Laptops performance tests report

w1k0 · 10-23-2008, 10:01 AM

I use ThinkPads T60 and T41 with Slackware 12.1 and generic kernel 2.6.24.5-smp. I decided to compare the performance of T60 and T41 using OpenOffice.org 3.0.0 (http://download.openoffice.org/index.html).

The first machine has Intel Core Duo CPU 1.83 GHz, 1 GB RAM, and 160 GB SATA HDD -- the second machine has Intel Pentium M CPU 1.4 GHz, 512 MB RAM, and 80 GB ATA HDD. The first reaches 1109 MB/s timing cached reads and 59 MB/s timing buffered disk reads -- the second reaches 500 MB/s timing cached reads and 34 MB/s timing buffered disk reads.

To test the performance I rebooted both machines, I stayed in the console framebuffer mode without Internet connection, I unpacked OOo_3.0.0_LinuxIntel_install_wJRE_en-US.tar.gz file, I jumped to RPMS directory, and I ran the command: time for f in `ls *.rpm` ; do rpm2tgz $f ; done.

Real time for the first machine was about 2'14'' (134'') -- real time for the second machine was about 3'54'' (234''). T60 is about 1.75 times faster than T41.

First machine (T60)

# dmesg | grep CPU

Code:

  Initializing CPU#0
  SLUB: Genslabs=11, HWalign=64, Order=0-1, MinObjects=4, CPUs=2, Nodes=1
  CPU: After generic identify, caps: bfe9fbff 00100000 00000000 00000000 0000c1a9 00000000 00000000 00000000
  CPU: L1 I cache: 32K, L1 D cache: 32K
  CPU: L2 cache: 2048K
  CPU: Physical Processor ID: 0
  CPU: Processor Core ID: 0
  CPU: After all inits, caps: bfe9fbff 00100000 00000000 00002940 0000c1a9 00000000 00000000 00000000
  Intel machine check reporting enabled on CPU#0.
  CPU0: Intel(R) Core(TM) Duo CPU      T2400  @ 1.83GHz stepping 0c
  Initializing CPU#1
  CPU: After generic identify, caps: bfe9fbff 00100000 00000000 00000000 0000c1a9 00000000 00000000 00000000
  CPU: L1 I cache: 32K, L1 D cache: 32K
  CPU: L2 cache: 2048K
  CPU: Physical Processor ID: 0
  CPU: Processor Core ID: 1
  CPU: After all inits, caps: bfe9fbff 00100000 00000000 00002940 0000c1a9 00000000 00000000 00000000
  Intel machine check reporting enabled on CPU#1.
  CPU1: Intel(R) Core(TM) Duo CPU      T2400  @ 1.83GHz stepping 0c
  checking TSC synchronization [CPU#0 -> CPU#1]:
  Measured 520927 cycles TSC warp between CPUs, turning off TSC clock.
  Brought up 2 CPUs
  ACPI: CPU0 (power states: C1[C1] C2[C2] C3[C3])
  ACPI: Processor [CPU0] (supports 8 throttling states)
  ACPI: CPU1 (power states: C1[C1] C2[C2] C3[C3])
  ACPI: Processor [CPU1] (supports 8 throttling states)

# dmesg | grep Memory

Code:

Memory: 1033060k/1047360k available (2946k kernel code, 13744k reserved, 1128k data, 256k init, 129856k highmem)

# dmesg | grep sda

Code:

sd 0:0:0:0: [sda] 312581808 512-byte hardware sectors (160042 MB)
sd 0:0:0:0: [sda] Write Protect is off
sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA
sd 0:0:0:0: [sda] 312581808 512-byte hardware sectors (160042 MB)
sd 0:0:0:0: [sda] Write Protect is off
sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
sd 0:0:0:0: [sda] Write cache: enabled, read cache: enabled, doesn't support DPO or FUA

# hdparm -tT /dev/sda

Code:

/dev/sda:
 Timing cached reads:   2218 MB in  2.00 seconds = 1109.27 MB/sec
  Timing buffered disk reads:  178 MB in  3.02 seconds =  58.95 MB/sec

# time for f in `ls *.rpm` ; do rpm2tgz $f ; done

Code:

real    2m13.525s
user    1m46.063s
sys     0m12.373s

Second machine (T41)

# dmesg | grep CPU

Code:

  Initializing CPU#0
  SLUB: Genslabs=11, HWalign=64, Order=0-1, MinObjects=4, CPUs=1, Nodes=1
  CPU: After generic identify, caps: a7e9f9bf 00000000 00000000 00000000 00000180 00000000 00000000 00000000
  CPU: L1 I cache: 32K, L1 D cache: 32K
  CPU: L2 cache: 1024K
  CPU: After all inits, caps: a7e9f9bf 00000000 00000000 00002040 00000180 00000000 00000000 00000000
  Intel machine check reporting enabled on CPU#0.
  CPU0: Intel(R) Pentium(R) M processor 1400MHz stepping 05
  Brought up 1 CPUs
  ACPI: CPU0 (power states: C1[C1] C2[C2] C3[C3])
  ACPI: Processor [CPU] (supports 8 throttling states)

# dmesg | grep Memory

Code:

Memory: 513300k/523648k available (2781k kernel code, 9904k reserved, 1093k data, 260k init, 0k highmem)

# dmesg | grep hda

Code:

    ide0: BM-DMA at 0x1860-0x1867, BIOS settings: hda:DMA, hdb:pio
hda: TOSHIBA MK8026GAX, ATA DISK drive
hda: host max PIO4 wanted PIO255(auto-tune) selected PIO4
hda: UDMA/100 mode selected
hda: max request size: 128KiB
hda: 156301488 sectors (80026 MB), CHS=65535/16/63
hda: cache flushes supported

# hdparm -tT /dev/hda

Code:

/dev/hda:
 Timing cached reads:   1000 MB in  2.00 seconds = 499.68 MB/sec
  Timing buffered disk reads:  102 MB in  3.00 seconds =  33.97 MB/sec

# time for f in `ls *rpm` ; do rpm2tgz $f ; done

Code:

real    3m54.211s
user    3m15.320s
sys     0m14.501s

H_TeXMeX_H · 10-23-2008, 10:42 AM

So you want to compare, here's the times for my desktop:

time to extract rpms:

Code:

bash-3.1$ time extractrpms

real	0m30.013s
user	0m21.989s
sys	0m1.591s

hdparm:

Code:

bash-3.1# hdparm -tT /dev/sda

/dev/sda:
 Timing cached reads:   4026 MB in  2.00 seconds = 2013.21 MB/sec
 Timing buffered disk reads:  222 MB in  3.02 seconds =  73.43 MB/sec

CPU model name : Intel(R) Core(TM)2 Quad CPU Q9300 @ 2.50GHz
Memory: 2041224k/2079744k available (2651k kernel code, 36140k reserved, 1072k data, 224k init)
this is Corsair DDR2 800 MHz CL5
HDD Model Family: Seagate Barracuda 7200.10 family
from smartctl

w1k0 · 10-23-2008, 11:02 AM

Quote:

So you want to compare, here's the times for my desktop:

I haven't extractrpms program to precisely compare the results. I used standard Slackware's rpm2tgz program to perform my tests (it does two actions: extracts RPM files and then creates TGZ ones).

H_TeXMeX_H · 10-23-2008, 01:07 PM

Quote:

Originally Posted by w1k0

I haven't extractrpms program to precisely compare the results.

You won't find it, because it's a script I made, it has this in it:

Code:

for i in *.rpm
do
	rpm2cpio $i | cpio -id --quiet
done

w1k0 · 10-23-2008, 02:18 PM

Quote:

You won't find it, because it's a script I made

No wonder I didn't find it in my system. It's good news both for me and for you.

I just tried your command...

T60

# time for i in *.rpm; do rpm2cpio $i | cpio -id --quiet; done

Code:

real    0m24.963s
user    0m6.332s
sys     0m6.644s

T41

# time for i in *.rpm; do rpm2cpio $i | cpio -id --quiet; done

Code:

real    0m54.454s
user    0m11.289s
sys     0m7.120s

Summary

T60 finished work in 25" -- T41 finished work in 54". In that test T60 is 2.16 times faster than T41.

My original command described above is more demanding for the machine than your command. I think my test is more reliable.

bassmadrigal · 10-23-2008, 02:53 PM

Code:

$ time for f in `ls *rpm` ; do rpm2tgz $f ; done

real    1m59.897s
user    0m28.454s
sys     0m24.234s

Code:

$ time for i in *.rpm; do rpm2cpio $i | cpio -id --quiet; done

real    0m26.318s
user    0m0.700s
sys     0m13.705s

Code:

jbhansen@dead-therapist:~/program-downloads/OOO300_m9_native_packed-1_en-US.9358/RPMS$ sudo hdparm -Tt /dev/hda

/dev/hda:
 Timing cached reads:   2258 MB in  1.99 seconds = 1132.11 MB/sec
 Timing buffered disk reads:  230 MB in  3.00 seconds =  76.61 MB/sec

This is actually on a Virtual Machine. My host machine is an AMD Athlon 64 X2 6400+ (3.2GHz dual-core), with 4GB of ram on Windows XP Pro installed to a 150GB Raptor. I am using VirtualBox (no dual core support), so essentially for that computer it is a 3.2GHz Athlon 64, with 512MB of RAM with the hard drive images being stored on my 1TB Western Digital drive which will adjust the spin rate from 5400rpm to 7200rpm.

As seen by linux...

Code:

jbhansen@dead-therapist:~$ cat /proc/cpuinfo
processor       : 0
vendor_id       : AuthenticAMD
cpu family      : 15
model           : 67
model name      : AMD Athlon(tm) 64 X2 Dual Core Processor 6400+
stepping        : 3
cpu MHz         : 3199.944
cache size      : 1024 KB
fdiv_bug        : no
hlt_bug         : no
f00f_bug        : no
coma_bug        : no
fpu             : yes
fpu_exception   : yes
cpuid level     : 1
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge
mca cmov pat pse36 clflush mmx fxsr sse sse2 syscall fxsr_opt 3dnowext 3dnow up
bogomips        : 6410.98
clflush size    : 64

jbhansen@dead-therapist:~$ free
             total       used       free     shared    buffers     cached
Mem:        510656     505096       5560          0       8108     253376
-/+ buffers/cache:     243612     267044
Swap:       516056       5192     510864