From: Saeed <ionictea@gmail.com>
To: fio@vger.kernel.org
Subject: Re: multiple entries for each second for bw/iop/xlat log files
Date: Mon, 22 Aug 2016 16:17:35 -0500 [thread overview]
Message-ID: <npfq5d$74n$1@blaine.gmane.org> (raw)
In-Reply-To: CAJ9yE1AnR2s_c8iheFdMsOCk9D5wD+AqPR5CuyXsTJtZtQribw@mail.gmail.com
Why are there duplicate entries for a time interval in the log file and
the iop log file shows '1' iop througout
the entire file. This doesn't seem right since fio reports up to 100K
iops in the summary:
write: (groupid=0, jobs=1): err= 0: pid=12012: Mon Aug 22 20:25:25 2016
write: io=11245MB, bw=95956KB/s, iops=23988, runt=120001msec
slat (usec): min=7, max=31939, avg=38.82, stdev=41.96
clat (usec): min=0, max=18067, avg= 0.65, stdev=10.68
lat (usec): min=7, max=31950, avg=39.86, stdev=43.63
--
read: (groupid=1, jobs=1): err= 0: pid=12824: Mon Aug 22 20:25:25 2016
read : io=221419MB, bw=472360KB/s, iops=118090, runt=480001msec
slat (usec): min=3, max=5438, avg= 7.22, stdev= 4.77
clat (usec): min=0, max=1287, avg= 0.27, stdev= 0.73
lat (usec): min=3, max=5441, avg= 7.64, stdev= 5.35
On 2016-08-22 20:58:54 +0000, Karl Cronburg said:
> The format of the log is:
>
> time, #iops, r/w direction, size
>
> So the '1' you're seeing is saying "one read IOP of size 4096 bytes
> completed at 479.999 seconds". This happened 7 times, followed by
> another completion at 480.000 seconds (in your log excerpt).
>
> -Karl Cronburg-
>
> On Mon, Aug 22, 2016 at 4:47 PM, Saeed
> <ionictea@gmail.com> wrote:
>> I'm still getting the same problem where there seems to be duplicate time
>> interval entries and no data for the iops log using the latest git:
>>
>> 479999, 1, 0, 4096
>> 479999, 1, 0, 4096
>> 479999, 1, 0, 4096
>> 479999, 1, 0, 4096
>> 479999, 1, 0, 4096
>> 479999, 1, 0, 4096
>> 479999, 1, 0, 4096
>> 480000, 1, 0, 4096
>>
>> I do see the following errors during the configure process but not sure if
>> its related:
>>
>> /tmp/fio-conf--8430-.c:2:2: error: #error __ANDROID__ not defined
>> #error __ANDROID__ not defined
>> /tmp/fio-conf--8430-.c:2:2: error: #error __i386__ not defined
>> #error __i386__ not defined
>> /tmp/fio-conf--8430-.c:5:3: error: size of unnamed array is negative
>> collect2: error: ld returned 1 exit status
>> /tmp/fio-conf--8430-.c:2:24: fatal error: sys/asynch.h: No such file or
>> directory
>> /tmp/fio-conf--8430-.c:2:29: fatal error: infiniband/arch.h: No such file or
>> directory
>> /tmp/fio-conf--8430-.c:2:27: fatal error: rdma/rdma_cma.h: No such file or
>> directory
>>
>> /tmp/fio-conf--8430-.c:5:24: error: 'CLOCK_MONOTONIC_PRECISE' undeclared
>> (first use in this function)
>> /tmp/fio-conf--8430-.c:5:22: error: storage size of 'me' isn't known
>> /tmp/fio-conf--8430-.c:6:19: error: 'EXT4_IOC_MOVE_EXT' undeclared (first
>> use in this function)
>> /tmp/fio-conf--8430-.c:1:19: fatal error: guasi.h: No such file or directory
>> /tmp/fio-conf--8430-.c:1:32: fatal error: nvm/nvm_primitives.h: No such file
>> or directory
>> /tmp/fio-conf--8430-.c:1:18: fatal error: numa.h: No such file or directory
>> collect2: error: ld returned 1 exit status
>> collect2: error: ld returned 1 exit status
>> /tmp/fio-conf--8430-.c:1:24: fatal error: rbd/librbd.h: No such file or
>> directory
>> /tmp/fio-conf--8430-.c:1:24: fatal error: rbd/librbd.h: No such file or
>> directory
>> /tmp/fio-conf--8430-.c:1:32: fatal error: glusterfs/api/glfs.h: No such file
>> or directory
>> /tmp/fio-conf--8430-.c:7: Error: unknown pseudo-op: `.machine'
>> /tmp/fio-conf--8430-.c:8: Error: unknown pseudo-op: `.machine'
>> /tmp/fio-conf--8430-.c:9: Error: no such instruction: `stfle %rcx'
>> /tmp/fio-conf--8430-.c:10: Error: unknown pseudo-op: `.machine'
>> /tmp/fio-conf--8430-.c:6:17: error: storage size of 'st' isn't known
>> /tmp/fio-conf--8430-.c:7:26: error: 'MNT_NOWAIT' undeclared (first use in
>> this function)
>>
>> On 2016-08-22 17:33:13 +0000, Jens Axboe said:
>>
>>> On 08/22/2016 10:37 AM, Saeed wrote:
>>>>
>>>> Why are there multiple entries for each interval / second in the fio log
>>>> generated?
>>>>
>>>> 1, 585142, 1, 4096
>>>> 1, 4096000, 1, 4096
>>>> 1, 4096000, 1, 4096
>>>> 1, 0, 1, 4096
>>>> 1, 0, 1, 4096
>>>> 1, 4096000, 1, 4096
>>>> 1, 0, 1, 4096
>>>> 1, 0, 1, 4096
>>>> 1, 4096000, 1, 4096
>>>> 1, 0, 1, 4096
>>>> 2, 4096000, 1, 4096
>>>> 2, 4096000, 1, 4096
>>>> 2, 4096000, 1, 4096
>>>> 2, 0, 1, 4096
>>>> 2, 4096000, 1, 4096
>>>> 2, 4096000, 1, 4096
>>>> 2, 4096000, 1, 4096
>>>> 2, 0, 1, 4096
>>>> 2, 0, 1, 4096
>>>> 2, 0, 1, 4096
>>>
>>>
>>> Ditto for this one, try current -git.
>>
>>
>>
>>
>> --
>> To unsubscribe from this list: send the line "unsubscribe fio" in
>> the body of a message to majordomo@vger.kernel.org
>> More majordomo info at http://vger.kernel.org/majordomo-info.html
next prev parent reply other threads:[~2016-08-22 21:17 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-08-22 16:37 multiple entries for each second for bw/iop/xlat log files Saeed
2016-08-22 17:33 ` Jens Axboe
2016-08-22 20:47 ` Saeed
2016-08-22 20:58 ` Karl Cronburg
2016-08-22 21:17 ` Saeed [this message]
2016-08-23 1:05 ` Saeed
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='npfq5d$74n$1@blaine.gmane.org' \
--to=ionictea@gmail.com \
--cc=fio@vger.kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox