Messages in this thread | | | From | "Daniel J Blueman" <> | Subject | Re: Strange IDE performance observations | Date | Sat, 18 Mar 2000 11:29:19 -0000 |
| |
Hi Mike,
The ATA-6 spec defines IDE cable lengths as 12-18 inches long, but having 6 inches between the end two connectors. ie plug the end with the 6-12 inch gap into your motherboard, and install a device on the other end of the cable first, NOT the middle, two devices is fine also. (signal ringing occurs).
Check all this is right. It _may_ help.
Dan
__________________________ Daniel J Blueman Undergraduate - BSc Computing Science UMIST university - Manchester Direct line: 0161 933 3569 Mobile: 07775 583766 Email: daniel.j.blueman@stud.umist.ac.uk SMS: daniel.j.blueman@sms.genie.co.uk ----- Original Message ----- From: "Mike Castle" <dalgoda@ix.netcom.com> To: "Linux Kernel List" <linux-kernel@vger.rutgers.edu> Sent: Thursday, March 16, 2000 2:44 PM Subject: Strange IDE performance observations
> > I strongly suspect that what I'm about to describe is due either to a flaky > motherboard or a harddrive going bad, as opposed to a kernel or config > issue. I'm hoping someone here can confirm. <beg>Andre?</beg> > > I've tried researching deja/usenet for answers, but really didn't find > anything that I could piece together. > > First, some filtered output from dmesg: > > Linux version 2.2.14 (root@thune) (gcc version 2.95.2 19991024 (release)) #5 Mon Mar 6 20:41:52 CST 2000 > Detected 233224515 Hz processor. > Calibrating delay loop... 465.31 BogoMIPS > Memory: 79676k/81920k available (756k kernel code, 412k reserved, 1020k data, 56k init) > Dentry hash table entries: 16384 (order 5, 128k) > Buffer cache hash table entries: 131072 (order 7, 512k) > Page cache hash table entries: 32768 (order 5, 128k) > CPU: Intel Pentium MMX stepping 03 > PCI: PCI BIOS revision 2.10 entry at 0xfb000 > PCI: Using configuration type 1 > PCI: Probing PCI hardware > Uniform Multi-Platform E-IDE driver Revision: 6.30 > PIIX3: IDE controller on PCI bus 00 dev 39 > PIIX3: not 100% native mode: will probe irqs later > ide0: BM-DMA at 0xf000-0xf007, BIOS settings: hda:pio, hdb:pio > ide1: BM-DMA at 0xf008-0xf00f, BIOS settings: hdc:pio, hdd:pio > hda: Maxtor 82560A4, ATA DISK drive > hdb: Maxtor 91303D6, ATA DISK drive > hdc: Maxtor 93652U8, ATA DISK drive > hdd: Maxtor 92048U8, ATA DISK drive > ide0 at 0x1f0-0x1f7,0x3f6 on irq 14 > ide1 at 0x170-0x177,0x376 on irq 15 > hda: Maxtor 82560A4, 2442MB w/256kB Cache, CHS=620/128/63, DMA > hdb: Maxtor 91303D6, 12427MB w/512kB Cache, CHS=25249/16/63, (U)DMA > hdc: Maxtor 93652U8, 34837MB w/2048kB Cache, CHS=70780/16/63, (U)DMA > hdd: Maxtor 92048U8, 19470MB w/2048kB Cache, CHS=39560/16/63, (U)DMA > > Now some output from hdparm 3.6 (note it gets the 93652U8 wrong, but then > so does fdisk 2.10d, but it *seems* to work, so far): > /dev/hda: > multcount = 16 (on) > I/O support = 1 (32-bit) > unmaskirq = 1 (on) > using_dma = 1 (on) > keepsettings = 1 (on) > nowerr = 0 (off) > readonly = 0 (off) > readahead = 8 (on) > geometry = 620/128/63, sectors = 5001728, start = 0 > > Model=Maxtor 82560A4, FwRev=AA8Z2726, SerialNo=C40JRRRA > Config={ Fixed } > RawCHS=4962/16/63, TrkSize=0, SectSize=0, ECCbytes=20 > BuffType=3(DualPortCache), BuffSize=256kB, MaxMultSect=16, MultSect=16 > DblWordIO=no, OldPIO=2, DMA=yes, OldDMA=2 > CurCHS=4962/16/63, CurSects=5001696, LBA=yes, LBAsects=5001728 > tDMA={min:120,rec:120}, DMA modes: mword0 mword1 *mword2 > IORDY=on/off, tPIO={min:120,w/IORDY:120}, PIO modes: mode3 mode4 > > > /dev/hdb: > multcount = 16 (on) > I/O support = 1 (32-bit) > unmaskirq = 1 (on) > using_dma = 1 (on) > keepsettings = 1 (on) > nowerr = 0 (off) > readonly = 0 (off) > readahead = 8 (on) > geometry = 25249/16/63, sectors = 25450992, start = 0 > > Model=Maxtor 91303D6, FwRev=GAS54112, SerialNo=A609WPDC > Config={ Fixed } > RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=29 > BuffType=3(DualPortCache), BuffSize=512kB, MaxMultSect=16, MultSect=16 > DblWordIO=no, OldPIO=2, DMA=yes, OldDMA=2 > CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=25450992 > tDMA={min:120,rec:120}, DMA modes: mword0 mword1 *mword2 > IORDY=on/off, tPIO={min:120,w/IORDY:120}, PIO modes: mode3 mode4 > UDMA modes: mode0 mode1 mode2 > > > /dev/hdc: > multcount = 16 (on) > I/O support = 1 (32-bit) > unmaskirq = 1 (on) > using_dma = 1 (on) > keepsettings = 1 (on) > nowerr = 0 (off) > readonly = 0 (off) > readahead = 8 (on) > geometry = 5244/16/63, sectors = 71346240, start = 0 > > Model=Maxtor 93652U8, FwRev=FA550480, SerialNo=M0000000 > Config={ Fixed } > RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=57 > BuffType=3(DualPortCache), BuffSize=2048kB, MaxMultSect=16, MultSect=16 > DblWordIO=no, OldPIO=2, DMA=yes, OldDMA=0 > CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=71346240 > tDMA={min:120,rec:120}, DMA modes: mword0 mword1 *mword2 > IORDY=on/off, tPIO={min:120,w/IORDY:120}, PIO modes: mode3 mode4 > UDMA modes: mode0 mode1 mode2 mode3 mode4 > > > /dev/hdd: > multcount = 16 (on) > I/O support = 1 (32-bit) > unmaskirq = 1 (on) > using_dma = 1 (on) > keepsettings = 1 (on) > nowerr = 0 (off) > readonly = 0 (off) > readahead = 8 (on) > geometry = 39560/16/63, sectors = 39876480, start = 0 > > Model=Maxtor 92048U8, FwRev=VA510PF0, SerialNo=W805Y9LA > Config={ Fixed } > RawCHS=16383/16/63, TrkSize=0, SectSize=0, ECCbytes=57 > BuffType=3(DualPortCache), BuffSize=2048kB, MaxMultSect=16, MultSect=16 > DblWordIO=no, OldPIO=2, DMA=yes, OldDMA=0 > CurCHS=16383/16/63, CurSects=16514064, LBA=yes, LBAsects=39876480 > tDMA={min:120,rec:120}, DMA modes: mword0 mword1 *mword2 > IORDY=on/off, tPIO={min:120,w/IORDY:120}, PIO modes: mode3 mode4 > UDMA modes: mode0 mode1 mode2 mode3 mode4 > > The motherboard I'm using is a Spacewalker/Shuttle HOT-557 v1.5 with > latest BIOS. This motherboard is 430VX chipset based and is supposed to > support PIO mode 4/DMA mode 2. It hangs trying to detect the 93652U8, > so I have it autodetect only hda and let Linux find everything else. > > Now, what I'm seeing is a wide variety of performance results (via hdparm > -t), depending on where the harddrives are logically placed. > > The following chart will demonstrate, I hope. I'll list by size. > > Config 1: > hda: 2442: 8.43 MB/sec > hdb: 12427: 10.13 MB/sec > hdc: 19470: 6.96 MB/sec > hdd: 34837: 7.49 MB/sec > > Config 2: > hda: 2442: 8.43 MB/sec > hdb: 12427: 10.14 MB/sec > hdc: 34837: 8.56 MB/sec > hdd: 19470: 6.69 MB/sec > > Config 3: > hda: 2442: 8.43 MB/sec > hdb: 34837: 8.48 MB/sec > hdc: 12427: 10.19 MB/sec > hdd: 19470: 6.72 MB/sec > > Config 4: > hda: 2442: 8.43 MB/sec > hdb: 34837: 8.50 MB/sec > hdc: 19470: 6.96 MB/sec > hdd: 12427: 7.49 MB/sec > > To be honest, almost no tweaking of hdparm really makes a difference, > except to change PIO modes down to something below 4, which slows things > down, of course. > > Also, I'm somewhat regularly getting: > hdd: irq timeout: status=0xd0 { Busy } > ide1: reset: success > > Same on hdc. > > I've swapped cables, moved power connectors around, etc. I've seen similar > performance issues before I got the 34837 drive and was using a 3G IBM. I > figured I'd try all the same brand and see what that did. > > If I move the 19470 drive to hdb, all hell breaks loose. Lots of drive not > ready/seek type errors just doing a "du -s". Didn't explore other things > too much at that point; I felt I was going to lose my file systems if I > wasn't careful, and I just didn't want to deal with that at this point. > > So, is the performance issue I'm seeing with the 19470 drive due to it > getting ready to go out on me? Is this a piece of crap motherboard (hey, I > got it for free, so no complaints)? > > Also, when booting, and it says: > ide0: BM-DMA at 0xf000-0xf007, BIOS settings: hda:pio, hdb:pio > ide1: BM-DMA at 0xf008-0xf00f, BIOS settings: hdc:pio, hdd:pio > > With this motherboard and these drives, should I expect to see DMA in there > anywhere instead of pio? I thought I had all of the correct tuning options > turned on in the kernel. But since those say BIOS settings, and BIOS > really doesn't even know about the other drives, I'm wouldn't be too > surprised. > > Thanks, > mrc > -- > Mike Castle Life is like a clock: You can work constantly > dalgoda@ix.netcom.com and be right all the time, or not work at all > www.netcom.com/~dalgoda/ and be right at least twice a day. -- mrc > We are all of us living in the shadow of Manhattan. -- Watchmen > > - > 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/
| |