DaemonForums  

Go Back   DaemonForums > FreeBSD > FreeBSD General
Reload this Page STORAGE: benchmarks results (diskinfo)
FAQ Search Today's Posts Mark Forums Read

FreeBSD General Other questions regarding FreeBSD which do not fit in any of the categories below.

Reply
Page 2 of 3 1 2 3
 
Thread Tools Display Modes
  #21   (View Single Post)  
Old 13th November 2008
tangram's Avatar
tangram tangram is offline
Real Name: Ricardo Jesus
Port Guard
  
Join Date: May 2008
Location: Portugal
Posts: 36
Thanked 2 Times in 2 Posts
Default
ad4: 114473MB <Seagate ST3120022A 3.04> at ata2-master UDMA100

Code:
/dev/ad4
        512             # sectorsize
        120034123776    # mediasize in bytes (112G)
        234441648       # mediasize in sectors
        232581          # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.
        ad:3JT03PGJ     # Disk ident.

I/O command overhead:
        time to read 10MB block      0.254739 sec       =    0.012 msec/sector
        time to read 20480 sectors   9.037125 sec       =    0.441 msec/sector
        calculated command overhead                     =    0.429 msec/sector

Seek times:
        Full stroke:      250 iter in   5.730336 sec =   22.921 msec
        Half stroke:      250 iter in   4.476435 sec =   17.906 msec
        Quarter stroke:   500 iter in   7.122016 sec =   14.244 msec
        Short forward:    400 iter in   2.161611 sec =    5.404 msec
        Short backward:   400 iter in   1.193050 sec =    2.983 msec
        Seq outer:       2048 iter in   0.932468 sec =    0.455 msec
        Seq inner:       2048 iter in   0.942871 sec =    0.460 msec
Transfer rates:
        outside:       102400 kbytes in   1.964194 sec =    52133 kbytes/sec
        middle:        102400 kbytes in   2.175116 sec =    47078 kbytes/sec
        inside:        102400 kbytes in   3.431121 sec =    29844 kbytes/sec
ad10: 953869MB <SAMSUNG HD103UJ 1AA01112> at ata5-master SATA150

Code:
/dev/ad10
        512             # sectorsize
        1000204886016   # mediasize in bytes (932G)
        1953525168      # mediasize in sectors
        1938021         # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.
        ad:S13PJ1MQ602787       # Disk ident.

I/O command overhead:
        time to read 10MB block      0.180889 sec       =    0.009 msec/sector
        time to read 20480 sectors   9.345026 sec       =    0.456 msec/sector
        calculated command overhead                     =    0.447 msec/sector

Seek times:
        Full stroke:      250 iter in   6.147410 sec =   24.590 msec
        Half stroke:      250 iter in   4.646249 sec =   18.585 msec
        Quarter stroke:   500 iter in   8.820316 sec =   17.641 msec
        Short forward:    400 iter in   1.664426 sec =    4.161 msec
        Short backward:   400 iter in   2.615189 sec =    6.538 msec
        Seq outer:       2048 iter in   0.996294 sec =    0.486 msec
        Seq inner:       2048 iter in   0.995813 sec =    0.486 msec
Transfer rates:
        outside:       102400 kbytes in   1.647798 sec =    62144 kbytes/sec
        middle:        102400 kbytes in   1.619156 sec =    63243 kbytes/sec
        inside:        102400 kbytes in   1.930229 sec =    53051 kbytes/sec
Last edited by tangram; 13th November 2008 at 03:35 PM. Reason: Added another disk to the mix.
Reply With Quote
  #22   (View Single Post)  
Old 13th November 2008
Oliver_H's Avatar
Oliver_H Oliver_H is offline
Real Name: Oliver Herold
UNIX lover
  
Join Date: May 2008
Location: Germany
Posts: 429
Thanked 26 Times in 22 Posts
Default
ad0: 286167MB <Seagate ST3300622A 3.AAH> at ata0-master UDMA100

Code:
/dev/ad0
	512         	# sectorsize
	300067970560	# mediasize in bytes (279G)
	586070255   	# mediasize in sectors
	581418      	# Cylinders according to firmware.
	16          	# Heads according to firmware.
	63          	# Sectors according to firmware.
	ad:5NF2VE47 	# Disk ident.

I/O command overhead:
	time to read 10MB block      0.179757 sec	=    0.009 msec/sector
	time to read 20480 sectors   1.481450 sec	=    0.072 msec/sector
	calculated command overhead			=    0.064 msec/sector

Seek times:
	Full stroke:	  250 iter in   5.713823 sec =   22.855 msec
	Half stroke:	  250 iter in   4.523551 sec =   18.094 msec
	Quarter stroke:	  500 iter in   6.768790 sec =   13.538 msec
	Short forward:	  400 iter in   2.183977 sec =    5.460 msec
	Short backward:	  400 iter in   1.524321 sec =    3.811 msec
	Seq outer:	 2048 iter in   0.169669 sec =    0.083 msec
	Seq inner:	 2048 iter in   0.191090 sec =    0.093 msec
Transfer rates:
	outside:       102400 kbytes in   1.705157 sec =    60053 kbytes/sec
	middle:        102400 kbytes in   1.945732 sec =    52628 kbytes/sec
	inside:        102400 kbytes in   3.297897 sec =    31050 kbytes/sec
__________________
use UNIX or die :-)
Reply With Quote
  #23   (View Single Post)  
Old 13th November 2008
Oliver_H's Avatar
Oliver_H Oliver_H is offline
Real Name: Oliver Herold
UNIX lover
  
Join Date: May 2008
Location: Germany
Posts: 429
Thanked 26 Times in 22 Posts
Default
ad0: 114473MB <Hitachi HTS541612J9SA00 SBDOC70P> at ata0-master SATA150 | Laptop 2.5"

Code:
/dev/ad0
	512         	# sectorsize
	120034123776	# mediasize in bytes (112G)
	234441648   	# mediasize in sectors
	232581      	# Cylinders according to firmware.
	16          	# Heads according to firmware.
	63          	# Sectors according to firmware.
	ad:SB2D41E4CGEKKE	# Disk ident.

I/O command overhead:
	time to read 10MB block      0.287116 sec	=    0.014 msec/sector
	time to read 20480 sectors   2.480988 sec	=    0.121 msec/sector
	calculated command overhead			=    0.107 msec/sector

Seek times:
	Full stroke:	  250 iter in   6.031056 sec =   24.124 msec
	Half stroke:	  250 iter in   5.037848 sec =   20.151 msec
	Quarter stroke:	  500 iter in   8.506920 sec =   17.014 msec
	Short forward:	  400 iter in   3.550424 sec =    8.876 msec
	Short backward:	  400 iter in   2.049560 sec =    5.124 msec
	Seq outer:	 2048 iter in   0.291115 sec =    0.142 msec
	Seq inner:	 2048 iter in   0.295479 sec =    0.144 msec
Transfer rates:
	outside:       102400 kbytes in   2.690707 sec =    38057 kbytes/sec
	middle:        102400 kbytes in   3.281864 sec =    31202 kbytes/sec
	inside:        102400 kbytes in   5.554393 sec =    18436 kbytes/sec
__________________
use UNIX or die :-)
Reply With Quote
  #24   (View Single Post)  
Old 13th November 2008
ephemera's Avatar
ephemera ephemera is offline
Knuth's homeboy
  
Join Date: Apr 2008
Posts: 537
Thanked 49 Times in 43 Posts
Default
Quote:
Originally Posted by vermaden View Post
Yes, but your results are from Virtual image on disk within wirtualization, You wil ALWAYS get "strange" results about disk performance when you use disk in a file for your virtualized OS, I also got strange and realtively faster results then the drive can do even in slower QEMU.
I gave a look at the code and TBH its even more naive than I expected.
check it out for yourself.

The fantastic scores i was getting were bogus. i think its because of 2 factors:
1. The virtual disk was not preallocated so there is some kind of COW mechanism going on here though i don't know the details. This layer of abstraction was i believe causing the skewed result.
2. The disk is too small so the f, q, h stoke readings have no meaning here.

here is the o/p with a preallocated disk. this is more in line with what one would expect:
Code:
/dev/ad1
        512             # sectorsize
        8589934592      # mediasize in bytes (8.0G)
        16777216        # mediasize in sectors
        17753           # Cylinders according to firmware.
        15              # Heads according to firmware.
        63              # Sectors according to firmware.
        ad:01000000000000000001 # Disk ident.

I/O command overhead:
        time to read 10MB block      0.192098 sec       =    0.009 msec/sector
        time to read 20480 sectors   2.492608 sec       =    0.122 msec/sector
        calculated command overhead                     =    0.112 msec/sector

Seek times:
        Full stroke:      250 iter in   2.628599 sec =   10.514 msec
        Half stroke:      250 iter in   2.394040 sec =    9.576 msec
        Quarter stroke:   500 iter in   3.194460 sec =    6.389 msec
        Short forward:    400 iter in   3.233777 sec =    8.084 msec
        Short backward:   400 iter in   3.047335 sec =    7.618 msec
        Seq outer:       2048 iter in   0.335767 sec =    0.164 msec
        Seq inner:       2048 iter in   0.335223 sec =    0.164 msec
Transfer rates:
        outside:       102400 kbytes in   1.474514 sec =    69447 kbytes/sec
        middle:        102400 kbytes in   1.627657 sec =    62913 kbytes/sec
        inside:        102400 kbytes in   1.558496 sec =    65704 kbytes/sec
the f/h/q stroke readings may look overoptimistic but they are not. this has to do with how the benchmark calculates this value. if the whole disk was used for this virt. disk I would expect the numbers to be worse than 25 ms.

the transfer rates are more or less the same, as expected.

also, I would expect the COW results to degenerate to the above values when the disk becomes full.
Last edited by ephemera; 13th November 2008 at 05:49 PM.
Reply With Quote
  #25   (View Single Post)  
Old 13th November 2008
ephemera's Avatar
ephemera ephemera is offline
Knuth's homeboy
  
Join Date: Apr 2008
Posts: 537
Thanked 49 Times in 43 Posts
Default
Quote:
Originally Posted by killasmurf86
Transfer rates:
outside: 102400 kbytes in 3.457052 sec = 29621 kbytes/sec
middle: 102400 kbytes in 3.437947 sec = 29785 kbytes/sec
inside: 102400 kbytes in 3.399791 sec = 30119 kbytes/sec
your disk is bottlenecked by the ATA33 interface?
Reply With Quote
  #26   (View Single Post)  
Old 13th November 2008
vermaden's Avatar
vermaden vermaden is offline
Administrator
  
Join Date: Apr 2008
Location: pl_PL.lodz
Posts: 1,041
Thanked 118 Times in 93 Posts
Default
Quote:
Originally Posted by ephemera View Post
your disk is bottlenecked by the ATA33 interface?
Quote:
Originally Posted by killasmurf86
da0: 15424MB (31588352 512 byte sectors: 255H 63S/T 1966C)
adata PD16 16GB flash-key:
Its a pendrive mate
__________________
religions, worst damnation of mankind
"If 386BSD had been available when I started on Linux, Linux would probably never had happened." Linus Torvalds
Linux is not UNIX! Face it! It is not an insult. It is fact: GNU is a recursive acronym for “GNU's Not UNIX”.
vermaden's: links resources deviantart spreadbsd
Reply With Quote
  #27   (View Single Post)  
Old 13th November 2008
ephemera's Avatar
ephemera ephemera is offline
Knuth's homeboy
  
Join Date: Apr 2008
Posts: 537
Thanked 49 Times in 43 Posts
Default
Quote:
Originally Posted by vermaden View Post
Its a pendrive mate
Quote:
Originally Posted by killasmurf86
Code:
ad0: 152627MB <SAMSUNG SP1604N TM100-30> at ata0-master UDMA33

killasmurf86 $ diskinfo -c -t /dev/ad0
/dev/ad0
512 # sectorsize
160041885696 # mediasize in bytes (149G)
312581808 # mediasize in sectors
310101 # Cylinders according to firmware.
16 # Heads according to firmware.
63 # Sectors according to firmware.
ad:S013J10Y333525 # Disk ident.

I/O command overhead:
time to read 10MB block 0.397548 sec = 0.019 msec/sector
time to read 20480 sectors 2.393213 sec = 0.117 msec/sector
calculated command overhead = 0.097 msec/sector

Seek times:
Full stroke: 250 iter in 5.550619 sec = 22.202 msec
Half stroke: 250 iter in 3.911959 sec = 15.648 msec
Quarter stroke: 500 iter in 6.194812 sec = 12.390 msec
Short forward: 400 iter in 2.468873 sec = 6.172 msec
Short backward: 400 iter in 1.654048 sec = 4.135 msec
Seq outer: 2048 iter in 0.267607 sec = 0.131 msec
Seq inner: 2048 iter in 0.283663 sec = 0.139 msec
Transfer rates:
outside: 102400 kbytes in 3.457052 sec = 29621 kbytes/sec
middle: 102400 kbytes in 3.437947 sec = 29785 kbytes/sec
inside: 102400 kbytes in 3.399791 sec = 30119 kbytes/sec
:-)
Reply With Quote
  #28   (View Single Post)  
Old 13th November 2008
BSDKaffee's Avatar
BSDKaffee BSDKaffee is offline
Real Name: Jason Hale
Coffee Addict
  
Join Date: May 2008
Location: Wintersville, Ohio
Posts: 212
Thanked 36 Times in 34 Posts
Default
Toshiba HDDR320E03X: 2.5" external, 320GB, 5400 rpm, 8MB cache, USB 2.0
Code:
umass0: <Toshiba External USB HDD, class 0/0, rev 2.00/1.02, addr 2> on uhub6
da0 at umass-sim0 bus 0 target 0 lun 0
da0: <Toshiba External USB HDD 1.02> Fixed Direct Access SCSI-4 device
da0: 40.000MB/s transfers
da0: 305245MB (625142448 512 byte sectors: 255H 63S/T 38913C)
Code:
$ diskinfo -ct /dev/da0
/dev/da0
        512             # sectorsize
        320072933376    # mediasize in bytes (298G)
        625142448       # mediasize in sectors
        38913           # Cylinders according to firmware.
        255             # Heads according to firmware.
        63              # Sectors according to firmware.

I/O command overhead:
        time to read 10MB block      0.394168 sec       =    0.019 msec/sector
        time to read 20480 sectors  15.482948 sec       =    0.756 msec/sector
        calculated command overhead                     =    0.737 msec/sector

Seek times:
        Full stroke:      250 iter in   6.751905 sec =   27.008 msec
        Half stroke:      250 iter in   5.185917 sec =   20.744 msec
        Quarter stroke:   500 iter in   8.595056 sec =   17.190 msec
        Short forward:    400 iter in   4.456332 sec =   11.141 msec
        Short backward:   400 iter in   4.038749 sec =   10.097 msec
        Seq outer:       2048 iter in   1.578434 sec =    0.771 msec
        Seq inner:       2048 iter in   1.596359 sec =    0.779 msec
Transfer rates:
        outside:       102400 kbytes in   3.605207 sec =    28403 kbytes/sec
        middle:        102400 kbytes in   3.674450 sec =    27868 kbytes/sec
        inside:        102400 kbytes in   3.664630 sec =    27943 kbytes/sec
Seagate Momentus ST9160823AS: 2.5" internal, 160 GB, 7200 rpm, 8MB cache, SATA 300
Code:
ad4: 152627MB <Seagate ST9160823AS 3.AAB> at ata2-master SATA300
Code:
$ diskinfo -ct /dev/ad4
/dev/ad4
        512             # sectorsize
        160041885696    # mediasize in bytes (149G)
        312581808       # mediasize in sectors
        310101          # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.
        ad:5NK09WJ7     # Disk ident.

I/O command overhead:
        time to read 10MB block      0.151252 sec       =    0.007 msec/sector
        time to read 20480 sectors   2.180065 sec       =    0.106 msec/sector
        calculated command overhead                     =    0.099 msec/sector

Seek times:
        Full stroke:      250 iter in   6.011026 sec =   24.044 msec
        Half stroke:      250 iter in   4.217025 sec =   16.868 msec
        Quarter stroke:   500 iter in   6.468610 sec =   12.937 msec
        Short forward:    400 iter in   2.069217 sec =    5.173 msec
        Short backward:   400 iter in   2.401825 sec =    6.005 msec
        Seq outer:       2048 iter in   0.256851 sec =    0.125 msec
        Seq inner:       2048 iter in   0.250946 sec =    0.123 msec
Transfer rates:
        outside:       102400 kbytes in   1.707083 sec =    59985 kbytes/sec
        middle:        102400 kbytes in   2.117032 sec =    48370 kbytes/sec
        inside:        102400 kbytes in   3.322629 sec =    30819 kbytes/sec
Last edited by BSDKaffee; 13th November 2008 at 06:50 PM.
Reply With Quote
  #29   (View Single Post)  
Old 13th November 2008
vermaden's Avatar
vermaden vermaden is offline
Administrator
  
Join Date: Apr 2008
Location: pl_PL.lodz
Posts: 1,041
Thanked 118 Times in 93 Posts
Default
Quote:
Originally Posted by ephemera View Post
:-)
THAT one you say ...
__________________
religions, worst damnation of mankind
"If 386BSD had been available when I started on Linux, Linux would probably never had happened." Linus Torvalds
Linux is not UNIX! Face it! It is not an insult. It is fact: GNU is a recursive acronym for “GNU's Not UNIX”.
vermaden's: links resources deviantart spreadbsd
Reply With Quote
  #30   (View Single Post)  
Old 13th November 2008
23588974223Huj 23588974223Huj is offline
New User
  
Join Date: Nov 2008
Posts: 1
Thanked 0 Times in 0 Posts
Default
Code:
mfid0: <MFI Logical Disk> on mfi0
mfid0: 2860032MB (5857345536 sectors) RAID volume '5' is optimal

Code:
#diskinfo -c -t /dev/mfid0
/dev/mfid0
        512             # sectorsize
        2998960914432   # mediasize in bytes (2.7T)
        5857345536      # mediasize in sectors
        364602          # Cylinders according to firmware.
        255             # Heads according to firmware.
        63              # Sectors according to firmware.

I/O command overhead:
        time to read 10MB block      0.064440 sec       =    0.003 msec/sector
        time to read 20480 sectors   1.267939 sec       =    0.062 msec/sector
        calculated command overhead                     =    0.059 msec/sector

Seek times:
        Full stroke:      250 iter in   1.329967 sec =    5.320 msec
        Half stroke:      250 iter in   2.698421 sec =   10.794 msec
        Quarter stroke:   500 iter in   4.543504 sec =    9.087 msec
        Short forward:    400 iter in   2.859718 sec =    7.149 msec
        Short backward:   400 iter in   3.124898 sec =    7.812 msec
        Seq outer:       2048 iter in   0.128327 sec =    0.063 msec
        Seq inner:       2048 iter in   0.129799 sec =    0.063 msec
Transfer rates:
        outside:       102400 kbytes in   0.325093 sec =   314987 kbytes/sec
        middle:        102400 kbytes in   0.398649 sec =   256868 kbytes/sec
        inside:        102400 kbytes in   0.376817 sec =   271750 kbytes/sec
4x1TB Samsung on hw raid5
Reply With Quote
  #31   (View Single Post)  
Old 14th November 2008
tangram's Avatar
tangram tangram is offline
Real Name: Ricardo Jesus
Port Guard
  
Join Date: May 2008
Location: Portugal
Posts: 36
Thanked 2 Times in 2 Posts
Default
ad0: 4103MB <Seagate ST34321A 3.04> at ata0-master UDMA33
Code:
/dev/ad0
        512             # sectorsize
        4303272960      # mediasize in bytes (4.0G)
        8404830         # mediasize in sectors
        8894            # Cylinders according to firmware.
        15              # Heads according to firmware.
        63              # Sectors according to firmware.
        ad:GT430125     # Disk ident.

I/O command overhead:
        time to read 10MB block      1.061872 sec       =    0.052 msec/sector
        time to read 20480 sectors  12.702438 sec       =    0.620 msec/sector
        calculated command overhead                     =    0.568 msec/sector

Seek times:
        Full stroke:      250 iter in   5.703315 sec =   22.813 msec
        Half stroke:      250 iter in   5.139045 sec =   20.556 msec
        Quarter stroke:   500 iter in   8.856557 sec =   17.713 msec
        Short forward:  diskinfo: read error or disk too small for test.: Input/output error
Reply With Quote
  #32   (View Single Post)  
Old 15th November 2008
Oliver_H's Avatar
Oliver_H Oliver_H is offline
Real Name: Oliver Herold
UNIX lover
  
Join Date: May 2008
Location: Germany
Posts: 429
Thanked 26 Times in 22 Posts
Default
da0: <SAMSUNG SP0802N 0000> Fixed Direct Access SCSI-0 device
da0: 40.000MB/s transfers
da0: 76351MB (156368016 512 byte sectors: 255H 63S/T 9733C)

Code:
/dev/da0
	512         	# sectorsize
	80060424192 	# mediasize in bytes (75G)
	156368016   	# mediasize in sectors
	9733        	# Cylinders according to firmware.
	255         	# Heads according to firmware.
	63          	# Sectors according to firmware.

I/O command overhead:
	time to read 10MB block      0.653984 sec	=    0.032 msec/sector
	time to read 20480 sectors  15.376827 sec	=    0.751 msec/sector
	calculated command overhead			=    0.719 msec/sector

Seek times:
	Full stroke:	  250 iter in   5.690934 sec =   22.764 msec
	Half stroke:	  250 iter in   4.177804 sec =   16.711 msec
	Quarter stroke:	  500 iter in   6.369803 sec =   12.740 msec
	Short forward:	  400 iter in   3.462061 sec =    8.655 msec
	Short backward:	  400 iter in   2.018708 sec =    5.047 msec
	Seq outer:	 2048 iter in   1.563425 sec =    0.763 msec
	Seq inner:	 2048 iter in   1.564339 sec =    0.764 msec
Transfer rates:
	outside:       102400 kbytes in   6.454496 sec =    15865 kbytes/sec
	middle:        102400 kbytes in   6.438555 sec =    15904 kbytes/sec
	inside:        102400 kbytes in   6.440142 sec =    15900 kbytes/sec
__________________
use UNIX or die :-)
Reply With Quote
  #33   (View Single Post)  
Old 8th January 2009
tangram's Avatar
tangram tangram is offline
Real Name: Ricardo Jesus
Port Guard
  
Join Date: May 2008
Location: Portugal
Posts: 36
Thanked 2 Times in 2 Posts
Default
ad4: 194481MB <Maxtor 6B200M0 BANC19J0> at ata2-master SATA150

Code:
/dev/ad4
        512             # sectorsize
        203928109056    # mediasize in bytes (190G)
        398297088       # mediasize in sectors
        395136          # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.
        ad:B4068BQH     # Disk ident.

I/O command overhead:
        time to read 10MB block      0.154790 sec       =    0.008 msec/sector
        time to read 20480 sectors   1.395390 sec       =    0.068 msec/sector
        calculated command overhead                     =    0.061 msec/sector

Seek times:
        Full stroke:      250 iter in   5.094325 sec =   20.377 msec
        Half stroke:      250 iter in   3.887557 sec =   15.550 msec
        Quarter stroke:   500 iter in   6.358262 sec =   12.717 msec
        Short forward:    400 iter in   2.689920 sec =    6.725 msec
        Short backward:   400 iter in   1.899913 sec =    4.750 msec
        Seq outer:       2048 iter in   0.156133 sec =    0.076 msec
        Seq inner:       2048 iter in   0.170133 sec =    0.083 msec
Transfer rates:
        outside:       102400 kbytes in   1.614106 sec =    63441 kbytes/sec
        middle:        102400 kbytes in   1.854823 sec =    55207 kbytes/sec
        inside:        102400 kbytes in   2.940022 sec =    34830 kbytes/sec
ad6: 194481MB <Maxtor 6B200M0 BANC19J0> at ata3-master SATA150

Code:
/dev/ad6
        512             # sectorsize
        203928109056    # mediasize in bytes (190G)
        398297088       # mediasize in sectors
        395136          # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.
        ad:B40A9TDH     # Disk ident.

I/O command overhead:
        time to read 10MB block      0.181736 sec       =    0.009 msec/sector
        time to read 20480 sectors   1.393423 sec       =    0.068 msec/sector
        calculated command overhead                     =    0.059 msec/sector

Seek times:
        Full stroke:      250 iter in   5.133403 sec =   20.534 msec
        Half stroke:      250 iter in   3.825589 sec =   15.302 msec
        Quarter stroke:   500 iter in   6.326555 sec =   12.653 msec
        Short forward:    400 iter in   2.658225 sec =    6.646 msec
        Short backward:   400 iter in   0.849711 sec =    2.124 msec
        Seq outer:       2048 iter in   0.166015 sec =    0.081 msec
        Seq inner:       2048 iter in   0.198724 sec =    0.097 msec
Transfer rates:
        outside:       102400 kbytes in   1.624582 sec =    63032 kbytes/sec
        middle:        102400 kbytes in   1.901403 sec =    53855 kbytes/sec
        inside:        102400 kbytes in   3.025676 sec =    33844 kbytes/sec
__________________
BSD and Linux tips and tutorials: Blog Linux/BSD: sharing experiences
Reply With Quote
  #34   (View Single Post)  
Old 8th January 2009
vermaden's Avatar
vermaden vermaden is offline
Administrator
  
Join Date: Apr 2008
Location: pl_PL.lodz
Posts: 1,041
Thanked 118 Times in 93 Posts
Default
ad5: 152627MB <Hitachi HDS721616PLA380 P22OABEA> at ata2-slave SATA300

Code:
ad5
        512             # sectorsize
        160041885696    # mediasize in bytes (149G)
        312581808       # mediasize in sectors
        310101          # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.
        ad:PVG904Z9SKTP4V       # Disk ident.

I/O command overhead:
        time to read 10MB block      0.142901 sec       =    0.007 msec/sector
        time to read 20480 sectors   1.492392 sec       =    0.073 msec/sector
        calculated command overhead                     =    0.066 msec/sector

Seek times:
        Full stroke:      250 iter in   4.835676 sec =   19.343 msec
        Half stroke:      250 iter in   3.722539 sec =   14.890 msec
        Quarter stroke:   500 iter in   6.306675 sec =   12.613 msec
        Short forward:    400 iter in   2.471495 sec =    6.179 msec
        Short backward:   400 iter in   2.303877 sec =    5.760 msec
        Seq outer:       2048 iter in   0.210722 sec =    0.103 msec
        Seq inner:       2048 iter in   0.236722 sec =    0.116 msec
Transfer rates:
        outside:       102400 kbytes in   1.317523 sec =    77722 kbytes/sec
        middle:        102400 kbytes in   1.541296 sec =    66438 kbytes/sec
        inside:        102400 kbytes in   2.836419 sec =    36102 kbytes/sec
__________________
religions, worst damnation of mankind
"If 386BSD had been available when I started on Linux, Linux would probably never had happened." Linus Torvalds
Linux is not UNIX! Face it! It is not an insult. It is fact: GNU is a recursive acronym for “GNU's Not UNIX”.
vermaden's: links resources deviantart spreadbsd
Reply With Quote
  #35   (View Single Post)  
Old 4th March 2009
tangram's Avatar
tangram tangram is offline
Real Name: Ricardo Jesus
Port Guard
  
Join Date: May 2008
Location: Portugal
Posts: 36
Thanked 2 Times in 2 Posts
Default
ad6: 953869MB <WDC WD10EACS-00D6B0 01.01A01> at ata3-master SATA150

Code:
/dev/ad6
        512             # sectorsize
        1000204886016   # mediasize in bytes (932G)
        1953525168      # mediasize in sectors
        1938021         # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.
        ad:WD-WCAU45117539      # Disk ident.

I/O command overhead:
        time to read 10MB block      0.109959 sec       =    0.005 msec/sector
        time to read 20480 sectors   2.683528 sec       =    0.131 msec/sector
        calculated command overhead                     =    0.126 msec/sector

Seek times:
        Full stroke:      250 iter in   5.610738 sec =   22.443 msec
        Half stroke:      250 iter in   3.930699 sec =   15.723 msec
        Quarter stroke:   500 iter in   6.540445 sec =   13.081 msec
        Short forward:    400 iter in   2.188200 sec =    5.471 msec
        Short backward:   400 iter in   2.764503 sec =    6.911 msec
        Seq outer:       2048 iter in   0.354225 sec =    0.173 msec
        Seq inner:       2048 iter in   0.305607 sec =    0.149 msec
Transfer rates:
        outside:       102400 kbytes in   1.097995 sec =    93261 kbytes/sec
        middle:        102400 kbytes in   1.287081 sec =    79560 kbytes/sec
        inside:        102400 kbytes in   2.244471 sec =    45623 kbytes/sec
__________________
BSD and Linux tips and tutorials: Blog Linux/BSD: sharing experiences
Reply With Quote
  #36   (View Single Post)  
Old 3rd July 2009
vermaden's Avatar
vermaden vermaden is offline
Administrator
  
Join Date: Apr 2008
Location: pl_PL.lodz
Posts: 1,041
Thanked 118 Times in 93 Posts
Smile
Upgrades ...

Western Digital Blue / WD6400AAKS 640GB

ad5: 610480MB <WDC WD6400AAKS-65A7B0 01.03B01> at ata2-slave SATA300

Code:

ad5
        512             # sectorsize
        640135028736    # mediasize in bytes (596G)
        1250263728      # mediasize in sectors
        1240341         # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.
        ad:WD-WMASY4717993      # Disk ident.

I/O command overhead:
        time to read 10MB block      0.109003 sec       =    0.005 msec/sector
        time to read 20480 sectors   2.518405 sec       =    0.123 msec/sector
        calculated command overhead                     =    0.116 msec/sector

Seek times:
        Full stroke:      250 iter in   6.452317 sec =   25.809 msec
        Half stroke:      250 iter in   4.548534 sec =   18.194 msec
        Quarter stroke:   500 iter in   7.791786 sec =   15.584 msec
        Short forward:    400 iter in   1.489479 sec =    3.724 msec
        Short backward:   400 iter in   1.896791 sec =    4.742 msec
        Seq outer:       2048 iter in   0.303669 sec =    0.148 msec
        Seq inner:       2048 iter in   0.294785 sec =    0.144 msec
Transfer rates:
        outside:       102400 kbytes in   0.997335 sec =   102674 kbytes/sec
        middle:        102400 kbytes in   0.984513 sec =   104011 kbytes/sec
        inside:        102400 kbytes in   1.843912 sec =    55534 kbytes/sec
__________________
religions, worst damnation of mankind
"If 386BSD had been available when I started on Linux, Linux would probably never had happened." Linus Torvalds
Linux is not UNIX! Face it! It is not an insult. It is fact: GNU is a recursive acronym for “GNU's Not UNIX”.
vermaden's: links resources deviantart spreadbsd
Reply With Quote
  #37   (View Single Post)  
Old 6th July 2009
Carpetsmoker's Avatar
Carpetsmoker Carpetsmoker is offline
Real Name: Martin
Old man from scene 24
  
Join Date: Apr 2008
Location: Eindhoven, Netherlands
Posts: 2,023
Thanked 198 Times in 156 Posts
Default
gmirror using two 500GB WD RE3:
Code:
ad4: 476940MB <WDC WD5002ABYS-01B1B0 02.03B02> at ata2-master SATA300
ad6: 476940MB <WDC WD5002ABYS-01B1B0 02.03B02> at ata3-master SATA300
These times are not 100% accurate since this disks are being used while testing (Not too heavily though).

Huge difference in seek times vs. your 640GB WD drive vermaden ...

Code:
[~]# diskinfo -c -t /dev/mirror/datad
/dev/mirror/datad
        512             # sectorsize
        500107853312    # mediasize in bytes (466G)
        976773151       # mediasize in sectors

I/O command overhead:
        time to read 10MB block      0.126509 sec       =    0.006 msec/sector
        time to read 20480 sectors   2.599029 sec       =    0.127 msec/sector
        calculated command overhead                     =    0.121 msec/sector

Seek times:
        Full stroke:      250 iter in   1.269161 sec =    5.077 msec
        Half stroke:      250 iter in   1.257387 sec =    5.030 msec
        Quarter stroke:   500 iter in   2.042965 sec =    4.086 msec
        Short forward:    400 iter in   1.785337 sec =    4.463 msec
        Short backward:   400 iter in   2.027775 sec =    5.069 msec
        Seq outer:       2048 iter in   0.349996 sec =    0.171 msec
        Seq inner:       2048 iter in   0.315424 sec =    0.154 msec
Transfer rates:
        outside:       102400 kbytes in   0.994393 sec =   102977 kbytes/sec
        middle:        102400 kbytes in   1.153631 sec =    88763 kbytes/sec
        inside:        102400 kbytes in   1.708459 sec =    59937 kbytes/sec
__________________
UNIX was not designed to stop you from doing stupid things, because that would also stop you from doing clever things.
Reply With Quote
  #38   (View Single Post)  
Old 18th July 2009
vermaden's Avatar
vermaden vermaden is offline
Administrator
  
Join Date: Apr 2008
Location: pl_PL.lodz
Posts: 1,041
Thanked 118 Times in 93 Posts
Default
Quote:
Originally Posted by Carpetsmoker View Post
Huge difference in seek times vs. your 640GB WD drive vermaden ...
Yeah, I will have to check it out maybe ...

Also mine is from Blue series (more desktop), not Black series (more performance series).

I found that in most benchmarks Blue done really well (almost the same) compared to Black/RE3 series, and were a lot cheaper, seems that not in this benchmark.

It will also be nice to see RAW results of a single RE3, without gmirror layer.

I am generally very happy with this new 'Blue' drive, comparing to my older Hitachi 160GB drive of course.
__________________
religions, worst damnation of mankind
"If 386BSD had been available when I started on Linux, Linux would probably never had happened." Linus Torvalds
Linux is not UNIX! Face it! It is not an insult. It is fact: GNU is a recursive acronym for “GNU's Not UNIX”.
vermaden's: links resources deviantart spreadbsd
Reply With Quote
  #39   (View Single Post)  
Old 27th October 2009
colinpl colinpl is offline
New User
  
Join Date: Oct 2009
Location: Bielsko Biała / Poland
Posts: 1
Thanked 0 Times in 0 Posts
Default
Hello, it's my first post so first of all I want to say hello to everybody Here's my output it's GEOM Mirror on two disks:

ad4: 1430799MB <Seagate ST31500341AS CC1H> at ata2-master SATA300
ad6: 1430799MB <Seagate ST31500341AS CC1H> at ata3-master SATA300


diskinfo output:

Code:
[root@veyron ~]# diskinfo -ct /dev/mirror/gm0
/dev/mirror/gm0
        512             # sectorsize
        1500301909504   # mediasize in bytes (1.4T)
        2930277167      # mediasize in sectors

I/O command overhead:
        time to read 10MB block      0.112191 sec       =    0.005 msec/sector
        time to read 20480 sectors   1.668870 sec       =    0.081 msec/sector
        calculated command overhead                     =    0.076 msec/sector

Seek times:
        Full stroke:      250 iter in   1.676040 sec =    6.704 msec
        Half stroke:      250 iter in   1.599739 sec =    6.399 msec
        Quarter stroke:   500 iter in   2.930891 sec =    5.862 msec
        Short forward:    400 iter in   2.380783 sec =    5.952 msec
        Short backward:   400 iter in   2.317805 sec =    5.795 msec
        Seq outer:       2048 iter in   0.200717 sec =    0.098 msec
        Seq inner:       2048 iter in   0.446196 sec =    0.218 msec
Transfer rates:
        outside:       102400 kbytes in   0.849167 sec =   120589 kbytes/sec
        middle:        102400 kbytes in   0.998289 sec =   102576 kbytes/sec
        inside:        102400 kbytes in   1.864922 sec =    54908 kbytes/sec

[root@veyron ~]#
Regards!
colinpl
Reply With Quote
  #40   (View Single Post)  
Old 12th November 2009
vermaden's Avatar
vermaden vermaden is offline
Administrator
  
Join Date: Apr 2008
Location: pl_PL.lodz
Posts: 1,041
Thanked 118 Times in 93 Posts
Default
Samsung 64GB SSD (SLC) from Lenovo ThinkPad X300
Code:
/dev/ad4
	512         	# sectorsize
	64023257088 	# mediasize in bytes (60G)
	125045424   	# mediasize in sectors
	124053      	# Cylinders according to firmware.
	16          	# Heads according to firmware.
	63          	# Sectors according to firmware.
	SE815K0462  	# Disk ident.

I/O command overhead:
	time to read 10MB block      0.118183 sec	=    0.006 msec/sector
	time to read 20480 sectors   1.747203 sec	=    0.085 msec/sector
	calculated command overhead			=    0.080 msec/sector

Seek times:
	Full stroke:	  250 iter in   0.046148 sec =    0.185 msec
	Half stroke:	  250 iter in   0.045511 sec =    0.182 msec
	Quarter stroke:	  500 iter in   0.091325 sec =    0.183 msec
	Short forward:	  400 iter in   0.072594 sec =    0.181 msec
	Short backward:	  400 iter in   0.073381 sec =    0.183 msec
	Seq outer:	 2048 iter in   0.234476 sec =    0.114 msec
	Seq inner:	 2048 iter in   0.231109 sec =    0.113 msec
Transfer rates:
	outside:       102400 kbytes in   1.148034 sec =    89196 kbytes/sec
	middle:        102400 kbytes in   1.156049 sec =    88578 kbytes/sec
	inside:        102400 kbytes in   1.178575 sec =    86885 kbytes/sec
__________________
religions, worst damnation of mankind
"If 386BSD had been available when I started on Linux, Linux would probably never had happened." Linus Torvalds
Linux is not UNIX! Face it! It is not an insult. It is fact: GNU is a recursive acronym for “GNU's Not UNIX”.
vermaden's: links resources deviantart spreadbsd
Reply With Quote
Reply
Page 2 of 3 1 2 3

Tags
benchmark, diskinfo

« Previous Thread | Next Thread »
Thread Tools
Display Modes
Linear Mode Linear Mode

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts
BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Forum Jump

Similar Threads
Thread Thread Starter Forum Replies Last Post
Successfully booting NetBSD Live on a Sony Vaio PCG-GRZ530 with limited results Mr-Biscuit NetBSD General 6 26th May 2009 11:47 AM
question about "sockstat -4" results bgobs FreeBSD General 3 10th June 2008 09:57 AM
Incorrect df results (not -h, not a FAQ) nathang FreeBSD General 5 8th June 2008 06:44 AM


All times are GMT. The time now is 04:09 AM.

DaemonForums.org RSS Feeds - Contact Us - DaemonForums.org - Archive - Privacy Statement - Top

Powered by vBulletin® Version 3.8.4
Copyright ©2000 - 2013, Jelsoft Enterprises Ltd.
Content copyright © 2007-2010, the authors
Daemon image copyright ©1988, Marshall Kirk McKusick