On 12/04/2015 04:56 PM, Chao Fan wrote:
Hi Zhou Wenjian and Kumagai,
I have follow Zhou Wenjian's words to do some tests, in the condition of
"-c", makdumpfile 1.5.9 does perform better than "-l".
I have done more tests in a machine with 128G memory, in the condition
of "-d 0" and "-d 3", the makedumpfile 1.5.9 performs well. But if with
"--num-threads 1", it does need more time than without "--num-threads".
Here is my results(makedumpfile -c):
"-d 0" (the size of vmcore is 2.6G):
--num-threads time(seconds)
0 556
1 1186
4 307
8 186
12 131
16 123
"-d 3" (the size of vmcore is 1.3G):
--num-threads time(seconds)
0 141
1 262
2 137
4 91
8 121
16 137
Hello Chao,
This result also seems not so good.
We had test it, and you can refer to:
http://lists.infradead.org/pipermail/kexec/2015-October/014576.html
Could you collect the information by *perf stat -e page-faults* on both
--num-threads 0 and --num-threads 1 ?
Your result looks like the performance without the patch which dividing
compress2().
--
Thanks
Zhou
So, I think makedumpfile 1.5.9 can save time in the condition of "-c"
and not "-d 31" and not "--num-threads 1".
----- Original Message -----
From: "Wenjian Zhou/周文剑" <[email protected]>
To: "Atsushi Kumagai" <[email protected]>
Cc: [email protected]
Sent: Friday, December 4, 2015 11:33:36 AM
Subject: Re: [PATCH RFC 00/11] makedumpfile: parallel processing
Hello Kumagai,
On 12/04/2015 10:30 AM, Atsushi Kumagai wrote:
Hello, Zhou
On 12/02/2015 03:24 PM, Dave Young wrote:
Hi,
On 12/02/15 at 01:29pm, "Zhou, Wenjian/周文剑" wrote:
I think there is no problem if other test results are as expected.
--num-threads mainly reduces the time of compressing.
So for lzo, it can't do much help at most of time.
Seems the help of --num-threads does not say it exactly:
[--num-threads THREADNUM]:
Using multiple threads to read and compress data of each page in
parallel.
And it will reduces time for saving DUMPFILE.
This feature only supports creating DUMPFILE in kdump-comressed
format from
VMCORE in kdump-compressed format or elf format.
Lzo is also a compress method, it should be mentioned that --num-threads
only
supports zlib compressed vmcore.
Sorry, it seems that something I said is not so clear.
lzo is also supported. Since lzo compresses data at a high speed, the
improving of the performance is not so obvious at most of time.
Also worth to mention about the recommended -d value for this feature.
Yes, I think it's worth. I forgot it.
I saw your patch, but I think I should confirm what is the problem first.
However, when "-d 31" is specified, it will be worse.
Less than 50 buffers are used to cache the compressed page.
And even the page has been filtered, it will also take a buffer.
So if "-d 31" is specified, the filtered page will use a lot
of buffers. Then the page which needs to be compressed can't
be compressed parallel.
Could you explain why compression will not be parallel in more detail ?
Actually the buffers are used also for filtered pages, it sounds
inefficient.
However, I don't understand why it prevents parallel compression.
Think about this, in a huge memory, most of the page will be filtered, and
we have 5 buffers.
page1 page2 page3 page4 page5 page6 page7 .....
[buffer1] [2] [3] [4] [5]
unfiltered filtered filtered filtered filtered unfiltered filtered
Since filtered page will take a buffer, when compressing page1,
page6 can't be compressed at the same time.
That why it will prevent parallel compression.
Further, according to Chao's benchmark, there is a big performance
degradation even if the number of thread is 1. (58s vs 240s)
The current implementation seems to have some problems, we should
solve them.
If "-d 31" is specified, on the one hand we can't save time by compressing
parallel, on the other hand we will introduce some extra work by adding
"--num-threads". So it is obvious that it will have a performance
degradation.
I'm not so sure if it is a problem that the performance degradation is so
big.
But I think if in other cases, it works as expected, this won't be a problem(
or a problem needs to be fixed), for the performance degradation existing
in theory.
Or the current implementation should be replaced by a new arithmetic.
For example:
We can add an array to record whether the page is filtered or not.
And only the unfiltered page will take the buffer.
But I'm not sure if it is worth.
For "-l -d 31" is fast enough, the new arithmetic also can't do much help.
--
Thanks
Zhou
_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec
_______________________________________________
kexec mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/kexec
