RE: fio replay

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Jens,

Finally got back to this.

I do get different results with 2.1.6.1.
Not sure what is wrong.

[root@x3650M4 Run2]# ls
bprun2all.bin
[root@x3650M4 Run2]# fio --name=rp2 --ioengine=libaio --iodepth=12 --read_iolog=bprun2all.bin
rp2: (g=0): rw=read, bs=4K-4K/4K-4K/4K-4K, ioengine=libaio, iodepth=12
fio-2.1.6.1
Starting 1 process
blktrace: got timestamp notify: 4000001, 0
fio: filesetup.c:1264: get_file: Assertion `fio_file_open(f)' failed.:00s]
fio: pid=14664, got signal=6e] [0KB/37KB/0KB /s] [0/9/0 iops] [eta 09h:02m:07s]

rp2: (groupid=0, jobs=1): err= 0: pid=14664: Fri Mar 28 08:47:57 2014
    lat (usec) : 100=10.71%, 250=89.29%
  cpu          : usr=0.00%, sys=0.00%, ctx=0, majf=0, minf=0
  IO depths    : 1=3.6%, 2=7.1%, 4=14.3%, 8=75.0%, 16=0.0%, 32=0.0%, >=64=0.0%
     submit    : 0=0.0%, 4=100.0%, 8=0.0%, 16=0.0%, 32=0.0%, 64=0.0%, >=64=0.0%
     complete  : 0=0.0%, 4=94.4%, 8=0.0%, 16=5.6%, 32=0.0%, 64=0.0%, >=64=0.0%
     issued    : total=r=0/w=28/d=0, short=r=0/w=0/d=0
     latency   : target=0, window=0, percentile=100.00%, depth=12

Run status group 0 (all jobs):
  WRITE: io=0KB, aggrb=0KB/s, minb=0KB/s, maxb=0KB/s, mint=595msec, maxt=595msec
[root@x3650M4 Run2]#

Eric
-----Original Message-----
From: fio-owner@xxxxxxxxxxxxxxx [mailto:fio-owner@xxxxxxxxxxxxxxx] On Behalf Of Lamkin, Eric
Sent: Thursday, March 06, 2014 10:12 AM
To: Jens Axboe
Cc: fio@xxxxxxxxxxxxxxx; David Nellans
Subject: RE: fio replay

OK, will grab 2.1.6 and reply with observations.

I've only recently subscribed to this mail-list and it amazes me that you can give attention to such a barrage of requests.

Eric
-----Original Message-----
From: Jens Axboe [mailto:axboe@xxxxxxxxx]
Sent: Thursday, March 06, 2014 9:55 AM
To: Lamkin, Eric; David Nellans
Cc: fio@xxxxxxxxxxxxxxx
Subject: Re: fio replay

On 03/03/2014 06:25 AM, Lamkin, Eric wrote:
> Here's my update with a blktrace captured on a single device with no dropped events.
> Also switched to fio 2.1.4.
>
> Capture a single device trace with no dropped events.

[snip]

Thanks for the detailed report. But why are you replaying with fio-2.1.4? If there's a bug here (and it looks like it), then please replay the blktrace with fio-2.1.6 and I can take a look at it.

--
Jens Axboe


--
To unsubscribe from this list: send the line "unsubscribe fio" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at  http://vger.kernel.org/majordomo-info.html

--
To unsubscribe from this list: send the line "unsubscribe fio" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html




[Index of Archives]     [Linux Kernel]     [Linux SCSI]     [Linux IDE]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux SCSI]

  Powered by Linux