From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stefano Stabellini Subject: Re: freemem-slack and large memory environments Date: Fri, 27 Feb 2015 10:52:59 +0000 Message-ID: References: <4321015.nah3j6dvJq@mlatimer1.dnsdhcp.provo.novell.com> <2100847.1PzneRuFSU@mlatimer1.dnsdhcp.provo.novell.com> <1424966274.14641.89.camel@citrix.com> <4455263.R3RfNP62EE@mlatimer1.dnsdhcp.provo.novell.com> <54F037E70200007800064704@mail.emea.novell.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <54F037E70200007800064704@mail.emea.novell.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Jan Beulich Cc: wei.liu2@citrix.com, Ian Campbell , Stefano Stabellini , ian.jackson@eu.citrix.com, xen-devel@lists.xen.org, Mike Latimer List-Id: xen-devel@lists.xenproject.org On Fri, 27 Feb 2015, Jan Beulich wrote: > >>> On 26.02.15 at 18:53, wrote: > > Or maybe we just need to change the libxl_set_memory_target call to use > > an absolute memory target to avoid restricting dom0 memory more than > > necessary at each iteration. Also increasing the timeout argument passed > > to the libxl_wait_for_free_memory call could help. > > Wouldn't that lead to problems with multiple racing invocations of > that function (perhaps from different processes)? (Note that I ask > this without knowledge on whether libxl already suitably serializes > things.) Calls to freemem are serialized using a lockfile.