RHEL Engineering is moving the tracking of its product development work on RHEL 6 through RHEL 9 to Red Hat Jira (issues.redhat.com). If you're a Red Hat customer, please continue to file support cases via the Red Hat customer portal. If you're not, please head to the "RHEL project" in Red Hat Jira and file new tickets here. Individual Bugzilla bugs in the statuses "NEW", "ASSIGNED", and "POST" are being migrated throughout September 2023. Bugs of Red Hat partners with an assigned Engineering Partner Manager (EPM) are migrated in late September as per pre-agreed dates. Bugs against components "kernel", "kernel-rt", and "kpatch" are only migrated if still in "NEW" or "ASSIGNED". If you cannot log in to RH Jira, please consult article #7032570. That failing, please send an e-mail to the RH Jira admins at rh-issues@redhat.com to troubleshoot your issue as a user management inquiry. The email creates a ServiceNow ticket with Red Hat. Individual Bugzilla bugs that are migrated will be moved to status "CLOSED", resolution "MIGRATED", and set with "MigratedToJIRA" in "Keywords". The link to the successor Jira issue will be found under "Links", have a little "two-footprint" icon next to it, and direct you to the "RHEL project" in Red Hat Jira (issue links are of type "https://issues.redhat.com/browse/RHEL-XXXX", where "X" is a digit). This same link will be available in a blue banner at the top of the page informing you that that bug has been migrated.
Bug 921891 - The speed of changed balloon size slower after change balloon size
Summary: The speed of changed balloon size slower after change balloon size
Keywords:
Status: CLOSED DUPLICATE of bug 997720
Alias: None
Product: Red Hat Enterprise Linux 7
Classification: Red Hat
Component: virtio-win
Version: 7.0
Hardware: Unspecified
OS: Unspecified
low
low
Target Milestone: rc
: ---
Assignee: Gal Hammer
QA Contact: Virtualization Bugs
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2013-03-15 08:12 UTC by langfang
Modified: 2014-01-06 02:38 UTC (History)
13 users (show)

Fixed In Version:
Doc Type: Bug Fix
Doc Text:
Clone Of:
Environment:
Last Closed: 2014-01-06 02:38:33 UTC
Target Upstream Version:
Embargoed:

Attachments (Terms of Use)

Description langfang 2013-03-15 08:12:04 UTC 
Description of problem:
Eg:Boot guest with "-M 6114 "-->(qemu)ballon 2000---> the balloon size change from 6114 to 2000 need about 80sec(change speed little slower)

Version-Release number of selected component (if applicable):
Host:
# uname -r
3.7.0-0.36.el7.x86_64             
# rpm -q qemu-kvm                       
qemu-kvm-1.4.0-1.el7.x86_64       

Guest:windown2012

How reproducible:
100%

Steps to Reproduce:
1.Boot guest with ballon device
"-device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x6"

2.After guest boot up,change balloon size
QEMU 1.4.0 monitor - type 'help' for more information
(qemu) info balloon
balloon: actual=6114
(qemu) balloon 2000
(qemu) info balloon
balloon: actual=5970
(qemu) info balloon
balloon: actual=5916
(qemu) info balloon
balloon: actual=5884
(qemu) info balloon
balloon: actual=5854
(qemu) info balloon
balloon: actual=5820
(qemu) info balloon
balloon: actual=5786
(qemu) info balloon
balloon: actual=5752
(qemu) info balloon
balloon: actual=5718
(qemu) info balloon
balloon: actual=5686
(qemu) info balloon
balloon: actual=5656
(qemu) info balloon
balloon: actual=5394
(qemu) info balloon
balloon: actual=5332
(qemu) info balloon
balloon: actual=5262
(qemu) info balloon
balloon: actual=5200
(qemu) info balloon
balloon: actual=5130
(qemu) info balloon
balloon: actual=5062
(qemu) info balloon
balloon: actual=3974
(qemu) info balloon
balloon: actual=3906
(qemu) info balloon
balloon: actual=3860
(qemu) info balloon
balloon: actual=3788
(qemu) info balloon
balloon: actual=3744
(qemu) info balloon
balloon: actual=3678
(qemu) info balloon
balloon: actual=3594
(qemu) info balloon
balloon: actual=3528
(qemu) info balloon
balloon: actual=3458
(qemu) info balloon
balloon: actual=3390
(qemu) info balloon
balloon: actual=3328
(qemu) info balloon
balloon: actual=3254
(qemu) info balloon
balloon: actual=3190
(qemu) info balloon
balloon: actual=3120
(qemu) info balloon
balloon: actual=3060
(qemu) info balloon
balloon: actual=2990
(qemu) info balloon
balloon: actual=2948
(qemu) info balloon
balloon: actual=2864
(qemu) info balloon
balloon: actual=2786
(qemu) info balloon
balloon: actual=2700
(qemu) info balloon
balloon: actual=2612
(qemu) info balloon
balloon: actual=2512
(qemu) info balloon
balloon: actual=2426
(qemu) info balloon
balloon: actual=2324
(qemu) info balloon
balloon: actual=2244
(qemu) info balloon
balloon: actual=2168
(qemu) info balloon
balloon: actual=2096
(qemu) info balloon
balloon: actual=2020
(qemu) info balloon
balloon: actual=2000


Actual results:
Need about 80sec change from 6114 to 2000. About 75M/s.
But  use same CLI,same configuration machine host(rhel6.4) to test,steps same--> Need about 45sec change from 6114 to 2000 ,about 120M/s.

Expected results:

The speed of change balloon size about 120M/s. 

Additional info:

1.Test rhel7 guest ,not hit the problem
2.both rhel7 and rhel 6 host not add any other stress

3.#cat /proc/cpuinfo
processor       : 3
vendor_id       : GenuineIntel
cpu family      : 6
model           : 23
model name      : Intel(R) Core(TM)2 Quad CPU    Q9400  @ 2.66GHz
stepping        : 10
microcode       : 0xa0b
cpu MHz         : 2000.000
cache size      : 3072 KB
physical id     : 0
siblings        : 4
core id         : 3
cpu cores       : 4
apicid          : 3
initial apicid  : 3
fpu             : yes
fpu_exception   : yes
cpuid level     : 13
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx lm constant_tsc arch_perfmon pebs bts rep_good nopl aperfmperf pni dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm sse4_1 xsave lahf_lm dtherm tpr_shadow vnmi flexpriority
bogomips        : 5319.81
clflush size    : 64
cache_alignment : 64
address sizes   : 36 bits physical, 48 bits virtual
power management:

[root@localhost home]# cat /proc/meminfo
MemTotal:        7560776 kB
MemFree:         6861012 kB
Buffers:            1176 kB
Cached:           318472 kB
SwapCached:            4 kB
Active:            70796 kB
Inactive:         312236 kB
Active(anon):       3776 kB
Inactive(anon):    67584 kB
Active(file):      67020 kB
Inactive(file):   244652 kB
Unevictable:        3868 kB
Mlocked:            3868 kB
SwapTotal:       7897084 kB
SwapFree:        7897080 kB
Dirty:                 0 kB
Writeback:             0 kB
AnonPages:         67264 kB
Mapped:            25192 kB
Shmem:              5636 kB
Slab:             188316 kB
SReclaimable:      48552 kB
SUnreclaim:       139764 kB
KernelStack:        1416 kB
PageTables:         5968 kB
NFS_Unstable:          0 kB
Bounce:                0 kB
WritebackTmp:          0 kB
CommitLimit:    11677472 kB
Committed_AS:     345036 kB
VmallocTotal:   34359738367 kB
VmallocUsed:       57444 kB
VmallocChunk:   34359661344 kB
HardwareCorrupted:     0 kB
AnonHugePages:      8192 kB
HugePages_Total:       0
HugePages_Free:        0
HugePages_Rsvd:        0
HugePages_Surp:        0
Hugepagesize:       2048 kB
DirectMap4k:       84480 kB
DirectMap2M:     7745536 kB

4.CLI on rhel7
/usr/libexec/qemu-kvm  -M pc-1.3 -enable-kvm -m 6114 -smp 2,sockets=2,cores=1,threads=1 -name win2012 -uuid `uuidgen` -nodefconfig -nodefaults -monitor stdio -rtc base=utc  -device piix3-usb-uhci,id=usb,bus=pci.0,addr=0x1.0x2  -drive file=/home/win2012-64.qcow2,if=none,id=drive-virtio-disk0,format=qcow2,cache=none -device ide-drive,drive=drive-virtio-disk0,id=virtio-disk0,bootindex=1  -device usb-tablet,id=input0 -vnc :10 -vga std  -device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x6
Comment 2 Amit Shah 2013-03-15 08:30:38 UTC 
It's not very clear which case causes this regression.

Can you mention which host causes the problem to reproduce?  Or does host system not matter?

Can you mention which guest causes the problem to reproduce?  Or does the guest not matter?

A matrix of host and guest OSes and results will make the picture clearer.

Thanks.
Comment 3 langfang 2013-03-15 09:53:09 UTC 
(In reply to comment #2)
> It's not very clear which case causes this regression.
> 
> Can you mention which host causes the problem to reproduce?  Or does host
> system not matter?
> 
> Can you mention which guest causes the problem to reproduce?  Or does the
> guest not matter?
> 
> A matrix of host and guest OSes and results will make the picture clearer.
> 
> Thanks.

_____________________________________
|host    |    guest |   results      |
|________|__________|________________|
|        |  win2012 |   failed[1]    |
|rhel7   |__________|________________|
|        |  rhel7   |    pass[2]     |
|________|__________|________________|
|        |  win2012 |    pass[1]     |
|        |__________|________________|
|rhel6.4 |   rhel7  |    pass[2]     |
|________|__________|________________|


failed[1]:After step2 ,change balloon size from 6114 to 2000,use 80sec.75M/s-->slower
  pass[1]:After step2 ,change balloon size from 6114 to 2000,use 45sec.120M/s
  pass[2]:Balloon size change very fast
Comment 4 Amit Shah 2013-03-15 10:05:38 UTC 
Thanks, changing component to virtio-win.
Comment 5 langfang 2013-03-15 12:00:34 UTC 
Talk with amit ,closed this bug now ,wait rhel7 virtio-win package come out,test again.If have same problem.then reopen.

thanks

<flang> OK  in case something wrong .let me tried test again? if get same results .maybe we can closed this bug first , wait rhel7 virtio-win package come out ,retest again,if have same problem then reopen . 
<amit> sure
Comment 6 Qunfang Zhang 2013-08-15 09:30:24 UTC 
(In reply to langfang from comment #5)
> Talk with amit ,closed this bug now ,wait rhel7 virtio-win package come
> out,test again.If have same problem.then reopen.
> 
> thanks
> 
> <flang> OK  in case something wrong .let me tried test again? if get same
> results .maybe we can closed this bug first , wait rhel7 virtio-win package
> come out ,retest again,if have same problem then reopen . 
> <amit> sure

Hi, Amit and flang

As we have no rhel7 virtio-win package, so let's re-open this bug? Some other guys hit same problem as well. Please correct me if I'm wrong.

Thanks,
Qunfang
Comment 8 langfang 2014-01-02 04:19:23 UTC 
Test on latest version:
Host:
# uname -r
3.10.0-64.el7.x86_64
# rpm -q qemu-kvm-rhev
qemu-kvm-rhev-1.5.3-30.el7.x86_64


Results:

Guest:win2012-64/rhel7
______________________________________
|host    |    guest |   results      |
|________|__________|________________|
|        |  win2012 |    pass[1]     |
|rhel7   |__________|________________|
|        |  rhel7   |    pass[2]     |
|________|__________|________________|


pass[1]:Change balloon size from 6114 to 2000,use 29sec. 130M/s

Pass[2]:Balloon size change very fast,need about 2 sec.

According to above test ,seem the results same as  on rhel6 test . Please see  comment3 test on rhel6.4.
Comment 9 Ronen Hod 2014-01-02 12:55:40 UTC 
It is not so surprising that RHEL guest balloons faster than a windows guest. Probably Windows accesses and maps more memory, and the ballooning has more work to do. It would be interesting to try to balloon after running something that accesses memory (on the RHEL guest), and then sleeps while the memory is still allocated.
Comment 10 Gal Hammer 2014-01-02 13:00:37 UTC 
Isn't that a duplicate of bug 997720?
Comment 11 Mike Cao 2014-01-06 02:38:33 UTC 

*** This bug has been marked as a duplicate of bug 997720 ***
Note You need to log in before you can comment on or make changes to this bug.