From: Shirley Ma <mashirle@us.ibm.com>
To: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Avi Kivity <avi@redhat.com>, Arnd Bergmann <arnd@arndb.de>,
xiaohui.xin@intel.com, netdev@vger.kernel.org,
kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH 0/1] macvtap TX zero copy between guest and host kernel
Date: Tue, 14 Sep 2010 08:15:56 -0700 [thread overview]
Message-ID: <1284477356.13351.46.camel@localhost.localdomain> (raw)
In-Reply-To: <20100914120545.GC703@redhat.com>
Hello Miachel,
On Tue, 2010-09-14 at 14:05 +0200, Michael S. Tsirkin wrote:
> While others pointed out correctness issues with the patch,
> I would still like to see the performance numbers, just so we
> understand what's possible.
The performance looks good, it either saves the host CPU utilization the
guest is running on (by 8-10% in 8 cpus) or gain high BW w/i more guest
CPU utilization when host utilization is similar or less than before.
And I run 32 netperf instants and didn't hit any problem.
Here are output from host perf top: (I am upgrading my guest to most
recent kernel now to collect perf top data.) My guest has 2 vcpus, host
has 8 cpus.
Please let me know what performance data you would like to see. I will
run more
w/o zero copy patch:
-----------------------------------------------------------------------------------------------------------------------------------------------------------
PerfTop: 1708 irqs/sec kernel:63.7% exact: 0.0% [1000Hz cycles], (all, 8 CPUs)
-----------------------------------------------------------------------------------------------------------------------------------------------------------
samples pcnt function DSO
_______ _____ ____________________________ __________________________________________________________
6842.00 47.4% copy_user_generic_string /lib/modules/2.6.36-rc3+/build/vmlinux
329.00 2.3% get_page_from_freelist /lib/modules/2.6.36-rc3+/build/vmlinux
307.00 2.1% list_del /lib/modules/2.6.36-rc3+/build/vmlinux
289.00 2.0% alloc_pages_current /lib/modules/2.6.36-rc3+/build/vmlinux
283.00 2.0% __alloc_pages_nodemask /lib/modules/2.6.36-rc3+/build/vmlinux
234.00 1.6% ixgbe_xmit_frame /lib/modules/2.6.36-rc3+/kernel/drivers/net/ixgbe/ixgbe.ko
232.00 1.6% vmx_vcpu_run /lib/modules/2.6.36-rc3+/kernel/arch/x86/kvm/kvm-intel.ko
210.00 1.5% schedule /lib/modules/2.6.36-rc3+/build/vmlinux
173.00 1.2% _cond_resched /lib/modules/2.6.36-rc3+/build/vmlinux
w/i zero copy patch:
-------------------------------------------------------------------------------
PerfTop: 1108 irqs/sec kernel:43.0% exact: 0.0% [1000Hz cycles], (all, 8 CPUs)
-------------------------------------------------------------------------------
samples pcnt function DSO
_______ _____ ________________________ ___________
281.00 5.1% copy_user_generic_string [kernel]
235.00 4.3% vmx_vcpu_run [kvm_intel]
228.00 4.1% gup_pte_range [kernel]
211.00 3.8% tg_shares_up [kernel]
179.00 3.2% schedule [kernel]
148.00 2.7% _raw_spin_lock_irqsave [kernel]
139.00 2.5% iommu_no_mapping [kernel]
124.00 2.2% ixgbe_xmit_frame [ixgbe]
123.00 2.2% kvm_arch_vcpu_ioctl_run [kvm]
122.00 2.2% _raw_spin_lock [kernel]
113.00 2.1% put_page [kernel]
92.00 1.7% vhost_get_vq_desc [vhost_net]
81.00 1.5% get_user_pages_fast [kernel]
81.00 1.5% memcpy_fromiovec [kernel]
80.00 1.5% translate_desc [vhost_net]
w/i zero copy patch, and NIC IRQ cpu affinity (netper/netserver on cpu 0, interrupts on cpu1)
[root@localhost ~]# netperf -H 10.0.4.74 -c -C -l 60 -T0,0 -- -m 65536
TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.0.4.74 (10.0.4.74) port 0 AF_INET : cpu bind
Recv Send Send Utilization Service Demand
Socket Socket Message Elapsed Send Recv Send Recv
Size Size Size Time Throughput local remote local remote
bytes bytes bytes secs. 10^6bits/s % S % S us/KB us/KB
87380 16384 65536 60.00 9384.25 53.92 13.62 0.941 0.951
[root@localhost ~]#
prev parent reply other threads:[~2010-09-14 15:16 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-09-13 20:43 [RFC PATCH 0/1] macvtap TX zero copy between guest and host kernel Shirley Ma
2010-09-13 20:47 ` RFC PATCH 1/2] macvtap: A new sock zero copy flag Shirley Ma
2010-09-13 20:48 ` [RFC PATCH 2/2] macvtap: TX zero copy between guest and host kernel Shirley Ma
2010-09-14 3:17 ` David Miller
2010-09-14 9:12 ` Avi Kivity
2010-09-14 15:05 ` Shirley Ma
2010-09-14 15:21 ` Arnd Bergmann
2010-09-14 15:22 ` Michael S. Tsirkin
2010-09-14 16:00 ` Shirley Ma
2010-09-14 16:29 ` Michael S. Tsirkin
2010-09-14 17:02 ` Shirley Ma
2010-09-14 18:27 ` Michael S. Tsirkin
2010-09-14 18:49 ` Shirley Ma
2010-09-14 19:01 ` Michael S. Tsirkin
2010-09-14 19:20 ` Shirley Ma
2010-09-15 5:31 ` Michael S. Tsirkin
2010-09-14 19:36 ` Shirley Ma
2010-09-15 5:12 ` Michael S. Tsirkin
2010-09-15 6:21 ` Shirley Ma
2010-09-15 10:10 ` Michael S. Tsirkin
2010-09-15 14:52 ` Shirley Ma
2010-09-15 15:04 ` Michael S. Tsirkin
2010-09-15 15:39 ` Michael S. Tsirkin
2010-09-15 17:00 ` Shirley Ma
2010-09-15 17:30 ` Michael S. Tsirkin
2010-09-15 18:48 ` Shirley Ma
2010-09-29 3:24 ` Shirley Ma
2010-09-29 8:16 ` Michael S. Tsirkin
2010-09-29 8:28 ` Michael S. Tsirkin
2010-09-29 14:33 ` Shirley Ma
2010-09-29 14:56 ` Shirley Ma
2010-09-29 14:31 ` Shirley Ma
2010-09-29 14:37 ` Shirley Ma
2010-09-29 15:14 ` Michael S. Tsirkin
2010-09-29 15:23 ` Shirley Ma
2010-09-15 2:46 ` Xin, Xiaohui
2010-09-15 9:58 ` Michael S. Tsirkin
2010-09-16 8:18 ` Xin, Xiaohui
2010-09-16 10:02 ` Michael S. Tsirkin
2010-09-15 1:56 ` Xin, Xiaohui
2010-09-15 1:50 ` Xin, Xiaohui
2010-09-15 2:40 ` Shirley Ma
2010-09-15 2:55 ` Xin, Xiaohui
2010-09-15 5:27 ` Michael S. Tsirkin
2010-09-15 6:17 ` Shirley Ma
2010-09-14 12:05 ` [RFC PATCH 0/1] macvtap " Michael S. Tsirkin
2010-09-14 15:15 ` Shirley Ma [this message]
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=1284477356.13351.46.camel@localhost.localdomain \
--to=mashirle@us.ibm.com \
--cc=arnd@arndb.de \
--cc=avi@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=xiaohui.xin@intel.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).