From owner-freebsd-stable Tue Jun 27 14:22:56 2000 Delivered-To: freebsd-stable@freebsd.org Received: from wat-border.sentex.ca (waterloo-hespler.sentex.ca [199.212.135.66]) by hub.freebsd.org (Postfix) with ESMTP id 62CA437C264; Tue, 27 Jun 2000 14:22:35 -0700 (PDT) (envelope-from mike@sentex.net) Received: from granite.sentex.net (granite-atm.sentex.ca [209.112.4.1]) by wat-border.sentex.ca (8.9.3/8.9.3) with ESMTP id RAA08845; Tue, 27 Jun 2000 17:22:33 -0400 (EDT) (envelope-from mike@sentex.net) Received: from simoeon (simeon.sentex.ca [209.112.4.47]) by granite.sentex.net (8.8.8/8.6.9) with SMTP id RAA01491; Tue, 27 Jun 2000 17:22:32 -0400 (EDT) Message-Id: <3.0.5.32.20000627171840.031b45f0@marble.sentex.ca> X-Sender: mdtpop@marble.sentex.ca X-Mailer: QUALCOMM Windows Eudora Light Version 3.0.5 (32) Date: Tue, 27 Jun 2000 17:18:40 -0400 To: questions@freebsd.org From: Mike Tancsa Subject: Strange FreeBSD 4.x network problems with SQUID Cc: stable@freebsd.org Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG Hello, I am just starting to play with Squid 2.3 on a box with 512M of RAM, (configured for 256 users in the kernel with no other special tweaks). I notice that after a few hrs, the server becomes extremely 'jerky' in that my ssh session freezes (same results when physically on the console) for a good 5-10 seconds where I have a quick window to kill squid. Once it is dead, all comes back to normal until again soon after it becomes rather sluggish. It seems some resource is being starved or over loaded some how, but I am not sure where to look beyond the obvious places. I had a look at the FreeBSD related threads on the squid list and didnt see anything obviously related to my situation. I did read http://www.squid-cache.org/Doc/FAQ/FAQ-9.html#paging which talks about paging and the "'memory_pools off'" off issue and FreeBSD. I have tried setting it to 'memory_pools off' to see if it makes a difference... Dont know yet. One thing I found in the archives that *might* be related is KERN/19479, but thats a different version of SQUID on 3.x. 4.0-STABLE FreeBSD 4.0-STABLE #1: Tue Jun 27 15:32:46 EDT 2000 Here is a snapshot of various stats when the problem begins. UID PID PPID CPU PRI NI VSZ RSS WCHAN STAT TT TIME COMMAND 0 0 0 0 -18 0 0 0 sched DLs ?? 0:00.01 (swapper) 0 1 0 0 10 0 524 208 wait ILs ?? 0:00.01 /sbin/init - 0 2 0 0 -18 0 0 0 psleep DL ?? 0:00.74 (pagedaemon 0 3 0 0 18 0 0 0 psleep DL ?? 0:00.00 (vmdaemon) 0 4 0 0 -18 0 0 0 psleep DL ?? 0:00.12 (bufdaemon) 0 5 0 2 18 0 0 0 syncer DL ?? 6:59.12 (syncer) 0 32 1 0 18 0 208 64 pause Is ?? 0:00.00 adjkerntz -i 0 107 1 0 2 0 900 560 select Ss ?? 0:04.52 syslogd -s 1 110 1 0 2 0 888 428 select Is ?? 0:00.00 /usr/sbin/po 0 130 1 0 2 0 1024 684 select Is ?? 0:00.01 inetd -wWl 0 132 1 1 10 0 940 632 nanslp Ss ?? 0:00.10 cron 0 135 1 0 2 0 1408 968 select Ss ?? 0:00.23 sendmail: ac 0 139 1 0 2 0 1948 1068 select Is ?? 0:01.01 /usr/sbin/ss 0 276 139 0 2 0 2048 1288 select I ?? 0:00.54 sshd: mdtanc 0 556 130 4 2 0 1988 1192 select Is ?? 0:00.05 telnetd 65533 581 192 149 46 0 66368 65620 - R ?? 0:30.62 squid -NsY 65533 582 581 2 -6 0 816 304 piperd Is ?? 0:00.00 (unlinkd) (u 0 559 556 4 3 0 1020 564 ttyin Is+ p0 0:00.02 login -h gra 1001 277 276 0 18 0 1612 1260 pause Is p1 0:00.09 -tcsh (tcsh) 0 283 277 2 3 0 1628 1256 ttyin I+ p1 0:00.13 _su (tcsh) 0 200 1 2 3 0 1644 1260 ttyin Is+ v0 0:00.14 -tcsh (tcsh) 0 201 1 0 18 0 1644 1252 pause Ss v1 0:00.13 -tcsh (tcsh) 0 591 201 1 28 0 416 244 - R+ v1 0:00.00 ps -axl 0 202 1 0 3 0 904 536 ttyin Is+ v2 0:00.01 /usr/libexec 0 203 1 0 3 0 904 536 ttyin Is+ v3 0:00.01 /usr/libexec 0 204 1 0 3 0 904 536 ttyin Is+ v4 0:00.01 /usr/libexec 0 205 1 0 3 0 904 536 ttyin Is+ v5 0:00.01 /usr/libexec 0 206 1 0 3 0 904 536 ttyin Is+ v6 0:00.01 /usr/libexec 0 207 1 0 3 0 904 536 ttyin Is+ v7 0:00.01 /usr/libexec 0 186 1 0 2 0 2280 1344 select I con- 0:00.12 /usr/local/s 0 192 1 0 10 0 624 224 wait I con- 0:00.01 /bin/sh /usr Memory statistics by bucket size Size In Use Free Requests HighWater Couldfree 16 670 1634 3524520 0 1280 32 384 0 319717 0 640 64 1945 103 972923 0 320 128 1179 5 3717 0 160 256 47155 93 314216 0 80 512 646 2818 1906029 0 40 1K 376 44 3340 0 20 2K 22 6 100 0 10 4K 17 1 48 0 5 8K 4 1 6 0 5 16K 8 0 8 0 5 32K 2 0 2 0 5 64K 2 0 2 0 5 128K 3 0 3 0 5 256K 2 0 2 0 5 Memory usage type by bucket size Size Type(s) 16 kld, proc-args, atexit, temp, sysctl, bus, rman, soname, pcb, mount, vnodes, ether_multi, routetbl, IpFw/IpAcct, Ip6Fw/Ip6Acct, key mgmt, p1003.1b, devbuf, isa_devlist 32 kld, sigio, proc-args, temp, ip6ndp, pgrp, proc, subproc, sysctl, bus, eventhandler, SWAP, soname, pcb, cluster_save buffer, vnodes, BPF, ifaddr, ether_multi, routetbl, in_multi, tseg_qent, devbuf, atkbddev 64 file, proc-args, lockf, temp, session, subproc, bus, eventhandler, rman, pcb, vfscache, cluster_save buffer, vnodes, ifaddr, ether_multi, routetbl, in6_multi, isadev, devbuf 128 ppbusdev, kld, timecounter, dev_t, proc-args, zombie, temp, cred, bus, ttys, soname, vfscache, cluster_save buffer, mount, vnodes, ifaddr, routetbl, ZONE, devbuf 256 file desc, proc-args, temp, subproc, bus, ttys, vnodes, ifaddr, routetbl, IpFw/IpAcct, Ip6Fw/Ip6Acct, NFS daemon, FFS node, devbuf 512 file desc, temp, ip6ndp, proc, bus, ioctlops, ptys, BIO buffer, mount, ifaddr, key mgmt, UFS mount, devbuf, isa_devlist 1K file desc, temp, bus, ioctlops, BIO buffer, NQNFS Lease, devbuf, isa_devlist 2K proc, bus, pcb, BIO buffer, UFS mount, devbuf 4K temp, bus, UFS mount, devbuf, memdesc 8K temp, shm, UFS mount, devbuf, mbuf 16K devbuf 32K devbuf 64K temp, UFS mount 128K NFS hash, UFS ihash, VM pgdata 256K SWAP, vfscache Memory statistics by type Type Kern Type InUse MemUse HighUse Limit Requests Limit Limit Size(s) ppbusdev 3 1K 1K 85720K 3 0 0 128 kld 7 1K 1K 85720K 40 0 0 16,32,128 timecounter 10 2K 2K 85720K 10 0 0 128 dev_t 529 67K 67K 85720K 529 0 0 128 file desc 33 9K 11K 85720K 607 0 0 256,512,1K file 74 5K 13K 85720K 957849 0 0 64 sigio 1 1K 1K 85720K 1 0 0 32 proc-args 27 1K 2K 85720K 1082 0 0 16,32,64,128,256 zombie 0 0K 1K 85720K 570 0 0 128 atexit 1 1K 1K 85720K 1 0 0 16 lockf 1 1K 1K 85720K 1187 0 0 64 temp 228 72K 85K 85720K 1512 0 0 16,32,64,128,256,512,1K,4K,8K,64K ip6ndp 1 1K 1K 85720K 3 0 0 32,512 pgrp 24 1K 1K 85720K 175 0 0 32 session 21 2K 2K 85720K 88 0 0 64 proc 7 5K 5K 85720K 8 0 0 32,512,2K subproc 77 7K 8K 85720K 1286 0 0 32,64,256 cred 15 2K 2K 85720K 244 0 0 128 sysctl 0 0K 1K 85720K 95 0 0 16,32 bus 327 34K 34K 85720K 445 0 0 16,32,64,128,256,512,1K,2K,4K eventhandler 13 1K 1K 85720K 13 0 0 32,64 SWAP 2 173K 173K 85720K 2 0 0 32,256K ioctlops 0 0K 1K 85720K 16 0 0 512,1K rman 56 4K 4K 85720K 94 0 0 16,64 shm 1 8K 8K 85720K 1 0 0 8K ttys 488 63K 63K 85720K 1268 0 0 128,256 ptys 3 2K 2K 85720K 3 0 0 512 soname 1 1K 1K 85720K 2577225 0 0 16,32,128 pcb 18 9K 10K 85720K 313413 0 0 16,32,64,2K BIO buffer 12 14K 71K 85720K 2611 0 0 512,1K,2K vfscache 1552 353K 353K 85720K 10524 0 0 64,128,256K cluster_save buffer 0 0K 1K 85720K 3739 0 0 32,64,128 mount 6 3K 3K 85720K 8 0 0 16,128,512 vnodes 20 5K 5K 85720K 249 0 0 16,32,64,128,256 BPF 12 1K 1K 85720K 12 0 0 32 ifaddr 54 13K 13K 85720K 54 0 0 32,64,128,256,512 ether_multi 56 3K 3K 85720K 56 0 0 16,32,64 routetbl 215 31K 35K 85720K 405 0 0 16,32,64,128,256 in_multi 3 1K 1K 85720K 3 0 0 32 IpFw/IpAcct 14 2K 2K 85720K 14 0 0 16,256 tseg_qent 0 0K 1K 85720K 316300 0 0 32 in6_multi 16 1K 1K 85720K 16 0 0 64 Ip6Fw/Ip6Acct 2 1K 1K 85720K 2 0 0 16,256 key mgmt 903 306K 1735K 85720K 2538775 0 0 16,512 NFS daemon 1 1K 1K 85720K 1 0 0 256 NQNFS Lease 1 1K 1K 85720K 1 0 0 1K NFS hash 1 128K 128K 85720K 1 0 0 128K p1003.1b 1 1K 1K 85720K 1 0 0 16 FFS node 46911 11728K 11744K 85720K 312993 0 0 256 UFS ihash 1 128K 128K 85720K 1 0 0 128K UFS mount 15 81K 81K 85720K 15 0 0 512,2K,4K,8K,64K VM pgdata 1 128K 128K 85720K 1 0 0 128K ZONE 20 3K 3K 85720K 20 0 0 128 isadev 13 1K 1K 85720K 13 0 0 64 devbuf 614 644K 644K 85720K 1025 0 0 16,32,64,128,256,512,1K,2K,4K,8K,16K,32K mbuf 1 8K 8K 85720K 1 0 0 8K memdesc 1 4K 4K 85720K 1 0 0 4K isa_devlist 0 0K 2K 85720K 19 0 0 16,512,1K atkbddev 2 1K 1K 85720K 2 0 0 32 Memory Totals: In Use Free Requests 14040K 1533K 7044633 699/2128/14592 mbufs in use (current/peak/max): 192 mbufs allocated to data 507 mbufs allocated to packet headers 150/356/3648 mbuf clusters in use (current/peak/max) 1244 Kbytes allocated to network (38% in use) proxy1# netstat -na | wc 1422 8539 109275 proxy1# In terms of active connections, they are all generally of this variety Active Internet connections (including servers) Proto Recv-Q Send-Q Local Address Foreign Address (state) tcp4 0 0 192.168.1.243.3128 192.168.1.242.3787 TIME_WAIT tcp4 0 0 192.168.1.243.3128 192.168.1.242.3786 TIME_WAIT tcp4 0 0 192.168.1.243.3128 192.168.1.242.3785 TIME_WAIT tcp4 0 0 192.168.1.243.3128 192.168.1.242.3784 TIME_WAIT tcp4 0 0 192.168.1.243.3128 192.168.1.242.3783 TIME_WAIT tcp4 0 0 192.168.1.243.3128 192.168.1.242.3782 TIME_WAIT tcp4 0 0 192.168.1.243.3128 192.168.1.242.3781 TIME_WAIT tcp4 0 0 192.168.1.243.3128 192.168.1.242.3780 TIME_WAIT proxy1# df Filesystem 1K-blocks Used Avail Capacity Mounted on /dev/da0s1a 198399 29795 152733 16% / /dev/da0s1f 5931961 2240905 3216500 41% /usr /dev/da0s1e 1984479 28252 1797469 2% /var /dev/twed0e 77576569 5154208 66216236 7% /usr/local/squid/cache /dev/da2e 8695079 518685 7480788 6% /usr/local/squid/cache2 procfs 4 4 0 100% /proc Copyright (c) 1992-2000 The FreeBSD Project. Copyright (c) 1982, 1986, 1989, 1991, 1993 The Regents of the University of California. All rights reserved. FreeBSD 4.0-STABLE #1: Tue Jun 27 15:32:46 EDT 2000 mdtancsa@proxy1.sentex.ca:/usr/src/sys/compile/proxy1 Timecounter "i8254" frequency 1193182 Hz Timecounter "TSC" frequency 467728506 Hz CPU: Pentium II/Pentium II Xeon/Celeron (467.73-MHz 686-class CPU) Origin = "GenuineIntel" Id = 0x665 Stepping = 5 Features=0x183f9ff real memory = 536805376 (524224K bytes) config> q avail memory = 518565888 (506412K bytes) Preloaded elf kernel "kernel" at 0xc032b000. Preloaded userconfig_script "/boot/kernel.conf" at 0xc032b09c. Preloaded elf module "twe.ko" at 0xc032b0ec. Pentium Pro MTRR support enabled npx0: on motherboard npx0: INT 16 interface pcib0: on motherboard pci0: on pcib0 pcib1: at device 1.0 on pci0 pci1: on pcib1 pci1: at 0.0 isab0: at device 7.0 on pci0 isa0: on isab0 atapci0: port 0xf000-0xf00f at device 7.1 on pci0 pci0: at 7.2 irq 11 chip1: port 0x5000-0x500f at device 7.3 on pci0 ahc0: port 0xd400-0xd4ff mem 0xec200000-0xec200fff irq 10 at device 9.0 on pci0 ahc0: aic7880 Wide Channel A, SCSI Id=7, 16/255 SCBs fxp0: port 0xd800-0xd83f mem 0xec000000-0xec0fffff,0xec201000-0xec201fff irq 12 at device 10. 0 on pci0 fxp0: Ethernet address 00:d0:b7:27:55:43 fxp0: supplying EUI64: 00:d0:b7:ff:fe:27:55:43 fxp1: port 0xdc00-0xdc3f mem 0xec100000-0xec1fffff,0xec202000-0xec202fff irq 9 at device 11.0 on pci0 fxp1: Ethernet address 00:d0:b7:23:66:76 twe0: <3ware Storage Controller> port 0xe000-0xe00f irq 11 at device 12.0 on pci0 fdc0: at port 0x3f0-0x3f5,0x3f7 irq 6 drq 2 on isa0 fdc0: FIFO enabled, 8 bytes threshold fd0: <1440-KB 3.5" drive> on fdc0 drive 0 atkbdc0: at port 0x60,0x64 on isa0 atkbd0: irq 1 on atkbdc0 vga0: at port 0x3c0-0x3df iomem 0xa0000-0xbffff on isa0 sc0: on isa0 sc0: VGA <16 virtual consoles, flags=0x200> sio0 at port 0x3f8-0x3ff irq 4 flags 0x10 on isa0 sio0: type 16550A sio1 at port 0x2f8-0x2ff irq 3 on isa0 sio1: type 16550A ppc0: at port 0x278-0x27f irq 5 on isa0 ppc0: Generic chipset (NIBBLE-only) in COMPATIBLE mode plip0: on ppbus0 lpt0: on ppbus0 lpt0: Interrupt-driven port ppi0: on ppbus0 sio4 at port 0x100-0x107 flags 0x404 on isa0 sio4: type 8250 sio5 at port 0x108-0x10f flags 0x404 on isa0 sio5: type 8250 sio6 at port 0x110-0x117 flags 0x404 on isa0 sio6: type 8250 sio7 at port 0x118-0x11f irq 7 flags 0x404 on isa0 sio7: type 8250 IP packet filtering initialized, divert disabled, rule-based forwarding enabled, default to deny, logging limited to 20100 pack ets/entry by default IPv6 packet filtering initialized, logging limited to 100 packets/entry IPsec: Initialized Security Association Processing. Waiting 5 seconds for SCSI devices to settle twed0: <3ware RAID unit> on twe0 twed0: 78163MB (160078336 sectors) RAID 255 (unknown) Mounting root from ufs:/dev/da0s1a da0 at ahc0 bus 0 target 0 lun 0 da0: Fixed Direct Access SCSI-3 device da0: 40.000MB/s transfers (20.000MHz, offset 8, 16bit), Tagged Queueing Enabled da0: 8761MB (17942584 512 byte sectors: 255H 63S/T 1116C) da2 at ahc0 bus 0 target 8 lun 0 da2: Fixed Direct Access SCSI-3 device da2: 40.000MB/s transfers (20.000MHz, offset 8, 16bit), Tagged Queueing Enabled da2: 8761MB (17942584 512 byte sectors: 255H 63S/T 1116C) da1 at ahc0 bus 0 target 4 lun 0 da1: Fixed Direct Access SCSI-2 device da1: 40.000MB/s transfers (20.000MHz, offset 8, 16bit), Tagged Queueing Enabled da1: 8709MB (17836668 512 byte sectors: 255H 63S/T 1110C) fxp0: starting DAD for fe80:0001::02d0:b7ff:fe27:5543 fxp1: starting DAD for fe80:0002::02d0:b7ff:fe23:6676 Any pointers on how to track down this issue or work around it ? Thanks, ---Mike ------------------------------------------------------------------------ Mike Tancsa, tel +1 519 651 3400 Sentex Communications mike@sentex.net Cambridge, Ontario Canada www.sentex.net To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message