qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Peter Lieven <pl@kamp.de>
To: qemu-devel@nongnu.org
Cc: quintela@redhat.com, Stefan Hajnoczi <stefanha@gmail.com>,
	Peter Lieven <pl@kamp.de>, Orit Wasserman <owasserm@redhat.com>,
	Paolo Bonzini <pbonzini@redhat.com>
Subject: [Qemu-devel] [PATCHv4 5/9] migration: search for zero instead of dup pages
Date: Fri, 22 Mar 2013 13:46:06 +0100	[thread overview]
Message-ID: <1363956370-23681-6-git-send-email-pl@kamp.de> (raw)
In-Reply-To: <1363956370-23681-1-git-send-email-pl@kamp.de>

virtually all dup pages are zero pages. remove
the special is_dup_page() function and use the
optimized buffer_find_nonzero_offset() function
instead.

here buffer_find_nonzero_offset() is used directly
to avoid the unnecssary additional checks in
buffer_is_zero().

raw performace gain checking zeroed memory
over is_dup_page() is approx. 15-20% with SSE2.

Signed-off-by: Peter Lieven <pl@kamp.de>
---
 arch_init.c |   21 ++++++---------------
 1 file changed, 6 insertions(+), 15 deletions(-)

diff --git a/arch_init.c b/arch_init.c
index 1b71912..9ebca83 100644
--- a/arch_init.c
+++ b/arch_init.c
@@ -144,19 +144,10 @@ int qemu_read_default_config_files(bool userconfig)
     return 0;
 }
 
-static int is_dup_page(uint8_t *page)
+static inline bool is_zero_page(uint8_t *p)
 {
-    VECTYPE *p = (VECTYPE *)page;
-    VECTYPE val = SPLAT(page);
-    int i;
-
-    for (i = 0; i < TARGET_PAGE_SIZE / sizeof(VECTYPE); i++) {
-        if (!ALL_EQ(val, p[i])) {
-            return 0;
-        }
-    }
-
-    return 1;
+    return buffer_find_nonzero_offset(p, TARGET_PAGE_SIZE) ==
+        TARGET_PAGE_SIZE;
 }
 
 /* struct contains XBZRLE cache and a static page
@@ -443,12 +434,12 @@ static int ram_save_block(QEMUFile *f, bool last_stage)
 
             /* In doubt sent page as normal */
             bytes_sent = -1;
-            if (is_dup_page(p)) {
+            if (is_zero_page(p)) {
                 acct_info.dup_pages++;
                 bytes_sent = save_block_hdr(f, block, offset, cont,
                                             RAM_SAVE_FLAG_COMPRESS);
-                qemu_put_byte(f, *p);
-                bytes_sent += 1;
+                qemu_put_byte(f, 0);
+                bytes_sent++;
             } else if (migrate_use_xbzrle()) {
                 current_addr = block->offset + offset;
                 bytes_sent = save_xbzrle_page(f, p, current_addr, block,
-- 
1.7.9.5

  parent reply	other threads:[~2013-03-22 12:52 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-03-22 12:46 [Qemu-devel] [PATCHv4 0/9] buffer_is_zero / migration optimizations Peter Lieven
2013-03-22 12:46 ` [Qemu-devel] [PATCHv4 1/9] move vector definitions to qemu-common.h Peter Lieven
2013-03-25  8:35   ` Orit Wasserman
2013-03-22 12:46 ` [Qemu-devel] [PATCHv4 2/9] cutils: add a function to find non-zero content in a buffer Peter Lieven
2013-03-22 19:37   ` Eric Blake
2013-03-22 20:03     ` Peter Lieven
2013-03-22 20:22       ` [Qemu-devel] indentation hints [was: [PATCHv4 2/9] cutils: add a function to find non-zero content in a buffer] Eric Blake
2013-03-23 11:18         ` Peter Maydell
2013-03-25  8:53   ` [Qemu-devel] [PATCHv4 2/9] cutils: add a function to find non-zero content in a buffer Orit Wasserman
2013-03-25  8:56     ` Peter Lieven
2013-03-25  9:26       ` Orit Wasserman
2013-03-25  9:42         ` Paolo Bonzini
2013-03-25 10:03           ` Orit Wasserman
2013-03-22 12:46 ` [Qemu-devel] [PATCHv4 3/9] buffer_is_zero: use vector optimizations if possible Peter Lieven
2013-03-25  8:53   ` Orit Wasserman
2013-03-22 12:46 ` [Qemu-devel] [PATCHv4 4/9] bitops: use vector algorithm to optimize find_next_bit() Peter Lieven
2013-03-25  9:04   ` Orit Wasserman
2013-03-22 12:46 ` Peter Lieven [this message]
2013-03-22 19:49   ` [Qemu-devel] [PATCHv4 5/9] migration: search for zero instead of dup pages Eric Blake
2013-03-22 20:02     ` Peter Lieven
2013-03-25  9:30   ` Orit Wasserman
2013-03-22 12:46 ` [Qemu-devel] [PATCHv4 6/9] migration: add an indicator for bulk state of ram migration Peter Lieven
2013-03-25  9:32   ` Orit Wasserman
2013-03-22 12:46 ` [Qemu-devel] [PATCHv4 7/9] migration: do not sent zero pages in bulk stage Peter Lieven
2013-03-22 20:13   ` Eric Blake
2013-03-25  9:44   ` Orit Wasserman
2013-03-22 12:46 ` [Qemu-devel] [PATCHv4 8/9] migration: do not search dirty " Peter Lieven
2013-03-25 10:05   ` Orit Wasserman
2013-03-22 12:46 ` [Qemu-devel] [PATCHv4 9/9] migration: use XBZRLE only after " Peter Lieven
2013-03-25 10:16   ` Orit Wasserman
2013-03-22 17:25 ` [Qemu-devel] [PATCHv4 0/9] buffer_is_zero / migration optimizations Paolo Bonzini
2013-03-22 19:20   ` Peter Lieven
2013-03-22 21:24     ` Paolo Bonzini
2013-03-23  7:34       ` Peter Lieven
2013-03-25 10:17       ` Peter Lieven
2013-03-25 10:53         ` Paolo Bonzini
2013-03-25 11:26           ` Peter Lieven
2013-03-25 13:02             ` Paolo Bonzini
2013-03-25 13:23               ` Peter Lieven
2013-03-25 13:32                 ` Peter Lieven
2013-03-25 14:34                   ` Paolo Bonzini
2013-03-25 21:37                     ` Peter Lieven
2013-03-26  8:14                     ` Peter Lieven
2013-03-26  9:20                       ` Paolo Bonzini

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=1363956370-23681-6-git-send-email-pl@kamp.de \
    --to=pl@kamp.de \
    --cc=owasserm@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=quintela@redhat.com \
    --cc=stefanha@gmail.com \
    /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).