[ 
https://issues.apache.org/jira/browse/TS-4897?focusedWorklogId=32780&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-32780
 ]

ASF GitHub Bot logged work on TS-4897:
--------------------------------------

                Author: ASF GitHub Bot
            Created on: 01/Dec/16 23:23
            Start Date: 01/Dec/16 23:23
    Worklog Time Spent: 10m 
      Work Description: Github user zwoop commented on the issue:

    https://github.com/apache/trafficserver/pull/1050
  
    It's fixed elsewhere?


Issue Time Tracking
-------------------

    Worklog Id:     (was: 32780)
    Time Spent: 3h 10m  (was: 3h)

> Unbound growth of number of memory maps for traffic_server under SSL 
> termination load when ssl_ticket_enabled=0
> ---------------------------------------------------------------------------------------------------------------
>
>                 Key: TS-4897
>                 URL: https://issues.apache.org/jira/browse/TS-4897
>             Project: Traffic Server
>          Issue Type: Bug
>          Components: TLS
>            Reporter: Can Selcik
>            Assignee: Phil Sorber
>            Priority: Blocker
>             Fix For: 7.1.0
>
>          Time Spent: 3h 10m
>  Remaining Estimate: 0h
>
> The number of {{\[anon\]}} memory regions mapped to the {{traffic_server}} 
> process displays unbound growth until the kernel thresholds are reached and 
> the process is terminated. 
> This happens when ATS is used to terminate SSL and {{ssl_ticket_enabled=0}} 
> in {{ssl_multicert.config}}.
> We've experienced this issue on our staging and production hosts and were 
> able to replicate it with the above configuration under high volume HTTPS 
> load. We didn't experience this with {{5.2.x}} and it will make sense why at 
> the end.
> While generating {{https}} traffic with {{siege}} or {{ab}}, the issue can be 
> observed with:
> {{watch "pmap $(pidof traffic_server) | wc -l"}}
> {{git bisect}} pointed us to: <TS-3883: Fix madvise>
> Turns out a no-op {{ats_madvise}} hides the symptoms of the issue.
> Going in deeper, we realize that {{ssl_ticket_enabled}} option is relevant 
> because after enabling the {{ssl.session_cache}} tag, we see that ATS doesn't 
> manage its own session cache for SSL, it is done by the library instead. In 
> that case, the code path doing the problematic allocation within ATS doesn't 
> get executed often since OpenSSL takes care of the session tokens.
> But why does this happen? It happens because {{MADV_DONTDUMP}} is passed to 
> {{posix_madvise}} even though {{MADV_DONTDUMP}} is not a valid flag for 
> {{posix_madvise}} as it is not a drop-in replacement to {{madvise}}.
> Looking at {{<bits/mman.h>}}:
> {noformat}
>      87 /* Advice to `madvise'.  */
>      88 #ifdef __USE_BSD
>      89 # define MADV_NORMAL▸     0▸    /* No further special treatment.  */
>      90 # define MADV_RANDOM▸     1▸    /* Expect random page references.  */
>      91 # define MADV_SEQUENTIAL  2▸    /* Expect sequential page references. 
>  */
>      92 # define MADV_WILLNEED▸   3▸    /* Will need these pages.  */
>      93 # define MADV_DONTNEED▸   4▸    /* Don't need these pages.  */
>      94 # define MADV_REMOVE▸     9▸    /* Remove these pages and resources.  
> */
>      95 # define MADV_DONTFORK▸   10▸   /* Do not inherit across fork.  */
>      96 # define MADV_DOFORK▸     11▸   /* Do inherit across fork.  */
>      97 # define MADV_MERGEABLE▸  12▸   /* KSM may merge identical pages.  */
>      98 # define MADV_UNMERGEABLE 13▸   /* KSM may not merge identical pages. 
>  */
>      99 # define MADV_DONTDUMP▸   16    /* Explicity exclude from the core 
> dump,
>     100                                    overrides the coredump filter 
> bits.  */
>     101 # define MADV_DODUMP▸     17▸   /* Clear the MADV_DONTDUMP flag.  */
>     102 # define MADV_HWPOISON▸   100▸  /* Poison a page for testing.  */
>     103 #endif
> {noformat}
> However {{posix_madvise}} takes:
> {noformat}
>     107 # define POSIX_MADV_NORMAL▸     0 /* No further special treatment.  */
>     108 # define POSIX_MADV_RANDOM▸     1 /* Expect random page references.  
> */
>     109 # define POSIX_MADV_SEQUENTIAL▸ 2 /* Expect sequential page 
> references.  */
>     110 # define POSIX_MADV_WILLNEED▸   3 /* Will need these pages.  */
>     111 # define POSIX_MADV_DONTNEED▸   4 /* Don't need these pages.  */
> {noformat}
> Also {{posix_madvise}} and {{madvise}} can both be present on the same 
> system. However they do not have the same capability. That's why {{Explicity 
> exclude from the core dump, overrides the coredump filter bits}} 
> functionality isn't achievable through {{posix_madvise}}.
> Will post a PR momentarily.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Reply via email to