Re: Tips on Measuring Performance

From: Martin (mumrikman_at_yahoo.com)
Date: 05/23/04 

Date: 23 May 2004 04:33:31 -0700

harry holbeck <shpero@netcologne.de> wrote in message news:<c8khl2$46s$1@newsreader2.netcologne.de>...
> hi martin,
>
> did you try ubench

Thanks for the tip! I ran ubench and got the results below.

Memory and CPU in the machine used

# dmesg | egrep 'mem|cpu'
real mem = 1072492544 (1047356K)
avail mem = 909316096 (888004K)
using 22937 buffers containing 107458560 bytes (104940K) of memory
cpu0 at mainbus0: (uniprocessor)
cpu0: AMD Athlon(tm) 64 FX-53 Processor, 2400.48 MHz
cpu0: FPU,VME,DE,PSE,TSC,MSR,PAE,MCE,CX8,APIC,SEP,MTRR,PGE,MCA,CMOV,PAT,PSE36,CFLUSH,MMX,FXSR,SSE,SSE2,NXE,MMXX,LONG,3DNOW2,3DNOW
cpu0: 64KB 64b/line 2-way I-cache, 64KB 64b/line 2-way D-cache, 1MB
64b/line 16-way L2 cache
cpu0: ITLB 32 4KB entries fully associative, 8 4MB entries fully
associative
cpu0: DTLB 32 4KB entries fully associative, 8 4MB entries fully
associative

Ubench with i386 installed:

OpenBSD 3.5 GENERIC#34 i386
Ubench CPU: 100167
Ubench MEM: 69454
--------------------
Ubench AVG: 84810

Ubench with amd64 installed:

OpenBSD 3.5 GENERIC#72 amd64
Ubench CPU: 111814
Ubench MEM: 65733
--------------------
Ubench AVG: 88733

So, roughly 5% better cpu usage from the same system when using amd64.
What this might mean in terms of increased real life application
performance we will probably have to wait a while find out ...

Relevant Pages

  • Performance Problems.. Server hardware smoked by $500 box?
    ... webserver with a separate db/file server sitting behind it. ... Now granted the development machine has the most Mhz, ... CPU: Intel Pentium III Origin = ... Ubench CPU: 25713 ...
    (freebsd-questions)
  • Performance Problems.. Server hardware smoked by $500 box?
    ... webserver with a separate db/file server sitting behind it. ... Now granted the development machine has the most Mhz, ... CPU: Intel Pentium III Origin = ... Ubench CPU: 25713 ...
    (freebsd-performance)
  • Re: 7.0 CPU and Memory Performance
    ... As for whether it indicates a bug, someone would have to look more closely at what ubench does. ... The author's description of his benchmark doesn't inspire confidence: it does "rather senseless memory allocation and memory to memory copying operations for another 3 mins concurrently using several processes". ... The ubench memory benchmark operates almost entirely on 1024B buffers, which is nearly worst case for jemalloc. ... That is where most of the difference is; jemalloc is more aggressive/effective in returning pages to the VM than is phkmalloc. ...
    (freebsd-performance)
  • Re: 7.0 CPU and Memory Performance
    ... able to grab the binary from the old disk and move it over to the new ... And a rerun of the FreeBSD 7.0 ubench making sure there is absolutely ... still be quite a difference in the memory tests... ...
    (freebsd-performance)
  • Re: 7.0 CPU and Memory Performance
    ... Kris Kennaway wrote: ... able to grab the binary from the old disk and move it over to the new ... And a rerun of the FreeBSD 7.0 ubench making sure there is absolutely ... still be quite a difference in the memory tests... ...
    (freebsd-performance)