Bruce's orginal e-mail:
On the receiver, execute the DCCP-augmented ttcp:
       ttcp -c -r
On the sender execute
       ttcp -c  -n5000000 -l1 -t receiver

The receiver crashes, requiring a kernel reboot.

the -l1 isn't required, but I found it using -l50.
The -l1 ought to  be an extreme case.

Subsequent e-mail:
On 26/10/05, Bruce Barnett <[EMAIL PROTECTED]> wrote:
> >>
> > Are you running the latest version of code?
>
>
> I got the code from yesterday's snapshot of Torvalds's branch. (Oct 24 14:47 
> EST)
>
>
> > Can you provide a crash dump please - see
>
>
> Well, technically the kernel didn't crash. It froze. I could ping the system, 
> but nothing else.
>
> > Documentation/oops-tracing.txt on where you might find this.
>
>
> Here's all of the DCCP/kernel info from /var/log/messages for the last crash.
>
>
> Oct 25 09:27:17 localhost kernel: CCID: Registered CCID 3 (ccid3)
> Oct 25 09:27:37 localhost kernel: ccid3_hc_tx_packet_recv: r_sample=185us, 
> t_elapsed=2920us
> Oct 25 09:27:37 localhost kernel: ccid3_hc_tx_packet_recv: r_sample=181us, 
> t_elapsed=2450us
> Oct 25 09:27:37 localhost kernel: ccid3_hc_tx_packet_recv: r_sample=173us, 
> t_elapsed=2140us
> Oct 25 09:27:37 localhost kernel: ccid3_hc_tx_packet_recv: server, 
> sk=f5a79040, seqno 7814857844(DATAACK) does't exist in history!
> Oct 25 09:27:37 localhost kernel: ccid3_hc_tx_packet_recv: server, 
> sk=f5a79040, seqno 7814857845(DATAACK) does't exist in history!
> Oct 25 09:27:37 localhost kernel: ccid3_hc_tx_packet_recv: server, 
> sk=f5a79040, seqno 7814857846(DATAACK) does't exist in history!
> Oct 25 09:27:37 localhost kernel: ccid3_hc_tx_packet_recv: server, 
> sk=f5a79040, seqno 7814857847(DATAACK) does't exist in history!
> Oct 25 09:27:37 localhost kernel: ccid3_hc_tx_packet_recv: server, 
> sk=f5a79040, seqno 7814857848(DATAACK) does't exist in history!
> Oct 25 09:27:37 localhost kernel: ccid3_hc_tx_packet_recv: server, 
> sk=f5a79040, seqno 7814857849(DATAACK) does't exist in history!
> Oct 25 09:27:38 localhost kernel: ccid3_hc_tx_packet_recv: server, 
> sk=f5a79040, seqno 7814857850(DATAACK) does't exist in history!
> Oct 25 09:27:42 localhost kernel: printk: 99 messages suppressed.
> Oct 25 09:27:42 localhost kernel: ccid3_hc_tx_packet_recv: r_sample=183us, 
> t_elapsed=18100us
> Oct 25 09:27:47 localhost kernel: printk: 240 messages suppressed.
> Oct 25 09:27:47 localhost kernel: ccid3_hc_tx_packet_recv: r_sample=195us, 
> t_elapsed=2200us
> Oct 25 09:27:52 localhost kernel: printk: 51 messages suppressed.
> Oct 25 09:27:52 localhost kernel: ccid3_hc_tx_packet_recv: server, 
> sk=f5a79040, seqno 7814858403(DATAACK) does't exist in history!
> Oct 25 09:27:58 localhost kernel: printk: 27 messages suppressed.
> Oct 25 09:27:58 localhost kernel: ccid3_hc_tx_packet_recv: r_sample=185us, 
> t_elapsed=2200us
> Oct 25 09:28:02 localhost kernel: printk: 132 messages suppressed.
> Oct 25 09:28:02 localhost kernel: ccid3_hc_tx_packet_recv: r_sample=185us, 
> t_elapsed=18100us
> Oct 25 09:28:07 localhost kernel: printk: 246 messages suppressed.
> Oct 25 09:28:07 localhost kernel: ccid3_hc_tx_packet_recv: r_sample=196us, 
> t_elapsed=2160us
> Oct 25 09:36:37 localhost kernel: printk: 142 messages suppressed.
> Oct 25 09:36:37 localhost kernel: ttcp-dccp: page allocation failure. 
> order:0, mode:0x20
> Oct 25 09:36:37 localhost kernel:  [<c013edbb>] __alloc_pages+0x35b/0x403
> Oct 25 09:36:37 localhost kernel:  [<c0141689>] kmem_getpages+0x2a/0x77
> Oct 25 09:36:37 localhost kernel:  [<c0142311>] cache_grow+0xab/0x155
> Oct 25 09:36:37 localhost kernel:  [<c014256b>] cache_alloc_refill+0x1b0/0x1e5
> Oct 25 09:36:37 localhost kernel:  [<c0142830>] __kmalloc+0x78/0x7a
> Oct 25 09:36:37 localhost kernel:  [<c029bac3>] __alloc_skb+0x45/0x114
> Oct 25 09:36:37 localhost kernel:  [<f8903a6e>] tg3_rx+0x1a3/0x3c5 [tg3]
> Oct 25 09:36:37 localhost kernel:  [<f8903ce7>] tg3_poll+0x57/0x14b [tg3]
> Oct 25 09:36:37 localhost kernel:  [<c02a13f7>] net_rx_action+0x71/0x13e
> Oct 25 09:36:37 localhost kernel:  [<c01201fe>] __do_softirq+0x3e/0x8a
> Oct 25 09:36:37 localhost kernel:  [<c0104350>] do_softirq+0x39/0x40
> Oct 25 09:36:37 localhost kernel:  =======================
> Oct 25 09:36:37 localhost kernel:  [<c01202b7>] local_bh_enable+0x6d/0x6f
> Oct 25 09:36:37 localhost kernel:  [<c02fef38>] _spin_unlock_bh+0x5/0xa
> Oct 25 09:36:37 localhost kernel:  [<f8ac92d3>] dccp_recvmsg+0x15d/0x251 
> [dccp]
> Oct 25 09:36:37 localhost kernel:  [<c029b170>] sock_common_recvmsg+0x3e/0x54
> Oct 25 09:36:38 localhost kernel:  [<c0297ac0>] sock_aio_read+0x123/0x127
> Oct 25 09:36:38 localhost kernel:  [<c01af325>] inode_has_perm+0x39/0x81
> Oct 25 09:36:38 localhost kernel:  [<c010423f>] do_IRQ+0x53/0x85
> Oct 25 09:36:38 localhost kernel:  [<c0156616>] do_sync_read+0xbf/0x11a
> Oct 25 09:36:38 localhost kernel:  [<c01b10ed>] 
> selinux_file_permission+0xee/0x137
> Oct 25 09:36:38 localhost kernel:  [<c012da9b>] 
> autoremove_wake_function+0x0/0x37
> Oct 25 09:36:38 localhost kernel:  [<c01567be>] vfs_read+0x14d/0x152
> Oct 25 09:36:38 localhost kernel:  [<c0156a72>] sys_read+0x41/0x6a
> Oct 25 09:36:38 localhost kernel:  [<c0102cb7>] sysenter_past_esp+0x54/0x75
> Oct 25 09:36:38 localhost kernel: Mem-info:
> Oct 25 09:36:38 localhost kernel: DMA per-cpu:
> Oct 25 09:36:38 localhost kernel: cpu 0 hot: low 2, high 6, batch 1 used:2
> Oct 25 09:36:38 localhost kernel: cpu 0 cold: low 0, high 2, batch 1 used:0
> Oct 25 09:36:38 localhost kernel: Normal per-cpu:
> Oct 25 09:36:38 localhost kernel: cpu 0 hot: low 62, high 186, batch 31 
> used:92
> Oct 25 09:36:38 localhost kernel: cpu 0 cold: low 0, high 62, batch 31 used:52
> Oct 25 09:36:38 localhost kernel: HighMem per-cpu:
> Oct 25 09:36:38 localhost kernel: cpu 0 hot: low 62, high 186, batch 31 
> used:81
> Oct 25 09:36:38 localhost kernel: cpu 0 cold: low 0, high 62, batch 31 used:10
> Oct 25 09:36:38 localhost kernel: Free pages:      911884kB (906936kB HighMem)
> Oct 25 09:36:38 localhost kernel: Active:34372 inactive:37245 dirty:10 
> writeback:0 unstable:0 free:227971 slab:214583 mapped:23421 pagetables:416
> Oct 25 09:36:38 localhost kernel: DMA free:3548kB min:68kB low:84kB 
> high:100kB active:0kB inactive:0kB present:16384kB pages_scanned:0 
> all_unreclaimable? yes
> Oct 25 09:36:38 localhost kernel: lowmem_reserve[]: 0 880 2031
> Oct 25 09:36:38 localhost kernel: Normal free:1400kB min:3756kB low:4692kB 
> high:5632kB active:10816kB inactive:8972kB present:901120kB pages_scanned:66 
> all_unreclaimable? no
> Oct 25 09:36:38 localhost kernel: lowmem_reserve[]: 0 0 9213
> Oct 25 09:36:38 localhost kernel: HighMem free:906936kB min:512kB low:640kB 
> high:768kB active:126672kB inactive:140008kB present:1179320kB 
> pages_scanned:0 all_unreclaimable? no
> Oct 25 09:36:38 localhost kernel: lowmem_reserve[]: 0 0 0
> Oct 25 09:36:38 localhost kernel: DMA: 1*4kB 1*8kB 1*16kB 0*32kB 1*64kB 
> 1*128kB 1*256kB 0*512kB 1*1024kB 1*2048kB 0*4096kB = 3548kB
> Oct 25 09:36:38 localhost kernel: Normal: 0*4kB 1*8kB 1*16kB 1*32kB 1*64kB 
> 0*128kB 1*256kB 0*512kB 1*1024kB 0*2048kB 0*4096kB = 1400kB
> Oct 25 09:36:38 localhost kernel: HighMem: 0*4kB 13*8kB 75*16kB 67*32kB 
> 55*64kB 27*128kB 10*256kB 2*512kB 0*1024kB 0*2048kB 218*4096kB = 906936kB
> Oct 25 09:36:38 localhost kernel: Swap cache: add 0, delete 0, find 0/0, race 
> 0+0
> Oct 25 09:36:38 localhost kernel: Free swap  = 2031608kB
> Oct 25 09:36:38 localhost kernel: Total swap = 2031608kB
> Oct 25 09:36:38 localhost kernel: Free swap:       2031608kB
> Oct 25 09:36:38 localhost kernel: 524206 pages of RAM
> Oct 25 09:36:38 localhost kernel: 294830 pages of HIGHMEM
> Oct 25 09:36:38 localhost kernel: 5304 reserved pages
> Oct 25 09:36:38 localhost kernel: 39595 pages shared
> Oct 25 09:36:38 localhost kernel: 0 pages swap cached
> Oct 25 09:36:38 localhost kernel: 10 pages dirty
> Oct 25 09:36:38 localhost kernel: 0 pages writeback
> Oct 25 09:36:38 localhost kernel: 23421 pages mapped
> Oct 25 09:36:38 localhost kernel: 214583 pages slab
> Oct 25 09:36:38 localhost kernel: 416 pages pagetables
> Oct 25 09:36:38 localhost kernel: ttcp-dccp: page allocation failure. 
> order:0, mode:0x20
> Oct 25 09:36:38 localhost kernel:  [<c013edbb>] __alloc_pages+0x35b/0x403
> Oct 25 09:36:38 localhost kernel:  [<c0141689>] kmem_getpages+0x2a/0x77
> Oct 25 09:36:38 localhost kernel:  [<c0142311>] cache_grow+0xab/0x155
> Oct 25 09:36:38 localhost kernel:  [<c010423f>] do_IRQ+0x53/0x85
> Oct 25 09:36:38 localhost kernel:  [<c014256b>] cache_alloc_refill+0x1b0/0x1e5
> Oct 25 09:36:38 localhost kernel:  [<c0142830>] __kmalloc+0x78/0x7a
> Oct 25 09:36:39 localhost kernel:  [<c029bac3>] __alloc_skb+0x45/0x114
> Oct 25 09:36:39 localhost kernel:  [<f8903a6e>] tg3_rx+0x1a3/0x3c5 [tg3]
> Oct 25 09:40:08 localhost syslogd 1.4.1: restart.
> Oct 25 09:40:08 localhost syslog: syslogd startup succeeded
> Oct 25 09:40:08 localhost kernel: klogd 1.4.1, log source = /proc/kmsg 
> started.
> Oct 25 09:40:08 localhost kernel: Linux version 2.6.14-rc5DCCP-g10ded949 
> ([EMAIL PROTECTED]) (gcc version 3.4.3 20050227 (Red Hat 3.4.3-22.fc3)) #2 
> Mon Oct 24 18:05:40 EDT 2005
>
>
> --- Hmm. The last time I ran it without X windows. The time before that I had 
> gnome running. It said something similar, except instead of giving the page 
> allocaiton fault on ttcp-dccp, it did it on gnome-terminal.
>
>
>
> Oct 25 09:14:48 localhost kernel: CCID: Registered CCID 3 (ccid3)
> Oct 25 09:16:56 localhost kernel: gnome-terminal: page allocation failure. 
> order:0, mode:0x20
> Oct 25 09:16:56 localhost kernel:  [<c013edbb>] __alloc_pages+0x35b/0x403
> Oct 25 09:16:56 localhost kernel:  [<c0141689>] kmem_getpages+0x2a/0x77
> Oct 25 09:16:56 localhost kernel:  [<c0142311>] cache_grow+0xab/0x155
> Oct 25 09:16:56 localhost kernel:  [<c014256b>] cache_alloc_refill+0x1b0/0x1e5
> Oct 25 09:16:56 localhost kernel:  [<c0142830>] __kmalloc+0x78/0x7a
> Oct 25 09:16:56 localhost kernel:  [<c029bac3>] __alloc_skb+0x45/0x114
> Oct 25 09:16:56 localhost kernel:  [<c0124983>] 
> check_kill_permission+0x51/0xcb
> Oct 25 09:16:56 localhost kernel:  [<f8903a6e>] tg3_rx+0x1a3/0x3c5 [tg3]
> Oct 25 09:16:56 localhost kernel:  [<f8903ce7>] tg3_poll+0x57/0x14b [tg3]
> Oct 25 09:16:56 localhost kernel:  [<c02a13f7>] net_rx_action+0x71/0x13e
> Oct 25 09:16:57 localhost kernel:  [<c01201fe>] __do_softirq+0x3e/0x8a
> Oct 25 09:16:57 localhost kernel:  [<c0104350>] do_softirq+0x39/0x40
> Oct 25 09:16:57 localhost kernel:  =======================
> Oct 25 09:16:57 localhost kernel:  [<c010423f>] do_IRQ+0x53/0x85
> Oct 25 09:16:57 localhost kernel:  [<c0102ede>] common_interrupt+0x1a/0x20
> Oct 25 09:16:57 localhost kernel: Mem-info:
> Oct 25 09:16:57 localhost kernel: DMA per-cpu:
> Oct 25 09:16:57 localhost kernel: cpu 0 hot: low 2, high 6, batch 1 used:2
> Oct 25 09:16:57 localhost kernel: cpu 0 cold: low 0, high 2, batch 1 used:0
> Oct 25 09:16:57 localhost kernel: Normal per-cpu:
> Oct 25 09:16:57 localhost kernel: cpu 0 hot: low 62, high 186, batch 31 
> used:92
> Oct 25 09:16:57 localhost kernel: cpu 0 cold: low 0, high 62, batch 31 used:39
> Oct 25 09:16:57 localhost kernel: HighMem per-cpu:
> Oct 25 09:16:57 localhost kernel: cpu 0 hot: low 62, high 186, batch 31 
> used:84
> Oct 25 09:16:57 localhost kernel: cpu 0 cold: low 0, high 62, batch 31 used:30
> Oct 25 09:16:57 localhost kernel: Free pages:      930972kB (926032kB HighMem)
> Oct 25 09:16:57 localhost kernel: Active:30054 inactive:35507 dirty:14 
> writeback:0 unstable:0 free:232743 slab:215831 mapped:23195 pagetables:429
> Oct 25 09:16:57 localhost kernel: DMA free:3548kB min:68kB low:84kB 
> high:100kB active:0kB inactive:0kB present:16384kB pages_scanned:0 
> all_unreclaimable? yes
> Oct 25 09:16:57 localhost kernel: lowmem_reserve[]: 0 880 2031
> Oct 25 09:16:57 localhost kernel: Normal free:1392kB min:3756kB low:4692kB 
> high:5632kB active:6452kB inactive:8384kB present:901120kB pages_scanned:33 
> all_unreclaimable? no
> Oct 25 09:16:57 localhost kernel: lowmem_reserve[]: 0 0 9213
> Oct 25 09:16:57 localhost kernel: HighMem free:926032kB min:512kB low:640kB 
> high:768kB active:113764kB inactive:133644kB present:1179320kB 
> pages_scanned:0 all_unreclaimable? no
> Oct 25 09:16:57 localhost kernel: lowmem_reserve[]: 0 0 0
> Oct 25 09:16:57 localhost kernel: DMA: 1*4kB 1*8kB 1*16kB 0*32kB 1*64kB 
> 1*128kB 1*256kB 0*512kB 1*1024kB 1*2048kB 0*4096kB = 3548kB
> Oct 25 09:16:57 localhost kernel: Normal: 0*4kB 0*8kB 1*16kB 1*32kB 1*64kB 
> 0*128kB 1*256kB 0*512kB 1*1024kB 0*2048kB 0*4096kB = 1392kB
> Oct 25 09:16:57 localhost kernel: HighMem: 0*4kB 0*8kB 1*16kB 0*32kB 1*64kB 
> 0*128kB 1*256kB 2*512kB 1*1024kB 1*2048kB 225*4096kB = 926032kB
> Oct 25 09:16:57 localhost kernel: Swap cache: add 0, delete 0, find 0/0, race 
> 0+0
> Oct 25 09:16:57 localhost kernel: Free swap  = 2031608kB
> Oct 25 09:16:57 localhost kernel: Total swap = 2031608kB
> Oct 25 09:16:57 localhost kernel: Free swap:       2031608kB
> Oct 25 09:16:57 localhost kernel: 524206 pages of RAM
> Oct 25 09:16:57 localhost kernel: 294830 pages of HIGHMEM
> Oct 25 09:16:57 localhost kernel: 5308 reserved pages
> Oct 25 09:16:57 localhost kernel: 38654 pages shared
> Oct 25 09:16:57 localhost kernel: 0 pages swap cached
> Oct 25 09:16:57 localhost kernel: 14 pages dirty
> Oct 25 09:16:57 localhost kernel: 0 pages writeback
> Oct 25 09:16:57 localhost kernel: 23195 pages mapped
> Oct 25 09:16:57 localhost kernel: 215831 pages slab
> Oct 25 09:16:57 localhost kernel: 429 pages pagetables
>
> [snip]
>

I just tried replicating this but it didn't do the same for me. It did
run slow due to constant resyncing like you were having also. This is
a problem that we are aware of but shouldn't cause the crash.

I don't claim to understand what the memory parts are saying but I
suspect you have fast machines with fast ethernet cards and it is
running the machine out of memory. Can somebody else confirm that the
machine is actually running out of memory?

If this is the case then I think we need to put some limits on DCCP
buffers much like TCP does.

Comments anyone?

Ian

--
Ian McDonald
http://wand.net.nz/~iam4
WAND Network Research Group
University of Waikato
New Zealand
-
To unsubscribe from this list: send the line "unsubscribe dccp" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to