DaemonForums  

Go Back   DaemonForums > FreeBSD > FreeBSD General

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

Reply
 
Thread Tools Display Modes
Old 14th November 2009
stonecoldsed stonecoldsed is offline
New User
 
Join Date: May 2008
Posts: 3
Thanked 0 Times in 0 Posts
Default

Hi,
Here is the output of an un-formatted 250GB WD RE3 drive.


Code:
ad12: 239429MB <WDC WD2502ABYS-01B7A0 02.03B02> at ata6-master SATA300
> diskinfo -c -t /dev/ad12
/dev/ad12
        512             # sectorsize
        251059544064    # mediasize in bytes (234G)
        490350672       # mediasize in sectors
        486459          # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.
        ad:WD-WCAT1A421098      # Disk ident.

I/O command overhead:
        time to read 10MB block      0.095959 sec       =    0.005 msec/sector
        time to read 20480 sectors   2.701192 sec       =    0.132 msec/sector
        calculated command overhead                     =    0.127 msec/sector

Seek times:
        Full stroke:      250 iter in   4.623722 sec =   18.495 msec
        Half stroke:      250 iter in   3.267142 sec =   13.069 msec
        Quarter stroke:   500 iter in   5.422215 sec =   10.844 msec
        Short forward:    400 iter in   2.438332 sec =    6.096 msec
        Short backward:   400 iter in   1.147096 sec =    2.868 msec
        Seq outer:       2048 iter in   0.341796 sec =    0.167 msec
        Seq inner:       2048 iter in   0.291963 sec =    0.143 msec
Transfer rates:
        outside:       102400 kbytes in   0.903144 sec =   113382 kbytes/sec
        middle:        102400 kbytes in   1.016205 sec =   100767 kbytes/sec
        inside:        102400 kbytes in   1.584498 sec =    64626 kbytes/sec
__________________
Vini Vidi Vici
Reply With Quote
Old 18th December 2009
lumiwa lumiwa is offline
Package Pilot
 
Join Date: May 2008
Posts: 145
Thanked 4 Times in 3 Posts
Default

Code:
diskinfo -c -t /dev/ad0
/dev/ad0                 
        512             # sectorsize
        80026361856     # mediasize in bytes (75G)
        156301488       # mediasize in sectors
        155061          # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.
        WD-WCAJD1048022 # Disk ident.

I/O command overhead:
        time to read 10MB block      0.198769 sec       =    0.010 msec/sector
        time to read 20480 sectors   1.698406 sec       =    0.083 msec/sector
        calculated command overhead                     =    0.073 msec/sector

Seek times:
        Full stroke:      250 iter in   5.653904 sec =   22.616 msec
        Half stroke:      250 iter in   4.002821 sec =   16.011 msec
        Quarter stroke:   500 iter in   6.254353 sec =   12.509 msec
        Short forward:    400 iter in   2.406205 sec =    6.016 msec
        Short backward:   400 iter in   3.432481 sec =    8.581 msec
        Seq outer:       2048 iter in   0.176710 sec =    0.086 msec
        Seq inner:       2048 iter in   0.344202 sec =    0.168 msec
Transfer rates:
        outside:       102400 kbytes in   1.843513 sec =    55546 kbytes/sec
        middle:        102400 kbytes in   2.023078 sec =    50616 kbytes/sec
        inside:        102400 kbytes in   3.261300 sec =    31399 kbytes/sec
Disk is old a little more than six years.
Reply With Quote
Old 18th December 2009
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

Latop harddrive (2.5", 5400RPM), ZFS and the new ahci in FreeBSD 8 stable

Code:
ada0: <Hitachi HTS543232L9SA00 FB4OC43C> ATA/ATAPI-8 SATA 1.x device
ada0: 150.000MB/s transfers (SATA 1.x, UDMA6, PIO size 8192bytes)
ada0: Command Queueing enabled


/dev/ada0
	512         	# sectorsize
	320072933376	# mediasize in bytes (298G)
	625142448   	# mediasize in sectors
	620181      	# Cylinders according to firmware.
	16          	# Heads according to firmware.
	63          	# Sectors according to firmware.
	081105FB2400LECP257A	# Disk ident.

I/O command overhead:
	time to read 10MB block      0.487962 sec	=    0.024 msec/sector
	time to read 20480 sectors   2.898023 sec	=    0.142 msec/sector
	calculated command overhead			=    0.118 msec/sector

Seek times:
	Full stroke:	  250 iter in   6.993660 sec =   27.975 msec
	Half stroke:	  250 iter in   5.626813 sec =   22.507 msec
	Quarter stroke:	  500 iter in   9.323333 sec =   18.647 msec
	Short forward:	  400 iter in   2.720834 sec =    6.802 msec
	Short backward:	  400 iter in   3.033109 sec =    7.583 msec
	Seq outer:	 2048 iter in   0.391258 sec =    0.191 msec
	Seq inner:	 2048 iter in   0.394341 sec =    0.193 msec
Transfer rates:
	outside:       102400 kbytes in   1.662847 sec =    61581 kbytes/sec
	middle:        102400 kbytes in   1.938533 sec =    52823 kbytes/sec
	inside:        102400 kbytes in   3.416859 sec =    29969 kbytes/sec
__________________
use UNIX or die :-)
Reply With Quote
Old 2nd February 2010
eabris
-Guest-
 
Posts: n/a
Default IBM SCSI RAID-5EE 6x73GB

FreeBSD 7.2 amd64

Code:
/dev/ipsd0
        512             # sectorsize
        293626445824    # mediasize in bytes (273G)
        573489152       # mediasize in sectors
        35838           # Cylinders according to firmware.
        254             # Heads according to firmware.
        63              # Sectors according to firmware.

I/O command overhead:
        time to read 10MB block      0.189786 sec       =    0.009 msec/sector
        time to read 20480 sectors   1.913369 sec       =    0.093 msec/sector
        calculated command overhead                     =    0.084 msec/sector

Seek times:
        Full stroke:      250 iter in   0.989590 sec =    3.958 msec
        Half stroke:      250 iter in   2.148981 sec =    8.596 msec
        Quarter stroke:   500 iter in   1.888773 sec =    3.778 msec
        Short forward:    400 iter in   0.471670 sec =    1.179 msec
        Short backward:   400 iter in   1.470429 sec =    3.676 msec
        Seq outer:       2048 iter in   0.193860 sec =    0.095 msec
        Seq inner:       2048 iter in   0.197215 sec =    0.096 msec
Transfer rates:
        outside:       102400 kbytes in   1.433645 sec =    71426 kbytes/sec
        middle:        102400 kbytes in   1.567306 sec =    65335 kbytes/sec
        inside:        102400 kbytes in   1.566834 sec =    65355 kbytes/sec

Last edited by vermaden; 2nd February 2010 at 09:27 AM. Reason: Use [ code ] tags.
Reply With Quote
Old 4th February 2010
vermaden's Avatar
vermaden vermaden is offline
Administrator
 
Join Date: Apr 2008
Location: pl_PL.lodz
Posts: 1,051
Thanked 118 Times in 93 Posts
Default

Code:
# dmesg | grep ada0
ada0 at ahcich0 bus 0 target 0 lun 0
ada0: <SAMSUNG HD103SJ 1AJ100E4> ATA/ATAPI-8 SATA 2.x device
ada0: 300.000MB/s transfers
ada0: 953869MB (1953525168 512 byte sectors: 16H 63S/T 16383C)
ada0: Native Command Queueing enabled
Code:
# diskinfo -c -v -t ada0
ada0    
        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.
        S246J90Z131004  # Disk ident.

I/O command overhead:
        time to read 10MB block      0.077151 sec       =    0.004 msec/sector
        time to read 20480 sectors   2.211735 sec       =    0.108 msec/sector
        calculated command overhead                     =    0.104 msec/sector

Seek times:
        Full stroke:      250 iter in   5.234394 sec =   20.938 msec
        Half stroke:      250 iter in   3.918627 sec =   15.675 msec
        Quarter stroke:   500 iter in   6.541610 sec =   13.083 msec
        Short forward:    400 iter in   1.145674 sec =    2.864 msec
        Short backward:   400 iter in   2.402746 sec =    5.992 msec
        Seq outer:       2048 iter in   0.161329 sec =    0.079 msec
        Seq inner:       2048 iter in   0.216652 sec =    0.106 msec
Transfer rates:
        outside:       102400 kbytes in   0.697989 sec =   146707 kbytes/sec
        middle:        102400 kbytes in   0.832913 sec =   122942 kbytes/sec
        inside:        102400 kbytes in   1.297791 sec =    78903 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
Old 16th September 2010
Carpetsmoker's Avatar
Carpetsmoker Carpetsmoker is offline
Real Name: Martin
Old man from scene 24
 
Join Date: Apr 2008
Location: Eindhoven, Netherlands
Posts: 2,051
Thanked 198 Times in 156 Posts
Default

So I got some new disks:

Code:
[~]# dmesg | grep ^ad
ad0: 3811MB <CF CARD 4GB Ver3.06K> at ata0-master UDMA100
ad1: 1943MB <TRANSCEND 20100323> at ata0-slave UDMA66
ad6: 1430799MB <WDC WD15EADS-00S2B0 01.00A01> at ata3-master UDMA100 SATA 3Gb/s
ad10: 1430799MB <WDC WD15EADS-00S2B0 01.00A01> at ata5-master UDMA100 SATA 3Gb/s
Code:
[~]# diskinfo -c -t /dev/mirror/newdatad 
/dev/mirror/newdatad
        512             # sectorsize
        10737418240     # mediasize in bytes (10G)
        20971520        # mediasize in sectors
        0               # stripesize
        8192            # stripeoffset
        1305            # Cylinders according to firmware.
        255             # Heads according to firmware.
        63              # Sectors according to firmware.

I/O command overhead:
        time to read 10MB block      0.097558 sec       =    0.005 msec/sector
        time to read 20480 sectors   3.493613 sec       =    0.171 msec/sector
        calculated command overhead                     =    0.166 msec/sector

Seek times:
        Full stroke:      250 iter in   1.851474 sec =    7.406 msec
        Half stroke:      250 iter in   1.967489 sec =    7.870 msec
        Quarter stroke:   500 iter in   3.482903 sec =    6.966 msec
        Short forward:    400 iter in   2.997552 sec =    7.494 msec
        Short backward:   400 iter in   3.032469 sec =    7.581 msec
        Seq outer:       2048 iter in   0.392586 sec =    0.192 msec
        Seq inner:       2048 iter in   0.393736 sec =    0.192 msec
Transfer rates:
        outside:       102400 kbytes in   0.977659 sec =   104740 kbytes/sec
        middle:        102400 kbytes in   1.071896 sec =    95532 kbytes/sec
        inside:        102400 kbytes in   0.996447 sec =   102765 kbytes/sec
For comparison, here are two WD 500GB RE3 disks in the same system:
http://www.daemonforums.org/showpost...6&postcount=37

Transfer rates are faster, but seek times are slower. Actually, performance isn't that bad for the GP disks,
The GP disks are a *lot* quieter too. I had the 500GB disks in a "silent hard drive enclosure", which helped a bit with the noise, but the GP disks made *significantly* less noise without enclose than the RE disks inside the enclosure! (My system is now inaudible at ~75cm).

ad0 and ad1 are CF cards with a CF -> ATA converter I got off ebay for 90 cents.
The Transcend is a 300x card, the kingston is a cheap one I had lying around.

Diskinfo won't run on them ( diskinfo: read error or disk too small for test.: Input/output error), but here's what dd says:

This is the Transcend:
Code:
[~]# dd if=/dev/zero of=/TEST bs=1M count=100                                                                                                                    glitch:1:33
100+0 records in
100+0 records out
104857600 bytes transferred in 4.592359 secs (22833058 bytes/sec)
The Kingston:
Code:
[~]# dd if=/dev/zero of=/var/tmp/TEST bs=1M count=100
100+0 records in
100+0 records out
104857600 bytes transferred in 19.193520 secs (5463177 bytes/sec)
300x is supposed to be 40MB/s ... meh, not even close ... Still a lot faster than the Kingston ...
I got the kingston after some experiences with the ssd in my laptop, I have a memoryfs for /var/ and /tmp/, which works OK, but sometimes I ran into problems and some tweaking is required ... I got the kingston for /var/ and avoid all of that.

In hindsight, it might have been a better idea to get the 4GB Transcend (... But that one was 15 euros more expensive ).
__________________
UNIX was not designed to stop you from doing stupid things, because that would also stop you from doing clever things.
Reply With Quote
Old 17th September 2010
vermaden's Avatar
vermaden vermaden is offline
Administrator
 
Join Date: Apr 2008
Location: pl_PL.lodz
Posts: 1,051
Thanked 118 Times in 93 Posts
Default

Quote:
Originally Posted by Carpetsmoker View Post
Code:
[~]# diskinfo -c -t /dev/mirror/newdatad 
/dev/mirror/newdatad
        512             # sectorsize
        10737418240     # mediasize in bytes (10G)
(...)
Is that mirror of ad4/ad10, only 10G, a typo?

Also, why You do not use AHCI, no hardware support?
__________________
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
Old 17th September 2010
Carpetsmoker's Avatar
Carpetsmoker Carpetsmoker is offline
Real Name: Martin
Old man from scene 24
 
Join Date: Apr 2008
Location: Eindhoven, Netherlands
Posts: 2,051
Thanked 198 Times in 156 Posts
Default

No, that particular partition is 10G. It's a feature, not a bug

Quote:
Also, why You do not use AHCI, no hardware support?
I don't know ... I just copied the old installation which is ~6 years old
__________________
UNIX was not designed to stop you from doing stupid things, because that would also stop you from doing clever things.
Reply With Quote
Old 17th September 2010
vermaden's Avatar
vermaden vermaden is offline
Administrator
 
Join Date: Apr 2008
Location: pl_PL.lodz
Posts: 1,051
Thanked 118 Times in 93 Posts
Default

Quote:
Originally Posted by Carpetsmoker View Post
No, that particular partition is 10G. It's a feature, not a bug
I thought about that for a short period of time because of that 'd' at the end of mirror name

Quote:
Originally Posted by Carpetsmoker View Post
I don't know ... I just copied the old installation which is ~6 years old
I havent done any comparisions, but tests provided on lists.freebsd.org shown about 20-30% peroformance increase, especially in 'random access' tests, generally its only about adding ahci_load="YES" into the loader.conf and making sure that /etc/fstab shows / using label (it may be as well ada0 but labels are far more better). Probably Your ad4 will become ada0 and ad10 will be ada1.

/etc/fstab
Code:
#dev             #mnt        #fs     #opts       #dump/pass
/dev/label/root  /           ufs     rw,noatime  1 1
/dev/label/var   /var        ufs     rw,noatime  2 2
/dev/label/usr   /usr        ufs     rw,noatime  2 2
__________________
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
Old 17th September 2010
Carpetsmoker's Avatar
Carpetsmoker Carpetsmoker is offline
Real Name: Martin
Old man from scene 24
 
Join Date: Apr 2008
Location: Eindhoven, Netherlands
Posts: 2,051
Thanked 198 Times in 156 Posts
Default

I'll try ahci and run the benchmark again, see if it matters.

I also got a SSD for my laptop, a OCZ Onyx II 32GB.
Actually the cheapest SSD, but it's fairly fast and 32GB should be enough.
IIRC I payed about 70 euro for it. So that's not bad.

Code:
[~]# dmesg | grep ^ada 
ada0 at ahcich0 bus 0 scbus0 target 0 lun 0
ada0: <OCZ-ONYX 1.6> ATA-8 SATA 2.x device
ada0: 150.000MB/s transfers (SATA 1.x, UDMA6, PIO 512bytes)
ada0: Command Queueing enabled
ada0: 30533MB (62533296 512 byte sectors: 16H 63S/T 16383C)
Code:
[~]# diskinfo -c -t /dev/ada0s1f   
/dev/ada0s1f
        512             # sectorsize
        18058371584     # mediasize in bytes (17G)
        35270257        # mediasize in sectors
        0               # stripesize
        1073774080      # stripeoffset
        34990           # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.
        W21G9Y329504E1RF38XE    # Disk ident.

I/O command overhead:
        time to read 10MB block      0.101228 sec       =    0.005 msec/sector
        time to read 20480 sectors   2.086315 sec       =    0.102 msec/sector
        calculated command overhead                     =    0.097 msec/sector

Seek times:
        Full stroke:      250 iter in   0.037098 sec =    0.148 msec
        Half stroke:      250 iter in   0.036503 sec =    0.146 msec
        Quarter stroke:   500 iter in   0.073275 sec =    0.147 msec
        Short forward:    400 iter in   0.058375 sec =    0.146 msec
        Short backward:   400 iter in   0.058785 sec =    0.147 msec
        Seq outer:       2048 iter in   0.224201 sec =    0.109 msec
        Seq inner:       2048 iter in   0.223191 sec =    0.109 msec
Transfer rates:
        outside:       102400 kbytes in   0.969869 sec =   105581 kbytes/sec
        middle:        102400 kbytes in   1.012393 sec =   101146 kbytes/sec
        inside:        102400 kbytes in   0.963893 sec =   106236 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
Old 18th September 2010
vermaden's Avatar
vermaden vermaden is offline
Administrator
 
Join Date: Apr 2008
Location: pl_PL.lodz
Posts: 1,051
Thanked 118 Times in 93 Posts
Default

Quote:
Originally Posted by Carpetsmoker View Post
I also got a SSD for my laptop, a OCZ Onyx II 32GB.
Actually the cheapest SSD, but it's fairly fast and 32GB should be enough.
IIRC I payed about 70 euro for it. So that's not bad.
Most important 'thing' about SSDs is Random Write performance, or (Average) Write Latency, check how big the differences can be here:
http://anandtech.com/show/2614/8

Currently is far easier to find a good SSD because of SandForse SF1200/SF1500 controllers, which provide good Random Write (and overall Random I/O) performance.
__________________
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
Old 26th September 2010
da1 da1 is offline
Port Guard
 
Join Date: Feb 2009
Location: Berlin, DE
Posts: 28
Thanked 1 Time in 1 Post
Default

Code:
ad4: 476938MB <Seagate ST3500418AS CC34> at ata2-master UDMA100 SATA 1.5Gb/s
ad6: 610480MB <WDC WD6400AARS-00Y5B1 80.00A80> at ata3-master UDMA100 SATA 1.5Gb/s
ad8: 476940MB <Seagate ST3500312CS SC13> at ata4-master UDMA100 SATA 1.5Gb/s
ad10: 476940MB <Seagate ST3500312CS SC13> at ata5-master UDMA100 SATA 1.5Gb/s
ad14: 152626MB <SAMSUNG HD160JJ ZM100-47> at ata7-master UDMA100 SATA
ad16: 156334MB <Maxtor 6Y160M0 YAR51BW0> at ata8-master UDMA100 SATA
ad14+16 -> gm0 (mirror)
ad8+10 -> gm1 (mirror)

Code:
/dev/mirror/gm0s1a
        512             # sectorsize
        154671596032    # mediasize in bytes (144G)
        302092961       # mediasize in sectors
        0               # stripesize
        1073774080      # stripeoffset
        18804           # Cylinders according to firmware.
        255             # Heads according to firmware.
        63              # Sectors according to firmware.

I/O command overhead:
        time to read 10MB block      0.487426 sec       =    0.024 msec/sector
        time to read 20480 sectors   2.774225 sec       =    0.135 msec/sector
        calculated command overhead                     =    0.112 msec/sector

Seek times:
        Full stroke:      250 iter in   1.905288 sec =    7.621 msec
        Half stroke:      250 iter in   1.656508 sec =    6.626 msec
        Quarter stroke:   500 iter in   3.134943 sec =    6.270 msec
        Short forward:    400 iter in   2.531556 sec =    6.329 msec
        Short backward:   400 iter in   2.589457 sec =    6.474 msec
        Seq outer:       2048 iter in   0.350186 sec =    0.171 msec
        Seq inner:       2048 iter in   0.341217 sec =    0.167 msec
Transfer rates:
        outside:       102400 kbytes in   3.977510 sec =    25745 kbytes/sec
        middle:        102400 kbytes in   4.372004 sec =    23422 kbytes/sec
        inside:        102400 kbytes in   5.359596 sec =    19106 kbytes/sec


/dev/mirror/gm1a
        512             # sectorsize
        500107853824    # mediasize in bytes (466G)
        976773152       # mediasize in sectors
        0               # stripesize
        8192            # stripeoffset
        969020          # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.

I/O command overhead:
        time to read 10MB block      0.248465 sec       =    0.012 msec/sector
        time to read 20480 sectors   1.773934 sec       =    0.087 msec/sector
        calculated command overhead                     =    0.074 msec/sector

Seek times:
        Full stroke:      250 iter in   1.659988 sec =    6.640 msec
        Half stroke:      250 iter in   1.499807 sec =    5.999 msec
        Quarter stroke:   500 iter in   2.801351 sec =    5.603 msec
        Short forward:    400 iter in   2.652671 sec =    6.632 msec
        Short backward:   400 iter in   2.641057 sec =    6.603 msec
        Seq outer:       2048 iter in   0.521088 sec =    0.254 msec
        Seq inner:       2048 iter in   0.436988 sec =    0.213 msec
Transfer rates:
        outside:       102400 kbytes in   2.209148 sec =    46353 kbytes/sec
        middle:        102400 kbytes in   2.190127 sec =    46755 kbytes/sec
        inside:      diskinfo: read error or disk too small for test.: Operation not supported <- no idea wtf


/dev/ad4s1d
        512             # sectorsize
        500106281472    # mediasize in bytes (466G)
        976770081       # mediasize in sectors
        0               # stripesize
        32256           # stripeoffset
        969017          # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.
        6VM31DD4        # Disk ident.

I/O command overhead:
        time to read 10MB block      0.118732 sec       =    0.006 msec/sector
        time to read 20480 sectors   1.537903 sec       =    0.075 msec/sector
        calculated command overhead                     =    0.069 msec/sector

Seek times:
        Full stroke:      250 iter in   5.978958 sec =   23.916 msec
        Half stroke:      250 iter in   4.153111 sec =   16.612 msec
        Quarter stroke:   500 iter in   6.673901 sec =   13.348 msec
        Short forward:    400 iter in   2.011170 sec =    5.028 msec
        Short backward:   400 iter in   2.430351 sec =    6.076 msec
        Seq outer:       2048 iter in   0.181747 sec =    0.089 msec
        Seq inner:       2048 iter in   0.183024 sec =    0.089 msec
Transfer rates:
        outside:       102400 kbytes in   0.990563 sec =   103376 kbytes/sec
        middle:        102400 kbytes in   0.991175 sec =   103312 kbytes/sec
        inside:        102400 kbytes in   1.545671 sec =    66250 kbytes/sec


/dev/ad6s1d
        512             # sectorsize
        640134996480    # mediasize in bytes (596G)
        1250263665      # mediasize in sectors
        0               # stripesize
        32256           # stripeoffset
        1240340         # Cylinders according to firmware.
        16              # Heads according to firmware.
        63              # Sectors according to firmware.
        WD-WCAV5D144732 # Disk ident.

I/O command overhead:
        time to read 10MB block      0.132170 sec       =    0.006 msec/sector
        time to read 20480 sectors   2.507678 sec       =    0.122 msec/sector
        calculated command overhead                     =    0.116 msec/sector

Seek times:
        Full stroke:      250 iter in   4.996024 sec =   19.984 msec
        Half stroke:      250 iter in   3.932058 sec =   15.728 msec
        Quarter stroke:   500 iter in   6.775971 sec =   13.552 msec
        Short forward:    400 iter in   2.097176 sec =    5.243 msec
        Short backward:   400 iter in   3.413464 sec =    8.534 msec
        Seq outer:       2048 iter in   0.346267 sec =    0.169 msec
        Seq inner:       2048 iter in   0.285257 sec =    0.139 msec
Transfer rates:
        outside:       102400 kbytes in   1.040689 sec =    98396 kbytes/sec
        middle:        102400 kbytes in   1.171794 sec =    87387 kbytes/sec
        inside:        102400 kbytes in   1.605200 sec =    63793 kbytes/sec
however, I consider these results useless since I could never reach the values stated @ Transfer rate.

Tops was ~51MB write on ad6 (s-ata1 controller)
Reply With Quote
Old 28th November 2010
que_pasa que_pasa is offline
New User
 
Join Date: May 2008
Posts: 2
Thanked 0 Times in 0 Posts
Default

ada0: <KINGSTON SNVP325S2128GB AGYA0202> ATA-8 SATA 2.x device
Code:
dom# diskinfo -c -t /dev/ada0
/dev/ada0
	512         	# sectorsize
	128035676160	# mediasize in bytes (119G)
	250069680   	# mediasize in sectors
	0           	# stripesize
	0           	# stripeoffset
	248085      	# Cylinders according to firmware.
	16          	# Heads according to firmware.
	63          	# Sectors according to firmware.
	30OS10VDT73Z	# Disk ident.

I/O command overhead:
	time to read 10MB block      0.052866 sec	=    0.003 msec/sector
	time to read 20480 sectors   1.696796 sec	=    0.083 msec/sector
	calculated command overhead			=    0.080 msec/sector

Seek times:
	Full stroke:	  250 iter in   0.053766 sec =    0.215 msec
	Half stroke:	  250 iter in   0.056914 sec =    0.228 msec
	Quarter stroke:	  500 iter in   0.119215 sec =    0.238 msec
	Short forward:	  400 iter in   0.097655 sec =    0.244 msec
	Short backward:	  400 iter in   0.097810 sec =    0.245 msec
	Seq outer:	 2048 iter in   0.205498 sec =    0.100 msec
	Seq inner:	 2048 iter in   0.206845 sec =    0.101 msec
Transfer rates:
	outside:       102400 kbytes in   0.527318 sec =   194190 kbytes/sec
	middle:        102400 kbytes in   0.510211 sec =   200701 kbytes/sec
	inside:        102400 kbytes in   0.498011 sec =   205618 kbytes/sec
ada1: <SAMSUNG HD103UJ 1AA01113> ATA-7 SATA 2.x device
Code:
dom# diskinfo -t -c /dev/ada1
/dev/ada1
	512         	# sectorsize
	1000203804160	# mediasize in bytes (932G)
	1953523055  	# mediasize in sectors
	0           	# stripesize
	0           	# stripeoffset
	1938018     	# Cylinders according to firmware.
	16          	# Heads according to firmware.
	63          	# Sectors according to firmware.
	S13PJDWS367397	# Disk ident.

I/O command overhead:
	time to read 10MB block      0.103866 sec	=    0.005 msec/sector
	time to read 20480 sectors   2.484636 sec	=    0.121 msec/sector
	calculated command overhead			=    0.116 msec/sector

Seek times:
	Full stroke:	  250 iter in   6.037526 sec =   24.150 msec
	Half stroke:	  250 iter in   4.138115 sec =   16.552 msec
	Quarter stroke:	  500 iter in   6.182982 sec =   12.366 msec
	Short forward:	  400 iter in   2.342788 sec =    5.857 msec
	Short backward:	  400 iter in   2.528760 sec =    6.322 msec
	Seq outer:	 2048 iter in   0.330712 sec =    0.161 msec
	Seq inner:	 2048 iter in   0.309506 sec =    0.151 msec
Transfer rates:
	outside:       102400 kbytes in   0.826238 sec =   123935 kbytes/sec
	middle:        102400 kbytes in   1.096036 sec =    93428 kbytes/sec
	inside:        102400 kbytes in   1.862258 sec =    54987 kbytes/sec
ada2: <SAMSUNG HD154UI 1AG01118> ATA-7 SATA 2.x device
Code:
dom# diskinfo -c -t /dev/ada2
/dev/ada2
	512         	# sectorsize
	1500301910016	# mediasize in bytes (1.4T)
	2930277168  	# mediasize in sectors
	0           	# stripesize
	0           	# stripeoffset
	2907021     	# Cylinders according to firmware.
	16          	# Heads according to firmware.
	63          	# Sectors according to firmware.
	S1XWJD1Z903317	# Disk ident.

I/O command overhead:
	time to read 10MB block      0.102603 sec	=    0.005 msec/sector
	time to read 20480 sectors   2.257225 sec	=    0.110 msec/sector
	calculated command overhead			=    0.105 msec/sector

Seek times:
	Full stroke:	  250 iter in   6.760438 sec =   27.042 msec
	Half stroke:	  250 iter in   5.569470 sec =   22.278 msec
	Quarter stroke:	  500 iter in  11.142470 sec =   22.285 msec
	Short forward:	  400 iter in   3.495375 sec =    8.738 msec
	Short backward:	  400 iter in   3.518908 sec =    8.797 msec
	Seq outer:	 2048 iter in   0.328933 sec =    0.161 msec
	Seq inner:	 2048 iter in   0.306861 sec =    0.150 msec
Transfer rates:
	outside:       102400 kbytes in   0.978641 sec =   104635 kbytes/sec
	middle:        102400 kbytes in   1.119367 sec =    91480 kbytes/sec
	inside:        102400 kbytes in   1.988708 sec =    51491 kbytes/sec
Reply With Quote
Old 28th November 2010
vermaden's Avatar
vermaden vermaden is offline
Administrator
 
Join Date: Apr 2008
Location: pl_PL.lodz
Posts: 1,051
Thanked 118 Times in 93 Posts
Default

Code:
# diskinfo -c -v -t ada0
ada0
	512         	# sectorsize
	160041885696	# mediasize in bytes (149G)
	312581808   	# mediasize in sectors
	0           	# stripesize
	0           	# stripeoffset
	310101      	# Cylinders according to firmware.
	16          	# Heads according to firmware.
	63          	# Sectors according to firmware.
	CVPO01160261160AGN	# Disk ident.

I/O command overhead:
	time to read 10MB block      0.062244 sec	=    0.003 msec/sector
	time to read 20480 sectors   2.370014 sec	=    0.116 msec/sector
	calculated command overhead			=    0.113 msec/sector

Seek times:
	Full stroke:	  250 iter in   0.050404 sec =    0.202 msec
	Half stroke:	  250 iter in   0.035163 sec =    0.141 msec
	Quarter stroke:	  500 iter in   0.210494 sec =    0.421 msec
	Short forward:	  400 iter in   0.049615 sec =    0.124 msec
	Short backward:	  400 iter in   0.085646 sec =    0.214 msec
	Seq outer:	 2048 iter in   0.326711 sec =    0.160 msec
	Seq inner:	 2048 iter in   0.231657 sec =    0.113 msec
Transfer rates:
	outside:       102400 kbytes in   0.538245 sec =   190248 kbytes/sec
	middle:        102400 kbytes in   0.568161 sec =   180231 kbytes/sec
	inside:        102400 kbytes in   0.550574 sec =   185988 kbytes/sec

# dmesg | grep ada0
ada0 at ahcich0 bus 0 scbus0 target 0 lun 0
ada0: <INTEL SSDSA2M160G2GC 2CV102HD> ATA-7 SATA 2.x device
ada0: 300.000MB/s transfers (SATA 2.x, UDMA6, PIO 8192bytes)
ada0: Command Queueing enabled
ada0: 152627MB (312581808 512 byte sectors: 16H 63S/T 16383C)
__________________
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

Tags
benchmark, diskinfo

Thread Tools
Display Modes

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 01:15 PM.


Powered by vBulletin® Version 3.8.4
Copyright ©2000 - 2014, Jelsoft Enterprises Ltd.
Content copyright © 2007-2010, the authors
Daemon image copyright ©1988, Marshall Kirk McKusick