From: Eric Blake <eblake@redhat.com>
To: Alberto Garcia <berto@igalia.com>, Max Reitz <mreitz@redhat.com>,
Kevin Wolf <kwolf@redhat.com>
Cc: qemu-block@nongnu.org, qemu-devel@nongnu.org,
Markus Armbruster <armbru@redhat.com>,
Stefan Hajnoczi <stefanha@redhat.com>,
John Snow <jsnow@redhat.com>
Subject: Re: [Qemu-devel] [PATCH v5 17/38] block: Add BlockBackendRootState
Date: Tue, 29 Sep 2015 06:30:04 -0600 [thread overview]
Message-ID: <560A844C.6020801@redhat.com> (raw)
In-Reply-To: <w51mvw58of2.fsf@maestria.local.igalia.com>
[-- Attachment #1: Type: text/plain, Size: 1906 bytes --]
On 09/29/2015 05:17 AM, Alberto Garcia wrote:
> On Tue 22 Sep 2015 05:00:05 PM CEST, Max Reitz wrote:
>
>>> The correct way to solve this seems to be that each BB has its own
>>> I/O throttling filter. Actually, if we could lift the throttling code
>>> to BlockBackend, that might solve the problem.
>>
>> So yes, as long as we have throttling on the BDS level, something may
>> always break when having multiple BBs per BDS, because you'd probably
>> want throttling to be on the BB level. But lifting that doesn't seem a
>> trivial task, and I don't really know whether I want this in this
>> series.
>>
>> Especially considering that right now you cannot have multiple BBs per
>> BDS.
>>
>> All in all: Yes, before we allow multiple BBs per BDS we want
>> throttling to be on the BB level. But this is nothing that should be
>> done in or for this series, since right now we do not allow multiple
>> BBs per BDS.
>
> I agree that it makes sense to move throttling to the BB level. It's
> probably not trivial but I don't think it's too complex either. I can
> give it a look once this series has been merged.
Ultimately, I think we want throttling at both levels. I can make the
argument that in a cloud, a guest should not be able to consume more
than X resources (throttling at the BB, regardless of what BDS tree it
is associated with); but I can also argue that I may want to throttle
specific BDS (a backing chain with network backing file and local active
file: throttle the backing file to limit network traffic, and the guest
gets faster as it moves more local; or conversely, a common backing file
and one-off guest: throttle the active layer to do performance analysis
of the bottlenecks where the guest differs from the common backing layer).
--
Eric Blake eblake redhat com +1-919-301-3266
Libvirt virtualization library http://libvirt.org
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 604 bytes --]
next prev parent reply other threads:[~2015-09-29 12:30 UTC|newest]
Thread overview: 74+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-18 15:22 [Qemu-devel] [PATCH v5 00/38] blockdev: BlockBackend and media Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 01/38] block: Remove host floppy support Max Reitz
2015-09-18 15:31 ` Eric Blake
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 02/38] block: Set BDRV_O_INCOMING in bdrv_fill_options() Max Reitz
2015-09-18 15:32 ` Eric Blake
2015-09-29 8:53 ` Alberto Garcia
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 03/38] blockdev: Allow creation of BDS trees without BB Max Reitz
2015-09-18 15:34 ` Eric Blake
2015-09-29 8:45 ` Alberto Garcia
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 04/38] iotests: Only create BB if necessary Max Reitz
2015-09-18 16:00 ` Eric Blake
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 05/38] block: Make bdrv_is_inserted() return a bool Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 06/38] block: Add blk_is_available() Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 07/38] block: Make bdrv_is_inserted() recursive Max Reitz
2015-09-18 16:20 ` Eric Blake
2015-09-29 9:15 ` Alberto Garcia
2015-09-30 14:32 ` Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 08/38] block/raw_bsd: Drop raw_is_inserted() Max Reitz
2015-09-18 16:20 ` Eric Blake
2015-09-29 10:47 ` Alberto Garcia
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 09/38] block: Invoke change media CB before NULLing drv Max Reitz
2015-09-18 16:22 ` Eric Blake
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 10/38] hw/block/fdc: Implement tray status Max Reitz
2015-09-18 16:24 ` Eric Blake
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 11/38] hw/usb-storage: Check whether BB is inserted Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 12/38] block: Fix BB AIOCB AioContext without BDS Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 13/38] block: Move guest_block_size into BlockBackend Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 14/38] block: Remove wr_highest_sector from BlockAcctStats Max Reitz
2015-09-18 16:59 ` Eric Blake
2015-09-21 7:57 ` Kevin Wolf
2015-09-21 15:53 ` Eric Blake
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 15/38] block: Move BlockAcctStats into BlockBackend Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 16/38] block: Move I/O status and error actions into BB Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 17/38] block: Add BlockBackendRootState Max Reitz
2015-09-22 14:17 ` Kevin Wolf
2015-09-22 15:00 ` Max Reitz
2015-09-29 11:17 ` Alberto Garcia
2015-09-29 12:30 ` Eric Blake [this message]
2015-09-29 13:12 ` Kevin Wolf
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 18/38] block: Make some BB functions fall back to BBRS Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 19/38] block: Fail requests to empty BlockBackend Max Reitz
2015-09-22 14:30 ` Kevin Wolf
2015-09-22 15:05 ` Max Reitz
2015-09-22 15:13 ` Kevin Wolf
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 20/38] block: Prepare remaining BB functions for NULL BDS Max Reitz
2015-09-22 14:35 ` Kevin Wolf
2015-09-22 15:07 ` Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 21/38] block: Add blk_insert_bs() Max Reitz
2015-09-22 14:42 ` Kevin Wolf
2015-09-22 15:20 ` Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 22/38] block: Prepare for NULL BDS Max Reitz
2015-09-18 19:42 ` Eric Blake
2015-10-07 10:43 ` Kevin Wolf
2015-10-07 15:08 ` Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 23/38] blockdev: Do not create BDS for empty drive Max Reitz
2015-09-18 15:22 ` [Qemu-devel] [PATCH v5 24/38] blockdev: Pull out blockdev option extraction Max Reitz
2015-09-30 11:16 ` Alberto Garcia
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 25/38] blockdev: Allow more options for BB-less BDS tree Max Reitz
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 26/38] block: Add blk_remove_bs() Max Reitz
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 27/38] blockdev: Add blockdev-open-tray Max Reitz
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 28/38] blockdev: Add blockdev-close-tray Max Reitz
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 29/38] blockdev: Add blockdev-remove-medium Max Reitz
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 30/38] blockdev: Add blockdev-insert-medium Max Reitz
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 31/38] blockdev: Implement eject with basic operations Max Reitz
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 32/38] blockdev: Implement change " Max Reitz
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 33/38] block: Inquire tray state before tray-moved events Max Reitz
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 34/38] qmp: Introduce blockdev-change-medium Max Reitz
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 35/38] hmp: Use blockdev-change-medium for change command Max Reitz
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 36/38] blockdev: read-only-mode for blockdev-change-medium Max Reitz
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 37/38] hmp: Add read-only-mode option to change command Max Reitz
2015-09-18 15:23 ` [Qemu-devel] [PATCH v5 38/38] iotests: Add test for change-related QMP commands Max Reitz
2015-09-22 14:45 ` [Qemu-devel] [PATCH v5 00/38] blockdev: BlockBackend and media Kevin Wolf
2015-09-22 15:09 ` Max Reitz
2015-09-23 6:20 ` Wen Congyang
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=560A844C.6020801@redhat.com \
--to=eblake@redhat.com \
--cc=armbru@redhat.com \
--cc=berto@igalia.com \
--cc=jsnow@redhat.com \
--cc=kwolf@redhat.com \
--cc=mreitz@redhat.com \
--cc=qemu-block@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=stefanha@redhat.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).