From: Joe Thornber <thornber-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
To: OS Engineering <osengineering-FZ1t8LVTR2ZWk0Htik3J/w@public.gmane.org>
Cc: "koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org"
<koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>,
"linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org"
<linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
"dm-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org"
<dm-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>,
LKML <linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org>,
Jens Axboe <axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org>,
Padmini Balasubramaniyan
<padminib-FZ1t8LVTR2ZWk0Htik3J/w@public.gmane.org>,
Amit Phansalkar
<aphansalkar-FZ1t8LVTR2ZWk0Htik3J/w@public.gmane.org>
Subject: Re: Performance Comparison among EnhanceIO, bcache and dm-cache.
Date: Mon, 17 Jun 2013 11:29:44 +0100 [thread overview]
Message-ID: <20130617102943.GA11121@debian> (raw)
In-Reply-To: <D399C715A2AD7F4F891A75871FC3117507866B-/Mge6msRHKZU8iYRzhpb3QxBAXYc4onH@public.gmane.org>
On Tue, Jun 11, 2013 at 03:05:07PM +0000, OS Engineering wrote:
...
> Dm-cache commits on-disk metadata every time a REQ_SYNC or REQ_FUA
> bio is written. If no such requests are made then it commits
> metadata once every second. If power is lost, it may lose some
> recent writes.
Not true (though it is true for thinp, which may be where you got this
idea?). For caching we have to commit whenever data is moved about,
otherwise a crash could result in us reading data that is not just out
of date (acceptable for some), but used to belong to a totally
different part of the device (always unacceptable).
- Joe
WARNING: multiple messages have this Message-ID (diff)
From: Joe Thornber <thornber@redhat.com>
To: OS Engineering <osengineering@stec-inc.com>
Cc: "koverstreet@google.com" <koverstreet@google.com>,
"linux-bcache@vger.kernel.org" <linux-bcache@vger.kernel.org>,
"dm-devel@redhat.com" <dm-devel@redhat.com>,
LKML <linux-kernel@vger.kernel.org>, Jens Axboe <axboe@kernel.dk>,
Padmini Balasubramaniyan <padminib@stec-inc.com>,
Amit Phansalkar <aphansalkar@stec-inc.com>
Subject: Re: Performance Comparison among EnhanceIO, bcache and dm-cache.
Date: Mon, 17 Jun 2013 11:29:44 +0100 [thread overview]
Message-ID: <20130617102943.GA11121@debian> (raw)
In-Reply-To: <D399C715A2AD7F4F891A75871FC3117507866B@MYMBX3.stec-inc.ad>
On Tue, Jun 11, 2013 at 03:05:07PM +0000, OS Engineering wrote:
...
> Dm-cache commits on-disk metadata every time a REQ_SYNC or REQ_FUA
> bio is written. If no such requests are made then it commits
> metadata once every second. If power is lost, it may lose some
> recent writes.
Not true (though it is true for thinp, which may be where you got this
idea?). For caching we have to commit whenever data is moved about,
otherwise a crash could result in us reading data that is not just out
of date (acceptable for some), but used to belong to a totally
different part of the device (always unacceptable).
- Joe
next prev parent reply other threads:[~2013-06-17 10:29 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-06-11 15:05 Performance Comparison among EnhanceIO, bcache and dm-cache OS Engineering
2013-06-11 15:05 ` OS Engineering
[not found] ` <D399C715A2AD7F4F891A75871FC3117507866B-/Mge6msRHKZU8iYRzhpb3QxBAXYc4onH@public.gmane.org>
2013-06-12 4:58 ` Amit Kale
2013-06-12 4:58 ` Amit Kale
[not found] ` <201306121028.03278.amitkale-Gl6SwLIDy+bjyqlaT+yXCw@public.gmane.org>
2013-06-12 11:39 ` OS Engineering
2013-06-12 11:39 ` OS Engineering
2013-06-17 10:29 ` Joe Thornber [this message]
2013-06-17 10:29 ` Joe Thornber
2013-06-18 16:25 ` Michael Fortson
2013-06-18 16:30 ` [dm-devel] " Michael Fortson
2013-06-14 2:51 ` Mike Snitzer
[not found] ` <CAMM=eLfKku3CuHUS-0Akv=FdEzk_OWz3j+3oTAWCrFnFLZ0b1g-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2013-07-02 8:25 ` OS Engineering
2013-07-02 8:25 ` OS Engineering
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=20130617102943.GA11121@debian \
--to=thornber-h+wxahxf7alqt0dzr+alfa@public.gmane.org \
--cc=aphansalkar-FZ1t8LVTR2ZWk0Htik3J/w@public.gmane.org \
--cc=axboe-tSWWG44O7X1aa/9Udqfwiw@public.gmane.org \
--cc=dm-devel-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org \
--cc=koverstreet-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org \
--cc=linux-bcache-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org \
--cc=osengineering-FZ1t8LVTR2ZWk0Htik3J/w@public.gmane.org \
--cc=padminib-FZ1t8LVTR2ZWk0Htik3J/w@public.gmane.org \
/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.