All of lore.kernel.org
 help / color / mirror / Atom feed
From: Venkatesh Srinivas <venkateshs@google.com>
To: Wanlong Gao <gaowanlong@cn.fujitsu.com>
Cc: linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
	linux-scsi@vger.kernel.org, mst@redhat.com,
	JBottomley@parallels.com,
	virtualization@lists.linux-foundation.org, pbonzini@redhat.com,
	vsrinivas@ops101.org, digitaleric@google.com, mikew@google.com
Subject: Re: [PATCH V5 4/5] virtio-scsi: introduce multiqueue support
Date: Tue, 19 Mar 2013 18:46:57 -0700	[thread overview]
Message-ID: <20130320014657.GA14714@google.com> (raw)
In-Reply-To: <1363687057-13580-5-git-send-email-gaowanlong@cn.fujitsu.com>

This looks pretty good!

I rather like the (lack of) locking in I/O completion (around the req
count vs. target/queue binding). It is unfortunate that you need to 
hold the per-target lock in virtscsi_pick_vq() though; have any idea
how much that lock hurts?

Just two minor comments:

(in struct virtio_scsi_target_data):
+       /* This spinlock never help at the same time as vq_lock. */
                                ^^^^ held?

(in struct virtio_scsi):
+       /* Does the affinity hint is set for virtqueues? */
Could you rephrase that, please?

Tested on qemu and w/ Google Compute Engine's virtio-scsi device.

Reviewed-and-tested-by: Venkatesh Srinivas <venkateshs@google.com>

Thanks,
-- vs;

WARNING: multiple messages have this Message-ID (diff)
From: Venkatesh Srinivas <venkateshs@google.com>
To: Wanlong Gao <gaowanlong@cn.fujitsu.com>
Cc: linux-scsi@vger.kernel.org, kvm@vger.kernel.org, mst@redhat.com,
	linux-kernel@vger.kernel.org, JBottomley@parallels.com,
	virtualization@lists.linux-foundation.org, vsrinivas@ops101.org,
	pbonzini@redhat.com, mikew@google.com
Subject: Re: [PATCH V5 4/5] virtio-scsi: introduce multiqueue support
Date: Tue, 19 Mar 2013 18:46:57 -0700	[thread overview]
Message-ID: <20130320014657.GA14714@google.com> (raw)
In-Reply-To: <1363687057-13580-5-git-send-email-gaowanlong@cn.fujitsu.com>

This looks pretty good!

I rather like the (lack of) locking in I/O completion (around the req
count vs. target/queue binding). It is unfortunate that you need to 
hold the per-target lock in virtscsi_pick_vq() though; have any idea
how much that lock hurts?

Just two minor comments:

(in struct virtio_scsi_target_data):
+       /* This spinlock never help at the same time as vq_lock. */
                                ^^^^ held?

(in struct virtio_scsi):
+       /* Does the affinity hint is set for virtqueues? */
Could you rephrase that, please?

Tested on qemu and w/ Google Compute Engine's virtio-scsi device.

Reviewed-and-tested-by: Venkatesh Srinivas <venkateshs@google.com>

Thanks,
-- vs;

  reply	other threads:[~2013-03-20  1:47 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-03-19  9:57 [PATCH V5 0/5] virtio-scsi multiqueue Wanlong Gao
2013-03-19  9:57 ` Wanlong Gao
2013-03-19  9:57 ` [PATCH V5 1/5] virtio-scsi: redo allocation of target data Wanlong Gao
2013-03-19  9:57   ` Wanlong Gao
2013-03-19 11:32   ` James Bottomley
2013-03-19 11:45     ` Paolo Bonzini
2013-03-19 11:45       ` Paolo Bonzini
2013-03-19 12:00       ` James Bottomley
2013-03-19  9:57 ` [PATCH V5 2/5] virtio-scsi: pass struct virtio_scsi to virtqueue completion function Wanlong Gao
2013-03-19  9:57   ` Wanlong Gao
2013-03-19  9:57 ` [PATCH V5 3/5] virtio-scsi: push vq lock/unlock into virtscsi_vq_done Wanlong Gao
2013-03-19  9:57   ` Wanlong Gao
2013-03-19  9:57 ` [PATCH V5 4/5] virtio-scsi: introduce multiqueue support Wanlong Gao
2013-03-19  9:57   ` Wanlong Gao
2013-03-20  1:46   ` Venkatesh Srinivas [this message]
2013-03-20  1:46     ` Venkatesh Srinivas
2013-03-20  7:24     ` Wanlong Gao
2013-03-20  7:24       ` Wanlong Gao
2013-03-20  9:53     ` Paolo Bonzini
2013-03-20  9:53       ` Paolo Bonzini
2013-03-19  9:57 ` [PATCH V5 5/5] virtio-scsi: reset virtqueue affinity when doing cpu hotplug Wanlong Gao
2013-03-19  9:57   ` Wanlong Gao

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=20130320014657.GA14714@google.com \
    --to=venkateshs@google.com \
    --cc=JBottomley@parallels.com \
    --cc=digitaleric@google.com \
    --cc=gaowanlong@cn.fujitsu.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=mikew@google.com \
    --cc=mst@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=virtualization@lists.linux-foundation.org \
    --cc=vsrinivas@ops101.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.