From: Ye Xiaolong <xiaolong.ye@intel.com>
To: lkp@lists.01.org
Subject: Re: [lkp-robot] [mm/cma] 2b0f904a5a: fio.read_bw_MBps -16.1% regression
Date: Thu, 03 May 2018 12:46:21 +0800 [thread overview]
Message-ID: <20180503044621.GI15698@yexl-desktop> (raw)
In-Reply-To: <CAAmzW4OnpiBPWeKQtL4txbTU7PwYVEc=GAGTsiJRebTojY8uRQ@mail.gmail.com>
[-- Attachment #1: Type: text/plain, Size: 4908 bytes --]
Sorry for the late.
On 04/23, Joonsoo Kim wrote:
>2018-04-13 10:18 GMT+09:00 Ye Xiaolong <xiaolong.ye@intel.com>:
>> On 04/12, Joonsoo Kim wrote:
>>>
>>>Really thanks for testing!
>>>
>>>Could you give me /proc/zoneinfo dumped before/after this test
>>>for all these three commits?
>>
>> zoneinfo files for these three commits attached. Sample interval is 10s.
>
>Really thanks for giving the info.
>
>During last week, I studied hard on this problem and found a culprit.
>Your report showed that there was some big changes on allocator's numa stat.
>It seems that it's caused by classzone_idx.
>
>Assume the following setup that is the same with your machine.
>Assume that my patch is applied so there is a movable zone on Node1.
>
>Node0
>DMA
>DMA32
>Normal
>
>Node1
>Normal
>Movable
>
>classzone_idx of GFP_HIGHUSER_MOVABLE allocation happened on node0
>will be 2 and classzone_idx of the same allocation happend on node1 will be 3.
>So, different lowmem_reserve is applied to them and it causes bad numa
>effects in allocator.
>
>I can't think a perfect solution now but following patch that removes
>lowmem_reserve
>for ZONE_MOVABLE will remove bad numa effect to your machine setup.
>
>I'm not sure whether performance will be restored or not by this patch, however,
>at least, bad numa stat will be disappeared. (I observed in my test!!!)
>
>Could you test it?
>
>https://github.com/JoonsooKim/linux.git cma-fixup-thp-next-20180403
>
>Related commits are:
>2f54bc6 mm/page_alloc: workaround for node balance issue during allocation
>f11152b mm/thp: don't count ZONE_MOVABLE as the target for freepage reserving
>b2adb03 Revert "Revert "mm/cma: manage the memory of the CMA area by
>using the ZONE_MOVABLE""
>76148e2 Revert "Revert "mm/page_alloc: don't reserve ZONE_HIGHMEM for
>ZONE_MOVABLE request""
>
>Base commit is '76148e2' and this regression happens on 'b2adb03'.
>Fix is commit 'f11152b' and '2f54bc6'.
>
>Please also give me vmstat and zoneinfo. (before/after the test)
>
Here is the comparison of commit b2adb03 and commit 2f54bc6, seems the fix does
help recover the performance.
$ compare -at b2adb036011101120cd171db14f5f4f9e8b7938a 2f54bc68e487da5d5602629ff6e71c181d364698 -g fio-basic
tests: 1
testcase/path_params/tbox_group/run: fio-basic/2pmem-ext4-200s-50%-tb-randread-2M-mmap-200G-performance/lkp-hsw-ep6
b2adb03601110112 2f54bc68e487da5d5602629ff6
---------------- --------------------------
%stddev change %stddev
\ | \
9404 18% 11058 fio.read_bw_MBps
4702 18% 5529 fio.read_iops
52.93 28% 67.69 fio.latency_4ms%
4.709e+08 18% 5.552e+08 fio.time.major_page_faults
3.767e+09 18% 4.441e+09 fio.time.file_system_inputs
940450 18% 1105848 fio.workload
498 12% 558 fio.time.user_time
418315 11% 463880 fio.time.involuntary_context_switches
5103 5044 fio.time.system_time
11837 -6% 11115 fio.read_clat_stddev
25808 -7% 23936 fio.time.voluntary_context_switches
2322932 -8% 2134137 ± 3% fio.time.maximum_resident_set_size
23.38 -13% 20.32 ± 5% fio.latency_10ms%
5949 -15% 5059 fio.read_clat_mean_us
12864 -23% 9962 fio.read_clat_90%_us
14058 -23% 10816 fio.read_clat_95%_us
22485 -31% 15488 ± 8% fio.read_clat_99%_us
94150 ± 18% -34% 62254 ± 27% fio.time.minor_page_faults
0.39 ± 5% -44% 0.22 ± 12% fio.latency_1000us%
20.03 -53% 9.51 ± 4% fio.latency_20ms%
0.11 ± 11% -66% 0.04 ± 25% fio.latency_2ms%
1.38 ± 3% -67% 0.45 ± 23% fio.latency_50ms%
12591 34% 16884 ± 27% softirqs.NET_RX
vmstat and zoneinfo for both commits attached.
Thanks,
Xiaolong
>
>There is another regression report from mainline related to this patch since
>this patch is merged to mainline.
>
>http://lkml.kernel.org/r/<20180418010753.GA20825@yexl-desktop>
>[lkp-robot] [mm/cma] a57a290bd3: vm-scalability.throughput -15.5% regression
>
>If above fixes works, could you test above regression on the mainline
>kernel with
>'2f54bc6 mm/page_alloc: workaround for node balance issue during allocation'?
>commit 'f11152b mm/thp: don't count ZONE_MOVABLE as the target for
>freepage reserving'
>is already merged into mainline so only commit 2f54bc6 will be needed.
>
>Thanks.
[-- Attachment #2: proc-vmstat-2f54bc68.gz --]
[-- Type: application/octet-stream, Size: 56070 bytes --]
[-- Attachment #3: proc-vmstat-b2adb036.gz --]
[-- Type: application/octet-stream, Size: 56534 bytes --]
[-- Attachment #4: zoneinfo-2f54bc68.gz --]
[-- Type: application/octet-stream, Size: 49402 bytes --]
[-- Attachment #5: zoneinfo-b2adb0360.gz --]
[-- Type: application/octet-stream, Size: 47533 bytes --]
prev parent reply other threads:[~2018-05-03 4:46 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-02 6:35 [lkp-robot] [mm/cma] 2b0f904a5a: fio.read_bw_MBps -16.1% regression kernel test robot
2018-01-02 6:35 ` kernel test robot
2018-01-03 2:05 ` Joonsoo Kim
2018-01-03 2:05 ` Joonsoo Kim
2018-01-06 9:26 ` Ye Xiaolong
2018-01-06 9:26 ` Ye Xiaolong
2018-01-09 7:16 ` Joonsoo Kim
2018-01-09 7:16 ` Joonsoo Kim
2018-04-05 7:48 ` Joonsoo Kim
2018-04-05 7:48 ` Joonsoo Kim
2018-04-09 5:56 ` Ye Xiaolong
2018-04-09 7:25 ` Joonsoo Kim
2018-04-09 7:40 ` Ye Xiaolong
2018-04-12 1:12 ` Ye Xiaolong
2018-04-12 1:26 ` Joonsoo Kim
2018-04-13 1:18 ` Ye Xiaolong
2018-04-23 6:39 ` Joonsoo Kim
2018-05-03 4:46 ` Ye Xiaolong [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=20180503044621.GI15698@yexl-desktop \
--to=xiaolong.ye@intel.com \
--cc=lkp@lists.01.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.