Mailing-List: contact user-help@zookeeper.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@zookeeper.apache.org
Message-ID: <COL128-W548F689F929ECE47B5C0028F380@phx.gbl>
Content-Type: multipart/alternative;
	boundary="_e597a160-6ea4-4d2c-9a03-714f199fab6b_"
From: Adrian Hamza <adrian.hamza@hotmail.com>
To: "user@zookeeper.apache.org" <user@zookeeper.apache.org>
Subject: RE: Running zookeeper with journaling disabled on an ext4
Date: Wed, 21 Oct 2015 12:44:28 -0700
Importance: Normal
In-Reply-To: 
 <CANgQmrfqKd_DEy7LozS0FcM7t19A2eGq1xrY2KqqJT61BQhipA@mail.gmail.com>
References: 
 <COL128-W8497A9384F74F9A4E405B18F380@phx.gbl>,<CAJdLeK2LppxJQ3VoXjTX7tStsGSasUrzWBmcYHXp1eiFAATduw@mail.gmail.com>,<CANgQmrfqKd_DEy7LozS0FcM7t19A2eGq1xrY2KqqJT61BQhipA@mail.gmail.com>
MIME-Version: 1.0

--_e597a160-6ea4-4d2c-9a03-714f199fab6b_
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable

No fsync can lead to data loss as the data could be written only in the OS =
cache but no on the disk. We do use fsync to prevent that and we are not go=
ing to disable it.

> Date: Wed=2C 21 Oct 2015 14:00:57 -0400
> Subject: Re: Running zookeeper with journaling disabled on an ext4
> From: edward.capriolo@huffingtonpost.com
> To: user@zookeeper.apache.org
>=20
> There used to be this setting in zk.
>=20
> zookeeper.forceSync
> Using Kafka I used to set this setting to false=2C The reason is I had a
> number of clients writing offsets to zk and the disk system was always
> sync-ing dirty pages. The system would be super high IO wait.
>=20
> I set this to false and disk usage basically dropped to 0.
>=20
> On Wed=2C Oct 21=2C 2015 at 1:47 PM=2C Ivan Kelly <ivank@apache.org> wrot=
e:
>=20
> > >
> > > What's your opinion on running Zookeeper with file system journaling
> > > disabled on an EXT4 file system?
> > > We need every ounce of performance out of it=2C and I believe given t=
he
> > > Zookeeper implementation (operations are logged=2C majority quorum is
> > > required for succeeding=2C checkpoints are swapped only after being
> > complete)
> > > I feel that EXT4 journaling is redundant. Disabling EXT4 journaling c=
ould
> > > improve performance. We have 5 servers in a Zookeeper ensemble. Am I
> > > missing something or this should be fine?
> >
> > I would recommend against it. With ext4 journalling disabled=2C a serve=
r
> > crash will likely lose data=2C unless you have all write caching disabl=
ed. If
> > you have all write caching disabled=2C I'd expect to see worse performa=
nce
> > for all applications. It's not much safer than running in a ramdisk.
> >
> > -Ivan
> >
 		 	   		  =

--_e597a160-6ea4-4d2c-9a03-714f199fab6b_--