From mboxrd@z Thu Jan 1 00:00:00 1970 From: Subject: RE: [CEPH][Crush][Tunables] issue when updating tunables Date: Thu, 12 Nov 2015 14:11:36 +0000 Message-ID: <22767_1447337497_56449E19_22767_66_1_B9C8EFBF13B1354DB5FA000660D66DD00D64B970@OPEXCLILM22.corporate.adroot.infra.ftgroup> References: <25091_1447144373_5641ABB5_25091_8387_1_B9C8EFBF13B1354DB5FA000660D66DD00D64A5FA@OPEXCLILM22.corporate.adroot.infra.ftgroup> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Received: from relais-ias243.francetelecom.com ([80.12.204.243]:44987 "EHLO relais-inet.francetelecom.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753037AbbKLOLl convert rfc822-to-8bit (ORCPT ); Thu, 12 Nov 2015 09:11:41 -0500 In-Reply-To: Content-Language: fr-FR Sender: ceph-devel-owner@vger.kernel.org List-ID: To: Sage Weil Cc: "ceph-devel@vger.kernel.org" Hi Sage, Thanks for the reply You said=20 " You actually want straw_calc_version 1. This is just confusing outpu= t from the 'firefly' tunable detection... the straw_calc_version does n= ot have any client dependencies." My objective is to have the most relevant tunables for a firefly platfo= rm. I didn't understand if : - it's better to have straw_calc_version set to 1 but tunables_optimal= will be automatically set to 0. In other words are the following tunables OK ? { "choose_local_tries": 0, > "choose_local_fallback_tries": 0, > "choose_total_tries": 50, > "chooseleaf_descend_once": 1, > "chooseleaf_vary_r": 1, > "straw_calc_version": 0, > "profile": "firefly", > "optimal_tunables": 1, > "legacy_tunables": 0, > "require_feature_tunables": 1, > "require_feature_tunables2": 1, > "require_feature_tunables3": 1, > "has_v2_rules": 0, > "has_v3_rules": 0}=20 - there's an issue with the tunables detection and update? Best regards=20 -----Message d'origine----- De=A0: Sage Weil [mailto:sage@newdream.net]=20 Envoy=E9=A0: mardi 10 novembre 2015 11:23 =C0=A0: CHEVALIER Ghislain IMT/OLPS Cc=A0: ceph-devel@vger.kernel.org Objet=A0: Re: [CEPH][Crush][Tunables] issue when updating tunables On Tue, 10 Nov 2015, ghislain.chevalier@orange.com wrote: > Hi all, >=20 > Context: > Firefly 0.80.9 > Ubuntu 14.04.1 > Almost a production platform in an openstack environment > 176 OSD (SAS and SSD), 2 crushmap-oriented storage classes , 8 server= s=20 > in 2 rooms, 3 monitors on openstack controllers > Usage: Rados Gateway for object service and RBD as back-end for Cinde= r=20 > and Glance >=20 > The Ceph cluster was installed by Mirantis procedures (puppet/fuel/ce= ph-deploy): >=20 > I noticed that tunables were curiously set. > ceph osd crush show-tunables =3D=3D> > { "choose_local_tries": 0, > "choose_local_fallback_tries": 0, > "choose_total_tries": 50, > "chooseleaf_descend_once": 1, > "chooseleaf_vary_r": 1, > "straw_calc_version": 1, > "profile": "unknown", > "optimal_tunables": 0, > "legacy_tunables": 0, > "require_feature_tunables": 1, > "require_feature_tunables2": 1, > "require_feature_tunables3": 1, > "has_v2_rules": 0, > "has_v3_rules": 0} >=20 > I tried to update them > ceph osd crush tunables optimal =3D=3D> > adjusted tunables profile to optimal >=20 > But when checking > ceph osd crush show-tunables =3D=3D> > { "choose_local_tries": 0, > "choose_local_fallback_tries": 0, > "choose_total_tries": 50, > "chooseleaf_descend_once": 1, > "chooseleaf_vary_r": 1, > "straw_calc_version": 1, > "profile": "unknown", > "optimal_tunables": 0, > "legacy_tunables": 0, > "require_feature_tunables": 1, > "require_feature_tunables2": 1, > "require_feature_tunables3": 1, > "has_v2_rules": 0, > "has_v3_rules": 0} >=20 > Nothing has changed. >=20 > I finally did > ceph osd crush set-tunable straw_calc_version 0 You actually want straw_calc_version 1. This is just confusing output = from the 'firefly' tunable detection... the straw_calc_version does not= have any client dependencies. sage >=20 > and > ceph osd crush show-tunables =3D=3D> > { "choose_local_tries": 0, > "choose_local_fallback_tries": 0, > "choose_total_tries": 50, > "chooseleaf_descend_once": 1, > "chooseleaf_vary_r": 1, > "straw_calc_version": 0, > "profile": "firefly", > "optimal_tunables": 1, > "legacy_tunables": 0, > "require_feature_tunables": 1, > "require_feature_tunables2": 1, > "require_feature_tunables3": 1, > "has_v2_rules": 0, > "has_v3_rules": 0} >=20 > It's OK >=20 > My question: > Does the "ceph osd crush tunables " command change all the r= equested parameters in order to set the tunables to the right profile? >=20 > Brgds >=20 > _____________________________________________________________________= _ > ___________________________________________________ >=20 > Ce message et ses pieces jointes peuvent contenir des informations=20 > confidentielles ou privilegiees et ne doivent donc pas etre diffuses,= =20 > exploites ou copies sans autorisation. Si vous avez recu ce message=20 > par erreur, veuillez le signaler a l'expediteur et le detruire ainsi=20 > que les pieces jointes. Les messages electroniques etant susceptibles= =20 > d'alteration, France Telecom - Orange decline toute responsabilite si= =20 > ce message a ete altere, deforme ou falsifie. Merci >=20 > This message and its attachments may contain confidential or=20 > privileged information that may be protected by law; they should not = be distributed, used or copied without authorization. > If you have received this email in error, please notify the sender an= d delete this message and its attachments. > As emails may be altered, France Telecom - Orange shall not be liable= if this message was modified, changed or falsified. > Thank you. >=20 > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel"= =20 > in the body of a message to majordomo@vger.kernel.org More majordomo=20 > info at http://vger.kernel.org/majordomo-info.html >=20 >=20 _______________________________________________________________________= __________________________________________________ Ce message et ses pieces jointes peuvent contenir des informations conf= identielles ou privilegiees et ne doivent donc pas etre diffuses, exploites ou copies sans autorisation. Si vous avez = recu ce message par erreur, veuillez le signaler a l'expediteur et le detruire ainsi que les pieces jointes. Les message= s electroniques etant susceptibles d'alteration, Orange decline toute responsabilite si ce message a ete altere, deforme= ou falsifie. Merci. This message and its attachments may contain confidential or privileged= information that may be protected by law; they should not be distributed, used or copied without authorisation. If you have received this email in error, please notify the sender and = delete this message and its attachments. As emails may be altered, Orange is not liable for messages that have b= een modified, changed or falsified. Thank you. -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html