Date: Mon, 17 May 1999 18:44:04 -0700 (PDT) From: John Polstra <jdp@polstra.com> To: alpha@freebsd.org Subject: Clock drift on the alpha Message-ID: <XFMail.990517184404.jdp@polstra.com>
next in thread | raw e-mail | index | archive | help
My alpha machine, which I suspect may be haunted, has pretty bad clock drift. I started up xntpd, and the log messages will give you a sense of how bad the drift is: May 17 09:46:41 alpha xntpd[375]: xntpd version=3.4e (beta multicast); Sun May 16 11:27:50 PDT 1999 (1) May 17 09:46:41 alpha xntpd[375]: tickadj = 5, tick = 976, tvu_maxslew = 5115 May 17 09:46:41 alpha xntpd[375]: using xntpd phase-lock loop May 17 09:52:00 alpha xntpd[375]: time reset (step) -1.661376 s May 17 09:58:23 alpha xntpd[375]: time reset (step) -0.906801 s May 17 10:04:47 alpha xntpd[375]: time reset (step) -0.906982 s May 17 10:11:10 alpha xntpd[375]: time reset (step) -0.907095 s May 17 10:17:33 alpha xntpd[375]: time reset (step) -0.907238 s May 17 10:23:56 alpha xntpd[375]: time reset (step) -0.906743 s May 17 10:30:19 alpha xntpd[375]: time reset (step) -0.907094 s ... (It doesn't do any better if I use the kernel PLL.) Is this a common problem? My dmesg output is below. Also, is xntpd broken on the alpha? It has been running nonstop on this machine for 8 hours, and it has written a drift file. But the file contains "0.000 0", which is clearly wrong. John Copyright (c) 1992-1999 The FreeBSD Project. Copyright (c) 1982, 1986, 1989, 1991, 1993 The Regents of the University of California. All rights reserved. FreeBSD 4.0-CURRENT #2: Sun May 16 14:01:28 PDT 1999 jdp@alpha.polstra.com:/a/src/sys/compile/ALPHA EB164 Digital AlphaPC 164LX 533 MHz, 531MHz 8192 byte page size, 1 processor. CPU: EV56 (21164A) major=7 minor=2 extensions=0x1<BWX> OSF PAL rev: 0x1000100020116 real memory = 132276224 (129176K bytes) avail memory = 124215296 (121304K bytes) Preloaded elf kernel "kernel" at 0xfffffc0000580000. cia0: <2117x Core Logic chipset> cia0: Pyxis, pass 1 cia0: extended capabilities: 111<WLEN,MWEN,BWEN> pcib0: <2117x PCI host bus adapter> on cia0 pci0: <PCI bus> on pcib0 de0: <Digital 21140A Fast Ethernet> irq 0 at device 6.0 on pci0 de0: interrupting at CIA irq 0 de0: SMC 9332BDT 21140A [10-100Mb/s] pass 2.0 de0: address 00:e0:29:00:ce:a4 de0: enabling 100baseTX port ncr0: <ncr 53c875 fast20 wide scsi> irq 1 at device 7.0 on pci0 ncr0: interrupting at CIA irq 1 isab0: <Intel 82378IB PCI to ISA bridge> at device 8.0 on pci0 isa0: <ISA bus> on isab0 vga-pci0: <Trident model 9440 VGA-compatible display device> irq 3 at device 9.0 on pci0 chip0: <CMD 646 IDE controller> irq 5 at device 11.0 on pci0 mcclock0: <MC146818A real time clock> at ports 0x70-0x71 and 0xffff on isa0 sio0 at ports 0x3f8-0x3ff and 0xffff on isa0 sio0: type 16550A sio0: interrupting at ISA irq 4 sio1: reserved for low-level i/o atkbdc0: <keyboard controller (i8042)> at ports 0x60 and 0xffff on isa0 atkbd0: <AT Keyboard> irq 1 on atkbdc0 atkbd0: interrupting at ISA irq 1 psm0: <PS/2 Mouse> irq 12 on atkbdc0 psm0: model Generic PS/2 mouse, device ID 0 psm0: interrupting at ISA irq 12 vga0: <Generic ISA VGA> at ports 0xffff and 0xffff on isa0 sc0: <System console> at ports 0xffff and 0xffff on isa0 sc0: VGA color <16 virtual consoles, flags=0x0> struct nfssvc_sock bloated (> 256bytes) Try reducing NFS_UIDHASHSIZ struct nfsuid bloated (> 128bytes) Try unionizing the nu_nickname and nu_flag fields Timecounter "alpha" frequency 531914893 Hz Waiting 2 seconds for SCSI devices to settle da0 at ncr0 bus 0 target 0 lun 0 da0: <IBM DDRS-39130D DC1B> Fixed Direct Access SCSI-2 device da0: 40.000MB/s transfers (20.000MHz, offset 15, 16bit), Tagged Queueing Enabled da0: 8715MB (17850000 512 byte sectors: 255H 63S/T 1111C) To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-alpha" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?XFMail.990517184404.jdp>