qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
To: ???? <chenliang0016@icloud.com>
Cc: ChenLiang <chenliang88@huawei.com>,
	arei.gonglei@huawei.com, weidong.huang@huawei.com,
	qemu-devel@nongnu.org, pbonzini@redhat.com
Subject: Re: [Qemu-devel] [PATCH v4 5/8] XBZRLE: optimize XBZRLE to decrease the cache misses
Date: Thu, 3 Apr 2014 15:40:02 +0100	[thread overview]
Message-ID: <20140403144002.GD2658@work-vm> (raw)
In-Reply-To: <EE258159-E730-4165-848C-3C1315474CFF@icloud.com>

* ???? (chenliang0016@icloud.com) wrote:

<snip>

> Hi Dave, is it ok? 
> 
> -    if (it->it_data &&
> +    if (it->it_data && it->it_addr != addr &&
>         it->it_age + CACHED_PAGE_LIFETIME > current_age) {
> 

I've not had a chance to retry it yet; did you try google stressapptest on it?

Dave

> ChenLiang
> >> +        return -1;
> >> +    }
> >>     /* allocate page */
> >>     if (!it->it_data) {
> >>         it->it_data = g_try_malloc(cache->page_size);
> >> @@ -173,7 +188,7 @@ int cache_insert(PageCache *cache, uint64_t addr, const uint8_t *pdata)
> >> 
> >>     memcpy(it->it_data, pdata, cache->page_size);
> >> 
> >> -    it->it_age = ++cache->max_item_age;
> >> +    it->it_age = current_age;
> >>     it->it_addr = addr;
> >> 
> >>     return 0;
> >> -- 
> >> 1.7.12.4
> >> 
> >> 
> >> 
> > --
> > Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK
> > 
> 
--
Dr. David Alan Gilbert / dgilbert@redhat.com / Manchester, UK

  reply	other threads:[~2014-04-03 15:26 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-03-27  3:18 [Qemu-devel] [PATCH v4 0/8] migration: Optimizate the xbzrle and fix one corruption issue arei.gonglei
2014-03-27  3:18 ` [Qemu-devel] [PATCH v4 1/8] XBZRLE: Fix one XBZRLE corruption issues arei.gonglei
2014-03-27  3:26   ` [Qemu-devel] for 2.0? " Eric Blake
2014-03-27  3:45     ` Gonglei (Arei)
2014-03-27 12:31       ` Paolo Bonzini
2014-03-27  3:18 ` [Qemu-devel] [PATCH v4 2/8] migration: Add counts of updating the dirty bitmap arei.gonglei
2014-03-27  3:18 ` [Qemu-devel] [PATCH v4 3/8] migration: expose the bitmap_sync_count to the end user arei.gonglei
2014-03-27  3:27   ` Eric Blake
2014-03-27  3:18 ` [Qemu-devel] [PATCH v4 4/8] migration: expose xbzrle cache miss rate arei.gonglei
2014-03-27  3:28   ` Eric Blake
2014-03-27  3:18 ` [Qemu-devel] [PATCH v4 5/8] XBZRLE: optimize XBZRLE to decrease the cache misses arei.gonglei
2014-04-01 16:47   ` Dr. David Alan Gilbert
2014-04-02  9:01     ` Gonglei (Arei)
2014-04-03 14:37     ` 陈梁
2014-04-03 14:40       ` Dr. David Alan Gilbert [this message]
2014-04-03 15:36         ` 陈梁
2014-03-27  3:18 ` [Qemu-devel] [PATCH v4 6/8] XBZRLE: rebuild the cache_is_cached function arei.gonglei
2014-03-27  3:18 ` [Qemu-devel] [PATCH v4 7/8] migration: optimize xbzrle by reducing data copy arei.gonglei
2014-03-28 19:59   ` Dr. David Alan Gilbert
2014-03-29  7:51     ` Gonglei (Arei)
2014-03-27  3:18 ` [Qemu-devel] [PATCH v4 8/8] migration: clear the dead code arei.gonglei

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=20140403144002.GD2658@work-vm \
    --to=dgilbert@redhat.com \
    --cc=arei.gonglei@huawei.com \
    --cc=chenliang0016@icloud.com \
    --cc=chenliang88@huawei.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=weidong.huang@huawei.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).