[Bug 148807] [panic] 8.1-RELEASE panic: sbdrop and panic: sbsndptr: sockbuf _ and mbuf _ clashing under heavy load
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=148807 Hiren Panchasara hi...@freebsd.org changed: What|Removed |Added Version|8.1-RELEASE |10.1-STABLE CC||hi...@freebsd.org, ||nitrobo...@gmail.com --- Comment #15 from Hiren Panchasara hi...@freebsd.org --- We saw this panic on stable10 from Jan. Dump header from device /dev/da0s1b Architecture: amd64 Architecture Version: 2 Dump Length: 1050050560B (1001 MB) Blocksize: 512 Dumptime: Wed Mar 11 23:12:59 2015 Hostname: xx Magic: FreeBSD Kernel Dump Version String: FreeBSD 10.1-STABLE-llnw10 #0: Fri Jan 16 00:19:27 MST 2015 @xxx:/usr/obj/usr/src/sys/SIXFOUR Panic String: sbsndptr: sockbuf 0xf802d3e79440 and mbuf 0xf80238089b00 clashing Dump Parity: 747892521 Bounds: 0 Dump Status: good (kgdb) #0 doadump (textdump=1) at pcpu.h:219 #1 0x8072d397 in kern_reboot (howto=260) at /usr/src/sys/kern/kern_shutdown.c:452 #2 0x8072d774 in panic (fmt=value optimized out) at /usr/src/sys/kern/kern_shutdown.c:759 #3 0x807a38a0 in sbsndptr (sb=value optimized out, off=value optimized out, len=value optimized out, moff=value optimized out) at /usr/src/sys/kern/uipc_sockbuf.c:1011 #4 0x80895f1f in tcp_output (tp=0xf802d5315400) at /usr/src/sys/netinet/tcp_output.c:1092 #5 0x80891685 in tcp_do_segment (m=0xf80128e51d00, th=0xf8020ca95022, so=0xf802d3e792b8, tp=0xf802d5315400, drop_hdrlen=value optimized out, tlen=0, iptos=value optimized out, ti_locked=-1) at /usr/src/sys/netinet/tcp_input.c:2729 #6 0x8088f54d in tcp_input (m=value optimized out, off0=value optimized out) at /usr/src/sys/netinet/tcp_input.c:1388 #7 0x808216b7 in ip_input (m=0xf80128e51d00) at /usr/src/sys/netinet/ip_input.c:734 #8 0x807fbc92 in netisr_dispatch_src (proto=value optimized out, source=value optimized out, m=0x0) at /usr/src/sys/net/netisr.c:972 #9 0x807f4656 in ether_demux (ifp=value optimized out, m=0xf80128e51d00) at /usr/src/sys/net/if_ethersubr.c:851 #10 0x807f52e9 in ether_nh_input (m=value optimized out) at /usr/src/sys/net/if_ethersubr.c:646 #11 0x807fbc92 in netisr_dispatch_src (proto=value optimized out, source=value optimized out, m=0x0) at /usr/src/sys/net/netisr.c:972 #12 0x8042332b in em_rxeof (count=94) at /usr/src/sys/dev/e1000/if_em.c:4532 #13 0x80423703 in em_msix_rx (arg=0xf80003ce6600) at /usr/src/sys/dev/e1000/if_em.c:1600 #14 0x806fe0fb in intr_event_execute_handlers ( p=value optimized out, ie=0xf80003d04200) at /usr/src/sys/kern/kern_intr.c:1264 #15 0x806fea96 in ithread_loop (arg=0xf80003cfb3c0) at /usr/src/sys/kern/kern_intr.c:1277 #16 0x806fbd1a in fork_exit ( callout=0x806fea00 ithread_loop, arg=0xf80003cfb3c0, frame=0xfe03438d7c00) at /usr/src/sys/kern/kern_fork.c:1017 #17 0x80acdf5e in fork_trampoline () at /usr/src/sys/amd64/amd64/exception.S:611 #18 0x in ?? () Current language: auto; currently minimal (kgdb) Unfortunately I do not have a crashdump to investigate further. -- You are receiving this mail because: You are the assignee for the bug. ___ freebsd-net@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to freebsd-net-unsubscr...@freebsd.org
[Bug 138782] [panic] sbflush_internal: cc 0 || mb 0xffffff004127b000 || mbcnt 2304
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=138782 --- Comment #6 from Hiren Panchasara hi...@freebsd.org --- I could not figure out the root-cause but found an interesting fix that stops possible overflow in sockbuf which _may_ cause this. Discussion: https://lists.freebsd.org/pipermail/freebsd-arch/2015-February/016739.html Fix: https://svnweb.freebsd.org/changeset/base/278729 -- You are receiving this mail because: You are the assignee for the bug. ___ freebsd-net@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to freebsd-net-unsubscr...@freebsd.org
Re: Unremovable ARP entry and 'address already in use'
I just noticed that when obfuscating the IP, I added two dots. Please excuse them, the IP is proper (110.62.211.87 for the purposes of this thread) On 3/19/2015 午前 11:20, Paul S. wrote: Hi, Seeing this on 10.1-release p5. FreeBSD ipfw-0.syd.fqdn.tld 10.1-RELEASE-p5 FreeBSD 10.1-RELEASE-p5 #0 r278455: Mon Feb 9 07:18:21 UTC 2015 r...@ipfw-0.syd.fqdn.tld:/usr/obj/usr/src/sys/qfkern amd64 Basically, I have a static arp entry that I cannot remove. This in itself is not a problem. Problem is, when trying to assign that IP address to the same interface, it says the 'address is in use' (which it is not) ? (110.62..211.87) at 00:12:c0:88:03:8f on ix1 permanent [ethernet] Attempting to remove the entry produces an invalid argument error. root@ipfw-0:~ # arp -d 110.62..211.87 arp: writing to routing socket: Invalid argument ix1 does not have this IP configured anymore either. ix1: flags=8843UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST metric 0 mtu 1500 description: FW Upstream 0 options=8400bbRXCSUM,TXCSUM,VLAN_MTU,VLAN_HWTAGGING,JUMBO_MTU,VLAN_HWCSUM,VLAN_HWTSO ether 00:12:c0:88:03:8f inet6 fe80::212:c0ff:fe88:38f%ix1 prefixlen 64 scopeid 0x2 nd6 options=21PERFORMNUD,AUTO_LINKLOCAL media: Ethernet autoselect (10Gbase-LR full-duplex) status: active When I try to assign it back to ix1, I get this root@ipfw-0:~ # ifconfig ix1 inet 110.62..211.87 netmask 255.255.254.0 ifconfig: ioctl (SIOCAIFADDR): Address already in use I've verified with the provider that there isn't an arp entry at present for this IP address, so the issue seems local to freebsd. Anyone ever see anything like this? I'm aware rebooting will fix it, but this is a live firewall and I'd rather not do that. ___ freebsd-net@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to freebsd-net-unsubscr...@freebsd.org
Unremovable ARP entry and 'address already in use'
Hi, Seeing this on 10.1-release p5. FreeBSD ipfw-0.syd.fqdn.tld 10.1-RELEASE-p5 FreeBSD 10.1-RELEASE-p5 #0 r278455: Mon Feb 9 07:18:21 UTC 2015 r...@ipfw-0.syd.fqdn.tld:/usr/obj/usr/src/sys/qfkern amd64 Basically, I have a static arp entry that I cannot remove. This in itself is not a problem. Problem is, when trying to assign that IP address to the same interface, it says the 'address is in use' (which it is not) ? (110.62..211.87) at 00:12:c0:88:03:8f on ix1 permanent [ethernet] Attempting to remove the entry produces an invalid argument error. root@ipfw-0:~ # arp -d 110.62..211.87 arp: writing to routing socket: Invalid argument ix1 does not have this IP configured anymore either. ix1: flags=8843UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST metric 0 mtu 1500 description: FW Upstream 0 options=8400bbRXCSUM,TXCSUM,VLAN_MTU,VLAN_HWTAGGING,JUMBO_MTU,VLAN_HWCSUM,VLAN_HWTSO ether 00:12:c0:88:03:8f inet6 fe80::212:c0ff:fe88:38f%ix1 prefixlen 64 scopeid 0x2 nd6 options=21PERFORMNUD,AUTO_LINKLOCAL media: Ethernet autoselect (10Gbase-LR full-duplex) status: active When I try to assign it back to ix1, I get this root@ipfw-0:~ # ifconfig ix1 inet 110.62..211.87 netmask 255.255.254.0 ifconfig: ioctl (SIOCAIFADDR): Address already in use I've verified with the provider that there isn't an arp entry at present for this IP address, so the issue seems local to freebsd. Anyone ever see anything like this? I'm aware rebooting will fix it, but this is a live firewall and I'd rather not do that. ___ freebsd-net@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to freebsd-net-unsubscr...@freebsd.org
[Bug 148807] [panic] 8.1-RELEASE/10.1-STABLE panic: sbdrop and panic: sbsndptr: sockbuf _ and mbuf _ clashing
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=148807 Hiren Panchasara hi...@freebsd.org changed: What|Removed |Added Summary|[panic] 8.1-RELEASE panic: |[panic] |sbdrop and panic: |8.1-RELEASE/10.1-STABLE |sbsndptr: sockbuf _ and |panic: sbdrop and panic: |mbuf _ clashing under |sbsndptr: sockbuf _ and |heavy load |mbuf _ clashing -- You are receiving this mail because: You are the assignee for the bug. ___ freebsd-net@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to freebsd-net-unsubscr...@freebsd.org
Re: SIOCSVH, SIOCGVH ioctl(2) and virtio ethernet driver
On Tuesday 17 March 2015 15:25:09 Gleb Smirnoff wrote: On Mon, Mar 16, 2015 at 02:49:58AM +0300, Oleg Ginzburg wrote: O b) On FreeBSD-current r276500M CARP IP is established for some seconds, then vanishes: In my case on r280167, all works okay, despite the carp_alloc_if warning: #/sbin/ifconfig vtnet0 vhid 1 advskew 100 pass navuhodonosor 192.168.1.210/24 state master alias #dmesg | tail -n 3 carp_alloc_if: ifpromisc(vtnet0) failed: 45 carp: 1@vtnet0: INIT - BACKUP (initialization complete) carp: 1@vtnet0: BACKUP - MASTER (master timed out) Yes. On FreeBSD HEAD everything is good now (except carp_alloc_if warning message). Carp removal after seconds in my case was retated toh devd subsystem. ___ freebsd-net@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to freebsd-net-unsubscr...@freebsd.org
RFT: break out IPv4 fragment reassembly locking into per-bucket locks
Hi, I've created a review for this: https://reviews.freebsd.org/D2095 It does a couple things: * The IPv4 reassembly locking is now per-bucket, rather than global * If space needs to be made, it's made /after/ the reassembly queue manipulation is done. This way it's done without the queue lock held, rather than trying to grab a lock for bucket X whilst doing work in bucket Y. This dramatically reduces the lock contention when doing IPv4 fragment reassembly. I'd prefer this to be done along RSS bucket lines so there's /no/ lock contention during RSS based IPv4 fragment reassembly, but this is a good first step and applies even if RSS isn't being done. I'd appreciate any testing/reviews people may have. Thanks, -adrian ___ freebsd-net@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to freebsd-net-unsubscr...@freebsd.org