From user-return-64596-archive-asf-public=cust-asf.ponee.io@cassandra.apache.org Mon Oct 21 20:41:42 2019 Return-Path: X-Original-To: archive-asf-public@cust-asf.ponee.io Delivered-To: archive-asf-public@cust-asf.ponee.io Received: from mail.apache.org (hermes.apache.org [207.244.88.153]) by mx-eu-01.ponee.io (Postfix) with SMTP id A7B50180626 for ; Mon, 21 Oct 2019 22:41:41 +0200 (CEST) Received: (qmail 38356 invoked by uid 500); 21 Oct 2019 20:41:36 -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 38346 invoked by uid 99); 21 Oct 2019 20:41:35 -0000 Received: from pnap-us-west-generic-nat.apache.org (HELO spamd4-us-west.apache.org) (209.188.14.142) by apache.org (qpsmtpd/0.29) with ESMTP; Mon, 21 Oct 2019 20:41:35 +0000 Received: from localhost (localhost [127.0.0.1]) by spamd4-us-west.apache.org (ASF Mail Server at spamd4-us-west.apache.org) with ESMTP id 690B1C0CEF for ; Mon, 21 Oct 2019 20:41:35 +0000 (UTC) X-Virus-Scanned: Debian amavisd-new at spamd4-us-west.apache.org X-Spam-Flag: NO X-Spam-Score: 0 X-Spam-Level: X-Spam-Status: No, score=0 tagged_above=-999 required=6.31 tests=[DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, HTML_MESSAGE=0.2, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H2=-0.001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001, URIBL_BLOCKED=0.001] autolearn=disabled Authentication-Results: spamd4-us-west.apache.org (amavisd-new); dkim=pass (2048-bit key) header.d=backblaze.com Received: from mx1-ec2-va.apache.org ([10.40.0.8]) by localhost (spamd4-us-west.apache.org [10.40.0.11]) (amavisd-new, port 10024) with ESMTP id e37gCKK5ONmo for ; Mon, 21 Oct 2019 20:41:31 +0000 (UTC) Received-SPF: Pass (mailfrom) identity=mailfrom; client-ip=209.85.128.45; helo=mail-wm1-f45.google.com; envelope-from=elliott@backblaze.com; receiver= Received: from mail-wm1-f45.google.com (mail-wm1-f45.google.com [209.85.128.45]) by mx1-ec2-va.apache.org (ASF Mail Server at mx1-ec2-va.apache.org) with ESMTPS id 91A84BC618 for ; Mon, 21 Oct 2019 20:31:44 +0000 (UTC) Received: by mail-wm1-f45.google.com with SMTP id q13so4747482wmj.0 for ; Mon, 21 Oct 2019 13:31:44 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=backblaze.com; s=google; h=mime-version:references:in-reply-to:from:date:message-id:subject:to; bh=d1aLxBCX1Uf4k1NNSzvhoHtlfRkZz1bYYA4bvtkxTrk=; b=AdU3ozh/O5rfadMxfMzOiA1MJbPqd5MCgc2fGaZpH4fZQB2yHSQOhLSPoDeuP4VZ/Y qcO2cKV7hXflrc1mTXBBDLIXSqYR86Gw25k4lthamiThv8/orKYEeJnycxQZmNlLhH81 s92iysGUSluh+eh/lelI9TqcG87uszBNyjup3tn5j6/1palHYC2Mx4gIcIU9gah4plPm T9XgYeLSg9450Rhmlf1VXcQIAUPuzLpJdJ4dcKd39r+JFsCE7dwXDwHz8yFARm6MsGuW 6h7hl71tLamVX3YnwkjV3Ewu7ljA1vdTAi1G0h3jVA2AqQUSv+vHEhCr1vGSTNgURjnq KC9A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to; bh=d1aLxBCX1Uf4k1NNSzvhoHtlfRkZz1bYYA4bvtkxTrk=; b=q5epZcgClHeeBuRTMkkjr+37HLLreQupbdf0D54h3h73GviSNhveGp7L98xrr2vJES 2Hzix6A3xpLMTYJOBhK5pfxG/YVtnBRCF8Z5ZGQx1ez7WgkdcOF21Vc59aWonTTbVLSn 172+NQ4UOTqkYPw4V5nvUKZrmJYKzDbs4CQuqQjHwh3DJr/oKw1ZLinRjloWKLXE7Rdw exFvSoAb9CQ7Z5gnD9zXXYuAKHC/tHde06wZHpuG7DqBe616BilSY20vEocm6DU4LNmw BUbChEo4Iiuw2ZVJZE6U1zy9mWZwZqVCMR8Si7e268aK6nRblm/eM1AcLwy5QO8VDlFh MCCQ== X-Gm-Message-State: APjAAAWZe3a83rfvpRfkSb2SyHKKRmihycMKw4v3V0qVMwcabPzO2REh aGVnn/xlw/DDobihWHvRmfMZb4fiMGMVof4UJjAKKIUvpBA= X-Google-Smtp-Source: APXvYqwKb09Bu29fsOec+ISLC2Bj9KDTMVx4x2Hl/2TCxZ8bThoWkbcZRaRwtyGmV34vSaZa1w4/KJzmsLY3JUMgC74= X-Received: by 2002:a05:600c:34b:: with SMTP id u11mr20896006wmd.176.1571689903031; Mon, 21 Oct 2019 13:31:43 -0700 (PDT) MIME-Version: 1.0 References: In-Reply-To: From: Elliott Sims Date: Mon, 21 Oct 2019 13:31:06 -0700 Message-ID: Subject: Re: Cassandra Recommended System Settings To: user@cassandra.apache.org Content-Type: multipart/alternative; boundary="0000000000005e2c270595719221" --0000000000005e2c270595719221 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Based on my experiences, if you have a new enough kernel I'd strongly suggest switching the TCP scheduler algorithm to BBR. I've found the rest tend to be extremely sensitive to even small amounts of packet loss among cluster members where BBR holds up well. High ulimits for basically everything are probably a good idea, although "unlimited" may not be purely optimal for all cases. The TCP keepalive settings are probably only necessary for traffic buggy/misconfigured firewalls, but shouldn't really do any harm on a modern fast network. The TCP memory settings are pretty aggressive and probably result in unnecessary RAM usage. The net.core.rmem_default/net.core.wmem_default settings are overridden by the TCP-specific settings as far as I know, so they're not really relevant/helpful for Cassandra The net.ipv4.tcp_rmem/net.ipv4.tcp_wmem max settings are pretty aggressive. That works out to something like 1Gbps with 130ms latency per TCP connection, but on a local LAN with latencies <1ms it's enough buffer for over 100Gbps per TCP session. A much smaller value will probably make more sense for most setups. On Mon, Oct 21, 2019 at 10:21 AM Sergio wrote: > > Hello! > > This is the kernel that I am using > Linux 4.16.13-1.el7.elrepo.x86_64 #1 SMP Wed May 30 14:31:51 EDT 2018 > x86_64 x86_64 x86_64 GNU/Linux > > Best, > > Sergio > > Il giorno lun 21 ott 2019 alle ore 07:30 Reid Pinchback < > rpinchback@tripadvisor.com> ha scritto: > >> I don't know which distro and version you are using, but watch out for >> surprises in what vm.swappiness=3D0 means. In older kernels it means "o= nly >> use swap when desperate". I believe that newer kernels changed to have = 1 >> mean that, and 0 means to always use the oomkiller. Neither situation i= s >> strictly good or bad, what matters is what you intend the system behavio= r >> to be in comparison with whatever monitoring/alerting you have put in pl= ace. >> >> R >> >> >> =EF=BB=BFOn 10/18/19, 9:04 PM, "Sergio Bilello" >> wrote: >> >> Message from External Sender >> >> Hello everyone! >> >> >> >> Do you have any setting that you would change or tweak from the belo= w >> list? >> >> >> >> sudo cat /proc/4379/limits >> >> Limit Soft Limit Hard Limit >> Units >> >> Max cpu time unlimited unlimited >> seconds >> >> Max file size unlimited unlimited >> bytes >> >> Max data size unlimited unlimited >> bytes >> >> Max stack size unlimited unlimited >> bytes >> >> Max core file size unlimited unlimited >> bytes >> >> Max resident set unlimited unlimited >> bytes >> >> Max processes 32768 32768 >> processes >> >> Max open files 1048576 1048576 >> files >> >> Max locked memory unlimited unlimited >> bytes >> >> Max address space unlimited unlimited >> bytes >> >> Max file locks unlimited unlimited >> locks >> >> Max pending signals unlimited unlimited >> signals >> >> Max msgqueue size unlimited unlimited >> bytes >> >> Max nice priority 0 0 >> >> Max realtime priority 0 0 >> >> Max realtime timeout unlimited unlimited = us >> >> >> >> These are the sysctl settings >> >> default['cassandra']['sysctl'] =3D { >> >> 'net.ipv4.tcp_keepalive_time' =3D> 60, >> >> 'net.ipv4.tcp_keepalive_probes' =3D> 3, >> >> 'net.ipv4.tcp_keepalive_intvl' =3D> 10, >> >> 'net.core.rmem_max' =3D> 16777216, >> >> 'net.core.wmem_max' =3D> 16777216, >> >> 'net.core.rmem_default' =3D> 16777216, >> >> 'net.core.wmem_default' =3D> 16777216, >> >> 'net.core.optmem_max' =3D> 40960, >> >> 'net.ipv4.tcp_rmem' =3D> '4096 87380 16777216', >> >> 'net.ipv4.tcp_wmem' =3D> '4096 65536 16777216', >> >> 'net.ipv4.ip_local_port_range' =3D> '10000 65535', >> >> 'net.ipv4.tcp_window_scaling' =3D> 1, >> >> 'net.core.netdev_max_backlog' =3D> 2500, >> >> 'net.core.somaxconn' =3D> 65000, >> >> 'vm.max_map_count' =3D> 1048575, >> >> 'vm.swappiness' =3D> 0 >> >> } >> >> >> >> Am I missing something else? >> >> >> >> Do you have any experience to configure CENTOS 7 >> >> for >> >> JAVA HUGE PAGES >> >> >> https://urldefense.proofpoint.com/v2/url?u=3Dhttps-3A__docs.datastax.com= _en_dse_5.1_dse-2Dadmin_datastax-5Fenterprise_config_configRecommendedSetti= ngs.html-23CheckJavaHugepagessettings&d=3DDwIBaQ&c=3D9Hv6XPedRSA-5PSECC38X8= 0c1h60_XWA4z1k_R1pROA&r=3DOIgB3poYhzp3_A7WgD7iBCnsJaYmspOa2okNpf6uqWc&m=3Dz= ke-WpkD1c6Qt1cz8mJG0ZQ37h8kezqknMSnerQhXuU&s=3Db6lGdbtv1SN9opBsIOFRT6IX6Bro= MW-8Tudk9qEh3bI&e=3D >> >> >> >> OPTIMIZE SSD >> >> >> https://urldefense.proofpoint.com/v2/url?u=3Dhttps-3A__docs.datastax.com= _en_dse_5.1_dse-2Dadmin_datastax-5Fenterprise_config_configRecommendedSetti= ngs.html-23OptimizeSSDs&d=3DDwIBaQ&c=3D9Hv6XPedRSA-5PSECC38X80c1h60_XWA4z1k= _R1pROA&r=3DOIgB3poYhzp3_A7WgD7iBCnsJaYmspOa2okNpf6uqWc&m=3Dzke-WpkD1c6Qt1c= z8mJG0ZQ37h8kezqknMSnerQhXuU&s=3Dc0S3S3V_0YHVMx2I-pyOh24MiQs1D-L73JytaSw648= M&e=3D >> >> >> >> >> https://urldefense.proofpoint.com/v2/url?u=3Dhttps-3A__docs.datastax.com= _en_dse_5.1_dse-2Dadmin_datastax-5Fenterprise_config_configRecommendedSetti= ngs.html&d=3DDwIBaQ&c=3D9Hv6XPedRSA-5PSECC38X80c1h60_XWA4z1k_R1pROA&r=3DOIg= B3poYhzp3_A7WgD7iBCnsJaYmspOa2okNpf6uqWc&m=3Dzke-WpkD1c6Qt1cz8mJG0ZQ37h8kez= qknMSnerQhXuU&s=3DPZFG6SXF6dL5LRJ-aUoidHnnLGpKPbpxdKstM8M9JMk&e=3D >> >> >> >> We are using AWS i3.xlarge instances >> >> >> >> Thanks, >> >> >> >> Sergio >> >> >> >> --------------------------------------------------------------------= - >> >> To unsubscribe, e-mail: user-unsubscribe@cassandra.apache.org >> >> For additional commands, e-mail: user-help@cassandra.apache.org >> >> >> >> >> >> --0000000000005e2c270595719221 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Based on my experiences, if you have a new enoug= h kernel I'd strongly suggest switching the TCP scheduler algorithm to = BBR.=C2=A0 I've found the rest tend to be extremely sensitive to even s= mall amounts of packet loss among cluster members where BBR holds up well.<= br>
High ulimits for basically everything are probably a good idea= , although "unlimited" may not be purely optimal for all cases.
The TCP keepalive settings are probably only necessary for tra= ffic buggy/misconfigured firewalls, but shouldn't really do any harm on= a modern fast network.

The TCP memory settings are prett= y aggressive and probably result in unnecessary RAM usage.=C2=A0
The ne= t.core.rmem_default/net.core.wmem_default settings are overridden by the TC= P-specific settings as far as I know, so they're not really relevant/he= lpful for Cassandra
The net.ipv4.tcp_rmem/net.ipv4.tcp_wmem m= ax settings are pretty aggressive.=C2=A0 That works out to something like 1= Gbps with 130ms latency per TCP connection, but on a local LAN with latenci= es <1ms it's enough buffer for over 100Gbps per TCP session.=C2=A0 A= much smaller value will probably make more sense for most setups.=C2=A0


On Mon, Oct 21, 2019 at 10:21 AM Sergio <lapostadisergio@gmail.com> wro= te:

Hello!

This is the kernel that I am using=C2=A0
Linux=C2= =A0 4.16.13-1.el7.elrepo.x86_64 #1 SMP Wed May 30 14:31:51 EDT 2018 x86_64 = x86_64 x86_64 GNU/Linux

Best,

Sergio

Il giorno lun 21 ott 2019= alle ore 07:30 Reid Pinchback <rpinchback@tripadvisor.com> ha scritto:
<= /div>
I don't know whi= ch distro and version you are using, but watch out for surprises in what vm= .swappiness=3D0 means.=C2=A0 In older kernels it means "only use swap = when desperate".=C2=A0 I believe that newer kernels changed to have 1 = mean that, and 0 means to always use the oomkiller.=C2=A0 Neither situation= is strictly good or bad, what matters is what you intend the system behavi= or to be in comparison with whatever monitoring/alerting you have put in pl= ace.

R


=EF=BB=BFOn 10/18/19, 9:04 PM, "Sergio Bilello" <lapostadisergio@gmail.com= > wrote:

=C2=A0 =C2=A0 =C2=A0Message from External Sender

=C2=A0 =C2=A0 Hello everyone!



=C2=A0 =C2=A0 Do you have any setting that you would change or tweak from t= he below list?



=C2=A0 =C2=A0 sudo cat /proc/4379/limits

=C2=A0 =C2=A0 Limit=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0Soft Limit=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0Hard= Limit=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0Units

=C2=A0 =C2=A0 Max cpu time=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 = unlimited=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 seconds

=C2=A0 =C2=A0 Max file size=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0= unlimited=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 bytes

=C2=A0 =C2=A0 Max data size=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0= unlimited=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0 =C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 bytes

=C2=A0 =C2=A0 Max stack size=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlim= ited=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0 =C2=A0 =C2=A0= =C2=A0 =C2=A0 =C2=A0 bytes

=C2=A0 =C2=A0 Max core file size=C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0= =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 bytes

=C2=A0 =C2=A0 Max resident set=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited= =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 bytes

=C2=A0 =C2=A0 Max processes=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0= 32768=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 32768=C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 processes

=C2=A0 =C2=A0 Max open files=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 10485= 76=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 1048576=C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 files

=C2=A0 =C2=A0 Max locked memory=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0unlimited= =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 bytes

=C2=A0 =C2=A0 Max address space=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0unlimited= =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 bytes

=C2=A0 =C2=A0 Max file locks=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlim= ited=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0 =C2=A0 =C2=A0= =C2=A0 =C2=A0 =C2=A0 locks

=C2=A0 =C2=A0 Max pending signals=C2=A0 =C2=A0 =C2=A0 =C2=A0unlimited=C2=A0= =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0 =C2=A0 =C2=A0 =C2=A0 = =C2=A0 =C2=A0 signals

=C2=A0 =C2=A0 Max msgqueue size=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0unlimited= =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0 =C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 bytes

=C2=A0 =C2=A0 Max nice priority=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A00=C2=A0 = =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 0

=C2=A0 =C2=A0 Max realtime priority=C2=A0 =C2=A0 =C2=A00=C2=A0 =C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 0

=C2=A0 =C2=A0 Max realtime timeout=C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0 =C2= =A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 unlimited=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0= =C2=A0 us



=C2=A0 =C2=A0 These are the sysctl settings

=C2=A0 =C2=A0 default['cassandra']['sysctl'] =3D {

=C2=A0 =C2=A0 =C2=A0 =C2=A0 'net.ipv4.tcp_keepalive_time' =3D> 6= 0,

=C2=A0 =C2=A0 =C2=A0 =C2=A0 'net.ipv4.tcp_keepalive_probes' =3D>= 3,

=C2=A0 =C2=A0 =C2=A0 =C2=A0 'net.ipv4.tcp_keepalive_intvl' =3D> = 10,

=C2=A0 =C2=A0 =C2=A0 =C2=A0 'net.core.rmem_max' =3D> 16777216,
=C2=A0 =C2=A0 =C2=A0 =C2=A0 'net.core.wmem_max' =3D> 16777216,
=C2=A0 =C2=A0 =C2=A0 =C2=A0 'net.core.rmem_default' =3D> 1677721= 6,

=C2=A0 =C2=A0 =C2=A0 =C2=A0 'net.core.wmem_default' =3D> 1677721= 6,

=C2=A0 =C2=A0 =C2=A0 =C2=A0 'net.core.optmem_max' =3D> 40960,
=C2=A0 =C2=A0 =C2=A0 =C2=A0 'net.ipv4.tcp_rmem' =3D> '4096 8= 7380 16777216',

=C2=A0 =C2=A0 =C2=A0 =C2=A0 'net.ipv4.tcp_wmem' =3D> '4096 6= 5536 16777216',

=C2=A0 =C2=A0 =C2=A0 =C2=A0 'net.ipv4.ip_local_port_range' =3D> = '10000 65535',

=C2=A0 =C2=A0 =C2=A0 =C2=A0 'net.ipv4.tcp_window_scaling' =3D> 1= ,

=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0'net.core.netdev_max_backlog&#= 39; =3D> 2500,

=C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0 =C2=A0'net.core.somaxconn' =3D&g= t; 65000,

=C2=A0 =C2=A0 =C2=A0 =C2=A0 'vm.max_map_count' =3D> 1048575,

=C2=A0 =C2=A0 =C2=A0 =C2=A0 'vm.swappiness' =3D> 0

=C2=A0 =C2=A0 }



=C2=A0 =C2=A0 Am I missing something else?



=C2=A0 =C2=A0 Do you have any experience to configure CENTOS 7

=C2=A0 =C2=A0 for

=C2=A0 =C2=A0 JAVA HUGE PAGES

=C2=A0 =C2=A0 https://urldefense.proofpoint.com/v2/url?u=3D= https-3A__docs.datastax.com_en_dse_5.1_dse-2Dadmin_datastax-5Fenterprise_co= nfig_configRecommendedSettings.html-23CheckJavaHugepagessettings&d=3DDw= IBaQ&c=3D9Hv6XPedRSA-5PSECC38X80c1h60_XWA4z1k_R1pROA&r=3DOIgB3poYhz= p3_A7WgD7iBCnsJaYmspOa2okNpf6uqWc&m=3Dzke-WpkD1c6Qt1cz8mJG0ZQ37h8kezqkn= MSnerQhXuU&s=3Db6lGdbtv1SN9opBsIOFRT6IX6BroMW-8Tudk9qEh3bI&e=3D=



=C2=A0 =C2=A0 OPTIMIZE SSD

=C2=A0 =C2=A0 https://urldefense.proofpoint.com/v2/url?u=3Dhttps-3A__docs= .datastax.com_en_dse_5.1_dse-2Dadmin_datastax-5Fenterprise_config_configRec= ommendedSettings.html-23OptimizeSSDs&d=3DDwIBaQ&c=3D9Hv6XPedRSA-5PS= ECC38X80c1h60_XWA4z1k_R1pROA&r=3DOIgB3poYhzp3_A7WgD7iBCnsJaYmspOa2okNpf= 6uqWc&m=3Dzke-WpkD1c6Qt1cz8mJG0ZQ37h8kezqknMSnerQhXuU&s=3Dc0S3S3V_0= YHVMx2I-pyOh24MiQs1D-L73JytaSw648M&e=3D



=C2=A0 =C2=A0 https://urldefense.proofpoint.com/v2/url?u=3Dhttps-3A__docs.datastax.com_e= n_dse_5.1_dse-2Dadmin_datastax-5Fenterprise_config_configRecommendedSetting= s.html&d=3DDwIBaQ&c=3D9Hv6XPedRSA-5PSECC38X80c1h60_XWA4z1k_R1pROA&a= mp;r=3DOIgB3poYhzp3_A7WgD7iBCnsJaYmspOa2okNpf6uqWc&m=3Dzke-WpkD1c6Qt1cz= 8mJG0ZQ37h8kezqknMSnerQhXuU&s=3DPZFG6SXF6dL5LRJ-aUoidHnnLGpKPbpxdKstM8M= 9JMk&e=3D



=C2=A0 =C2=A0 We are using AWS i3.xlarge instances



=C2=A0 =C2=A0 Thanks,



=C2=A0 =C2=A0 Sergio



=C2=A0 =C2=A0 -------------------------------------------------------------= --------

=C2=A0 =C2=A0 To unsubscribe, e-mail: user-unsubscribe@cassandra.apache.org=

=C2=A0 =C2=A0 For additional commands, e-mail: user-help@cassandra.apache.org<= br>




--0000000000005e2c270595719221--