From: Nitin Gupta <ngupta@vflare.org>
To: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>,
Andrew Morton <akpm@linux-foundation.org>,
Greg KH <greg@kroah.com>,
Dan Magenheimer <dan.magenheimer@oracle.com>,
Rik van Riel <riel@redhat.com>, Avi Kivity <avi@redhat.com>,
Christoph Hellwig <hch@infradead.org>,
Minchan Kim <minchan.kim@gmail.com>,
Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
linux-mm <linux-mm@kvack.org>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 0/8] zcache: page cache compression support
Date: Sun, 18 Jul 2010 13:42:50 +0530 [thread overview]
Message-ID: <4C42B782.7060106@vflare.org> (raw)
In-Reply-To: <4C42B228.9040401@cs.helsinki.fi>
On 07/18/2010 01:20 PM, Pekka Enberg wrote:
> Nitin Gupta wrote:
>> Frequently accessed filesystem data is stored in memory to reduce access to
>> (much) slower backing disks. Under memory pressure, these pages are freed and
>> when needed again, they have to be read from disks again. When combined working
>> set of all running application exceeds amount of physical RAM, we get extereme
>> slowdown as reading a page from disk can take time in order of milliseconds.
>>
>> Memory compression increases effective memory size and allows more pages to
>> stay in RAM. Since de/compressing memory pages is several orders of magnitude
>> faster than disk I/O, this can provide signifant performance gains for many
>> workloads. Also, with multi-cores becoming common, benefits of reduced disk I/O
>> should easily outweigh the problem of increased CPU usage.
>>
>> It is implemented as a "backend" for cleancache_ops [1] which provides
>> callbacks for events such as when a page is to be removed from the page cache
>> and when it is required again. We use them to implement a 'second chance' cache
>> for these evicted page cache pages by compressing and storing them in memory
>> itself.
>>
<snip>
>
> So why would someone want to use zram if they have transparent page cache compression with zcache? That is, why is this not a replacement for zram?
>
zcache complements zram; it's not a replacement:
- zram compresses anonymous pages while zcache is for page cache compression.
So, workload which depends heavily on "heap memory" usage will tend to prefer
zram and those which are I/O intensive will prefer zcache. Though I have not
yet experimented much, most workloads may want to have a mix of them.
- zram is not just for swap. /dev/zram<id> are generic in-memory compressed
block devices which can be used for, say, /tmp, /var/... etc. temporary storage.
- /dev/zram<id> being a generic block devices, can be used as raw disk in other
OSes also (using virtualization): For example:
http://www.vflare.org/2010/05/compressed-ram-disk-for-windows-virtual.html
Thanks,
Nitin
--
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>
next prev parent reply other threads:[~2010-07-18 8:12 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-07-16 12:37 Nitin Gupta
2010-07-16 12:37 ` [PATCH 1/8] Allow sharing xvmalloc for zram and zcache Nitin Gupta
2010-07-17 18:10 ` Rik van Riel
2010-07-16 12:37 ` [PATCH 2/8] Basic zcache functionality Nitin Gupta
2010-07-18 8:14 ` Pekka Enberg
2010-07-18 9:45 ` Nitin Gupta
2010-07-18 8:27 ` Pekka Enberg
2010-07-18 8:44 ` Eric Dumazet
2010-07-18 9:51 ` Nitin Gupta
2010-07-16 12:37 ` [PATCH 3/8] Create sysfs nodes and export basic statistics Nitin Gupta
2010-07-16 12:37 ` [PATCH 4/8] Shrink zcache based on memlimit Nitin Gupta
2010-07-20 23:03 ` Minchan Kim
2010-07-21 4:52 ` Nitin Gupta
2010-07-21 11:32 ` Ed Tomlinson
2010-07-23 19:23 ` Nitin Gupta
2010-07-16 12:37 ` [PATCH 5/8] Eliminate zero-filled pages Nitin Gupta
2010-07-16 12:37 ` [PATCH 6/8] Compress pages using LZO Nitin Gupta
2010-07-16 12:37 ` [PATCH 7/8] Use xvmalloc to store compressed chunks Nitin Gupta
2010-07-18 7:53 ` Pekka Enberg
2010-07-18 8:21 ` Nitin Gupta
2010-07-19 4:36 ` Minchan Kim
2010-07-19 6:48 ` Nitin Gupta
2010-07-16 12:37 ` [PATCH 8/8] Document sysfs entries Nitin Gupta
2010-07-17 21:13 ` [PATCH 0/8] zcache: page cache compression support Ed Tomlinson
2010-07-18 2:23 ` Nitin Gupta
2010-07-18 7:50 ` Pekka Enberg
2010-07-18 8:12 ` Nitin Gupta [this message]
2010-07-19 19:57 ` Dan Magenheimer
2010-07-20 13:50 ` Nitin Gupta
2010-07-20 14:28 ` Dan Magenheimer
2010-07-21 4:27 ` Nitin Gupta
2010-07-21 17:37 ` Dan Magenheimer
2010-07-22 19:14 ` Greg KH
2010-07-22 19:54 ` Dan Magenheimer
2010-07-22 21:00 ` Greg KH
2011-01-10 13:16 ` Kirill A. Shutemov
2011-01-18 17:53 ` Dan Magenheimer
2011-01-20 12:33 ` Nitin Gupta
2011-01-20 12:47 ` Christoph Hellwig
2011-01-20 13:16 ` Pekka Enberg
2011-01-20 13:58 ` Nitin Gupta
[not found] <575348163.1113381279906498028.JavaMail.root@zmail06.collab.prod.int.phx2.redhat.com>
2010-07-23 17:36 ` caiqian
2010-07-23 17:41 ` CAI Qian
2010-07-23 18:02 ` CAI Qian
2010-07-24 14:41 ` Valdis.Kletnieks
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=4C42B782.7060106@vflare.org \
--to=ngupta@vflare.org \
--cc=akpm@linux-foundation.org \
--cc=avi@redhat.com \
--cc=dan.magenheimer@oracle.com \
--cc=greg@kroah.com \
--cc=hch@infradead.org \
--cc=hugh.dickins@tiscali.co.uk \
--cc=konrad.wilk@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=minchan.kim@gmail.com \
--cc=penberg@cs.helsinki.fi \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox