Peter Lieven
2013-06-09  4:12                               ` liu ping fan
2013-06-09  7:22                                 ` Peter Lieven
2013-06-04 15:10                     ` Peter Lieven [this message]
2013-06-08  8:27                       ` Wenchao Xia
2013-06-08  8:30                         ` Alexey Kardashevskiy
2013-06-09  2:16                           ` Wenchao Xia
2013-06-09  2:34                             ` Alexey Kardashevskiy
2013-06-09  2:52                               ` [Qemu-devel] [Qemu-ppc] " Benjamin Herrenschmidt
2013-06-09  3:01                                 ` Alexey Kardashevskiy
2013-06-09  3:01                               ` [Qemu-devel] " Wenchao Xia
2013-06-09  3:09                                 ` Alexey Kardashevskiy
2013-06-09  3:31                                   ` Wenchao Xia
2013-06-09  7:27                                   ` Peter Lieven
2013-06-10  6:39                                     ` Alexey Kardashevskiy
2013-06-10  6:50                                       ` Peter Lieven
2013-06-10  6:55                                         ` Alexey Kardashevskiy
2013-06-10  8:44                                           ` Peter Lieven
2013-06-10  9:10                                             ` Alexey Kardashevskiy
2013-06-10  9:33                                               ` [Qemu-devel] [Qemu-ppc] " Benjamin Herrenschmidt
2013-06-10  9:42                                                 ` Peter Lieven
2013-06-09  2:53                             ` Benjamin Herrenschmidt
2013-06-12 14:00                               ` Paolo Bonzini
2013-06-12 14:11                                 ` Benjamin Herrenschmidt
2013-06-12 20:10                                   ` Paolo Bonzini
2013-06-13  2:41                                     ` Wenchao Xia
2013-06-03 10:04           ` [Qemu-devel] " Alexey Kardashevskiy
2013-06-04 10:56             ` Peter Lieven
2013-06-08  8:24         ` Wenchao Xia
2013-05-30 10:18 ` Peter Maydell

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=51AE035A.5070301@kamp.de \
    --to=pl@kamp.de \
    --cc=aik@ozlabs.ru \
    --cc=david@gibson.dropbear.id.au \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-ppc@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).