mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Alex Tomas <bzzz@tmi.comex.ru>
To: Andrew Morton <akpm@digeo.com>
Cc: William Lee Irwin III <wli@holomorphy.com>,
	bzzz@tmi.comex.ru, adilger@clusterfs.com,
	linux-kernel@vger.kernel.org, ext2-devel@lists.sourceforge.net
Subject: Re: [Ext2-devel] Re: [PATCH] concurrent block allocation for ext2 against 2.5.64
Date: 15 Mar 2003 11:16:10 +0300	[thread overview]
Message-ID: <m3r899yrhx.fsf@lexa.home.net> (raw)
In-Reply-To: <20030314224413.6a1fc39c.akpm@digeo.com>

>>>>> Andrew Morton (AM) writes:

 AM> Nope.  What we're trying to measure here is pure in-memory lock
 AM> contention, locked bus traffic, context switches, etc, etc.  To
 AM> do that we need to get the IO system out of the picture.

I simple use own pretty simple test. btw, you may disable preallocation
to increase allocation rate


bash-script:
============================================================
#!/bin/sh

# args:
# 1 - how many processes to create
# 2 - how many blocks in file to be written
# 3 - how many times to repeat (write+truncate)
# for example: cd.sh 2 32 100000

let i=0
while let "i < $1"; do
        if [ ! -d /mnt/$i ]; then
                mkdir /mnt/$i
        fi
        rm -rf /mnt/$i/*
        let "i=i+1"
done

sync
sync

let i=0
while let "i < $1"; do
        time /root/cdsingle $2 $3 /mnt/$i/1 &
        let "i=i+1"
done

wait
============================================================

C programm, which does loop over writes and truncate:

#include <stdio.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>


main (int argc, char ** argv)
{
        int i, j, num, siz, err, k;
        int fd[1024];

        num = atoi(argv[2]);
        siz = atoi(argv[1]);
        
        for (i = 3; i < argc; i++) {
                fd[i] = creat(argv[i], 0666);
                if (fd[i] < 0) {
                        perror("can't create");
                        exit(1);
                }
        }

        for (j = 0; j < num; j++) {
                for (i = 3; i < argc; i++) {
                        for (k = 0; k < siz; k++)
                                if ((err = write(fd[i], main, 4096)) < 0) {
                                        printf("err=%d\n", err);
                                        perror("can't write");
                                        exit(1);
                                }
                }
                for (i = 3; i < argc; i++) {
                        ftruncate(fd[i], 0);
                        lseek(fd[i], 0, SEEK_SET);
                }
        }

        for(i = 3; i < argc; i++) {
                close(fd[i]);
                if (unlink(argv[i]) < 0)
                        perror("can't unlink");
        }
}



  parent reply	other threads:[~2003-03-15  8:13 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-03-13  8:55 Alex Tomas
2003-03-13  9:58 ` Andrew Morton
2003-03-13 19:17   ` Alex Tomas
2003-03-13 22:25     ` Andrew Morton
2003-03-13 23:03       ` Andreas Dilger
2003-03-13 23:10         ` Andrew Morton
2003-03-13 23:03       ` Alex Tomas
2003-03-13 23:25         ` Andrew Morton
2003-03-13 23:56     ` Andreas Dilger
2003-03-14  7:20       ` Alex Tomas
2003-03-14 20:59         ` Andreas Dilger
2003-03-14 21:14           ` Alex Tomas
2003-03-15  4:37         ` William Lee Irwin III
2003-03-15  4:54           ` Andrew Morton
2003-03-15  5:30             ` William Lee Irwin III
2003-03-15  5:43               ` Martin J. Bligh
2003-03-15  5:50                 ` William Lee Irwin III
2003-03-15  5:49             ` William Lee Irwin III
2003-03-15  6:20               ` William Lee Irwin III
2003-03-15  6:44                 ` Andrew Morton
2003-03-15  7:05                   ` William Lee Irwin III
2003-03-15  8:24                     ` William Lee Irwin III
2003-03-15  9:47                       ` William Lee Irwin III
2003-03-15 11:58                         ` William Lee Irwin III
2003-03-15 12:08                           ` Andrew Morton
2003-03-15 12:25                             ` William Lee Irwin III
2003-03-15  8:16                   ` Alex Tomas [this message]
2003-03-15  8:29                     ` [Ext2-devel] " William Lee Irwin III
2003-03-15  8:32                       ` Alex Tomas
2003-03-15  9:23                         ` William Lee Irwin III
2003-03-14 18:25       ` Martin J. Bligh
2003-03-14 19:30       ` [Ext2-devel] " Daniel Phillips
2003-03-14 19:55         ` Andrew Morton
2003-03-13 17:39 ` [Ext2-devel] " Andreas Dilger
2003-03-13 18:43   ` Alex Tomas
2003-03-13 19:09     ` Matthew Wilcox
2003-03-13 19:39       ` Andrew Morton
2003-03-13 19:23   ` Theodore Ts'o
2003-03-13 19:44     ` Andreas Dilger

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=m3r899yrhx.fsf@lexa.home.net \
    --to=bzzz@tmi.comex.ru \
    --cc=adilger@clusterfs.com \
    --cc=akpm@digeo.com \
    --cc=ext2-devel@lists.sourceforge.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=wli@holomorphy.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®