From: Paolo Bonzini <pbonzini@redhat.com>
To: Stefan Priebe - Profihost AG <s.priebe@profihost.ag>
Cc: qemu-devel@nongnu.org
Subject: Re: [Qemu-devel] scsi-hd with discard_granularity and unmap results in Aborted Commands
Date: Mon, 19 Nov 2012 10:54:08 +0100 [thread overview]
Message-ID: <50AA01C0.8030709@redhat.com> (raw)
In-Reply-To: <50A9FD86.3050400@profihost.ag>
Il 19/11/2012 10:36, Stefan Priebe - Profihost AG ha scritto:
> Hi Paolo,
>
> Am 19.11.2012 09:10, schrieb Paolo Bonzini:
>>> I'm sorry the discard requests aren't failing. Qemu / Block driver
>>> starts to cancel a bunch of requests.
>>
>> That is being done in the kernel (the guest, I think) because the UNMAPs
>> are taking too long.
>
> That makes sense. RBD handles discards as buffered I/O. When i do an
> mkfs.xfs on a 30GB device i see around 900 pending discard requests. rbd
> finishes them all before reporting success.
>
> If it is correct that a 3.6.7 kernel sends as many discard requests i
> only the a solution in using unbuffered I/O for discards.
>
> Do you know what is the correct way?
I think the correct fix is to serialize them in the kernel.
Paolo
next prev parent reply other threads:[~2012-11-19 9:54 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-08-18 21:49 [Qemu-devel] [PATCH RFT 0/3] iscsi: fix NULL dereferences / races between task completion and abort Paolo Bonzini
2012-08-18 21:49 ` [Qemu-devel] [PATCH 1/3] iscsi: move iscsi_schedule_bh and iscsi_readv_writev_bh_cb Paolo Bonzini
2012-08-18 21:49 ` [Qemu-devel] [PATCH 2/3] iscsi: simplify iscsi_schedule_bh Paolo Bonzini
2012-08-18 21:49 ` [Qemu-devel] [PATCH 3/3] iscsi: fix races between task completion and abort Paolo Bonzini
2012-08-19 7:55 ` [Qemu-devel] [PATCH RFT 0/3] iscsi: fix NULL dereferences / " Stefan Priebe
2012-08-19 13:11 ` Paolo Bonzini
2012-08-19 19:22 ` Stefan Priebe - Profihost AG
2012-08-20 7:22 ` Paolo Bonzini
2012-08-20 7:34 ` Stefan Priebe - Profihost AG
2012-08-20 8:08 ` Paolo Bonzini
2012-08-20 8:12 ` Stefan Priebe - Profihost AG
2012-08-20 22:36 ` ronnie sahlberg
2012-08-21 7:22 ` Stefan Priebe - Profihost AG
2012-08-21 7:30 ` Paolo Bonzini
2012-11-06 8:41 ` [Qemu-devel] scsi-hd with discard_granularity and unmap results in Aborted Commands Stefan Priebe - Profihost AG
2012-11-06 22:42 ` Paolo Bonzini
2012-11-07 18:57 ` Stefan Priebe
2012-11-18 22:00 ` Stefan Priebe
2012-11-19 8:10 ` Paolo Bonzini
2012-11-19 9:36 ` Stefan Priebe - Profihost AG
2012-11-19 9:54 ` Paolo Bonzini [this message]
2012-11-19 9:59 ` Stefan Priebe - Profihost AG
2012-11-19 10:06 ` Paolo Bonzini
2012-11-19 10:13 ` Stefan Priebe - Profihost AG
2012-11-19 10:23 ` Paolo Bonzini
2012-11-19 10:30 ` Stefan Priebe - Profihost AG
2012-11-19 10:36 ` Paolo Bonzini
2012-11-19 10:57 ` Stefan Priebe - Profihost AG
2012-11-19 11:16 ` Paolo Bonzini
2012-11-19 11:49 ` Stefan Priebe - Profihost AG
2012-11-19 12:24 ` Paolo Bonzini
2012-11-19 13:01 ` Stefan Priebe - Profihost AG
2012-11-19 13:06 ` Paolo Bonzini
2012-11-19 14:16 ` Stefan Priebe - Profihost AG
2012-11-19 14:32 ` Paolo Bonzini
2012-11-19 14:28 ` Stefan Priebe - Profihost AG
2012-11-19 14:41 ` Paolo Bonzini
2012-11-19 14:48 ` Stefan Priebe - Profihost AG
2012-11-19 15:03 ` Paolo Bonzini
2012-11-19 15:04 ` Stefan Priebe - Profihost AG
2012-11-19 15:22 ` Paolo Bonzini
2012-11-19 15:58 ` Stefan Priebe - Profihost AG
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=50AA01C0.8030709@redhat.com \
--to=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=s.priebe@profihost.ag \
/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.