All of lore.kernel.org
 help / color / mirror / Atom feed
From: Todd Lawall <tlawall@pivot3.com>
To: "fio@vger.kernel.org" <fio@vger.kernel.org>
Subject: Has anyone run into write_bw_log and write_io_log recording segments of low numbers?
Date: Wed, 15 Feb 2017 22:28:09 +0000	[thread overview]
Message-ID: <DM5PR10MB1625AEDC8488B039FBE439BF9D5B0@DM5PR10MB1625.namprd10.prod.outlook.com> (raw)

I've been running fio on an iSCSI volume where I can monitor things like the network traffic (to ensure that indeed it is flowing) as well as on the machine the volume is hosted on.  I'm seeing a steady state of 300MB/s, but when I stop the FIO process and writes the detailed bandwidth and iops logs, there's segments where iops drop to 0, but bandwidth for the same time point is somewhere around the single digits or teens.  

Has anyone else seen this behavior?  Does anyone have an idea why I might be seeing this?  Here is the job file I ran:

[global]
ioengine=windowsaio
do_verify=0
offset=0
write_bw_log=C:\\haggis\\manualfio\\stats-running
write_iops_log=C:\\haggis\\manualfio\\stats-running
write_lat_log=C:\\haggis\\manualfio\\stats-running
verify=crc32c-intel
runtime=292000
thread

[fio-0]
filename=\\.\PhysicalDrive1
iodepth=1
blocksize=256k
readwrite=write

[fio-1]                                                                                                                                                     
filename=\\.\PhysicalDrive2                                                                                                                                 
iodepth=1                                                                                                                                                   
blocksize=256k                                                                                                                                              
readwrite=write        

             reply	other threads:[~2017-02-15 22:28 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-02-15 22:28 Todd Lawall [this message]
2017-02-15 22:57 ` Has anyone run into write_bw_log and write_io_log recording segments of low numbers? Todd Lawall
2017-02-16  5:53   ` Sitsofe Wheeler

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=DM5PR10MB1625AEDC8488B039FBE439BF9D5B0@DM5PR10MB1625.namprd10.prod.outlook.com \
    --to=tlawall@pivot3.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 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.