All of lore.kernel.org
 help / color / mirror / Atom feed
From: A L <mail@lechevalier.se>
To: Hans van Kranenburg <hans@knorrie.org>, linux-btrfs@vger.kernel.org
Subject: Re: Debugging abysmal write performance with 100% cpu kworker/u16:X+flush-btrfs-2
Date: Sun, 26 Jul 2020 10:10:31 +0200	[thread overview]
Message-ID: <6662c137-862e-0fa8-b147-317c26db99ac@lechevalier.se> (raw)
In-Reply-To: <a370a2bf-25b5-eaa0-a5e5-595c967e82a6@knorrie.org>


> Now I have a btrfs receive running for >1.5T of customer garbage...
> Receive cannot stop and resume. So am I going to abort and redo it while
> it's at 75.2GiB 5:57:46 [1.44MiB/s]? Or just sit it out?
>
> Stay tuned for the next episode of Knorrie's btrfs adventures! :)
Always interesting stories :)

Anyways, can you throttle your send|receive by putting mbuffer in 
between? I have myself had quite good success with mbuffer in reducing 
overall I/O, not to mention the ability to limit overall speed.


A

  reply	other threads:[~2020-07-26  8:10 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-25 14:24 Debugging abysmal write performance with 100% cpu kworker/u16:X+flush-btrfs-2 Hans van Kranenburg
2020-07-25 15:37 ` Holger Hoffstätte
2020-07-25 16:43   ` Hans van Kranenburg
2020-07-25 19:44     ` Holger Hoffstätte
2020-07-25 21:03       ` Hans van Kranenburg
2020-07-26  1:00         ` Chris Murphy
2020-07-25 21:27 ` Hans van Kranenburg
2020-07-26  8:10   ` A L [this message]
2020-07-26  0:50 ` Chris Murphy
2020-07-27 11:09 ` Qu Wenruo
2020-07-27 17:17   ` Hans van Kranenburg
2020-07-27 19:23     ` Chris Murphy
2020-07-27 23:16     ` Chris Murphy
2020-07-28  0:51     ` Qu Wenruo
2020-07-28  1:52       ` Qu Wenruo
2020-07-28 14:52         ` Hans van Kranenburg
2020-07-29  0:15           ` Qu Wenruo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=6662c137-862e-0fa8-b147-317c26db99ac@lechevalier.se \
    --to=mail@lechevalier.se \
    --cc=hans@knorrie.org \
    --cc=linux-btrfs@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.