From owner-freebsd-hackers Sat Apr 13 18:08:42 1996 Return-Path: owner-hackers Received: (from root@localhost) by freefall.freebsd.org (8.7.3/8.7.3) id SAA11581 for hackers-outgoing; Sat, 13 Apr 1996 18:08:42 -0700 (PDT) Received: from post.io.org (post.io.org [198.133.36.6]) by freefall.freebsd.org (8.7.3/8.7.3) with ESMTP id SAA11576 for ; Sat, 13 Apr 1996 18:08:40 -0700 (PDT) Received: from zap.io.org (taob@zap.io.org [198.133.36.81]) by post.io.org (8.7.5/8.7.3) with SMTP id VAA19542 for ; Sat, 13 Apr 1996 21:05:28 -0400 (EDT) Date: Sat, 13 Apr 1996 21:07:34 -0400 (EDT) From: Brian Tao To: FREEBSD-HACKERS-L Subject: pmap_zero_page and kmem_malloc panics Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-hackers@freebsd.org X-Loop: FreeBSD.org Precedence: bulk For some reason, our Web/FTP server has been crashing/hanging a lot lately. I was able to take down the reason for two recent ones: panic: kmem_malloc: kmem_map too small panic: pmap_zero_page: CMAP busy The mysterious process deadlock hang also hit a couple of times (can switch virtual consoles, can ping, but nothing else), with no helpful errors logged. I'm going to upgrade to the latest snapshot too see if this problem goes away. The kernel has maxusers=128, SysV IPC options turned on, NMBCLUSTERS=8192, OPEN_MAX=1024, CHILD_MAX=512 and MAXMEM=131072. It isn't running out of mbufs (although it did hit 7202 out of 8192 once) and I doubt it is getting anywhere close to hitting swap. 'top' usually shows about 50MB free when there isn't a mirror process running. The de0 interface sees between 100K to 200K per second both ways on a 10Mbps link to our etherswitch, according to "netstat -b 1". The Web server gets between 3.5 to 4 million hits per week, including those to the 50 IP aliases on de0 (could this a problem?). The FTP server isn't as busy, about 1200 files per day. We've had two crashes already today. The second is the "CMAP busy" one shown above, and it happened less than three hours after a previous crash and reboot. FreeBSD 2.1.0-RELEASE #0: Fri Apr 5 13:37:27 EST 1996 taob@cabal.io.org:/usr/local/src/sys/compile/WWW CPU: 133-MHz Pentium 735\\90 or 815\\100 (Pentium-class CPU) Origin = "GenuineIntel" Id = 0x52b Stepping=11 Features=0x1bf real memory = 134217728 (131072K bytes) avail memory = 130084864 (127036K bytes) Probing for devices on the ISA bus: vt0 at 0x60-0x6f irq 1 on motherboard vt0: unknown trident, 80 col, color, 8 scr, mf2-kbd, [R3.20-b24] sio0 at 0x3f8-0x3ff irq 4 on isa sio0: type 16550A sio1 at 0x2f8-0x2ff irq 3 on isa sio1: type 16550A fdc0 at 0x3f0-0x3f7 irq 6 drq 2 on isa fdc0: NEC 72065B fd0: 1.44MB 3.5in npx0 on motherboard npx0: INT 16 interface Probing for devices on the PCI bus: chip0 rev 2 on pci0:0 chip1 rev 2 on pci0:7 de0 rev 18 int a irq 12 on pci0:9 de0: DC21140 [10-100Mb/s] pass 1.2 Ethernet address 00:00:c0:39:41:c8 de0: enabling 10baseT UTP port ncr0 rev 2 int a irq 10 on pci0:11 ncr0 waiting for scsi devices to settle (ncr0:0:0): "SEAGATE ST51080N 0913" type 0 fixed SCSI 2 sd0(ncr0:0:0): Direct-Access sd0(ncr0:0:0): FAST SCSI-2 100ns (10 Mb/sec) offset 8. 1030MB (2109840 512 byte sectors) sd0(ncr0:0:0): with 4826 cyls, 4 heads, and an average 109 sectors/track (ncr0:1:0): "QUANTUM XP34301 1051" type 0 fixed SCSI 2 sd1(ncr0:1:0): Direct-Access sd1(ncr0:1:0): FAST SCSI-2 100ns (10 Mb/sec) offset 8. 4106MB (8410200 512 byte sectors) sd1(ncr0:1:0): with 4076 cyls, 20 heads, and an average 103 sectors/track (ncr0:2:0): "QUANTUM XP34301 1051" type 0 fixed SCSI 2 sd2(ncr0:2:0): Direct-Access sd2(ncr0:2:0): FAST SCSI-2 100ns (10 Mb/sec) offset 8. 4106MB (8410200 512 byte sectors) sd2(ncr0:2:0): with 4076 cyls, 20 heads, and an average 103 sectors/track (ncr0:4:0): "QUANTUM XP34301 1071" type 0 fixed SCSI 2 sd3(ncr0:4:0): Direct-Access sd3(ncr0:4:0): FAST SCSI-2 100ns (10 Mb/sec) offset 8. 4106MB (8410200 512 byte sectors) sd3(ncr0:4:0): with 4076 cyls, 20 heads, and an average 103 sectors/track vga0 rev 227 int a irq 11 on pci0:12 -- Brian Tao (BT300, taob@io.org) Systems and Network Administrator, Internex Online Inc. "Though this be madness, yet there is method in't"