All of lore.kernel.org
 help / color / mirror / Atom feed
* ABORT after COOKIE_ECHO
@ 2017-07-01 17:02 Sun Paul
  2017-07-01 17:11 ` Marcelo Ricardo Leitner
                   ` (6 more replies)
  0 siblings, 7 replies; 8+ messages in thread
From: Sun Paul @ 2017-07-01 17:02 UTC (permalink / raw)
  To: linux-sctp

Hi

we have a setup that running normal, however, we found that some of
the conenctions are not able to establish and we (server) send ABORT
right after receiving COOKIE_ECHO.

any idea?

- RBK

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: ABORT after COOKIE_ECHO
  2017-07-01 17:02 ABORT after COOKIE_ECHO Sun Paul
@ 2017-07-01 17:11 ` Marcelo Ricardo Leitner
  2017-07-01 17:29 ` Sun Paul
                   ` (5 subsequent siblings)
  6 siblings, 0 replies; 8+ messages in thread
From: Marcelo Ricardo Leitner @ 2017-07-01 17:11 UTC (permalink / raw)
  To: linux-sctp

Hi,

On Sun, Jul 02, 2017 at 01:02:36AM +0800, Sun Paul wrote:
> Hi
> 
> we have a setup that running normal, however, we found that some of
> the conenctions are not able to establish and we (server) send ABORT
> right after receiving COOKIE_ECHO.
> 
> any idea?

Several reasons.. if it's not triggering a duplicate cookie processing,
it's being processed on sctp_sf_do_5_1D_ce(). Have a look at it to have
a better idea. Two reasons that stands out are somehow the cookie was
interpreted as an OOTB packet or the tcp-style listening socket got its
backlog full.

It can also be due to an out of memory situation, which is not often the
case.

OOTB packets are accounted for in netstat -s or /proc/net/sctp/snmp.

  Marcelo


^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: ABORT after COOKIE_ECHO
  2017-07-01 17:02 ABORT after COOKIE_ECHO Sun Paul
  2017-07-01 17:11 ` Marcelo Ricardo Leitner
@ 2017-07-01 17:29 ` Sun Paul
  2017-07-01 17:47 ` Marcelo
                   ` (4 subsequent siblings)
  6 siblings, 0 replies; 8+ messages in thread
From: Sun Paul @ 2017-07-01 17:29 UTC (permalink / raw)
  To: linux-sctp

OOTB means?

and below figure is the /proc/net/sctp/snmp, any idea

$ cat  /proc/net/sctp/snmp
SctpCurrEstab                   0
SctpActiveEstabs                 26061
SctpPassiveEstabs               204235
SctpAborteds                     811874
SctpShutdowns                   196524
SctpOutOfBlues                   19104636
SctpChecksumErrors               3070
SctpOutCtrlChunks               3515894374
SctpOutOrderChunks               43687436
SctpOutUnorderChunks             5244253158
SctpInCtrlChunks                 3820268182
SctpInOrderChunks               2553760409
SctpInUnorderChunks             2741444705
SctpFragUsrMsgs                 197031085
SctpReasmUsrMsgs                 207379860
SctpOutSCTPPacks                 6407590023
SctpInSCTPPacks                 6719200223
SctpT1InitExpireds               18041179
SctpT1CookieExpireds             365
SctpT2ShutdownExpireds           486
SctpT3RtxExpireds               4543012
SctpT4RtoExpireds               0
SctpT5ShutdownGuardExpireds     2
SctpDelaySackExpireds           2595840671
SctpAutocloseExpireds           0
SctpT3Retransmits               4527700
SctpPmtudRetransmits             3341
SctpFastRetransmits             4155577
SctpInPktSoftirq                 6711421746
SctpInPktBacklog                 7744553
SctpInPktDiscards               19253619
SctpInDataChunkDiscards         4248038

On Sun, Jul 2, 2017 at 1:11 AM, Marcelo Ricardo Leitner
<marcelo.leitner@gmail.com> wrote:
> Hi,
>
> On Sun, Jul 02, 2017 at 01:02:36AM +0800, Sun Paul wrote:
>> Hi
>>
>> we have a setup that running normal, however, we found that some of
>> the conenctions are not able to establish and we (server) send ABORT
>> right after receiving COOKIE_ECHO.
>>
>> any idea?
>
> Several reasons.. if it's not triggering a duplicate cookie processing,
> it's being processed on sctp_sf_do_5_1D_ce(). Have a look at it to have
> a better idea. Two reasons that stands out are somehow the cookie was
> interpreted as an OOTB packet or the tcp-style listening socket got its
> backlog full.
>
> It can also be due to an out of memory situation, which is not often the
> case.
>
> OOTB packets are accounted for in netstat -s or /proc/net/sctp/snmp.
>
>   Marcelo
>

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: ABORT after COOKIE_ECHO
  2017-07-01 17:02 ABORT after COOKIE_ECHO Sun Paul
  2017-07-01 17:11 ` Marcelo Ricardo Leitner
  2017-07-01 17:29 ` Sun Paul
@ 2017-07-01 17:47 ` Marcelo
  2017-07-03  2:56 ` Sun Paul
                   ` (3 subsequent siblings)
  6 siblings, 0 replies; 8+ messages in thread
From: Marcelo @ 2017-07-01 17:47 UTC (permalink / raw)
  To: linux-sctp

Means out of the blue below.
Your stats are interesting, you have expired cookies and also bad checksum.


Em 1 de julho de 2017 14:29:56 BRT, Sun Paul <paulrbk@gmail.com> escreveu:
>OOTB means?
>
>and below figure is the /proc/net/sctp/snmp, any idea
>
>$ cat  /proc/net/sctp/snmp
>SctpCurrEstab                   0
>SctpActiveEstabs                 26061
>SctpPassiveEstabs               204235
>SctpAborteds                     811874
>SctpShutdowns                   196524
>SctpOutOfBlues                   19104636
>SctpChecksumErrors               3070
>SctpOutCtrlChunks               3515894374
>SctpOutOrderChunks               43687436
>SctpOutUnorderChunks             5244253158
>SctpInCtrlChunks                 3820268182
>SctpInOrderChunks               2553760409
>SctpInUnorderChunks             2741444705
>SctpFragUsrMsgs                 197031085
>SctpReasmUsrMsgs                 207379860
>SctpOutSCTPPacks                 6407590023
>SctpInSCTPPacks                 6719200223
>SctpT1InitExpireds               18041179
>SctpT1CookieExpireds             365
>SctpT2ShutdownExpireds           486
>SctpT3RtxExpireds               4543012
>SctpT4RtoExpireds               0
>SctpT5ShutdownGuardExpireds     2
>SctpDelaySackExpireds           2595840671
>SctpAutocloseExpireds           0
>SctpT3Retransmits               4527700
>SctpPmtudRetransmits             3341
>SctpFastRetransmits             4155577
>SctpInPktSoftirq                 6711421746
>SctpInPktBacklog                 7744553
>SctpInPktDiscards               19253619
>SctpInDataChunkDiscards         4248038
>
>On Sun, Jul 2, 2017 at 1:11 AM, Marcelo Ricardo Leitner
><marcelo.leitner@gmail.com> wrote:
>> Hi,
>>
>> On Sun, Jul 02, 2017 at 01:02:36AM +0800, Sun Paul wrote:
>>> Hi
>>>
>>> we have a setup that running normal, however, we found that some of
>>> the conenctions are not able to establish and we (server) send ABORT
>>> right after receiving COOKIE_ECHO.
>>>
>>> any idea?
>>
>> Several reasons.. if it's not triggering a duplicate cookie
>processing,
>> it's being processed on sctp_sf_do_5_1D_ce(). Have a look at it to
>have
>> a better idea. Two reasons that stands out are somehow the cookie was
>> interpreted as an OOTB packet or the tcp-style listening socket got
>its
>> backlog full.
>>
>> It can also be due to an out of memory situation, which is not often
>the
>> case.
>>
>> OOTB packets are accounted for in netstat -s or /proc/net/sctp/snmp.
>>
>>   Marcelo
>>

-- 
Enviado de meu dispositivo Android com K-9 mail. Desculpe-me pela brevidade.

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: ABORT after COOKIE_ECHO
  2017-07-01 17:02 ABORT after COOKIE_ECHO Sun Paul
                   ` (2 preceding siblings ...)
  2017-07-01 17:47 ` Marcelo
@ 2017-07-03  2:56 ` Sun Paul
  2017-07-03  7:12 ` Sun Paul
                   ` (2 subsequent siblings)
  6 siblings, 0 replies; 8+ messages in thread
From: Sun Paul @ 2017-07-03  2:56 UTC (permalink / raw)
  To: linux-sctp

we found lots of entries when issue netstat command. seems the OS IP
stack level have issue.  anyone faced this before?

sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
    LISTEN
                    192.168.220.123             172.10.116.170
sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
    LISTEN
                    192.168.220.123             172.10.116.174
sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
    LISTEN
                    192.168.220.123             172.10.116.170
sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
    LISTEN
                    192.168.220.123             172.10.116.174
sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
    LISTEN
                    192.168.220.123             172.10.116.170
sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
    LISTEN
                    192.168.220.123             172.10.116.174
sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
    LISTEN
                    192.168.220.123             172.10.116.170
sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
    LISTEN
                    192.168.220.123             172.10.116.174
sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
    LISTEN
                    192.168.220.123             172.10.116.170
sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
    LISTEN
                    192.168.220.123             172.10.116.174
sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
    LISTEN
                    192.168.220.123             172.10.116.174
sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
    LISTEN
                    192.168.220.123             172.10.116.174

On Sun, Jul 2, 2017 at 1:47 AM, Marcelo <marcelo.leitner@gmail.com> wrote:
> Means out of the blue below.
> Your stats are interesting, you have expired cookies and also bad checksum.
>
>
> Em 1 de julho de 2017 14:29:56 BRT, Sun Paul <paulrbk@gmail.com> escreveu:
>>OOTB means?
>>
>>and below figure is the /proc/net/sctp/snmp, any idea
>>
>>$ cat  /proc/net/sctp/snmp
>>SctpCurrEstab                   0
>>SctpActiveEstabs                 26061
>>SctpPassiveEstabs               204235
>>SctpAborteds                     811874
>>SctpShutdowns                   196524
>>SctpOutOfBlues                   19104636
>>SctpChecksumErrors               3070
>>SctpOutCtrlChunks               3515894374
>>SctpOutOrderChunks               43687436
>>SctpOutUnorderChunks             5244253158
>>SctpInCtrlChunks                 3820268182
>>SctpInOrderChunks               2553760409
>>SctpInUnorderChunks             2741444705
>>SctpFragUsrMsgs                 197031085
>>SctpReasmUsrMsgs                 207379860
>>SctpOutSCTPPacks                 6407590023
>>SctpInSCTPPacks                 6719200223
>>SctpT1InitExpireds               18041179
>>SctpT1CookieExpireds             365
>>SctpT2ShutdownExpireds           486
>>SctpT3RtxExpireds               4543012
>>SctpT4RtoExpireds               0
>>SctpT5ShutdownGuardExpireds     2
>>SctpDelaySackExpireds           2595840671
>>SctpAutocloseExpireds           0
>>SctpT3Retransmits               4527700
>>SctpPmtudRetransmits             3341
>>SctpFastRetransmits             4155577
>>SctpInPktSoftirq                 6711421746
>>SctpInPktBacklog                 7744553
>>SctpInPktDiscards               19253619
>>SctpInDataChunkDiscards         4248038
>>
>>On Sun, Jul 2, 2017 at 1:11 AM, Marcelo Ricardo Leitner
>><marcelo.leitner@gmail.com> wrote:
>>> Hi,
>>>
>>> On Sun, Jul 02, 2017 at 01:02:36AM +0800, Sun Paul wrote:
>>>> Hi
>>>>
>>>> we have a setup that running normal, however, we found that some of
>>>> the conenctions are not able to establish and we (server) send ABORT
>>>> right after receiving COOKIE_ECHO.
>>>>
>>>> any idea?
>>>
>>> Several reasons.. if it's not triggering a duplicate cookie
>>processing,
>>> it's being processed on sctp_sf_do_5_1D_ce(). Have a look at it to
>>have
>>> a better idea. Two reasons that stands out are somehow the cookie was
>>> interpreted as an OOTB packet or the tcp-style listening socket got
>>its
>>> backlog full.
>>>
>>> It can also be due to an out of memory situation, which is not often
>>the
>>> case.
>>>
>>> OOTB packets are accounted for in netstat -s or /proc/net/sctp/snmp.
>>>
>>>   Marcelo
>>>
>
> --
> Enviado de meu dispositivo Android com K-9 mail. Desculpe-me pela brevidade.

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: ABORT after COOKIE_ECHO
  2017-07-01 17:02 ABORT after COOKIE_ECHO Sun Paul
                   ` (3 preceding siblings ...)
  2017-07-03  2:56 ` Sun Paul
@ 2017-07-03  7:12 ` Sun Paul
  2017-07-07 11:23 ` Xin Long
  2017-07-07 23:03 ` Marcelo
  6 siblings, 0 replies; 8+ messages in thread
From: Sun Paul @ 2017-07-03  7:12 UTC (permalink / raw)
  To: linux-sctp

also, how to determine it is OOTB packet?

On Mon, Jul 3, 2017 at 10:56 AM, Sun Paul <paulrbk@gmail.com> wrote:
> we found lots of entries when issue netstat command. seems the OS IP
> stack level have issue.  anyone faced this before?
>
> sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
>     LISTEN
>                     192.168.220.123             172.10.116.170
> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>     LISTEN
>                     192.168.220.123             172.10.116.174
> sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
>     LISTEN
>                     192.168.220.123             172.10.116.170
> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>     LISTEN
>                     192.168.220.123             172.10.116.174
> sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
>     LISTEN
>                     192.168.220.123             172.10.116.170
> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>     LISTEN
>                     192.168.220.123             172.10.116.174
> sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
>     LISTEN
>                     192.168.220.123             172.10.116.170
> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>     LISTEN
>                     192.168.220.123             172.10.116.174
> sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
>     LISTEN
>                     192.168.220.123             172.10.116.170
> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>     LISTEN
>                     192.168.220.123             172.10.116.174
> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>     LISTEN
>                     192.168.220.123             172.10.116.174
> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>     LISTEN
>                     192.168.220.123             172.10.116.174
>
> On Sun, Jul 2, 2017 at 1:47 AM, Marcelo <marcelo.leitner@gmail.com> wrote:
>> Means out of the blue below.
>> Your stats are interesting, you have expired cookies and also bad checksum.
>>
>>
>> Em 1 de julho de 2017 14:29:56 BRT, Sun Paul <paulrbk@gmail.com> escreveu:
>>>OOTB means?
>>>
>>>and below figure is the /proc/net/sctp/snmp, any idea
>>>
>>>$ cat  /proc/net/sctp/snmp
>>>SctpCurrEstab                   0
>>>SctpActiveEstabs                 26061
>>>SctpPassiveEstabs               204235
>>>SctpAborteds                     811874
>>>SctpShutdowns                   196524
>>>SctpOutOfBlues                   19104636
>>>SctpChecksumErrors               3070
>>>SctpOutCtrlChunks               3515894374
>>>SctpOutOrderChunks               43687436
>>>SctpOutUnorderChunks             5244253158
>>>SctpInCtrlChunks                 3820268182
>>>SctpInOrderChunks               2553760409
>>>SctpInUnorderChunks             2741444705
>>>SctpFragUsrMsgs                 197031085
>>>SctpReasmUsrMsgs                 207379860
>>>SctpOutSCTPPacks                 6407590023
>>>SctpInSCTPPacks                 6719200223
>>>SctpT1InitExpireds               18041179
>>>SctpT1CookieExpireds             365
>>>SctpT2ShutdownExpireds           486
>>>SctpT3RtxExpireds               4543012
>>>SctpT4RtoExpireds               0
>>>SctpT5ShutdownGuardExpireds     2
>>>SctpDelaySackExpireds           2595840671
>>>SctpAutocloseExpireds           0
>>>SctpT3Retransmits               4527700
>>>SctpPmtudRetransmits             3341
>>>SctpFastRetransmits             4155577
>>>SctpInPktSoftirq                 6711421746
>>>SctpInPktBacklog                 7744553
>>>SctpInPktDiscards               19253619
>>>SctpInDataChunkDiscards         4248038
>>>
>>>On Sun, Jul 2, 2017 at 1:11 AM, Marcelo Ricardo Leitner
>>><marcelo.leitner@gmail.com> wrote:
>>>> Hi,
>>>>
>>>> On Sun, Jul 02, 2017 at 01:02:36AM +0800, Sun Paul wrote:
>>>>> Hi
>>>>>
>>>>> we have a setup that running normal, however, we found that some of
>>>>> the conenctions are not able to establish and we (server) send ABORT
>>>>> right after receiving COOKIE_ECHO.
>>>>>
>>>>> any idea?
>>>>
>>>> Several reasons.. if it's not triggering a duplicate cookie
>>>processing,
>>>> it's being processed on sctp_sf_do_5_1D_ce(). Have a look at it to
>>>have
>>>> a better idea. Two reasons that stands out are somehow the cookie was
>>>> interpreted as an OOTB packet or the tcp-style listening socket got
>>>its
>>>> backlog full.
>>>>
>>>> It can also be due to an out of memory situation, which is not often
>>>the
>>>> case.
>>>>
>>>> OOTB packets are accounted for in netstat -s or /proc/net/sctp/snmp.
>>>>
>>>>   Marcelo
>>>>
>>
>> --
>> Enviado de meu dispositivo Android com K-9 mail. Desculpe-me pela brevidade.

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: ABORT after COOKIE_ECHO
  2017-07-01 17:02 ABORT after COOKIE_ECHO Sun Paul
                   ` (4 preceding siblings ...)
  2017-07-03  7:12 ` Sun Paul
@ 2017-07-07 11:23 ` Xin Long
  2017-07-07 23:03 ` Marcelo
  6 siblings, 0 replies; 8+ messages in thread
From: Xin Long @ 2017-07-07 11:23 UTC (permalink / raw)
  To: linux-sctp

On Mon, Jul 3, 2017 at 7:12 PM, Sun Paul <paulrbk@gmail.com> wrote:
> also, how to determine it is OOTB packet?
can you use systemtap on the host sending abort chunk ?

# stap --all-modules -v -e 'probe
module("sctp").function("sctp_make_abort").call{print_backtrace();println("");}'

So that we can see how the abort chunk is caused.

>
> On Mon, Jul 3, 2017 at 10:56 AM, Sun Paul <paulrbk@gmail.com> wrote:
>> we found lots of entries when issue netstat command. seems the OS IP
>> stack level have issue.  anyone faced this before?
>>
>> sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
>>     LISTEN
>>                     192.168.220.123             172.10.116.170
>> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>>     LISTEN
>>                     192.168.220.123             172.10.116.174
>> sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
>>     LISTEN
>>                     192.168.220.123             172.10.116.170
>> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>>     LISTEN
>>                     192.168.220.123             172.10.116.174
>> sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
>>     LISTEN
>>                     192.168.220.123             172.10.116.170
>> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>>     LISTEN
>>                     192.168.220.123             172.10.116.174
>> sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
>>     LISTEN
>>                     192.168.220.123             172.10.116.170
>> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>>     LISTEN
>>                     192.168.220.123             172.10.116.174
>> sctp    1540      0 192.168.220.115:3868        172.10.116.169:3868
>>     LISTEN
>>                     192.168.220.123             172.10.116.170
>> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>>     LISTEN
>>                     192.168.220.123             172.10.116.174
>> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>>     LISTEN
>>                     192.168.220.123             172.10.116.174
>> sctp    1540      0 192.168.220.115:3868        172.10.116.173:3868
>>     LISTEN
>>                     192.168.220.123             172.10.116.174
>>
>> On Sun, Jul 2, 2017 at 1:47 AM, Marcelo <marcelo.leitner@gmail.com> wrote:
>>> Means out of the blue below.
>>> Your stats are interesting, you have expired cookies and also bad checksum.
>>>
>>>
>>> Em 1 de julho de 2017 14:29:56 BRT, Sun Paul <paulrbk@gmail.com> escreveu:
>>>>OOTB means?
>>>>
>>>>and below figure is the /proc/net/sctp/snmp, any idea
>>>>
>>>>$ cat  /proc/net/sctp/snmp
>>>>SctpCurrEstab                   0
>>>>SctpActiveEstabs                 26061
>>>>SctpPassiveEstabs               204235
>>>>SctpAborteds                     811874
>>>>SctpShutdowns                   196524
>>>>SctpOutOfBlues                   19104636
>>>>SctpChecksumErrors               3070
>>>>SctpOutCtrlChunks               3515894374
>>>>SctpOutOrderChunks               43687436
>>>>SctpOutUnorderChunks             5244253158
>>>>SctpInCtrlChunks                 3820268182
>>>>SctpInOrderChunks               2553760409
>>>>SctpInUnorderChunks             2741444705
>>>>SctpFragUsrMsgs                 197031085
>>>>SctpReasmUsrMsgs                 207379860
>>>>SctpOutSCTPPacks                 6407590023
>>>>SctpInSCTPPacks                 6719200223
>>>>SctpT1InitExpireds               18041179
>>>>SctpT1CookieExpireds             365
>>>>SctpT2ShutdownExpireds           486
>>>>SctpT3RtxExpireds               4543012
>>>>SctpT4RtoExpireds               0
>>>>SctpT5ShutdownGuardExpireds     2
>>>>SctpDelaySackExpireds           2595840671
>>>>SctpAutocloseExpireds           0
>>>>SctpT3Retransmits               4527700
>>>>SctpPmtudRetransmits             3341
>>>>SctpFastRetransmits             4155577
>>>>SctpInPktSoftirq                 6711421746
>>>>SctpInPktBacklog                 7744553
>>>>SctpInPktDiscards               19253619
>>>>SctpInDataChunkDiscards         4248038
>>>>
>>>>On Sun, Jul 2, 2017 at 1:11 AM, Marcelo Ricardo Leitner
>>>><marcelo.leitner@gmail.com> wrote:
>>>>> Hi,
>>>>>
>>>>> On Sun, Jul 02, 2017 at 01:02:36AM +0800, Sun Paul wrote:
>>>>>> Hi
>>>>>>
>>>>>> we have a setup that running normal, however, we found that some of
>>>>>> the conenctions are not able to establish and we (server) send ABORT
>>>>>> right after receiving COOKIE_ECHO.
>>>>>>
>>>>>> any idea?
>>>>>
>>>>> Several reasons.. if it's not triggering a duplicate cookie
>>>>processing,
>>>>> it's being processed on sctp_sf_do_5_1D_ce(). Have a look at it to
>>>>have
>>>>> a better idea. Two reasons that stands out are somehow the cookie was
>>>>> interpreted as an OOTB packet or the tcp-style listening socket got
>>>>its
>>>>> backlog full.
>>>>>
>>>>> It can also be due to an out of memory situation, which is not often
>>>>the
>>>>> case.
>>>>>
>>>>> OOTB packets are accounted for in netstat -s or /proc/net/sctp/snmp.
>>>>>
>>>>>   Marcelo
>>>>>
>>>
>>> --
>>> Enviado de meu dispositivo Android com K-9 mail. Desculpe-me pela brevidade.
> --
> To unsubscribe from this list: send the line "unsubscribe linux-sctp" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

^ permalink raw reply	[flat|nested] 8+ messages in thread

* Re: ABORT after COOKIE_ECHO
  2017-07-01 17:02 ABORT after COOKIE_ECHO Sun Paul
                   ` (5 preceding siblings ...)
  2017-07-07 11:23 ` Xin Long
@ 2017-07-07 23:03 ` Marcelo
  6 siblings, 0 replies; 8+ messages in thread
From: Marcelo @ 2017-07-07 23:03 UTC (permalink / raw)
  To: linux-sctp

On Fri, Jul 07, 2017 at 11:23:02PM +1200, Xin Long wrote:
> On Mon, Jul 3, 2017 at 7:12 PM, Sun Paul <paulrbk@gmail.com> wrote:
> > also, how to determine it is OOTB packet?
> can you use systemtap on the host sending abort chunk ?
> 
> # stap --all-modules -v -e 'probe
> module("sctp").function("sctp_make_abort").call{print_backtrace();println("");}'
> 
> So that we can see how the abort chunk is caused.

Or the perf version:
# perf probe -m sctp -a sctp_make_abort
# perf record -e probe:sctp_make_abort -agR -- <command>
  (note the extra -g if compared to what the 1st command outputted)
# perf script

<command> should be either your reproducer or an sleep X that covers the
event.

  Marcelo

^ permalink raw reply	[flat|nested] 8+ messages in thread

end of thread, other threads:[~2017-07-07 23:03 UTC | newest]

Thread overview: 8+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2017-07-01 17:02 ABORT after COOKIE_ECHO Sun Paul
2017-07-01 17:11 ` Marcelo Ricardo Leitner
2017-07-01 17:29 ` Sun Paul
2017-07-01 17:47 ` Marcelo
2017-07-03  2:56 ` Sun Paul
2017-07-03  7:12 ` Sun Paul
2017-07-07 11:23 ` Xin Long
2017-07-07 23:03 ` Marcelo

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.