| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAAPL-u_aDgVm0D=0d+hzc0o_f1vV3whHn9fAVW2RAYNz4mqG9A@mail.gmail.com>
Date: Thu, 26 May 2022 13:30:16 -0700
From: Wei Xu <weixugc@...gle.com>
To: Jonathan Cameron <Jonathan.Cameron@...wei.com>
Cc: Aneesh Kumar K V <aneesh.kumar@...ux.ibm.com>,
Ying Huang <ying.huang@...el.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Greg Thelen <gthelen@...gle.com>,
Yang Shi <shy828301@...il.com>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
Jagdish Gediya <jvgediya@...ux.ibm.com>,
Michal Hocko <mhocko@...nel.org>,
Tim C Chen <tim.c.chen@...el.com>,
Dave Hansen <dave.hansen@...el.com>,
Alistair Popple <apopple@...dia.com>,
Baolin Wang <baolin.wang@...ux.alibaba.com>,
Feng Tang <feng.tang@...el.com>,
Davidlohr Bueso <dave@...olabs.net>,
Dan Williams <dan.j.williams@...el.com>,
David Rientjes <rientjes@...gle.com>,
Linux MM <linux-mm@...ck.org>,
Brice Goglin <brice.goglin@...il.com>,
Hesham Almatary <hesham.almatary@...wei.com>
Subject: Re: RFC: Memory Tiering Kernel Interfaces (v2)
On Thu, May 26, 2022 at 2:32 AM Jonathan Cameron
<Jonathan.Cameron@...wei.com> wrote:
>
> On Wed, 25 May 2022 10:27:42 -0700
> Wei Xu <weixugc@...gle.com> wrote:
>
> > On Wed, May 25, 2022 at 3:01 AM Aneesh Kumar K V
> > <aneesh.kumar@...ux.ibm.com> wrote:
> > >
> > > On 5/25/22 2:33 PM, Ying Huang wrote:
> > > > On Tue, 2022-05-24 at 22:32 -0700, Wei Xu wrote:
> > > >> On Tue, May 24, 2022 at 1:24 AM Ying Huang <ying.huang@...el.com> wrote:
> > > >>>
> > > >>> On Tue, 2022-05-24 at 00:04 -0700, Wei Xu wrote:
> > > >>>> On Thu, May 19, 2022 at 8:06 PM Ying Huang <ying.huang@...el.com> wrote:
> > > >>>>>
> > >
> > > ...
> > >
> > > >
> > > > OK. Just to confirm. Does this mean that we will have fixed device ID,
> > > > for example,
> > > >
> > > > GPU memtier255
> > > > DRAM (with CPU) memtier0
> > > > PMEM memtier1
> > > >
> > > > When we add a new memtier, it can be memtier254, or memter2? The rank
> > > > value will determine the real demotion order.
> > > >
> > > > I think you may need to send v3 to make sure everyone is at the same
> > > > page.
> > > >
> > >
> > > What we have implemented which we will send as RFC shortly is below.
> > >
> > > cd /sys/dekvaneesh@...ntu-guest:~$ cd /sys/devices/system/
> > > kvaneesh@...ntu-guest:/sys/devices/system$ pwd
> > > /sys/devices/system
> > > kvaneesh@...ntu-guest:/sys/devices/system$ ls
> > > clockevents clocksource container cpu edac memory memtier mpic
> > > node power
> > > kvaneesh@...ntu-guest:/sys/devices/system$ cd memtier/
> > > kvaneesh@...ntu-guest:/sys/devices/system/memtier$ pwd
> > > /sys/devices/system/memtier
> > > kvaneesh@...ntu-guest:/sys/devices/system/memtier$ ls
> > > default_rank max_rank memtier1 power uevent
> > > kvaneesh@...ntu-guest:/sys/devices/system/memtier$ cat default_rank
> > > 1
> > > kvaneesh@...ntu-guest:/sys/devices/system/memtier$ cat max_rank
> > > 3
> >
> > For flexibility, we don't want max_rank to be interpreted as the
> > number of memory tiers. Also, we want to leave spaces in rank values
> > to allow new memtiers to be inserted when needed. So I'd suggest to
> > make max_rank a much larger value (e.g. 255).
> >
> > > kvaneesh@...ntu-guest:/sys/devices/system/memtier$ cd memtier1/
> > > kvaneesh@...ntu-guest:/sys/devices/system/memtier/memtier1$ ls
> > > nodelist power rank subsystem uevent
> > > kvaneesh@...ntu-guest:/sys/devices/system/memtier/memtier1$ cat nodelist
> > > 0-3
> > > kvaneesh@...ntu-guest:/sys/devices/system/memtier/memtier1$ cat rank
> > > 1
> > > kvaneesh@...ntu-guest:/sys/devices/system/memtier/memtier1$ cd
> > > ../../node/node1/
> > > kvaneesh@...ntu-guest:/sys/devices/system/node/node1$ cat memtier
> > > 1
> > > kvaneesh@...ntu-guest:/sys/devices/system/node/node1$
> > > root@...ntu-guest:/sys/devices/system/node/node1# echo 0 > memtier
> > > root@...ntu-guest:/sys/devices/system/node/node1# cat memtier
> > > 0
> > > root@...ntu-guest:/sys/devices/system/node/node1# cd ../../memtier/
> > > root@...ntu-guest:/sys/devices/system/memtier# ls
> > > default_rank max_rank memtier0 memtier1 power uevent
> > > root@...ntu-guest:/sys/devices/system/memtier# cd memtier0/
> > > root@...ntu-guest:/sys/devices/system/memtier/memtier0# cat nodelist
> > > 1
> > > root@...ntu-guest:/sys/devices/system/memtier/memtier0# cat rank
> > > 0
> >
> > It looks like the example here demonstrates the dynamic creation of
> > memtier0. If so, how is the rank of memtier0 determined? If we want
> > to support creating new memtiers at runtime, I think an explicit
> > interface that specifies both device ID and rank is preferred to avoid
> > implicit dependencies between device IDs and ranks.
>
> Why make device ID explicit - it's meaningless I think?
> How about a creation interface that is simply writing the rank value
> to create a new one? The only race I can see would be to get
> two parallel attempts to create a new tier with the same rank.
> That seems unlikely to matter unless we support changing rank later.
>
> Two attempts to create the same device ID tier seems more likely to
> cause fiddly races.
That's right: Device ID is not needed when creating a new memtier. It
should be enough to provide only a rank value.
> Jonathan
>
>
> >
> > > root@...ntu-guest:/sys/devices/system/memtier/memtier0# echo 4 > rank
> > > bash: rank: Permission denied
> > > root@...ntu-guest:/sys/devices/system/memtier/memtier0#
>
>
Powered by blists - more mailing lists