hamachi@KIM.BERKELEY.EDU (Gordon Hamachi) (03/26/86)
Here are more measurements using Brecher disk benchmark on a Mac+ with Apple's internal 800K floppy drive. HFS and MFS volumes seem to perform differently. Of course, your mileage may differ... >The benchmark consists of three parts: >(1) 100 reads of 32KB of data from the start of the volume; >(2) 100 writes of 32KB of data to the start of the volume; >(3) 40 iterations of: read one 512-byte block from an offset of 1MB, followed > by read of one 512-byte block from start of volume; >( times are in ticks, i.e., sixtieths of a second): > > Data transfer time Access Time > ------------------ > Reads Writes > Apple Internal 800K drive (1) 8719 11543 (7) Apple Internal 800K drive (2) 8324 11540 (7) Apple Internal 800K drive (3) 8032 10902 (7) Apple Internal 800K drive (4) 7844 10908 (7) >Tecmar MacDrive (5) 6017 6719 401 >DataFrame 20 1344 2233 487 >HyperDrive (6) 1586 1600 563 >MicahDrive 20 AT 507 508 528 400K RAM Disk 192 192 (7) > Notes: (1) Disk cache disabled, 400K MFS Volume (2) 96K disk cache, 400K MFS Volume (3) Disk cache disabled, 800K HFS Volume (4) 256K disk cache, 800K HFS Volume (5) 10MB Fixed (6) original 10MB unit with old controller and version 5.1 software (7) Volume to small to complete this test
brad@gcc-milo.ARPA (Brad Parker) (03/27/86)
In article <8603252311.AA07791@kim.berkeley.edu> hamachi@KIM.BERKELEY.EDU (Gordon Hamachi) writes: >Here are more measurements using Brecher disk benchmark on a Mac+ >with Apple's internal 800K floppy drive. HFS and MFS volumes seem >to perform differently. To be fair, you need to note if the test was run on 64k or 128k roms. The file systems are different (even for HFS). I wouldn't be suprised if the same HFS benchmark on old and new roms produced different results (the new roms may be faster due to improved code). Any idea? -- J Bradford Parker General Computer (HyperDrive Beach) harvard!gcc-milo!brad "She said, 'Just drive.'" -heard on the radio.
hamachi@KIM.BERKELEY.EDU (Gordon Hamachi) (03/28/86)
>>Here are more measurements using Brecher disk benchmark on a Mac+ >>with Apple's internal 800K floppy drive. HFS and MFS volumes seem >>to perform differently. > >To be fair, you need to note if the test was run on 64k or 128k roms. To my knowledge all Mac Plus machines have 128K ROMS. Did you mean, "Which version of these ROMS"? I understand that there are several ROM revisions, but I don't know which one my machine has. How do I find out? Perhaps you meant, "What kind of machine did you use for the MFS tests"? I used the same machine for all tests; on a Mac+ you have the choice of formatting a disk as an HFS volume or an MFS volume. --Gordon Hamachi
gwe@cbdkc1.UUCP ( George Erhart x4021 CB 3D288 RNB ) (03/29/86)
In article <8603252311.AA07791@kim.berkeley.edu> hamachi@KIM.BERKELEY.EDU (Gordon Hamachi) writes: >Here are more measurements using Brecher disk benchmark on a Mac+ >with Apple's internal 800K floppy drive. HFS and MFS volumes seem >to perform differently. > >Of course, your mileage may differ... > >>The benchmark consists of three parts: >>(1) 100 reads of 32KB of data from the start of the volume; >>(2) 100 writes of 32KB of data to the start of the volume; >>(3) 40 iterations of: read one 512-byte block from an offset of 1MB, followed >> by read of one 512-byte block from start of volume; >>( times are in ticks, i.e., sixtieths of a second): >> >> Data transfer time Access Time >> ------------------ >> Reads Writes >> > Apple Internal 800K drive (1) 8719 11543 (7) > Apple Internal 800K drive (2) 8324 11540 (7) > Apple Internal 800K drive (3) 8032 10902 (7) > Apple Internal 800K drive (4) 7844 10908 (7) >>Tecmar MacDrive (5) 6017 6719 401 >>DataFrame 20 1344 2233 487 >>HyperDrive (6) 1586 1600 563 >>MicahDrive 20 AT 507 508 528 > 400K RAM Disk 192 192 (7) 1.5 Meg RamDisk (8) 137 137 5 >> >Notes: (1) Disk cache disabled, 400K MFS Volume > (2) 96K disk cache, 400K MFS Volume > (3) Disk cache disabled, 800K HFS Volume > (4) 256K disk cache, 800K HFS Volume > (5) 10MB Fixed > (6) original 10MB unit with old controller and version 5.1 software > (7) Volume to small to complete this test (8) Levco Monster Mac using The Assimilation Process Ram Disk (64k ROMS) The access time test ran okay on my Mac because I could run a >1 Meg Ram disk. -- George Erhart at AT&T Bell Laboratories Columbus, Ohio 614-860-4021 {ihnp4,cbosgd}!cbdkc1!gwe
ephraim@wang.UUCP (pri=8 Ephraim Vishniac x76659 ms1459) (04/02/86)
> In article <8603252311.AA07791@kim.berkeley.edu> hamachi@KIM.BERKELEY.EDU (Gordon Hamachi) writes: > >Here are more measurements using Brecher disk benchmark on a Mac+ > >with Apple's internal 800K floppy drive. HFS and MFS volumes seem > >to perform differently. > > To be fair, you need to note if the test was run on 64k or 128k roms. The > file systems are different (even for HFS). I wouldn't be suprised if the > same HFS benchmark on old and new roms produced different results (the > new roms may be faster due to improved code). > > J Bradford Parker > General Computer (HyperDrive Beach) > harvard!gcc-milo!brad > But the test doesn't operate through the file system! It does direct driver calls. So, neither the cache nor the file system should have any effect... *** REPLACE THIS MESS WITH YOUR MESSAGE ***
brad@gcc-milo.UUCP (04/06/86)
In article <785@wang.UUCP> ephraim@wang.UUCP (pri=8 Ephraim Vishniac x76659 ms1459) writes: >> In article <8603252311.AA07791@kim.berkeley.edu> hamachi@KIM.BERKELEY.EDU (Gordon Hamachi) writes: >> >with Apple's internal 800K floppy drive. HFS and MFS volumes seem >> >to perform differently... >> To be fair, you need to note if the test was run on 64k or 128k roms... >> J Bradford Parker >But the test doesn't operate through the file system! It does direct driver >calls. So, neither the cache nor the file system should have any effect... At the risk of flogging a dead horse, (something I *NEVER* do ;-) ) the benchmark makes calls to the driver at the device manager level. Some changes may have been made to the new ROMS to affect performance at this level. But, then again, the changes may make no difference. -just thought it should be noted. -- J Bradford Parker General Computer (HyperDrive Beach) harvard!gcc-milo!brad "She said, 'Just drive.'" -heard on the radio.