[OpenIndiana-discuss] Test on Sun X4170M2 between STEC Mach16 SLC/MLC and Intel DC S3700

Albert Chin openindiana-discuss at mlists.thewrittenword.com
Mon Feb 23 14:18:33 UTC 2015


On Mon, Feb 23, 2015 at 07:47:31AM -0600, Schweiss, Chip wrote:
> This may be a better topic for the Illumos ZFS mailing.

Ok.

> There are a couple things affecting your results here.
> 
> The SSDs  perform best when multiple threads are filling their
> queue.   In your test you have a single thread.
> 
> It is my understanding the ZIL is also one thread per ZFS file
> system. The latency of the SAS bus and SSD will stack up against you
> here.  You should get better results across the board if you execute
> against several ZFS file systems on the pool.

Thanks. I ran the dd command on five separate filesystems:
  ATA-STEC    MACH16 M-0289-186.31GB (MLC)
    $ /usr/gnu/bin/dd if=/dev/zero of=file bs=1 oflag=sync
    $ iostat -cnx 1
    r/s     w/s   kr/s     kw/s wait actv wsvc_t asvc_t  %w  %b
    0.0 26788.2    0.0 107152.9  0.1  3.6    0.0    0.1   6 100
    0.0 27470.8    0.0 109883.2  0.1  3.0    0.0    0.1   5 100
    0.0 27980.1    0.0 111924.3  0.1  2.8    0.0    0.1   5 100
    0.0 27100.3    0.0 108401.3  0.1  2.7    0.0    0.1   5  97
    0.0 25801.0    0.0 103204.2  0.0  2.6    0.0    0.1   5  99
    0.0 26955.1    0.0 107820.2  0.1  3.2    0.0    0.1   6 100
    0.0 26374.3    0.0 105497.3  0.1  3.6    0.0    0.1   6 100

  ATA-INTEL SSDSC2BA20-0270-186.31GB (MLC)
    $ /usr/gnu/bin/dd if=/dev/zero of=file bs=1 oflag=sync
    $ iostat -cnx 1
    r/s     w/s   kr/s    kw/s wait actv wsvc_t asvc_t  %w  %b
    0.0 16462.9    0.0 32927.8  0.0  1.8    0.0    0.1   3  94
    0.0 16441.1    0.0 32888.2  0.0  1.8    0.0    0.1   3  94
    0.0 16483.9    0.0 32963.8  0.0  1.8    0.0    0.1   2  93
    0.0 16468.7    0.0 32935.4  0.0  1.8    0.0    0.1   3  94
    0.0 16479.8    0.0 32965.7  0.0  1.8    0.0    0.1   3  94
    0.0 16472.2    0.0 32942.4  0.0  1.8    0.0    0.1   2  94

Performance of the Intel is so sad in comparison to the older STEC.

> -Chip
> 
> On Sun, Feb 22, 2015 at 9:28 PM, Albert Chin <
> openindiana-discuss at mlists.thewrittenword.com> wrote:
> 
> > I've tested three SSDs in a Sun X4170M2. This server has 8 internal
> > SSD 2.5" drive bays with a Sun Storage 6 Gb SAS PCIe RAID HBA. I
> > believe the chipset on the HBA is a LSI SAS2108 (according to
> > http://tinyurl.com/koc6kdn).
> >
> > I tested by adding each SSD as a ZIL for a pool and then running the
> > following command on one of the file systems in the pool:
> >   $ /usr/gnu/bin/dd if=/dev/zero of=file bs=1 oflag=sync
> >
> > Iostat numbers below are given by:
> >   $ iostat -cnx 1
> >
> > $ cat /kernel/drv/sd.conf
> > ...
> > sd-config-list="*MACH16*","disksort:false, cache-nonvolatile:true",
> >                "*INTELSSD*","disksort:false, cache-nonvolatile:true,
> > physical-block-size:8192";
> >
> > The 8k block size for the Intel S3700 comes from:
> >
> > http://wiki.illumos.org/display/illumos/List+of+sd-config-list+entries+for+Advanced-Format+drives
> >
> > Product part numbers:
> >   1. STEC Mach16 SLC 100GB - M16CSD2-100UIU
> >   2. STEC Mach16 MLC 200GB - M16ISD2-200UCV
> >   3. Intel DC S3700 - SSDSC2BA200G301
> >
> > ATA-STEC    MACH16 M-0300-93.16GB (SLC)
> >   $ /usr/gnu/bin/dd if=/dev/zero of=file bs=1 oflag=sync
> >   $ iostat -cnx 1
> >   r/s    w/s   kr/s   kw/s wait actv wsvc_t asvc_t  %w  %b
> >   0.0 1439.2    0.0 5756.9  0.0  0.8    0.0    0.6   0  84
> >   0.0 1478.7    0.0 5915.0  0.0  0.9    0.0    0.6   1  86
> >   0.0 1491.1    0.0 5964.2  0.0  0.9    0.0    0.6   1  88
> >   0.0 1506.0    0.0 6023.8  0.0  0.9    0.0    0.6   0  89
> >
> > ATA-STEC    MACH16 M-0289-186.31GB (MLC)
> >   $ /usr/gnu/bin/dd if=/dev/zero of=file bs=1 oflag=sync
> >   $ iostat -cnx 1
> >   r/s    w/s   kr/s    kw/s wait actv wsvc_t asvc_t  %w  %b
> >   0.0 8079.7    0.0 32318.9  0.0  0.5    0.0    0.1   2  52
> >   0.0 8229.1    0.0 32916.5  0.0  0.5    0.0    0.1   2  53
> >   0.0 7368.0    0.0 29471.9  0.0  0.5    0.0    0.1   2  47
> >   0.0 7318.0    0.0 29272.2  0.0  0.5    0.0    0.1   2  47
> >
> > ATA-INTEL SSDSC2BA20-0270-186.31GB (MLC)
> >   $ /usr/gnu/bin/dd if=/dev/zero of=file bs=1 oflag=sync
> >   $ iostat -cnx 1
> >   r/s    w/s   kr/s    kw/s wait actv wsvc_t asvc_t  %w  %b
> >   0.0 9196.0    0.0 18392.0  0.0  0.2    0.0    0.0   1  19
> >   0.0 9144.3    0.0 18288.6  0.0  0.2    0.0    0.0   1  19
> >   0.0 9288.7    0.0 18575.5  0.0  0.2    0.0    0.0   1  19
> >   0.0 8352.0    0.0 16704.0  0.0  0.2    0.0    0.0   1  17
> >
> > The STEC Mach16's are 3.0Gbps devices. The Intel SSD DC S3700 is a
> > 6.0Gbps device. Just two questions:
> >   1. Why don't I see double the IOPS performance between the
> >      6.0Gbps device than the 3.0Gbps devices?
> >   2. Why does the STEC Mach16 100GB SLC suck so badly in comparison
> >      to it's 200GB MLC cousin? I know that the 100GB drives won't
> >      perform as well as the 200GB models but I did not expect this
> >      much of a difference.
> >
> > Even using bs=4096 on the Intel S3700, I was hoping to see >10K IOPS,
> > possibly matching the numbers from the anandtech review:
> >   http://www.anandtech.com/show/6433/intel-ssd-dc-s3700-200gb-review/3
> > ATA-INTEL SSDSC2BA20-0270-186.31GB (MLC)
> >   $ /usr/gnu/bin/dd if=/dev/zero of=file bs=4096 oflag=sync
> >   $ iostat -cnx 1
> >   r/s    w/s   kr/s    kw/s wait actv wsvc_t asvc_t  %w  %b
> >   0.0 8714.5    0.0 34858.0  0.0  0.2    0.0    0.0   1  22
> >   0.0 8410.9    0.0 33639.6  0.0  0.2    0.0    0.0   1  21
> >   0.0 8431.1    0.0 33728.2  0.0  0.2    0.0    0.0   1  21
> >   0.0 8295.0    0.0 33224.0  0.0  0.2    0.0    0.0   1  21
> >   0.0 8970.1    0.0 35740.4  0.0  0.2    0.0    0.0   1  23
> >
> > Am I getting the best possible performance out of the Intel S3700?
> >
> > --
> > albert chin (china at thewrittenword.com)
> >
> > _______________________________________________
> > openindiana-discuss mailing list
> > openindiana-discuss at openindiana.org
> > http://openindiana.org/mailman/listinfo/openindiana-discuss
> _______________________________________________
> openindiana-discuss mailing list
> openindiana-discuss at openindiana.org
> http://openindiana.org/mailman/listinfo/openindiana-discuss

-- 
albert chin (china at thewrittenword.com)



More information about the openindiana-discuss mailing list