From: "Jarkko Sakkinen" <jarkko@kernel.org>
To: "Jarkko Sakkinen" <jarkko@kernel.org>,
"Haitao Huang" <haitao.huang@linux.intel.com>,
"Mehta, Sohil" <sohil.mehta@intel.com>,
"x86@kernel.org" <x86@kernel.org>,
"dave.hansen@linux.intel.com" <dave.hansen@linux.intel.com>,
"cgroups@vger.kernel.org" <cgroups@vger.kernel.org>,
"hpa@zytor.com" <hpa@zytor.com>,
"mingo@redhat.com" <mingo@redhat.com>,
"tj@kernel.org" <tj@kernel.org>,
"mkoutny@suse.com" <mkoutny@suse.com>,
"tglx@linutronix.de" <tglx@linutronix.de>,
"linux-sgx@vger.kernel.org" <linux-sgx@vger.kernel.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"bp@alien8.de" <bp@alien8.de>, "Huang, Kai" <kai.huang@intel.com>
Cc: "mikko.ylinen@linux.intel.com" <mikko.ylinen@linux.intel.com>,
"seanjc@google.com" <seanjc@google.com>,
"Zhang, Bo" <zhanb@microsoft.com>,
"kristen@linux.intel.com" <kristen@linux.intel.com>,
"anakrish@microsoft.com" <anakrish@microsoft.com>,
"sean.j.christopherson@intel.com"
<sean.j.christopherson@intel.com>,
"Li, Zhiquan1" <zhiquan1.li@intel.com>,
"yangjie@microsoft.com" <yangjie@microsoft.com>
Subject: Re: [PATCH v6 09/12] x86/sgx: Restructure top-level EPC reclaim function
Date: Sat, 13 Jan 2024 23:08:27 +0200 [thread overview]
Message-ID: <CYDVWF9BY27K.2MXXROH30QHBT@kernel.org> (raw)
In-Reply-To: <CYDVTPABVUJK.1BTJY8YUF9WPI@kernel.org>
On Sat Jan 13, 2024 at 11:04 PM EET, Jarkko Sakkinen wrote:
> On Fri Jan 12, 2024 at 7:07 PM EET, Haitao Huang wrote:
> > On Sun, 17 Dec 2023 19:44:56 -0600, Huang, Kai <kai.huang@intel.com> wrote:
> >
> > >
> > >> >
> > >> > The point is, with or w/o this patch, you can only reclaim 16 EPC
> > >> pages
> > >> > in one
> > >> > function call (as you have said you are going to remove
> > >> > SGX_NR_TO_SCAN_MAX,
> > >> > which is a cipher to both of us). The only difference I can see is,
> > >> > with this
> > >> > patch, you can have multiple calls of "isolate" and then call the
> > >> > "do_reclaim"
> > >> > once.
> > >> >
> > >> > But what's the good of having the "isolate" if the "do_reclaim" can
> > >> only
> > >> > reclaim
> > >> > 16 pages anyway?
> > >> >
> > >> > Back to my last reply, are you afraid of any LRU has less than 16
> > >> pages
> > >> > to
> > >> > "isolate", therefore you need to loop LRUs of descendants to get 16?
> > >> > Cause I
> > >> > really cannot think of any other reason why you are doing this.
> > >> >
> > >> >
> > >>
> > >> I think I see your point. By capping pages reclaimed per cycle to 16,
> > >> there is not much difference even if those 16 pages are spread in
> > >> separate
> > >> LRUs . The difference is only significant when we ever raise that cap.
> > >> To
> > >> preserve the current behavior of ewb loops independent on number of LRUs
> > >> to loop through for each reclaiming cycle, regardless of the exact value
> > >> of the page cap, I would still think current approach in the patch is
> > >> reasonable choice. What do you think?
> > >
> > > To me I won't bother to do that. Having less than 16 pages in one LRU is
> > > *extremely rare* that should never happen in practice. It's pointless
> > > to make
> > > such code adjustment at this stage.
> > >
> > > Let's focus on enabling functionality first. When you have some real
> > > performance issue that is related to this, we can come back then.
> > >
> >
> > I have done some rethinking about this and realize this does save quite
> > some significant work: without breaking out isolation part from
> > sgx_reclaim_pages(), I can remove the changes to use a list for isolated
> > pages, and no need to introduce "state" such as RECLAIM_IN_PROGRESS. About
> > 1/3 of changes for per-cgroup reclamation will be gone.
> >
> > So I think I'll go this route now. The only downside may be performance if
> > a enclave spreads its pages in different cgroups and even that is minimum
> > impact as we limit reclamation to 16 pages a time. Let me know if someone
> > feel strongly we need dealt with that and see some other potential issues
> > I may have missed.
>
> We could deal with possible performance regression later on (if there
> is need). I mean there should we a workload first that would so that
> sort stimulus...
I.e. no reason to deal with imaginary workload :-) Go ahead and we'll
go through it.
BR, Jarkko
next prev parent reply other threads:[~2024-01-13 21:08 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-10-30 18:20 [PATCH v6 00/12] Add Cgroup support for SGX EPC memory Haitao Huang
2023-10-30 18:20 ` [PATCH v6 01/12] cgroup/misc: Add per resource callbacks for CSS events Haitao Huang
2023-11-15 20:25 ` Jarkko Sakkinen
2024-01-09 3:37 ` Haitao Huang
2024-01-10 19:55 ` Jarkko Sakkinen
2024-01-05 9:45 ` Michal Koutný
2024-01-06 1:42 ` Haitao Huang
2023-10-30 18:20 ` [PATCH v6 02/12] cgroup/misc: Export APIs for SGX driver Haitao Huang
2023-10-30 18:20 ` [PATCH v6 03/12] cgroup/misc: Add SGX EPC resource type Haitao Huang
2023-10-30 18:20 ` [PATCH v6 04/12] x86/sgx: Implement basic EPC misc cgroup functionality Haitao Huang
2023-11-06 12:09 ` Huang, Kai
2023-11-06 18:59 ` Haitao Huang
2023-11-06 22:18 ` Huang, Kai
2023-11-07 1:16 ` Haitao Huang
2023-11-07 2:08 ` Haitao Huang
2023-11-07 19:07 ` Huang, Kai
2023-11-20 3:16 ` Huang, Kai
2023-11-26 16:01 ` Haitao Huang
2023-11-26 16:32 ` Haitao Huang
2023-11-06 22:23 ` Huang, Kai
2023-11-15 20:48 ` Jarkko Sakkinen
2023-10-30 18:20 ` [PATCH v6 05/12] x86/sgx: Add sgx_epc_lru_list to encapsulate LRU list Haitao Huang
2023-10-30 18:20 ` [PATCH v6 06/12] x86/sgx: Use sgx_epc_lru_list for existing active page list Haitao Huang
2023-10-30 18:20 ` [PATCH v6 07/12] x86/sgx: Introduce EPC page states Haitao Huang
2023-11-15 20:53 ` Jarkko Sakkinen
2024-01-05 17:57 ` Dave Hansen
2024-01-06 1:45 ` Haitao Huang
2023-10-30 18:20 ` [PATCH v6 08/12] x86/sgx: Use a list to track to-be-reclaimed pages Haitao Huang
2023-11-15 20:59 ` Jarkko Sakkinen
2023-10-30 18:20 ` [PATCH v6 09/12] x86/sgx: Restructure top-level EPC reclaim function Haitao Huang
2023-11-20 3:45 ` Huang, Kai
2023-11-26 16:27 ` Haitao Huang
2023-11-27 9:57 ` Huang, Kai
2023-12-12 4:04 ` Haitao Huang
2023-12-13 11:17 ` Huang, Kai
2023-12-15 19:49 ` Haitao Huang
2023-12-18 1:44 ` Huang, Kai
2023-12-18 17:32 ` Mikko Ylinen
2023-12-18 21:24 ` Haitao Huang
2024-01-03 16:37 ` Dave Hansen
2024-01-04 19:11 ` Haitao Huang
2024-01-04 19:19 ` Jarkko Sakkinen
2024-01-04 19:27 ` Dave Hansen
2024-01-04 21:01 ` Haitao Huang
2024-01-05 14:43 ` Mikko Ylinen
2024-01-04 12:38 ` Michal Koutný
2024-01-04 19:20 ` Haitao Huang
2024-01-12 17:07 ` Haitao Huang
2024-01-13 21:04 ` Jarkko Sakkinen
2024-01-13 21:08 ` Jarkko Sakkinen [this message]
2023-10-30 18:20 ` [PATCH v6 10/12] x86/sgx: Implement EPC reclamation for cgroup Haitao Huang
2023-11-06 15:58 ` [PATCH] x86/sgx: Charge proper mem_cgroup for usage due to EPC reclamation by cgroups Haitao Huang
2023-11-06 16:10 ` [PATCH v6 10/12] x86/sgx: Implement EPC reclamation for cgroup Haitao Huang
2023-10-30 18:20 ` [PATCH v6 11/12] Docs/x86/sgx: Add description for cgroup support Haitao Huang
2023-10-30 18:20 ` [PATCH v6 12/12] selftests/sgx: Add scripts for EPC cgroup testing Haitao Huang
2023-11-15 21:00 ` Jarkko Sakkinen
2023-11-15 21:22 ` Haitao Huang
2023-11-06 3:26 ` [PATCH v6 00/12] Add Cgroup support for SGX EPC memory Jarkko Sakkinen
2023-11-06 15:48 ` Haitao Huang
2023-11-08 1:00 ` Haitao Huang
2024-01-05 18:29 ` Dave Hansen
2024-01-05 20:13 ` Haitao Huang
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=CYDVWF9BY27K.2MXXROH30QHBT@kernel.org \
--to=jarkko@kernel.org \
--cc=anakrish@microsoft.com \
--cc=bp@alien8.de \
--cc=cgroups@vger.kernel.org \
--cc=dave.hansen@linux.intel.com \
--cc=haitao.huang@linux.intel.com \
--cc=hpa@zytor.com \
--cc=kai.huang@intel.com \
--cc=kristen@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-sgx@vger.kernel.org \
--cc=mikko.ylinen@linux.intel.com \
--cc=mingo@redhat.com \
--cc=mkoutny@suse.com \
--cc=sean.j.christopherson@intel.com \
--cc=seanjc@google.com \
--cc=sohil.mehta@intel.com \
--cc=tglx@linutronix.de \
--cc=tj@kernel.org \
--cc=x86@kernel.org \
--cc=yangjie@microsoft.com \
--cc=zhanb@microsoft.com \
--cc=zhiquan1.li@intel.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).