All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
To: "hch@lst.de" <hch@lst.de>
Cc: Bart Van Assche <Bart.VanAssche@wdc.com>,
	"linuxarm@huawei.com" <linuxarm@huawei.com>,
	"linux-scsi@vger.kernel.org" <linux-scsi@vger.kernel.org>
Subject: Re: [PATCH] scsi: default to scsi-mq
Date: Wed, 19 Jul 2017 00:24:53 +0800	[thread overview]
Message-ID: <20170719002453.00002876@huawei.com> (raw)
In-Reply-To: <20170718235803.000062b6@huawei.com>

On Tue, 18 Jul 2017 23:58:03 +0800
Jonathan Cameron <Jonathan.Cameron@huawei.com> wrote:

> On Fri, 14 Jul 2017 14:45:39 +0200
> "hch@lst.de" <hch@lst.de> wrote:
> 
> > On Fri, Jul 14, 2017 at 05:56:41PM +0800, Jonathan Cameron wrote:  
> > > Just wondering if you had any thoughts on how we can proceed with tracking
> > > down this regression?
> > > 
> > > I'm not familiar enough with the multiqueue code to really know where
> > > to start.
> > > 
> > > If there are any other tests that would be of use, let us know.    
> > 
> > Can you send the blktrace and perf output for each of the runs?
> > 
> > Thanks!  
> 
> Hi 
> 
> Sorry for the delay,

For perf what in particular would be of use?

Thanks,

Jonathan
> 
> blktrace for now (or at least the btt output based on blktrace).
> All runs are 1 minute of fio with reads and iodepth of 2048 as
> before. Just the summaries to keep this compact.  Also 6 disks
> were running but results just presented for first one.
> 
> mq disabled, noop scheduler
> 
> ==================== All Devices ====================
> 
>             ALL           MIN           AVG           MAX           N
> --------------- ------------- ------------- ------------- -----------
> 
> Q2Q               0.000003960   0.000008760   0.016291960     6849306
> Q2G               0.000000780   0.000001547   0.011354860     1420699
> G2I               0.000000660   0.000000975   0.011092540     1420699
> Q2M               0.000000340   0.000000431   0.003383260     5428608
> I2D               0.000000440   0.000196038   0.023731660     1420699
> M2D               0.000000480   0.001475398   0.023726860     5428608
> D2C               0.000022420   0.002887338   0.026416340     6849307
> Q2C               0.000025360   0.004098233   0.035045140     6849307
> 
> ==================== Device Overhead ====================
> 
>        DEV |       Q2G       G2I       Q2M       I2D       D2C
> ---------- | --------- --------- --------- --------- ---------
>  (  8,  0) |   0.0078%   0.0049%   0.0083%   0.9922%  70.4532%
> ---------- | --------- --------- --------- --------- ---------
>    Overall |   0.0078%   0.0049%   0.0083%   0.9922%  70.4532%
> 
> ==================== Device Merge Information ====================
> 
>        DEV |       #Q       #D   Ratio |   BLKmin   BLKavg   BLKmax    Total
> ---------- | -------- -------- ------- | -------- -------- -------- --------
>  (  8,  0) |  6849307  1420699     4.8 |        8       38      256 54794456
> 
> ==================== Device Q2Q Seek Information ====================
> 
>        DEV |          NSEEKS            MEAN          MEDIAN | MODE           
> ---------- | --------------- --------------- --------------- | ---------------
>  (  8,  0) |         6849307             0.0               0 | 0(6849307)
> ---------- | --------------- --------------- --------------- | ---------------
>    Overall |          NSEEKS            MEAN          MEDIAN | MODE           
>    Average |         6849307             0.0               0 | 0(6849307)
> 
> ==================== Device D2D Seek Information ====================
> 
>        DEV |          NSEEKS            MEAN          MEDIAN | MODE           
> ---------- | --------------- --------------- --------------- | ---------------
>  (  8,  0) |         1420699             0.0               0 | 0(1420699)
> ---------- | --------------- --------------- --------------- | ---------------
>    Overall |          NSEEKS            MEAN          MEDIAN | MODE           
>    Average |         1420699             0.0               0 | 0(1420699)
> 
> ==================== Plug Information ====================
> 
> 		            DEV |    # Plugs # Timer Us  | % Time Q Plugged
> ---------- | ---------- ----------  | ----------------
>  (  8,  0) |    1420699(         0) |   2.231949107%
> 
>        DEV |    IOs/Unp   IOs/Unp(to)
> ---------- | ----------   ----------
>  (  8,  0) |        1.0          0.0
> ---------- | ----------   ----------
>    Overall |    IOs/Unp   IOs/Unp(to)
>    Average |        1.0          0.0
> 
> ==================== Active Requests At Q Information ====================
> 
>        DEV |  Avg Reqs @ Q
> ---------- | -------------
>  (  8,  0) |           5.9
> 
> ==================== I/O Active Period Information ====================
> 
>        DEV |     # Live      Avg. Act     Avg. !Act % Live
> ---------- | ---------- ------------- ------------- ------
>  (  8,  0) |        340   0.175645918   0.001273008  99.28
> ---------- | ---------- ------------- ------------- ------
>  Total Sys |        340   0.175645918   0.001273008  99.28
> 
> # Total System
> #     Total System : q activity
>   0.145330280   0.0
>   0.145330280   0.4
>  60.145690780   0.4
>  60.145690780   0.0
> 
> #     Total System : c activity
>   0.145450660   0.5
>   0.145450660   0.9
>  60.151161760   0.9
>  60.151161760   0.5
> 
> 
> MQ none scheduler
> 
> ==================== All Devices ====================
> 
>             ALL           MIN           AVG           MAX           N
> --------------- ------------- ------------- ------------- -----------
> 
> Q2Q               0.000004000   0.000010185   0.011803940     5890750
> Q2G               0.000000320   0.000000763   0.011078580     1831198
> G2I               0.000001080   0.000001682   0.010839860     1831198
> Q2M               0.000000340   0.000000484   0.008391040     4059553
> I2D               0.000000560   0.000087068   0.014350600     1831198
> M2D               0.000000740   0.000874582   0.014343840     4059553
> D2C               0.000045440   0.001720173   0.022475360     5890751
> Q2C               0.000047940   0.002351043   0.027917120     5890751
> 
> ==================== Device Overhead ====================
> 
>        DEV |       Q2G       G2I       Q2M       I2D       D2C
> ---------- | --------- --------- --------- --------- ---------
>  (  8,  0) |   0.0101%   0.0222%   0.0142%   1.1512%  73.1664%
> ---------- | --------- --------- --------- --------- ---------
>    Overall |   0.0101%   0.0222%   0.0142%   1.1512%  73.1664%
> 
> ==================== Device Merge Information ====================
> 
>        DEV |       #Q       #D   Ratio |   BLKmin   BLKavg   BLKmax    Total
> ---------- | -------- -------- ------- | -------- -------- -------- --------
>  (  8,  0) |  6098099  1831198     3.3 |        8       25      256 47126008
> 
> ==================== Device Q2Q Seek Information ====================
> 
>        DEV |          NSEEKS            MEAN          MEDIAN | MODE           
> ---------- | --------------- --------------- --------------- | ---------------
>  (  8,  0) |         5890751             0.0               0 | 0(5890751)
> ---------- | --------------- --------------- --------------- | ---------------
>    Overall |          NSEEKS            MEAN          MEDIAN | MODE           
>    Average |         5890751             0.0               0 | 0(5890751)
> 
> ==================== Device D2D Seek Information ====================
> 
>        DEV |          NSEEKS            MEAN          MEDIAN | MODE           
> ---------- | --------------- --------------- --------------- | ---------------
>  (  8,  0) |         1831198            14.9               0 | 0(1788470)
> ---------- | --------------- --------------- --------------- | ---------------
>    Overall |          NSEEKS            MEAN          MEDIAN | MODE           
>    Average |         1831198            14.9               0 | 0(1788470)
> 
> ==================== Plug Information ====================
> 
>        DEV |    # Plugs # Timer Us  | % Time Q Plugged
> ---------- | ---------- ----------  | ----------------
>  (  8,  0) |          0(   1831198) |   1.413429756%
> 
>        DEV |    IOs/Unp   IOs/Unp(to)
> ---------- | ----------   ----------
>  (  8,  0) |        0.0          1.0
> ---------- | ----------   ----------
>    Overall |    IOs/Unp   IOs/Unp(to)
>    Average |        0.0          1.0
> 
> ==================== Active Requests At Q Information ====================
> 
>        DEV |  Avg Reqs @ Q
> ---------- | -------------
>  (  8,  0) |      103313.4
> 
> ==================== I/O Active Period Information ====================
> 
>        DEV |     # Live      Avg. Act     Avg. !Act % Live
> ---------- | ---------- ------------- ------------- ------
>  (  8,  0) |       3524   0.016706167   0.000374821  97.81
> ---------- | ---------- ------------- ------------- ------
>  Total Sys |       3524   0.016706167   0.000374821  97.81
> 
> # Total System
> #     Total System : q activity
>   0.192011040   0.0
>   0.192011040   0.4
>  60.191890980   0.4
>  60.191890980   0.0
> 
> #     Total System : c activity
>   0.192155040   0.5
>   0.192155040   0.9
>  60.193025700   0.9
>  60.193025700   0.5
> 
> mq-deadline
> 
> ==================== All Devices ====================
> 
>             ALL           MIN           AVG           MAX           N
> --------------- ------------- ------------- ------------- -----------
> 
> Q2Q               0.000004280   0.000021677   0.011974760     2767943
> Q2G               0.000000440   0.000000624   0.004582540     1784446
> G2I               0.000001060   0.000011345   0.010930560     1784446
> Q2M               0.000000400   0.000000497   0.000384020      983498
> I2D               0.000000840   0.005639927   1.439620540     1784446
> M2D               0.000001500   0.010220524   1.180956080      983498
> D2C               0.000062460   0.001896701   0.013208260     2767944
> Q2C               0.000066940   0.009172085   1.441107160     2767944
> 
> ==================== Device Overhead ====================
> 
>        DEV |       Q2G       G2I       Q2M       I2D       D2C
> ---------- | --------- --------- --------- --------- ---------
>  (  8,  0) |   0.0044%   0.0797%   0.0019%  39.6416%  20.6791%
> ---------- | --------- --------- --------- --------- ---------
>    Overall |   0.0044%   0.0797%   0.0019%  39.6416%  20.6791%
> 
> ==================== Device Merge Information ====================
> 
>        DEV |       #Q       #D   Ratio |   BLKmin   BLKavg   BLKmax    Total
> ---------- | -------- -------- ------- | -------- -------- -------- --------
>  (  8,  0) |  6224597  1784446     3.5 |        8       12      256 22143552
> 
> ==================== Device Q2Q Seek Information ====================
> 
>        DEV |          NSEEKS            MEAN          MEDIAN | MODE           
> ---------- | --------------- --------------- --------------- | ---------------
>  (  8,  0) |         2767944             0.0               0 | 0(2767944)
> ---------- | --------------- --------------- --------------- | ---------------
>    Overall |          NSEEKS            MEAN          MEDIAN | MODE           
>    Average |         2767944             0.0               0 | 0(2767944)
> 
> ==================== Device D2D Seek Information ====================
> 
>        DEV |          NSEEKS            MEAN          MEDIAN | MODE           
> ---------- | --------------- --------------- --------------- | ---------------
>  (  8,  0) |         1784446           358.3               0 | 0(1549194)
> ---------- | --------------- --------------- --------------- | ---------------
>    Overall |          NSEEKS            MEAN          MEDIAN | MODE           
>    Average |         1784446           358.3               0 | 0(1549194)
> 
> ==================== Plug Information ====================
> 
>        DEV |    # Plugs # Timer Us  | % Time Q Plugged
> ---------- | ---------- ----------  | ----------------
>  (  8,  0) |          0(   1784446) |   1.244944150%
> 
>        DEV |    IOs/Unp   IOs/Unp(to)
> ---------- | ----------   ----------
>  (  8,  0) |        0.0          1.0
> ---------- | ----------   ----------
>    Overall |    IOs/Unp   IOs/Unp(to)
>    Average |        0.0          1.0
> 
> ==================== Active Requests At Q Information ====================
> 
>        DEV |  Avg Reqs @ Q
> ---------- | -------------
>  (  8,  0) |     1731603.5
> 
> ==================== I/O Active Period Information ====================
> 
>        DEV |     # Live      Avg. Act     Avg. !Act % Live
> ---------- | ---------- ------------- ------------- ------
>  (  8,  0) |        554   0.108154299   0.000462375  99.58
> ---------- | ---------- ------------- ------------- ------
>  Total Sys |        554   0.108154299   0.000462375  99.58
> 
> # Total System
> #     Total System : q activity
>   0.167375140   0.0
>   0.167375140   0.4
>  60.167642920   0.4
>  60.167642920   0.0
> 
> #     Total System : c activity
>   0.167503100   0.5
>   0.167503100   0.9
>  60.173175400   0.9
>  60.173175400   0.5
> 
> Thanks
> 
> Jonathan
> 
> _______________________________________________
> linuxarm mailing list
> linuxarm@huawei.com
> http://rnd-openeuler.huawei.com/mailman/listinfo/linuxarm

      reply	other threads:[~2017-07-18 16:25 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-06-16  8:27 [PATCH] scsi: default to scsi-mq Christoph Hellwig
2017-06-19  6:03 ` [lkp-robot] [scsi] ebc76736f2: fio.write_bw_MBps -4% regression kernel test robot
2017-06-19  6:03   ` kernel test robot
2017-06-19  7:09   ` Christoph Hellwig
2017-06-19  7:09     ` Christoph Hellwig
2017-06-19  7:09     ` Christoph Hellwig
2017-06-19  7:49     ` Ye Xiaolong
2017-06-19  7:49       ` Ye Xiaolong
2017-06-19  7:49       ` Ye Xiaolong
2017-06-19  8:41       ` Christoph Hellwig
2017-06-19  8:41         ` Christoph Hellwig
2017-06-19  8:52         ` Ye Xiaolong
2017-06-19  8:52           ` Ye Xiaolong
2017-06-19  9:39           ` Christoph Hellwig
2017-06-19  9:39             ` Christoph Hellwig
2017-06-20  2:16             ` Ye Xiaolong
2017-06-20  2:16               ` Ye Xiaolong
2017-06-20  6:04               ` Christoph Hellwig
2017-06-20  6:04                 ` Christoph Hellwig
2017-06-22 15:05 ` [PATCH] scsi: default to scsi-mq Martin Wilck
2017-06-26  9:48   ` Christoph Hellwig
2017-06-26 12:13   ` Bart Van Assche
2017-06-26 15:31     ` Bart Van Assche
2017-06-26 18:55       ` Martin Wilck
2017-06-27  6:07         ` Bart Van Assche
2017-07-10 15:50 ` Bart Van Assche
2017-07-11 10:22   ` John Garry
2017-07-11 13:32     ` Bart Van Assche
2017-07-11 14:14       ` John Garry
2017-07-11 15:46         ` Bart Van Assche
2017-07-11 17:34           ` John Garry
2017-07-12  8:26             ` John Garry
2017-07-12 14:18               ` Bart Van Assche
2017-07-12 15:54                 ` Jonathan Cameron
2017-07-14  9:56                   ` Jonathan Cameron
2017-07-14 12:45                     ` hch
2017-07-18 15:58                       ` Jonathan Cameron
2017-07-18 16:24                         ` Jonathan Cameron [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=20170719002453.00002876@huawei.com \
    --to=jonathan.cameron@huawei.com \
    --cc=Bart.VanAssche@wdc.com \
    --cc=hch@lst.de \
    --cc=linux-scsi@vger.kernel.org \
    --cc=linuxarm@huawei.com \
    /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.