https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
Michael Tuexen changed:
What|Removed |Added
Status|In Progress |Closed
Flags|mfc-sta
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
Lutz Donnerhacke changed:
What|Removed |Added
CC||don...@freebsd.org
--- Comment
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #45 from Richard Scheffenegger ---
I don't quite understand that last comment, and why this PR got reopened? The
MFC was put in stable/13, /12 and even /11 in middle of April already (2 Months
ago).
--
You are receiving this m
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
Kubilay Kocak changed:
What|Removed |Added
Resolution|FIXED |---
Status|Closed
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
Richard Scheffenegger changed:
What|Removed |Added
Status|In Progress |Closed
Resolution|
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #43 from Richard Scheffenegger ---
I believe this PR can be marked closed, with the two fixes (the race leading to
erroneous accounting of the number of global entries, and the fix to not
excessively use kernel memory while prov
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
Kubilay Kocak changed:
What|Removed |Added
Keywords||performance
--
You are receiving
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #41 from commit-h...@freebsd.org ---
A commit in branch stable/11 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=a85003abdad402c27c12cf1a31b243c39483f263
commit a85003abdad402c27c12cf1a31b243c39483f263
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #42 from commit-h...@freebsd.org ---
A commit in branch stable/11 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=d20563819b9292ddcd42caf3449636b84825b1d6
commit d20563819b9292ddcd42caf3449636b84825b1d6
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #39 from commit-h...@freebsd.org ---
A commit in branch stable/11 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=c449b8a71bce7d7838164f6a5595f71c91b5b91b
commit c449b8a71bce7d7838164f6a5595f71c91b5b91b
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #40 from commit-h...@freebsd.org ---
A commit in branch stable/11 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=254b56ac2a9ee43d10b0a4f8eeb20b722bb7fd74
commit 254b56ac2a9ee43d10b0a4f8eeb20b722bb7fd74
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #38 from commit-h...@freebsd.org ---
A commit in branch stable/12 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=12ce9e4868d1454b263a2330ce95e91b145c1c8f
commit 12ce9e4868d1454b263a2330ce95e91b145c1c8f
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #37 from commit-h...@freebsd.org ---
A commit in branch stable/12 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=54beb1ef2c831394ef908ef52bac690a4fe362e0
commit 54beb1ef2c831394ef908ef52bac690a4fe362e0
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #36 from commit-h...@freebsd.org ---
A commit in branch stable/12 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=c0f8ed6ff81260fb4a26da354d3f06aaa83e74de
commit c0f8ed6ff81260fb4a26da354d3f06aaa83e74de
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #35 from commit-h...@freebsd.org ---
A commit in branch stable/12 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=e9ca38abc79b5ee0cc0052fb4e213b3dd5720716
commit e9ca38abc79b5ee0cc0052fb4e213b3dd5720716
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #34 from commit-h...@freebsd.org ---
A commit in branch stable/13 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=e610ebe5d351c0570101ec58f1642904a30051ae
commit e610ebe5d351c0570101ec58f1642904a30051ae
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #32 from commit-h...@freebsd.org ---
A commit in branch stable/13 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=831be7fa19ef10c78da51c222693a5a2083d1da4
commit 831be7fa19ef10c78da51c222693a5a2083d1da4
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #33 from commit-h...@freebsd.org ---
A commit in branch stable/13 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=4052275c2fc5f96b4a208404733713959afe68f6
commit 4052275c2fc5f96b4a208404733713959afe68f6
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #31 from commit-h...@freebsd.org ---
A commit in branch stable/13 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=632e3363087cb6ef2a7b26a291a044b97afabea7
commit 632e3363087cb6ef2a7b26a291a044b97afabea7
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #30 from commit-h...@freebsd.org ---
A commit in branch stable/11 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=6ab67f3b20ac44e9e9741bd0bdf557c3aa118d32
commit 6ab67f3b20ac44e9e9741bd0bdf557c3aa118d32
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #29 from commit-h...@freebsd.org ---
A commit in branch stable/12 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=dc5281a7d43917c55905d8b83a5bef69b8013071
commit dc5281a7d43917c55905d8b83a5bef69b8013071
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #28 from commit-h...@freebsd.org ---
A commit in branch stable/13 references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=13d418a967c90cfd845f41db96383ac7eb5862aa
commit 13d418a967c90cfd845f41db96383ac7eb5862aa
Author
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #27 from Richard Scheffenegger ---
The "hang" is due to a waiting malloc requesting much more memory any machine
will currently have.
The root cause for that, however, is a race condition (likely to hit busy
servers), fixed wi
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #26 from Maxim Shalomikhin ---
We have one more machine with hanging sysctl.
# sysctl net.inet.tcp.hostcache
net.inet.tcp.hostcache.purgenow: 0
net.inet.tcp.hostcache.purge: 0
net.inet.tcp.hostcache.prune: 300
net.inet.tcp.host
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #25 from commit-h...@freebsd.org ---
A commit in branch main references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=529a2a0f2765f6c57c50a5af6be242c03bf714e3
commit 529a2a0f2765f6c57c50a5af6be242c03bf714e3
Author:
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #24 from commit-h...@freebsd.org ---
A commit in branch main references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=95e56d31e348594973affd0ea81d8f8383bc3031
commit 95e56d31e348594973affd0ea81d8f8383bc3031
Author:
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #23 from commit-h...@freebsd.org ---
A commit in branch main references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=869880463cc2ce64e2e6599eaec880a981f3ced6
commit 869880463cc2ce64e2e6599eaec880a981f3ced6
Author:
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #22 from commit-h...@freebsd.org ---
A commit in branch main references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=c804c8f2c58ba42d476de07fbceff9ac4dd95f0e
commit c804c8f2c58ba42d476de07fbceff9ac4dd95f0e
Author:
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #21 from Michael Tuexen ---
One potential issue came up to my mind: The hch_length is protected by the
hch_mtx.
But which mutex is protecting the cache_count? Could that be an issue?
--
You are receiving this mail because:
You
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #20 from Michael Tuexen ---
(In reply to Richard Scheffenegger from comment #19)
As far as I can see, it is impossible to change the cache config at runtime,
the relevant variables are all only settable in /boot/loader.conf.
No
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #19 from Richard Scheffenegger ---
(In reply to Michael Tuexen from comment #18)
> Richard: Do you see a way how the counter could be off?
Unfortunately not. I was thinking about adding KASSERTS when the counter is
about to be
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #18 from Michael Tuexen ---
(In reply to Richard Scheffenegger from comment #17)
But tcp_hc_purge_internal() decrements the counter when it removes an entry and
frees it. I double checked the code and I think the counter is hand
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #17 from Richard Scheffenegger ---
net.inet.tcp.hostcache.count: 4294966447 is -849 (decimal).
tcp_hc_purge_internal decrements hostcache.count unconditionally, and would be
the most likely candidate where that counter can rap
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #16 from Michael Tuexen ---
Please note that you should not be able to set the
net.inet.tcp.hostcache.cachelimit too high. It is set automatically to
net.inet.tcp.hostcache.bucketlimit * net.inet.tcp.hostcache.hashsize and you
s
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #15 from Michael Tuexen ---
Could you also post for the output of netstat -sptcp the two lines with
counters for hostcache entries added and bucket overflow.
--
You are receiving this mail because:
You are on the CC list for t
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #14 from Michael Tuexen ---
I agree with Richard that we know he issue and the patches from Richard should
address the problem.
However, I would like to understand why net.inet.tcp.hostcache.count >
net.inet.tcp.hostcache.cache
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #13 from Richard Scheffenegger ---
Thanks. I can not comment as to why the hostcache.count counts up and beyond
the limit.
But the other data confirms that what you are seeing is the (unsuccessful)
attempt in allocating a huge
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #12 from Maxim Shalomikhin ---
I have one machine with hanging sysct:
99750 - D 22:33.32 /sbin/sysctl net.inet.tcp.hostcache.list
# procstat -kk 99750
PIDTID COMMTDNAME KSTACK
99750
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
Kubilay Kocak changed:
What|Removed |Added
Severity|Affects Only Me |Affects Many People
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #11 from Michael Tuexen ---
(In reply to commit-hook from comment #10)
If it is possible, please patch your system with the above patch and give it a
try. My guess is that it resolves your issue, but one doesn't know without
tes
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #10 from commit-h...@freebsd.org ---
A commit in branch main references this bug:
URL:
https://cgit.FreeBSD.org/src/commit/?id=cb0dd7e122b8936ad61a141e65ef8ef874bfebe5
commit cb0dd7e122b8936ad61a141e65ef8ef874bfebe5
Author:
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #9 from Richard Scheffenegger ---
See https://reviews.freebsd.org/D29471 for improving the situation by
addressing
(b) mentioned above.
Note that this may not fully alleviate the issue (I did not investigate the
inner workings
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #8 from Michael Tuexen ---
(In reply to Michael Tuexen from comment #7)
Just to be clear. You can provide these values as of now, you don't need to
wait until the hang occurs.
--
You are receiving this mail because:
You are th
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #7 from Michael Tuexen ---
(In reply to Richard Scheffenegger from comment #6)
That might be the reason... Good idea!
So it would be good to see the output of
sysctl net.inet.tcp.hostcache
and
vmstat -m | grep sbuf
--
You are
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #6 from Richard Scheffenegger ---
Also, as a quick workaround:
What is the output of sysctl net.inet.tcp.hostcache
and the above problem about the waiting for a contingeous chunk of kernel
memory could be reduced, by restricti
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #5 from Richard Scheffenegger ---
(Note that with sbuf_extent, the prior string could be overwritten with a more
detailed error (e.g. failed to extend sbuf at the 20th iteration...)
--
You are receiving this mail because:
You
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
Richard Scheffenegger changed:
What|Removed |Added
CC||rsch...@freebsd.org
--- Co
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #3 from Michael Tuexen ---
(In reply to Maxim Shalomikhin from comment #2)
I mentioned this issue on the bi-weekly transport call, since I don't see how
this problem can occur. It was asked if it is possible that the problem cou
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #2 from Maxim Shalomikhin ---
It will take some time to reproduce the issue. Plese let me now if there any
other information I can collect when sysctl hangs again.
--
You are receiving this mail because:
You are the assignee f
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
--- Comment #1 from Michael Tuexen ---
What is the output of procstat -kk PID, where PID is the PID of a hanging
sysctl process?
--
You are receiving this mail because:
You are the assignee for the bug.
___
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=254333
Michael Tuexen changed:
What|Removed |Added
CC||tue...@freebsd.org
Sum
51 matches
Mail list logo
