Re: [PATCH 2/5] virtio_blk: implement REQ_FLUSH/FUA support

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

From: Tejun Heo

Subject: Re: [PATCH 2/5] virtio_blk: implement REQ_FLUSH/FUA support

Date: Tuesday, August 17, 2010 - 1:17 am

Hello,

On 08/16/2010 08:33 PM, Christoph Hellwig wrote:
quoted text> On Mon, Aug 16, 2010 at 06:52:00PM +0200, Tejun Heo wrote:
>> From: Tejun Heo <tj@kernle.org>
>>
>> Remove now unused REQ_HARDBARRIER support and implement REQ_FLUSH/FUA
>> support instead.  A new feature flag VIRTIO_BLK_F_FUA is added to
>> indicate the support for FUA.
> 
> I'm not sure it's worth it.  The pure REQ_FLUSH path works not and is
> well tested with kvm/qemu.   We can still easily add a FUA bit, and
> even a pre-flush bit if the protocol roundtrips matter in real life
> benchmarking.

Hmmm... the underlying storage could be md/dm RAIDs in which case FUA
should be cheaper than FLUSH.

Thanks.

-- 
tejun
--
unsubscribe noticeTo unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:

[PATCH 2/5] virtio_blk: implement REQ_FLUSH/FUA support, Tejun Heo, (Mon Aug 16, 9:52 am)

Re: [PATCH 2/5] virtio_blk: implement REQ_FLUSH/FUA support, Christoph Hellwig, (Mon Aug 16, 11:33 am)

Re: [PATCH 2/5] virtio_blk: implement REQ_FLUSH/FUA support, Rusty Russell, (Mon Aug 16, 6:16 pm)

Re: [PATCH 2/5] virtio_blk: implement REQ_FLUSH/FUA support, Tejun Heo, (Tue Aug 17, 1:17 am)

Re: [PATCH 2/5] virtio_blk: implement REQ_FLUSH/FUA support, Tejun Heo, (Tue Aug 17, 1:18 am)

Re: [PATCH 2/5] virtio_blk: implement REQ_FLUSH/FUA support, Christoph Hellwig, (Tue Aug 17, 6:23 am)

Re: [PATCH 2/5] virtio_blk: implement REQ_FLUSH/FUA support, Tejun Heo, (Tue Aug 17, 9:22 am)

Re: [PATCH 2/5] virtio_blk: implement REQ_FLUSH/FUA support, Rusty Russell, (Wed Aug 18, 3:22 am)

[PATCH 2/5 UPDATED] virtio_blk: drop REQ_HARDBARRIER support, Tejun Heo, (Thu Aug 19, 8:14 am)


linux-kernel:
Christoph Lameter	Re: [bug] SLUB + mm/slab.c boot crash in -rc9
Grant Grundler	Re: [patch] e1000=y && e1000e=m regression fix (was: Re: [regression] e100...
Jörn	Re: [00/41] Large Blocksize Support V7 (adds memmap support)
Jeremy Fitzhardinge	Re: [2.6.25] compat VDSO option not disabling
Rafael J. Wysocki	[Bug #11551] Semi-repeatable hard lockup on 2.6.27-rc6
git:
Pat Thoyts	[PATCH] git-gui: use themed tk widgets with Tk 8.5
Frans Pop	'git gc --aggressive' effectively unusable
Stephan Beyer	Re: git sequencer prototype
Lynn Lin	Re: clearcase migration to git
Johannes Schindelin	Re: [PATCH 2/3] unpack-trees: fix path search bug in verify_absent
linux-netdev:
William Allen Simpson	[net-next-2.6 PATCH v8 0/7] TCPCT part 1: cookie option exchange
David Woodhouse	Re: [bug?] tg3: Failed to load firmware "tigon/tg3_tso.bin"
Eric Dumazet	Re: [PATCH net-next-2.6] net: Introduce skb_orphan_try()
Eric Dumazet	Re: [PATCH net-next-2.6] net: Introduce skb_orphan_try()
Sage Weil	Re: [2/3] POHMELFS: Documentation.
git-commits-head:
Linux Kernel Mailing List	sparc64: Fix sun4u execute bit check in TSB I-TLB load.
Linux Kernel Mailing List	init: Open /dev/console from rootfs
Linux Kernel Mailing List	Remove empty comment in acpi/power.c
Linux Kernel Mailing List	x86 boot: only pick up additional EFI memmap if add_efi_memmap flag
Linux Kernel Mailing List	udp: fix for unicast RX path optimization
openbsd-misc:
nixlists	Re: Which laptops do the developers use?
L. V. Lammert	OT, .. but has anyone seen a crontab editor
Nick Holland	Re: Upgrade 4.1->4.2->4.3
Darrin Chandler	Re: That whole "Linux stealing our code" thing
Siju George	Re: Blocking Teamviewer