qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Zhong Yang <yang.zhong@intel.com>
To: Stefan Hajnoczi <stefanha@redhat.com>
Cc: qemu-devel@nongnu.org, pbonzini@redhat.com, anthony.xu@intel.com,
	stone.xulei@huawei.com, arei.gonglei@huawei.com,
	wangxinxin.wang@huawei.com, weidong.huang@huawei.com,
	zhang.zhanghailiang@huawei.com, liujunjie23@huawei.com,
	yang.zhong@intel.com
Subject: Re: [Qemu-devel] [PATCH] rcu: reduce half heap memory size by malloc_trim()
Date: Mon, 20 Nov 2017 16:41:41 +0800	[thread overview]
Message-ID: <20171120084141.GA6622@yangzhon-Virtual> (raw)
In-Reply-To: <20171117135409.GA3669@stefanha-x1.localdomain>

On Fri, Nov 17, 2017 at 01:54:09PM +0000, Stefan Hajnoczi wrote:
> On Fri, Nov 17, 2017 at 02:23:34PM +0800, Yang Zhong wrote:
> > diff --git a/util/rcu.c b/util/rcu.c
> > index ca5a63e..8d491a6 100644
> > --- a/util/rcu.c
> > +++ b/util/rcu.c
> > @@ -26,6 +26,7 @@
> >   * IBM's contributions to this file may be relicensed under LGPLv2 or later.
> >   */
> >  
> > +#include <malloc.h>
> 
> This header file is not mentioned in the C99 standard or POSIX.  It is
> probably not available on all host OSes that QEMU supports.  Please use
> #ifdef CONFIG_LINUX.
> 
  Hello Stefan,

  Thanks for your remind! 
  
  Regards,

  Yang 
> >  #include "qemu/osdep.h"
> >  #include "qemu-common.h"
> >  #include "qemu/rcu.h"
> > @@ -272,6 +273,9 @@ static void *call_rcu_thread(void *opaque)
> >              node->func(node);
> >          }
> >          qemu_mutex_unlock_iothread();
> > +#ifdef CONFIG_LINUX
> > +        malloc_trim(0);
> > +#endif
> 
> It is important that the rcu thread isn't overzealous in minimizing heap
> size if that means ordinary malloc(3) calls will experience latency
> spikes.  Please leave a few MB free so that malloc(3) doesn't take the
> slow path.
> 
  Hello Stefan,

  From the Qemu bootup procedure, the qemu malloc chunk memory from OS, not
  from glibc free list which is freed before by Qemu. Maybe there are some 
  issues in glibc memory mechanism. I will continue to fine this parameter
  to get better balance, Many thanks!

  Regards,

  Yang 

> Stefan

  parent reply	other threads:[~2017-11-20  8:42 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-11-17  6:23 [Qemu-devel] [PATCH] rcu: reduce half heap memory size by malloc_trim() Yang Zhong
2017-11-17 13:54 ` Stefan Hajnoczi
2017-11-17 14:06   ` Daniel P. Berrange
2017-11-20  8:54     ` Zhong Yang
2017-11-20 14:14       ` Daniel P. Berrange
2017-11-21  5:46         ` Zhong Yang
2017-11-20  8:41   ` Zhong Yang [this message]
2017-11-20 14:03     ` Stefan Hajnoczi
2017-11-21  3:20       ` Zhong Yang
2017-11-20 14:28 ` Fam Zheng
2017-11-21  3:12   ` Zhong Yang

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=20171120084141.GA6622@yangzhon-Virtual \
    --to=yang.zhong@intel.com \
    --cc=anthony.xu@intel.com \
    --cc=arei.gonglei@huawei.com \
    --cc=liujunjie23@huawei.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=stefanha@redhat.com \
    --cc=stone.xulei@huawei.com \
    --cc=wangxinxin.wang@huawei.com \
    --cc=weidong.huang@huawei.com \
    --cc=zhang.zhanghailiang@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).