Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Subject: Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
From: Peter Lieven <pl@xxxxxxx>
Date: Wed, 10 Nov 2021 10:15:15 +0100
Cc: "ceph-users@xxxxxxx" <ceph-users@xxxxxxx>
In-reply-to: <1636534634595.93545@1und1.de>
References: <SL2PR01MB3385099EA0811416FA61B1A485869@SL2PR01MB3385.apcprd01.prod.exchangelabs.com> <20211028142159.063f6423@lxmlausch2> <CAN0f57ET4kwNE7NE8wK_LSJg9UeoBYa3FwpQtTN9aDphwNfPeg@mail.gmail.com> <20211102142946.2668f2d8@lxmlausch2> <CAN0f57GTCF1koysYutUMDGaypaB1q8vtcOGc5Cfdi9SY56SG+Q@mail.gmail.com> <20211104101459.6e48cb88@lxmlausch2> <CAN0f57GwMVk0g_vqmZ96+qF=1Luj5pr-BYkR5FXzsa8QmR-7XQ@mail.gmail.com> <26c7f2ba-7af0-9f96-ca1f-b9084fe59879@kamp.de> <20211105144049.61865f20@lxmlausch2> <CAN0f57F373gp9M=wcW52rEP85-Fa-KsxSfxEXjVLu-S6nHB6=A@mail.gmail.com> <20211108130324.4e97d834@lxmlausch2> <CAN0f57G32ThCXkXH5qKgyhHT7KknaQzcswj0tR4+2BH0cArpLQ@mail.gmail.com> <20211109101751.5dbea10a@lxmlausch2> <CAN0f57EV668fgdrhoxTrXCzvgU4jUwb+VmUAp2gxDdT4v47ZSg@mail.gmail.com> <20211109150823.6e503edd@lxmlausch2> <CAN0f57Fzm7xOWwm-cigC4maGntcxj3mcvFgtvCCAsEHv4kYZRg@mail.gmail.com> <CAN0f57H7W1MJQ-JBwTEeR3cFHwbaXppfqnTQdggq3ZMciF0MHw@mail.gmail.com> <1636534634595.93545@1und1.de>
User-agent: Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101 Thunderbird/68.10.0

Am 10.11.21 um 09:57 schrieb Manuel Lausch:
> Hi Sage,
>
>
> thank you for your help.
>
>
> My origin issue with slow ops on osd restarts are gone too. Even with default values for paxos_proposal_interval.
>
>
> Its a bit annoying, that I spent many hours to debug this and finally I missed only one step in the upgrade.
>
> Only during the update itself, until require_osd_release is set to the new version, there will be interruptions


However, in Octopus the issue does still exist, right?


Peter



_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx

Follow-Ups:
- Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Manuel Lausch

References:
- OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Szabo, Istvan (Agoda)
- Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Manuel Lausch
- Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Sage Weil
- Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Manuel Lausch
- Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Sage Weil
- Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Manuel Lausch
- Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Sage Weil
- Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Peter Lieven
- Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Manuel Lausch
- Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Sage Weil
- Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Manuel Lausch
- Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Sage Weil
- Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
  - From: Manuel Lausch

Prev by Date: Re: steady increasing of osd map epoch since octopus
Next by Date: Re: Question if WAL/block.db partition will benefit us
Previous by thread: Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
Next by thread: Re: OSD spend too much time on "waiting for readable" -> slow ops -> laggy pg -> rgw stop -> worst case osd restart
Index(es):
- Date
- Thread

[Index of Archives] [Information on CEPH] [Linux Filesystem Development] [Ceph Development] [Ceph Large] [Ceph Dev] [Linux USB Development] [Video for Linux] [Linux Audio Users] [Yosemite News] [Linux Kernel] [Linux SCSI] [xfs]