Return-Path: X-Original-To: apmail-cassandra-user-archive@www.apache.org Delivered-To: apmail-cassandra-user-archive@www.apache.org Received: from mail.apache.org (hermes.apache.org [140.211.11.3]) by minotaur.apache.org (Postfix) with SMTP id 98660D9B2 for ; Tue, 30 Oct 2012 17:50:02 +0000 (UTC) Received: (qmail 66737 invoked by uid 500); 30 Oct 2012 17:50:00 -0000 Delivered-To: apmail-cassandra-user-archive@cassandra.apache.org Received: (qmail 66702 invoked by uid 500); 30 Oct 2012 17:50:00 -0000 Mailing-List: contact user-help@cassandra.apache.org; run by ezmlm Precedence: bulk List-Help: List-Unsubscribe: List-Post: List-Id: Reply-To: user@cassandra.apache.org Delivered-To: mailing list user@cassandra.apache.org Received: (qmail 66694 invoked by uid 99); 30 Oct 2012 17:50:00 -0000 Received: from nike.apache.org (HELO nike.apache.org) (192.87.106.230) by apache.org (qpsmtpd/0.29) with ESMTP; Tue, 30 Oct 2012 17:50:00 +0000 X-ASF-Spam-Status: No, hits=2.2 required=5.0 tests=HTML_MESSAGE,RCVD_IN_DNSWL_NONE,SPF_PASS X-Spam-Check-By: apache.org Received-SPF: pass (nike.apache.org: local policy) Received: from [208.113.200.5] (HELO homiemail-a93.g.dreamhost.com) (208.113.200.5) by apache.org (qpsmtpd/0.29) with ESMTP; Tue, 30 Oct 2012 17:49:53 +0000 Received: from homiemail-a93.g.dreamhost.com (localhost [127.0.0.1]) by homiemail-a93.g.dreamhost.com (Postfix) with ESMTP id 723118405C for ; Tue, 30 Oct 2012 10:48:19 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha1; c=relaxed; d=thelastpickle.com; h=from :content-type:message-id:mime-version:subject:date:references:to :in-reply-to; s=thelastpickle.com; bh=ZSodpp4u0giteqDBjDSdSO+rI9 0=; b=aGqgdA4EYCKIJBIsSq4FX5Ge0gkBmODFd8NUVXxiV5tK/HCoSo4IysQXYj tG77Y5yc4tcv4DaT3XD7mCHFIu+R1fDl0av+WOg46z0KCIo2l/Z04X/zgh0sG4Jc qufkRC3F1kjn7RtbnX+MpHqsiUpyCOFf/gWGgTWTOMVI8Af8Y= Received: from [172.16.1.10] (unknown [203.86.207.101]) (using TLSv1 with cipher AES128-SHA (128/128 bits)) (No client certificate requested) (Authenticated sender: aaron@thelastpickle.com) by homiemail-a93.g.dreamhost.com (Postfix) with ESMTPSA id E09E98406C for ; Tue, 30 Oct 2012 10:48:18 -0700 (PDT) From: aaron morton Content-Type: multipart/alternative; boundary="Apple-Mail=_CE5DE528-F370-4BFD-95AC-9342C8920EA5" Message-Id: Mime-Version: 1.0 (Mac OS X Mail 6.2 \(1499\)) Subject: Re: Throughput decreases as latency increases with YCSB Date: Wed, 31 Oct 2012 06:49:31 +1300 References: <804E68F9-E80D-4316-BB58-4C0F2DC05F31@gmail.com> To: user@cassandra.apache.org In-Reply-To: <804E68F9-E80D-4316-BB58-4C0F2DC05F31@gmail.com> X-Mailer: Apple Mail (2.1499) X-Virus-Checked: Checked by ClamAV on apache.org --Apple-Mail=_CE5DE528-F370-4BFD-95AC-9342C8920EA5 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=us-ascii Out of interest can you quantify the throughput reduction ? It looks = like less than 10%.=20 Nice to see it roughly correspond to SEDA throughput :) > Check how many concurrent real requests you have vs size of thread = pools. Did the change the defaults for the hsha settings below? How many concurrent connections were running ?=20 It looks related to payload size, could you run some different sizes ?=20= # For the Hsha server, the min and max both default to quadruple the = number of # CPU cores. # # This configuration is ignored by the async server. # # rpc_min_threads: 16 # rpc_max_threads: 2048 Cheers ----------------- Aaron Morton Freelance Developer @aaronmorton http://www.thelastpickle.com On 30/10/2012, at 9:10 PM, Terje Marthinussen = wrote: > Check how many concurrent real requests you have vs size of thread = pools. >=20 > Regards, > Terje >=20 > On 30 Oct 2012, at 13:28, Peter Bailis = wrote: >=20 >> I'm using YCSB on EC2 with one m1.large instance to drive client load >>=20 >> To add, I don't believe this is due to YCSB. I've done a fair bit of = client-side profiling and neither client CPU or NIC (or server NIC) are = bottlenecks. >>=20 >> I'll also add that this dataset fits in memory. >>=20 >> Thanks! >> Peter --Apple-Mail=_CE5DE528-F370-4BFD-95AC-9342C8920EA5 Content-Transfer-Encoding: quoted-printable Content-Type: text/html; charset=us-ascii Out = of interest can you quantify the throughput reduction ? It looks like = less than 10%. 
Nice to see it roughly correspond to SEDA = throughput :)

Check how many concurrent real requests you have vs size of = thread pools.
Did the = change the defaults for the hsha settings below?
How many concurrent connections were running = ? 
It looks related to payload size, could = you run some different sizes ? 

# For the Hsha server, the min and max = both default to quadruple the number of
# CPU = cores.
#
# This configuration is ignored by the = async server.
#
# rpc_min_threads: 16
# = rpc_max_threads: 2048

Cheers
http://www.thelastpickle.com

On 30/10/2012, at 9:10 PM, Terje Marthinussen <tmarthinussen@gmail.com> = wrote:

Check how many concurrent real = requests you have vs size of thread = pools.

Regards,
Terje

On 30 Oct = 2012, at 13:28, Peter Bailis <pbailis@cs.berkeley.edu> = wrote:

I'm using YCSB on EC2 with one m1.large = instance to drive client load

To add, I don't believe this is due to YCSB. I've = done a fair bit of client-side profiling and neither client CPU or NIC = (or server NIC) are bottlenecks.

I'll also add = that this dataset fits in memory.

Thanks!
Peter

= --Apple-Mail=_CE5DE528-F370-4BFD-95AC-9342C8920EA5--