> Next time, do your test with 2x or more the amount of ram. I would have, but I wanted to test the FS's on the MO drive. I have 512MB of RAM in that box. I guess I could have cranked the size up as high as possible though. > -----Original Message----- > From: Scott Dier [mailto:dieman at ringworld.org] > Sent: Wednesday, December 13, 2000 11:59 AM > To: tclug-list at lists.real-time.com > Subject: Re: [TCLUG] REAL Verbatim drive Q (: > > > Next time, do your test with 2x or more the amount of ram. > > I did the tests with a 500MB file, for instance. > > * Austad, Jay <austad at marketwatch.com> [001213 01:42]: > > Sweet! I didn't even bother to try Reiser because the > version of mkreiserfs > > that I have won't let me adjust the block size, so I gave > up since the > > manual preaches about 2048B blocksize. > > > > I just reformatted my disk with reiser and I'm running > bonnie on it to > > compare it to ext2. > > > > ReiserFS: > > > > -------Sequential Output-------- ---Sequential Input-- > > --Random-- > > -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- > > --Seeks--- > > Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU > K/sec %CPU /sec > > %CPU > > 100 6205 96.5 43356 93.6 453 1.1 877 12.5 > 28765 18.3 17443.3 > > 95.9 > > 100 1744 26.7 47848 96.3 609 1.3 6820 96.2 > 91798 89.6 61.3 > > 0.3 > > 100 6256 96.4 48244 95.6 432 0.8 6866 96.1 > 114530 94.0 72.2 > > 0.4 > > 100 6114 95.5 47270 94.6 437 0.9 6861 96.3 > 117158 92.7 72.7 > > 0.4 > > > > > > ext2: > > > > -------Sequential Output-------- ---Sequential Input-- > > --Random-- > > -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- > > --Seeks--- > > Machine MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU > K/sec %CPU /sec > > %CPU > > 100 6272 92.6 88213 91.3 47749 92.8 6820 96.2 > 154711 92.2 119.1 > > 0.7 > > 100 6597 96.3 91556 94.8 50079 95.9 6854 96.5 > 160844 97.4 182.5 > > 1.0 > > 100 6484 95.2 93161 96.4 49358 93.0 6872 96.5 > 154766 92.2 149.8 > > 0.9 > > 100 6598 96.5 93746 95.2 51057 96.2 6798 96.0 > 156069 94.5 124.9 > > 0.7 > > > > > > > > Looks like ext2 whooped Reiser. I didn't add any special > options to reiser. > > I wonder if the reiserfs was 2048 byte blocks like the ext2 > one if it would > > make a difference. > > > > Jay > > > > > -----Original Message----- > > > From: Scott Dier [mailto:dieman at ringworld.org] > > > Sent: Tuesday, December 12, 2000 10:49 PM > > > To: tclug-list at lists.real-time.com > > > Subject: Re: [TCLUG] REAL Verbatim drive Q (: > > > > > > > > > * Austad, Jay <austad at marketwatch.com> [001212 22:19]: > > > > Can't use ReiserFS on it. Reiser will only format with > > > 4096 byte blocks. > > > > > > /dev/scsi/host0/bus0/target4/lun0/disc on /mnt/mo type reiserfs > > > (rw,noexec,nosuid,nodev,user=dieman) > > > > > > /dev/scsi/host0/bus0/target4/lun0/disc > > > 620680 131428 489252 22% /mnt/mo > > > > > > Worked fine here :) I'm using a Tekram DC-315U card. > > > > > > scsi0 : Tekram DC395U/UW/F DC315/U V1.32, 2000-12-02 > > > Vendor: OLYMPUS Model: MOS364 Rev: 1.02 > > > Type: Optical Device ANSI SCSI revision: 02 > > > Detected scsi removable disk sda at scsi0, channel 0, id 4, lun 0 > > > DC395x: Target 04: Sync: 100ns Offset 15 (10.0 MB/s) > > > SCSI device sda: 310352 2048-byte hdwr sectors (636 MB) > > > > > > > > > -- > > > Scott Dier <dieman at ringworld.org> #linuxos at irc.openprojects.net > > > http://www.ringworld.org/ finger:dieman at destiny.ringworld.org > > > > > > "Kupo, kupkup, kupopo... Po... Kupo!? KUPOPO!!! > > > <Chomp chomp> Kupooo." > > > -Moguta (FFIX) > > > > > _______________________________________________ > > tclug-list mailing list > > tclug-list at lists.real-time.com > > https://mailman.real-time.com/mailman/listinfo/tclug-list > > -- > Scott Dier <dieman at ringworld.org> #linuxos at irc.openprojects.net > http://www.ringworld.org/ finger:dieman at destiny.ringworld.org > > "Kupo, kupkup, kupopo... Po... Kupo!? KUPOPO!!! > <Chomp chomp> Kupooo." > -Moguta (FFIX) >