All of lore.kernel.org
 help / color / mirror / Atom feed
From: Seth Jennings <sjenning@linux.vnet.ibm.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Nitin Gupta <ngupta@vflare.org>, Minchan Kim <minchan@kernel.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	Dan Magenheimer <dan.magenheimer@oracle.com>,
	Robert Jennings <rcj@linux.vnet.ibm.com>,
	Jenifer Hopper <jhopper@us.ibm.com>, Mel Gorman <mgorman@suse.de>,
	Johannes Weiner <jweiner@redhat.com>,
	Rik van Riel <riel@redhat.com>,
	Larry Woodman <lwoodman@redhat.com>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Dave Hansen <dave@sr71.net>, Joe Perches <joe@perches.com>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	Cody P Schafer <cody@linux.vnet.ibm.com>,
	Hugh Dickens <hughd@google.com>,
	Paul Mackerras <paulus@samba.org>,
	Heesub Shin <heesub.shin@samsung.com>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	devel@driverdev.osuosl.org
Subject: Re: [PATCHv12 3/4] zswap: add to mm/
Date: Wed, 29 May 2013 14:50:27 -0500	[thread overview]
Message-ID: <20130529195027.GC428@cerebellum> (raw)
In-Reply-To: <20130529112929.24005ae9cf1d9d636b2ea42f@linux-foundation.org>

On Wed, May 29, 2013 at 11:29:29AM -0700, Andrew Morton wrote:
> On Wed, 29 May 2013 09:57:20 -0500 Seth Jennings <sjenning@linux.vnet.ibm.com> wrote:
> 
> > > > +/*********************************
> > > > +* helpers
> > > > +**********************************/
> > > > +static inline bool zswap_is_full(void)
> > > > +{
> > > > +	return (totalram_pages * zswap_max_pool_percent / 100 <
> > > > +		zswap_pool_pages);
> > > > +}
> > > 
> > > We have had issues in the past where percentage-based tunables were too
> > > coarse on very large machines.  For example, a terabyte machine where 0
> > > bytes is too small and 10GB is too large.
> > 
> > Yes, this is known limitation of the code right now and it is a high priority
> > to come up with something better.  It isn't clear what dynamic sizing policy
> > should be used so, until such time as that policy can be determined, this is a
> > simple stop-gap that works well enough for simple setups.
> 
> It's a module parameter and hence is part of the userspace interface. 
> It's undesirable that the interface be changed, and it would be rather
> dumb to merge it as-is when we *know* that it will be changed.
> 
> I don't think we can remove the parameter altogether (or can we?), so I
> suggest we finalise it ASAP.  Perhaps rename it to
> zswap_max_pool_ratio, with a range 1..999999.  Better ideas needed :(

zswap_max_pool_ratio is fine with me.  I'm not entirely clear on the change
though.  Would that just be a name change or a change in meaning?

Also, we can keep the tunable as I imagine there will always be some use for a
manual override of the (future) dynamic policy.  When the dynamic policy is
available, we can just say that zswap_max_pool_ratio = 0 means "use dynamic
policy" and change the default to 0.  Does that sounds reasonable?

Seth

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

WARNING: multiple messages have this Message-ID (diff)
From: Seth Jennings <sjenning@linux.vnet.ibm.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Nitin Gupta <ngupta@vflare.org>, Minchan Kim <minchan@kernel.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	Dan Magenheimer <dan.magenheimer@oracle.com>,
	Robert Jennings <rcj@linux.vnet.ibm.com>,
	Jenifer Hopper <jhopper@us.ibm.com>, Mel Gorman <mgorman@suse.de>,
	Johannes Weiner <jweiner@redhat.com>,
	Rik van Riel <riel@redhat.com>,
	Larry Woodman <lwoodman@redhat.com>,
	Benjamin Herrenschmidt <benh@kernel.crashing.org>,
	Dave Hansen <dave@sr71.net>, Joe Perches <joe@perches.com>,
	Joonsoo Kim <iamjoonsoo.kim@lge.com>,
	Cody P Schafer <cody@linux.vnet.ibm.com>,
	Hugh Dickens <hughd@google.com>,
	Paul Mackerras <paulus@samba.org>,
	Heesub Shin <heesub.shin@samsung.com>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	devel@driverdev.osuosl.org
Subject: Re: [PATCHv12 3/4] zswap: add to mm/
Date: Wed, 29 May 2013 14:50:27 -0500	[thread overview]
Message-ID: <20130529195027.GC428@cerebellum> (raw)
In-Reply-To: <20130529112929.24005ae9cf1d9d636b2ea42f@linux-foundation.org>

On Wed, May 29, 2013 at 11:29:29AM -0700, Andrew Morton wrote:
> On Wed, 29 May 2013 09:57:20 -0500 Seth Jennings <sjenning@linux.vnet.ibm.com> wrote:
> 
> > > > +/*********************************
> > > > +* helpers
> > > > +**********************************/
> > > > +static inline bool zswap_is_full(void)
> > > > +{
> > > > +	return (totalram_pages * zswap_max_pool_percent / 100 <
> > > > +		zswap_pool_pages);
> > > > +}
> > > 
> > > We have had issues in the past where percentage-based tunables were too
> > > coarse on very large machines.  For example, a terabyte machine where 0
> > > bytes is too small and 10GB is too large.
> > 
> > Yes, this is known limitation of the code right now and it is a high priority
> > to come up with something better.  It isn't clear what dynamic sizing policy
> > should be used so, until such time as that policy can be determined, this is a
> > simple stop-gap that works well enough for simple setups.
> 
> It's a module parameter and hence is part of the userspace interface. 
> It's undesirable that the interface be changed, and it would be rather
> dumb to merge it as-is when we *know* that it will be changed.
> 
> I don't think we can remove the parameter altogether (or can we?), so I
> suggest we finalise it ASAP.  Perhaps rename it to
> zswap_max_pool_ratio, with a range 1..999999.  Better ideas needed :(

zswap_max_pool_ratio is fine with me.  I'm not entirely clear on the change
though.  Would that just be a name change or a change in meaning?

Also, we can keep the tunable as I imagine there will always be some use for a
manual override of the (future) dynamic policy.  When the dynamic policy is
available, we can just say that zswap_max_pool_ratio = 0 means "use dynamic
policy" and change the default to 0.  Does that sounds reasonable?

Seth


  reply	other threads:[~2013-05-29 19:53 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-05-20 16:26 [PATCHv12 0/4] zswap: compressed swap caching Seth Jennings
2013-05-20 16:26 ` Seth Jennings
2013-05-20 16:26 ` [PATCHv12 1/4] debugfs: add get/set for atomic types Seth Jennings
2013-05-20 16:26   ` Seth Jennings
2013-05-29 17:42   ` Konrad Rzeszutek Wilk
2013-05-29 17:42     ` Konrad Rzeszutek Wilk
2013-05-20 16:26 ` [PATCHv12 2/4] zbud: add to mm/ Seth Jennings
2013-05-20 16:26   ` Seth Jennings
2013-05-21  3:37   ` Bob Liu
2013-05-21  3:37     ` Bob Liu
2013-05-28 21:59   ` Andrew Morton
2013-05-28 21:59     ` Andrew Morton
2013-05-29 15:45     ` Seth Jennings
2013-05-29 15:45       ` Seth Jennings
2013-05-29 18:34       ` Andrew Morton
2013-05-29 18:34         ` Andrew Morton
2013-05-29 20:42         ` Seth Jennings
2013-05-29 20:42           ` Seth Jennings
2013-05-29 20:48           ` Andrew Morton
2013-05-29 20:48             ` Andrew Morton
2013-05-29 21:09             ` Dan Magenheimer
2013-05-29 21:09               ` Dan Magenheimer
2013-05-29 21:29               ` Andrew Morton
2013-05-29 21:29                 ` Andrew Morton
2013-05-30 17:43                 ` Seth Jennings
2013-05-30 17:43                   ` Seth Jennings
2013-05-30 21:20                   ` Seth Jennings
2013-05-30 21:20                     ` Seth Jennings
2013-05-31  1:48                     ` Bob Liu
2013-05-31  1:48                       ` Bob Liu
2013-06-03 13:48                   ` Konrad Rzeszutek Wilk
2013-06-03 13:48                     ` Konrad Rzeszutek Wilk
2013-05-29 20:45         ` Seth Jennings
2013-05-29 20:45           ` Seth Jennings
2013-05-20 16:26 ` [PATCHv12 3/4] zswap: " Seth Jennings
2013-05-20 16:26   ` Seth Jennings
2013-05-21  3:31   ` Bob Liu
2013-05-21  3:31     ` Bob Liu
2013-05-28 21:59   ` Andrew Morton
2013-05-28 21:59     ` Andrew Morton
2013-05-29 14:57     ` Seth Jennings
2013-05-29 14:57       ` Seth Jennings
2013-05-29 18:29       ` Andrew Morton
2013-05-29 18:29         ` Andrew Morton
2013-05-29 19:50         ` Seth Jennings [this message]
2013-05-29 19:50           ` Seth Jennings
2013-05-29 19:57           ` Andrew Morton
2013-05-29 19:57             ` Andrew Morton
2013-05-29 21:08             ` Seth Jennings
2013-05-29 21:08               ` Seth Jennings
2013-05-29 21:16               ` Andrew Morton
2013-05-29 21:16                 ` Andrew Morton
2013-05-20 16:26 ` [PATCHv12 4/4] zswap: add documentation Seth Jennings
2013-05-20 16:26   ` Seth Jennings

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=20130529195027.GC428@cerebellum \
    --to=sjenning@linux.vnet.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=benh@kernel.crashing.org \
    --cc=cody@linux.vnet.ibm.com \
    --cc=dan.magenheimer@oracle.com \
    --cc=dave@sr71.net \
    --cc=devel@driverdev.osuosl.org \
    --cc=gregkh@linuxfoundation.org \
    --cc=heesub.shin@samsung.com \
    --cc=hughd@google.com \
    --cc=iamjoonsoo.kim@lge.com \
    --cc=jhopper@us.ibm.com \
    --cc=joe@perches.com \
    --cc=jweiner@redhat.com \
    --cc=konrad.wilk@oracle.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=lwoodman@redhat.com \
    --cc=mgorman@suse.de \
    --cc=minchan@kernel.org \
    --cc=ngupta@vflare.org \
    --cc=paulus@samba.org \
    --cc=rcj@linux.vnet.ibm.com \
    --cc=riel@redhat.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.