I have the same disk and get ~15-21 MB/sec with a BX chipset. I also
noticed
the "maxDMA=0(slow)" however I doubt that it has a meaning (I think it even
vanished in newer hdparm versions, your hdparm seems a bit dated it doesn't
even now about UDMA modes).
I have come to the conclusion that the UDMA33 implementation of certain
chipsets
is quite bad. Your results kind of confirm this observation. I also have
seen results where a Promise Ultra 33 (not 66) card has improved HD
performance
over a BX chipset.
-- Markus> -----Original Message----- > From: Harald Koenig [SMTP:koenig@tat.physik.uni-tuebingen.de] > Sent: Monday, March 06, 2000 10:01 AM > To: linux-kernel-list > Subject: max UDMA33 IDE performace ? > > which max. sustained read performace can be expected with UDMA33 ? > > I have a 40GB 7200rpm Maxtor disk which should give min/max 16.7/29.0 > MB/sec > accoring to a benchmark test in german c't magazine. > > but with DFI K6BV3+ main board (MVP3 chipset, only supports UDMA33 not > UDMA66), > AMD K6/2-400, 128MB PC100 ram, 2MB L2 cache only get ~11-14 MB/sec read > rate. > I noticed the "maxDMA=0(slow)" in "hdparm -i" output but can't find any > hint how to change this. > > is there any chance to improve/tune performace, or is UDMA33 the real > limit ? > do I need UDMA66 for 20-30 MB/sec ? why? > > > from startup (2.3.47): > > Uniform Multi-Platform E-IDE driver Revision: 6.30 > VP_IDE: IDE controller on PCI bus 00 dev 39 > VP_IDE: not 100% native mode: will probe irqs later > VT 82C598 Apollo MVP3 Chipset Core ATA-33 > Split FIFO Configuration: 16 Primary buffers, threshold = 3/4 > 0 Second. buffers, threshold = 1/2 > ide0: BM-DMA at 0xd000-0xd007, BIOS settings: hda:DMA, hdb:DMA > ide0: VIA Bus-Master (U)DMA Timing Config Success > hda: Maxtor 54098U8, ATA DISK drive > ide0 at 0x1f0-0x1f7,0x3f6 on irq 14 > hda: Maxtor 54098U8, 39082MB w/2048kB Cache, CHS=4982/255/63, UDMA(33) > Partition check: > hda: [EZD] [remap 0->1] [4982/255/63] hda1 hda2 hda3 hda4 > > # hdparm -tT /dev/hda > > /dev/hda: > Timing buffer-cache reads: 64 MB in 0.89 seconds =71.91 MB/sec > Timing buffered disk reads: 32 MB in 2.35 seconds =13.62 MB/sec > # hdparm /dev/hda > > /dev/hda: > multcount = 0 (off) > I/O support = 0 (default 16-bit) > unmaskirq = 0 (off) > using_dma = 1 (on) > keepsettings = 0 (off) > nowerr = 0 (off) > readonly = 0 (off) > readahead = 8 (on) > geometry = 4982/255/63, sectors = 80041248, start = 0 > > # hdparm -i /dev/hda > > /dev/hda: > > Model=Maxtor 54098U8, FwRev=DA620CQ0, SerialNo=K803ENKC > Config={ Fixed } > RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=57 > BuffType=3(DualPortCache), BuffSize=2048kB, MaxMultSect=16, MultSect=off > DblWordIO=no, maxPIO=2(fast), DMA=yes, maxDMA=0(slow) > CurCHS=4047/16/255, CurSects=16511760, LBA=yes, LBAsects=80041248 > tDMA={min:120,rec:120}, DMA modes: mword0 mword1 mword2 > IORDY=on/off, tPIO={min:120,w/IORDY:120}, PIO modes: mode3 mode4 > > > Harald > -- > All SCSI disks will from now on ___ _____ > be required to send an email notice 0--,| /OOOOOOO\ > 24 hours prior to complete hardware failure! <_/ / /OOOOOOOOOOO\ > \ \/OOOOOOOOOOOOOOO\ > \ > OOOOOOOOOOOOOOOOO|// > Harald Koenig, \/\/\/\/\/\/\/\/\/ > Inst.f.Theoret.Astrophysik // / \\ \ > koenig@tat.physik.uni-tuebingen.de ^^^^^ ^^^^^ > > - > To unsubscribe from this list: send the line "unsubscribe linux-kernel" in > the body of a message to majordomo@vger.rutgers.edu > Please read the FAQ at http://www.tux.org/lkml/
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Tue Mar 07 2000 - 21:00:19 EST