* [lkp] [block] fbccf1df065: +276.3% boot-meminfo.KernelStack
@ 2015-06-01 1:46 Huang Ying
2015-06-03 18:39 ` Ming Lin
0 siblings, 1 reply; 3+ messages in thread
From: Huang Ying @ 2015-06-01 1:46 UTC (permalink / raw)
To: Kent Overstreet; +Cc: Ming Lin, LKML, LKP ML, huang.ying.caritas
[-- Attachment #1: Type: text/plain, Size: 2978 bytes --]
FYI, we noticed the below changes on
git://git.kernel.org/pub/scm/linux/kernel/git/mlin/linux.git block-generic-req
commit fbccf1df06574add60bdb71103cc1662e477f02d ("block: make generic_make_request handle arbitrarily sized bios")
testcase/path_params/tbox_group: boot/1/vm-kbuild-1G
v4.1-rc4 fbccf1df06574add60bdb71103
---------------- --------------------------
%stddev %change %stddev
\ | \
1587 ± 7% +276.3% 5972 ± 1% boot-meminfo.KernelStack
152390 ± 0% +4.8% 159697 ± 0% boot-slabinfo.num_objs
10149 ± 0% +15.8% 11750 ± 0% boot-slabinfo.num_pages
35916 ± 5% +18.0% 42368 ± 9% boot-meminfo.DirectMap4k
478516 ± 0% -1.9% 469269 ± 0% boot-meminfo.MemFree
11477 ± 0% +49.1% 17111 ± 1% boot-meminfo.SUnreclaim
40551 ± 0% +15.7% 46910 ± 0% boot-meminfo.Slab
vm-kbuild-1G: qemu-system-x86_64 -enable-kvm -cpu Haswell,+smep,+smap
Memory: 1G
boot-meminfo.KernelStack
7000 ++-------------------------------------------------------------------+
| O O O O |
6000 O+ O O O O O O O O O O O O O O O O O O
| |
5000 ++ |
| |
4000 ++ |
| |
3000 ++ |
| |
2000 ++ *.. |
* *..*..*..* : * |
1000 ++ .. + : |
| + . + : |
0 ++-*--*--*---------------*-------------------------------------------+
[*] bisect-good sample
[O] bisect-bad sample
To reproduce:
apt-get install ruby
git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
cd lkp-tests
bin/setup-local job.yaml # the job file attached in this email
bin/run-local job.yaml
Disclaimer:
Results have been estimated based on internal Intel analysis and are provided
for informational purposes only. Any difference in system hardware or software
design or configuration may affect actual performance.
Thanks,
Ying Huang
-------------------------------------
lkp@eclists.intel.com
https://eclists.intel.com/sympa/info/lkp
Unsubscribe by sending email to sympa@eclists.intel.com with subject "Unsubscribe lkp"
[-- Attachment #2: job.yaml --]
[-- Type: text/plain, Size: 2538 bytes --]
---
LKP_SERVER: inn
testcase: boot
default-monitors:
default-watchdogs:
watch-oom:
watchdog:
cpufreq_governor:
model: qemu-system-x86_64 -enable-kvm -cpu Haswell,+smep,+smap
nr_vm: 16
nr_cpu: 2
memory: 1G
disk_type: virtio-scsi
rootfs: debian-x86_64-2015-02-07.cgz
hdd_partitions: "/dev/sda /dev/sdb /dev/sdc /dev/sdd"
swap_partitions: "/dev/sde"
boot-slabinfo:
boot-meminfo:
memmap:
boot-memory:
boot-time:
kernel-size:
timeout: 10m
sleep: 1
branch: linux-devel/devel-hourly-2015052515
commit: 9e46a1eba10500df620683e31742789ef2781e93
repeat_to: 2
testbox: vm-kbuild-1G-6
tbox_group: vm-kbuild-1G
kconfig: x86_64-lkp
enqueue_time: 2015-05-25 16:11:14.888350830 +08:00
user: lkp
queue: boot
compiler: gcc-4.9
kernel: "/pkg/linux/x86_64-lkp/gcc-4.9/9e46a1eba10500df620683e31742789ef2781e93/vmlinuz-4.1.0-rc5-02510-g9e46a1e"
result_root: "/result/boot/1/vm-kbuild-1G/debian-x86_64-2015-02-07.cgz/x86_64-lkp/gcc-4.9/9e46a1eba10500df620683e31742789ef2781e93/0"
job_file: "/lkp/scheduled/vm-kbuild-1G-6/boot_boot-1-debian-x86_64.cgz-x86_64-lkp-9e46a1eba10500df620683e31742789ef2781e93-1-20150525-48539-iakefb.yaml"
dequeue_time: 2015-05-25 16:11:19.987783209 +08:00
max_uptime: 600
initrd: "/osimage/debian/debian-x86_64-2015-02-07.cgz"
bootloader_append:
- root=/dev/ram0
- user=lkp
- job=/lkp/scheduled/vm-kbuild-1G-6/boot_boot-1-debian-x86_64.cgz-x86_64-lkp-9e46a1eba10500df620683e31742789ef2781e93-1-20150525-48539-iakefb.yaml
- ARCH=x86_64
- kconfig=x86_64-lkp
- branch=linux-devel/devel-hourly-2015052515
- commit=9e46a1eba10500df620683e31742789ef2781e93
- BOOT_IMAGE=/pkg/linux/x86_64-lkp/gcc-4.9/9e46a1eba10500df620683e31742789ef2781e93/vmlinuz-4.1.0-rc5-02510-g9e46a1e
- max_uptime=600
- RESULT_ROOT=/result/boot/1/vm-kbuild-1G/debian-x86_64-2015-02-07.cgz/x86_64-lkp/gcc-4.9/9e46a1eba10500df620683e31742789ef2781e93/0
- LKP_SERVER=inn
- |2-
earlyprintk=ttyS0,115200 systemd.log_level=err
debug apic=debug sysrq_always_enabled rcupdate.rcu_cpu_stall_timeout=100
panic=-1 softlockup_panic=1 nmi_watchdog=panic oops=panic load_ramdisk=2 prompt_ramdisk=0
console=ttyS0,115200 console=tty0 vga=normal
rw
lkp_initrd: "/lkp/lkp/lkp-x86_64.cgz"
modules_initrd: "/pkg/linux/x86_64-lkp/gcc-4.9/9e46a1eba10500df620683e31742789ef2781e93/modules.cgz"
bm_initrd: "/osimage/deps/debian-x86_64-2015-02-07.cgz/lkp.cgz,/osimage/deps/debian-x86_64-2015-02-07.cgz/run-ipconfig.cgz"
job_state: finished
loadavg: 0.13 0.03 0.01 1/373 2718
start_time: '1432541537'
end_time: '1432541538'
version: "/lkp/lkp/.src-20150525-131232"
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [lkp] [block] fbccf1df065: +276.3% boot-meminfo.KernelStack
2015-06-01 1:46 [lkp] [block] fbccf1df065: +276.3% boot-meminfo.KernelStack Huang Ying
@ 2015-06-03 18:39 ` Ming Lin
[not found] ` <CAC=cRTNMnyFJN=M7nyR65fwR8qFYYak_oJacoA_wpt7Lozdthw@mail.gmail.com>
0 siblings, 1 reply; 3+ messages in thread
From: Ming Lin @ 2015-06-03 18:39 UTC (permalink / raw)
To: Huang Ying; +Cc: Kent Overstreet, LKML, LKP ML, huang.ying.caritas
On Sun, May 31, 2015 at 6:46 PM, Huang Ying <ying.huang@intel.com> wrote:
> FYI, we noticed the below changes on
>
> git://git.kernel.org/pub/scm/linux/kernel/git/mlin/linux.git block-generic-req
> commit fbccf1df06574add60bdb71103cc1662e477f02d ("block: make generic_make_request handle arbitrarily sized bios")
>
>
> testcase/path_params/tbox_group: boot/1/vm-kbuild-1G
>
> v4.1-rc4 fbccf1df06574add60bdb71103
> ---------------- --------------------------
> %stddev %change %stddev
> \ | \
> 1587 ± 7% +276.3% 5972 ± 1% boot-meminfo.KernelStack
I tested with 5 virtual disks.
diff meminfo.v4.1-rc4 diff meminfo.fbccf1df0
-Slab: 16908 kB
-SReclaimable: 8708 kB
-SUnreclaim: 8200 kB
-KernelStack: 1456 kB
-PageTables: 1496 kB
+Slab: 17492 kB
+SReclaimable: 8860 kB
+SUnreclaim: 8632 kB
+KernelStack: 2144 kB
+PageTables: 1480 kB
The KernelStack increase is because now we create bio pool for each
request_queue.
> 152390 ± 0% +4.8% 159697 ± 0% boot-slabinfo.num_objs
> 10149 ± 0% +15.8% 11750 ± 0% boot-slabinfo.num_pages
> 35916 ± 5% +18.0% 42368 ± 9% boot-meminfo.DirectMap4k
> 478516 ± 0% -1.9% 469269 ± 0% boot-meminfo.MemFree
> 11477 ± 0% +49.1% 17111 ± 1% boot-meminfo.SUnreclaim
> 40551 ± 0% +15.7% 46910 ± 0% boot-meminfo.Slab
>
> vm-kbuild-1G: qemu-system-x86_64 -enable-kvm -cpu Haswell,+smep,+smap
> Memory: 1G
Could you send me the kernel config and full qemu command?
I'll try to reproduce it.
>
> boot-meminfo.KernelStack
>
> 7000 ++-------------------------------------------------------------------+
> | O O O O |
> 6000 O+ O O O O O O O O O O O O O O O O O O
> | |
> 5000 ++ |
> | |
> 4000 ++ |
> | |
> 3000 ++ |
> | |
> 2000 ++ *.. |
> * *..*..*..* : * |
> 1000 ++ .. + : |
> | + . + : |
> 0 ++-*--*--*---------------*-------------------------------------------+
>
> [*] bisect-good sample
> [O] bisect-bad sample
>
> To reproduce:
>
> apt-get install ruby
> git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git
> cd lkp-tests
> bin/setup-local job.yaml # the job file attached in this email
> bin/run-local job.yaml
I got below error.
root@mlin-dev:~/lkp-tests# ./bin/run-local job.yaml
/usr/lib/ruby/2.1.0/psych.rb:464:in `initialize': No such file or
directory @ rb_sysopen -
/result/boot/1/msl-lab-afa03/debian-x86_64-2015-02-07.cgz/x86_64-lkp/gcc-4.9/9e46a1eba10500df620683e31742789ef2781e93/1/job.yaml
(Errno::ENOENT)
from /usr/lib/ruby/2.1.0/psych.rb:464:in `open'
from /usr/lib/ruby/2.1.0/psych.rb:464:in `load_file'
from /root/tmp/lkp-tests/stats/kernel-size:7:in `<main>'
/root/tmp/lkp-tests/stats/kernel-size < /dev/null exit code 1, check
/dev/shm/lkp-stats.70d8CxI7
root@mlin-dev:~# tree /result/
/result/
└── boot
├── 1
│ └── msl-lab-afa03
│ └── debian-x86_64-2015-02-07.cgz
│ └── x86_64-lkp
│ └── gcc-4.9
│ └── 9e46a1eba10500df620683e31742789ef2781e93
│ ├── 0
│ │ ├── boot-meminfo
│ │ ├── boot-meminfo.json
│ │ ├── boot-slabinfo
│ │ ├── boot-slabinfo.json
│ │ ├── job.sh
│ │ ├── job.yaml
│ │ ├── matrix.json.gz
│ │ ├── memmap
│ │ ├── memmap.json
│ │ ├── sleep
│ │ ├── sleep.time
│ │ ├── sleep.time.json
│ │ ├── stats.json
│ │ ├── time
│ │ ├── time.json
│ │ ├── watchdog
│ │ └── watch-oom
│ ├── 1
│ │ ├── boot-meminfo
│ │ ├── boot-meminfo.json
│ │ ├── boot-slabinfo
│ │ ├── boot-slabinfo.json
│ │ ├── job.sh
│ │ ├── job.yaml
│ │ ├── matrix.json.gz
│ │ ├── memmap
│ │ ├── memmap.json
│ │ ├── sleep
│ │ ├── sleep.time
│ │ ├── sleep.time.json
│ │ ├── stats.json
│ │ ├── time
│ │ ├── time.json
│ │ ├── watchdog
│ │ └── watch-oom
│ ├── avg.json
│ ├── matrix.json
│ └── stddev.json
└── params.yaml
9 directories, 38 files
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [lkp] [block] fbccf1df065: +276.3% boot-meminfo.KernelStack
[not found] ` <CAC=cRTNMnyFJN=M7nyR65fwR8qFYYak_oJacoA_wpt7Lozdthw@mail.gmail.com>
@ 2015-06-04 6:56 ` Ming Lin
0 siblings, 0 replies; 3+ messages in thread
From: Ming Lin @ 2015-06-04 6:56 UTC (permalink / raw)
To: huang ying
Cc: Huang Ying, Kent Overstreet, LKML, LKP ML, Jeff Moyer,
Christoph Hellwig
On Thu, 2015-06-04 at 08:49 +0800, huang ying wrote:
> Hi, Ming,
>
> Here it is.
>
> qemu-system-x86_64 -enable-kvm -cpu Haswell,+smep,+smap
> -kernel /pkg/linux/x86_64-lkp/gcc-4.9/fbccf1df06574add60bdb71103cc1662e477f02d/vmlinuz-4.1.0-rc4-00001-gfbccf1d -append 'root=/dev/ram0 user=lkp job=/lkp/scheduled/vm-kbuild-1G-15/bisect_boot-1-debian-x86_64-2015-02-07.cgz-x86_64-lkp-fbccf1df06574add60bdb71103cc1662e477f02d-1-20150529-44276-1cpbx2s.yaml ARCH=x86_64 kconfig=x86_64-lkp branch=linux-devel/devel-hourly-2015052515 commit=fbccf1df06574add60bdb71103cc1662e477f02d BOOT_IMAGE=/pkg/linux/x86_64-lkp/gcc-4.9/fbccf1df06574add60bdb71103cc1662e477f02d/vmlinuz-4.1.0-rc4-00001-gfbccf1d max_uptime=600 RESULT_ROOT=/result/boot/1/vm-kbuild-1G/debian-x86_64-2015-02-07.cgz/x86_64-lkp/gcc-4.9/fbccf1df06574add60bdb71103cc1662e477f02d/0 LKP_SERVER=inn earlyprintk=ttyS0,115200 systemd.log_level=err debug apic=debug sysrq_always_enabled rcupdate.rcu_cpu_stall_timeout=100 panic=-1 softlockup_panic=1 nmi_watchdog=panic oops=panic load_ramdisk=2 prompt_ramdisk=0 console=ttyS0,115200 console=tty0 vga=normal rw ip=::::vm-kbuild-1G-15::dhcp' -initrd /fs/sda1/initrd-vm-kbuild-1G-15 -m 1024 -smp 2 -device e1000,netdev=net0 -netdev user,id=net0 -boot order=nc -no-reboot -watchdog i6300esb -rtc base=localtime -device virtio-scsi-pci,id=scsi0 -drive file=/fs/sda1/disk0-vm-kbuild-1G-15,if=none,id=hd0,media=disk,aio=native,cache=none -device scsi-hd,bus=scsi0.0,drive=hd0,scsi-id=1,lun=0 -drive file=/fs/sda1/disk1-vm-kbuild-1G-15,if=none,id=hd1,media=disk,aio=native,cache=none -device scsi-hd,bus=scsi0.0,drive=hd1,scsi-id=1,lun=1 -drive file=/fs/sda1/disk2-vm-kbuild-1G-15,if=none,id=hd2,media=disk,aio=native,cache=none -device scsi-hd,bus=scsi0.0,drive=hd2,scsi-id=1,lun=2 -drive file=/fs/sda1/disk3-vm-kbuild-1G-15,if=none,id=hd3,media=disk,aio=native,cache=none -device scsi-hd,bus=scsi0.0,drive=hd3,scsi-id=1,lun=3 -drive file=/fs/sda1/disk4-vm-kbuild-1G-15,if=none,id=hd4,media=disk,aio=native,cache=none -device scsi-hd,bus=scsi0.0,drive=hd4,scsi-id=1,lun=4 -pidfile /dev/shm/kboot/pid-vm-kbuild-1G-15 -serial file:/dev/shm/kboot/serial-vm-kbuild-1G-15 -daemonize -display none -monitor null
Here is the fix.
I'll merge it to patch "block: make generic_make_request handle
arbitrarily sized bios".
Thanks Ying.
>
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 2b8fd30..feaeb12 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -522,6 +522,8 @@ static void blk_release_queue(struct kobject *kobj)
blk_trace_shutdown(q);
+ bioset_free(q->bio_split);
+
ida_simple_remove(&blk_queue_ida, q->id);
call_rcu(&q->rcu_head, blk_free_queue_rcu);
}
^ permalink raw reply related [flat|nested] 3+ messages in thread
end of thread, other threads:[~2015-06-04 6:56 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2015-06-01 1:46 [lkp] [block] fbccf1df065: +276.3% boot-meminfo.KernelStack Huang Ying
2015-06-03 18:39 ` Ming Lin
[not found] ` <CAC=cRTNMnyFJN=M7nyR65fwR8qFYYak_oJacoA_wpt7Lozdthw@mail.gmail.com>
2015-06-04 6:56 ` Ming Lin
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox