Re: [HACKERS] Sequential scan speed, mmap, disk i/o

From: Bruce Momjian <maillist(at)candle(dot)pha(dot)pa(dot)us>
To: lockhart(at)alumni(dot)caltech(dot)edu (Thomas G(dot) Lockhart)
Cc: mimo(at)interdata(dot)com(dot)pl, hackers(at)postgresql(dot)org, info(at)bsdi(dot)com
Subject: Re: [HACKERS] Sequential scan speed, mmap, disk i/o
Date: 1998-05-16 04:43:49
Message-ID: 199805160443.AAA29238@candle.pha.pa.us
Views: Raw Message | Whole Thread | Download mbox | Resend email
Thread:
Lists: pgsql-hackers

>
> > Basically, Linux is double my speed for 8k mmap'ed chunks. Around 32k
> > chunks, I get closer, and 8mb chunks are the same. Glad to hear Linux
> > has optimized mmap() recently, because BSD/OS looks much slower than
> > Linux on this.
>
> Well Bruce, don't be too happy. Most people aren't yet running the
> optimized kernel; don't know if any of the benchmarks came from someone
> running a bleeding-edge development version, which is what 2.1.99 would
> be; first feature-freeze release in preparation for v2.2 afaik :)
>
> And scrappy, no need to note that _all_ Linux kernels are bleeding edge
> releases :)

[FYI, BSDI, Linux dev. release is beating BSDI for 8k mmaps() by 2x.]

I must say, when I saw Linux beating BSDI by 2x, I started wondering if
the great BSDI engineers were sleeping or something. Now that I
understand that this improvement is a somewhat new effort, I feel a
little better.

--
Bruce Momjian | 830 Blythe Avenue
maillist(at)candle(dot)pha(dot)pa(dot)us | Drexel Hill, Pennsylvania 19026
+ If your life is a hard drive, | (610) 353-9879(w)
+ Christ can be your backup. | (610) 853-3000(h)

In response to

Browse pgsql-hackers by date

  From Date Subject
Next Message The Hermit Hacker 1998-05-16 05:41:39 Re: [HACKERS] Sequential scan speed, mmap, disk i/o
Previous Message Thomas G. Lockhart 1998-05-16 02:40:14 Re: [HACKERS] Sequential scan speed, mmap, disk i/o