Mailing-List: contact user-help@cassandra.apache.org; run by ezmlm
Precedence: bulk
Reply-To: user@cassandra.apache.org
Received-SPF: pass (athena.apache.org: domain of rcoli@eventbrite.com
 designates 209.85.216.169 as permitted sender)
MIME-Version: 1.0
In-Reply-To: 
 <CAH9XgokoXOeMPWfVjjjDMV+MSke9F8ddr+1y2tXrfDH18TnSjw@mail.gmail.com>
References: 
 <CAH9Xgon=QO6-QybCiX=4d=J0pdTmp55+er6tbWCKpfejZnzENQ@mail.gmail.com>
	<CAAwnuDtS4=DxiKh_P46CEahnLoQcwMRXD1i-pSKjngR3E20Khw@mail.gmail.com>
	<45B81A29-6E63-471D-9C50-D0CC98ACA035@generalsentiment.com>
	<CAAwnuDvc4C6o+8BEcip_rUWPpp7idCB57Xwq3u-x_xvJBHFy9A@mail.gmail.com>
	<CAEDUwd2kC9SzsmT2=FYEHjfT8DcK0N3NxhbmPf2s1aG2QYU2Jw@mail.gmail.com>
	<CAN+ZzCh8tyYFDzpOT0RYEROGrHejDrNouHfCs-=r6KnG8cu00A@mail.gmail.com>
	<CAN+ZzCgzYv7JJT=rQjsROnEMewpMrZChkMC=+Bb--safhfwFzw@mail.gmail.com>
	<CAEDUwd1QKLGurAAQm29n290AmhPfeg7UMWprFzMHVpeuedNgfQ@mail.gmail.com>
	<CAAwnuDtXNktgAobDgPkAgtiuN+=9U03L1seTTJ3_iJZVGjnzXw@mail.gmail.com>
	<CAN+ZzChgKchMM5QuE0Pwt-2Tv0JM4TJ_EEkb7ju7mEXCJuK8Vw@mail.gmail.com>
	<CAOT3TWpuj9n2Ob43HwHgdAWWkS+PkWLisZqggddGru+p+RH_JA@mail.gmail.com>
	<CAN+ZzCi1XOLggQsWP6PwFsWW6r67sGGMkf3u3xu7ZqytQnMfVg@mail.gmail.com>
	<CAOT3TWrXsQAa_O2RDx_MFbnaz7n1jL8EGsCibdukWf_HGmrdqw@mail.gmail.com>
	<CAH9XgonhMAPqsFqX2gs4PFP9Hpu6MdMQkJZ02qk8D+sgr=9=aw@mail.gmail.com>
	<CAOT3TWrFgoLVZ9Fo8ByLGMpytDcnC6k2Pqtj2qFLW9Mjm8fUOQ@mail.gmail.com>
	<CAH9XgomzFBFPONtgJ1woQDdUWDy7hWcSWmffh+1A+RHC=CB+YQ@mail.gmail.com>
	<CAH9XgokoXOeMPWfVjjjDMV+MSke9F8ddr+1y2tXrfDH18TnSjw@mail.gmail.com>
Date: Fri, 20 Sep 2013 10:31:28 -0700
Message-ID: 
 <CAEDUwd3GCHrSEZ_g6RfDS0UL6OERfN+Mfhf3KCgwsDSBvphmtQ@mail.gmail.com>
Subject: Re: Cassandra 1.2.9 cluster with vnodes is heavily unbalanced.
From: Robert Coli <rcoli@eventbrite.com>
To: "user@cassandra.apache.org" <user@cassandra.apache.org>
Content-Type: multipart/alternative; boundary=089e01494b9a665da404e6d40a8c

--089e01494b9a665da404e6d40a8c
Content-Type: text/plain; charset=ISO-8859-1

On Fri, Sep 20, 2013 at 9:24 AM, Jayadev Jayaraman <jdisalive@gmail.com>wrote:

> As a follow-up, is operating a Cassandra cluster with machines on multiple
> racks and vnodes bound to cause load imbalance ? Shouldn't token-ranges
> assigned to individual machines via their vnodes be approximately balanced
> ? We're otherwise unable to explain why this imbalance occurs. ( it
> shouldn't be the fault of the Murmur3 partitioner which guarantees a
> uniform distribution of keys across token-ranges according to the doc. )
>

https://issues.apache.org/jira/browse/CASSANDRA-4658
https://issues.apache.org/jira/browse/CASSANDRA-4123

tl;dr : Yes, vnodes makes the imbalance factor slightly greater, but in
practice it "shouldn't" be significant.

If you are experiencing significant imbalance, one or both of those tickets
may be an appropriate forum to describe your experience.

=Rob

--089e01494b9a665da404e6d40a8c
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr">On Fri, Sep 20, 2013 at 9:24 AM, Jayadev Jayaraman <span d=
ir=3D"ltr">&lt;<a href=3D"mailto:jdisalive@gmail.com" target=3D"_blank">jdi=
salive@gmail.com</a>&gt;</span> wrote:<br><div class=3D"gmail_extra"><div c=
lass=3D"gmail_quote">
<blockquote class=3D"gmail_quote" style=3D"margin:0px 0px 0px 0.8ex;border-=
left-width:1px;border-left-color:rgb(204,204,204);border-left-style:solid;p=
adding-left:1ex"><div dir=3D"ltr">As a follow-up, is operating a Cassandra =
cluster with machines on multiple racks and vnodes bound to cause load imba=
lance ? Shouldn&#39;t token-ranges assigned to individual machines via thei=
r vnodes be approximately balanced ? We&#39;re otherwise unable to explain =
why this imbalance occurs. ( it shouldn&#39;t be the fault of the Murmur3 p=
artitioner which guarantees a uniform distribution of keys across token-ran=
ges according to the doc. )</div>
</blockquote><div><br></div><div><a href=3D"https://issues.apache.org/jira/=
browse/CASSANDRA-4658">https://issues.apache.org/jira/browse/CASSANDRA-4658=
</a></div><div><div><a href=3D"https://issues.apache.org/jira/browse/CASSAN=
DRA-4123">https://issues.apache.org/jira/browse/CASSANDRA-4123</a></div>
</div><div><br></div><div>tl;dr : Yes, vnodes makes the imbalance factor sl=
ightly greater, but in practice it &quot;shouldn&#39;t&quot; be significant=
.=A0</div><div><br></div><div>If you are experiencing significant imbalance=
, one or both of those tickets may be an appropriate forum to describe your=
 experience.<br>
</div><div><br></div><div>=3DRob</div><div>=A0</div></div></div></div>

--089e01494b9a665da404e6d40a8c--