rstone (Ryan Stone)
User

Projects

User Details

User Since
May 12 2014, 8:03 PM (214 w, 6 d)

Recent Activity

Tue, Jun 12

rstone added a comment to D15337: Add support for higher resolution timestamps.

@rstone do you think you might be able to share the work that you or Jeff did on the frontend to adaptively lower the minRTO if the pipe was full?

Tue, Jun 12, 7:23 PM

May 17 2018

rstone added a comment to D11560: Remove use of 9k clusters from mlx4_en rx path.
In D11560#326314, @kib wrote:

I do not see such code in mlx4_en_rx.c. Could you point it out, please ?

May 17 2018, 3:44 PM

May 16 2018

rstone added a comment to D11560: Remove use of 9k clusters from mlx4_en rx path.
In D11560#326054, @kib wrote:

Well, from my reading, your patch and this patch are quite similar, but this review provides two interesting optimizations.

  • Use page-size fragments if MTU >= PAGE_SIZE, already discussed on lists for mlx5.
  • Keep around mbufs and memory for unused fragments, if the received packed was shorter than MTU.

    If these changes are transplanted into your patch, I believe the things start look almost identical. I want to confirm my understanding with Ryan.
May 16 2018, 5:04 PM

May 7 2018

rstone added a comment to D15337: Add support for higher resolution timestamps.

The message that I got at BSDCan last year is that they wanted to see at least a full IETF draft before these changes could be merged in, which is why my work on it stalled. Has people's position on this changed?

May 7 2018, 8:16 PM
rstone added a comment to D15337: Add support for higher resolution timestamps.

FWIW, I had a short email conversation with the writers of that draft about a year ago and they went radio silent pretty quickly. I assumed that they weren't working on it anymore.

May 7 2018, 8:06 PM

Mar 19 2018

rstone accepted D14764: Fix initialization of eventhandler mutex..
Mar 19 2018, 10:28 PM

Mar 14 2018

rstone added a comment to D14559: Add test for regression fixed in r329743.

Where is route.subr? And where did ipv4_move_subnet_route come from? I think you used the wrong base revision to generate the review.

Mar 14 2018, 8:14 PM
rstone updated the diff for D14559: Add test for regression fixed in r329743.

Move non-fib test into separate test file

Mar 14 2018, 7:03 PM

Mar 8 2018

rstone added inline comments to D14540: Several LRO fixes.
Mar 8 2018, 4:28 PM · transport
rstone accepted D14540: Several LRO fixes.
Mar 8 2018, 2:34 PM · transport

Mar 7 2018

rstone accepted D14540: Several LRO fixes.

I've written some unit tests that covering these cases here:

Mar 7 2018, 10:32 PM · transport

Mar 5 2018

rstone added a comment to D14547: Allow IPv4 subnet routes to move to a different ifa.

I don't think that this conversation is going to go anywhere productive. Do you have specific technical objection to raise about this change?

Mar 5 2018, 6:02 PM
rstone added a comment to D14547: Allow IPv4 subnet routes to move to a different ifa.

Care to elaborate what are you trying to achieve by moving subnet route between interfaces?

Mar 5 2018, 5:43 PM
rstone updated the diff for D14547: Allow IPv4 subnet routes to move to a different ifa.

Uploaded the wrong test to this review; fixed now

Mar 5 2018, 5:32 PM
rstone updated the diff for D14547: Allow IPv4 subnet routes to move to a different ifa.

Move route(8) tests to their own atf test file

Mar 5 2018, 5:21 PM
rstone added a comment to D14547: Allow IPv4 subnet routes to move to a different ifa.

In any case, even if the use-case is weird, the current behaviour is clearly buggy and needs to be fixed in some way.

Well, I guess so. But original configuration may be supposed to be "buggy" too (read: not supported). What if you use /16 mask for single interface only and assign IP from the same prefix to other interfaces using /32 mask?

Mar 5 2018, 4:57 PM

Mar 1 2018

rstone created D14559: Add test for regression fixed in r329743.
Mar 1 2018, 9:37 PM
rstone added a comment to D14547: Allow IPv4 subnet routes to move to a different ifa.

And you do you insist in doing things manually while moving IP (first route change, then reassign IP) instead of just allowing system do all housekeeping for you by reassigning IP first?

Mar 1 2018, 8:54 PM
rstone updated the diff for D14547: Allow IPv4 subnet routes to move to a different ifa.

Add ATF test cases for IPv4/IPv6 subnet route migration

Mar 1 2018, 8:51 PM
rstone updated the test plan for D14547: Allow IPv4 subnet routes to move to a different ifa.
Mar 1 2018, 8:50 PM
rstone added a comment to D14547: Allow IPv4 subnet routes to move to a different ifa.

The fibs must actually exist. Set net.fibs=6 in /boot/loader.conf and reboot. Also, are you sure you need so many? I don't think there are any tests there that require more than two.

Mar 1 2018, 7:01 PM
rstone added a comment to D14547: Allow IPv4 subnet routes to move to a different ifa.

In tests/sys/netinet/fibs_test.sh there are some ATF tests that check this kind of functionality. They do it on separate FIBs so they won't upset the system running the tests, and they use tap(4) and/or epair(4) interfaces. You should be able to copy one of those to create a regression test for this problem.

Mar 1 2018, 6:46 PM

Feb 28 2018

rstone updated the diff for D14547: Allow IPv4 subnet routes to move to a different ifa.

Check for NULL pointers

Feb 28 2018, 7:48 PM
rstone updated the test plan for D14547: Allow IPv4 subnet routes to move to a different ifa.
Feb 28 2018, 7:03 PM
rstone created D14547: Allow IPv4 subnet routes to move to a different ifa.
Feb 28 2018, 6:56 PM

Feb 21 2018

rstone committed rS329744: Fix route manpage to show correct flush syntax.
Fix route manpage to show correct flush syntax
Feb 21 2018, 7:14 PM
rstone closed D14401: Fix route manpage to show correct flush syntax.
Feb 21 2018, 7:14 PM
rstone committed rS329743: Allow route change requests to not specify the gateway..
Allow route change requests to not specify the gateway.
Feb 21 2018, 7:13 PM
rstone closed D14291: Allow route change requests to not specify the gateway..
Feb 21 2018, 7:13 PM

Feb 16 2018

rstone added a comment to D14291: Allow route change requests to not specify the gateway..
In D14291#300646, @ae wrote:

How it supposed to work for RADIX_MPATH case? I know RADIX_MPATH is currently broken, but anyway...

Feb 16 2018, 7:59 PM
rstone added inline comments to D14291: Allow route change requests to not specify the gateway..
Feb 16 2018, 7:53 PM
rstone added inline comments to D14291: Allow route change requests to not specify the gateway..
Feb 16 2018, 6:34 PM
rstone updated the diff for D14291: Allow route change requests to not specify the gateway..

Clarify manpage update as per rgrimes' suggestion

Feb 16 2018, 6:32 PM
rstone added a reviewer for D14401: Fix route manpage to show correct flush syntax: manpages.
Feb 16 2018, 6:14 PM
rstone created D14401: Fix route manpage to show correct flush syntax.
Feb 16 2018, 6:13 PM
rstone updated the diff for D14291: Allow route change requests to not specify the gateway..

Fix the manpage to document that the gateway parameter is
optional for most route subcommands.

Feb 16 2018, 4:42 PM

Feb 10 2018

rstone created D14291: Allow route change requests to not specify the gateway..
Feb 10 2018, 1:52 AM

Jan 29 2018

rstone accepted D14120: Remove duplicate entries from various conf/files*.
Jan 29 2018, 5:27 PM

Jan 23 2018

rstone closed D13990: Increment the route table gen count after a modify.
Jan 23 2018, 3:16 AM
rstone committed rS328272: Increment the route table gen count after a modify.
Increment the route table gen count after a modify
Jan 23 2018, 3:16 AM
rstone committed rS328271: Reduce code duplication for inpcb route caching.
Reduce code duplication for inpcb route caching
Jan 23 2018, 3:16 AM
rstone closed D13989: Reduce code duplication for inpcb route caching.
Jan 23 2018, 3:16 AM
rstone closed D13988: Invalidate inpcb LLE cache if cached route is invalidated.
Jan 23 2018, 3:16 AM
rstone committed rS328270: Invalidate inpcb LLE cache if cached route is invalidated.
Invalidate inpcb LLE cache if cached route is invalidated
Jan 23 2018, 3:16 AM

Jan 22 2018

rstone updated the diff for D13990: Increment the route table gen count after a modify.

Add comment explaining generation increment

Jan 22 2018, 4:17 PM
rstone added a comment to D13988: Invalidate inpcb LLE cache if cached route is invalidated.

Could this use the new invalidate macro?

Jan 22 2018, 1:59 AM

Jan 19 2018

rstone updated the diff for D13989: Reduce code duplication for inpcb route caching.

NULL-out rte after route cache is invalidated

Jan 19 2018, 11:36 PM
rstone created D13990: Increment the route table gen count after a modify.
Jan 19 2018, 9:40 PM
rstone created D13989: Reduce code duplication for inpcb route caching.
Jan 19 2018, 9:40 PM
rstone created D13988: Invalidate inpcb LLE cache if cached route is invalidated.
Jan 19 2018, 9:40 PM

Dec 14 2017

rstone committed rS326860: Plug an ifaddr leak when changing a route's src.
Plug an ifaddr leak when changing a route's src
Dec 14 2017, 8:49 PM
rstone closed D13417: Plug an ifaddr leak when changing a route's src.
Dec 14 2017, 8:49 PM

Dec 13 2017

rstone added a comment to D13417: Plug an ifaddr leak when changing a route's src.
In D13417#281628, @ae wrote:

It would be nice if you describe why this leak happens, i.e. where leaked reference was acquired.

Dec 13 2017, 4:01 PM

Dec 7 2017

rstone updated the test plan for D13417: Plug an ifaddr leak when changing a route's src.
Dec 7 2017, 9:54 PM
rstone created D13417: Plug an ifaddr leak when changing a route's src.
Dec 7 2017, 9:50 PM

Nov 17 2017

rstone added inline comments to D12101: swfw_sync DELAY -> sleep conversion.
Nov 17 2017, 2:37 PM · network

Oct 24 2017

rstone created D12772: Prevent bge_init and bge_rxeof from running in parallel.
Oct 24 2017, 3:53 AM

Oct 23 2017

rstone accepted D12749: Move clear_unrhdr to tmpfs_free_tmp..
Oct 23 2017, 3:14 PM

Oct 16 2017

rstone accepted D12662: Properly reset fields in clean_unrhdr..
Oct 16 2017, 3:40 PM

Oct 11 2017

rstone accepted D12591: Add clearing function for unr(9), call it from tmpfs..
Oct 11 2017, 9:23 PM

Sep 22 2017

rstone accepted D12468: ddb(4): Add 'show badstacks' command to show witness badstacks.
Sep 22 2017, 7:43 PM

Sep 12 2017

rstone accepted D12191: Allow vlan interfaces to rx through netmap(4).
Sep 12 2017, 11:57 PM
rstone committed rS323506: Fix incorrect error message in iovctl.
Fix incorrect error message in iovctl
Sep 12 2017, 9:12 PM

Aug 15 2017

rstone accepted D11370: Rework vlan(4) locking..
Aug 15 2017, 5:05 PM

Aug 4 2017

rstone accepted D11777: Selectively print "hwaddr" from ifconfig(8)..
Aug 4 2017, 8:51 PM

Aug 2 2017

rstone committed rS321939: Add my birthdate to the calendar.
Add my birthdate to the calendar
Aug 2 2017, 7:45 PM

Jul 31 2017

rstone accepted D11797: Add myself to the calendar..
Jul 31 2017, 5:28 PM

Jul 20 2017

rstone accepted D11670: Add myself (mjoras) as a new src committer.
Jul 20 2017, 6:03 PM
rstone committed rS321300: Welcome Matt Joras (mjoras@) as a new src committer. Matt has been doing.
Welcome Matt Joras (mjoras@) as a new src committer. Matt has been doing
Jul 20 2017, 6:02 PM
rstone accepted D11672: Add myself and mentor line to committers-src.dot..
Jul 20 2017, 6:02 PM
rstone committed rD50525: Update my GPG key.
Update my GPG key
Jul 20 2017, 1:30 AM

Jul 13 2017

rstone accepted D11573: Fix kldload of if_ixl without PCI_IOV kernel option..
Jul 13 2017, 7:28 PM

Jul 12 2017

rstone added a comment to D11560: Remove use of 9k clusters from mlx4_en rx path.

Hi,

Don't pull the "old behaviour" into the driver. You should use a linked list of mbufs and load that instead of the mlx4_en_frag_info structure now we are using busdma!

There is a better way to implement this. Can Mellanox take over this issue?

--HPS

Jul 12 2017, 4:22 PM

Jul 11 2017

rstone created D11560: Remove use of 9k clusters from mlx4_en rx path.
Jul 11 2017, 10:59 PM

Jun 27 2017

rstone added inline comments to D11370: Rework vlan(4) locking..
Jun 27 2017, 8:09 PM
rstone added inline comments to D11370: Rework vlan(4) locking..
Jun 27 2017, 5:35 PM

May 29 2017

rstone added a comment to D8556: Fix spurious retransmit recovery on low latency networks.

@kmacy I have not. We probably have an equivalent fix committed locally @ $WORK but it might be tied too closely to the high-precision timestamp work to easily extract.

May 29 2017, 6:28 PM · network

May 24 2017

rstone accepted D10874: vmxnet3 crash when LRO is enabled.
May 24 2017, 7:23 PM

May 3 2017

rstone added a comment to D10535: ixgbe: Acquire lock for shared code API calls in handle_phy.

Maybe you've seen something that requires this lock acquisition in your testing. Can you explain why we need to acquire this lock here?

May 3 2017, 9:36 PM

Apr 28 2017

rstone created D10535: ixgbe: Acquire lock for shared code API calls in handle_phy.
Apr 28 2017, 3:13 PM

Apr 5 2017

rstone committed rS316527: Revert the optimization from r304436.
Revert the optimization from r304436
Apr 5 2017, 4:57 PM

Apr 3 2017

rstone updated the diff for D10255: Fix a double free in ixgbe_rxeof().

Add the locking mentioned the description but omitted from the
actual revision.

Apr 3 2017, 7:04 PM
rstone added a comment to D10255: Fix a double free in ixgbe_rxeof().

I'm not sure what we want to do with this fix given the imminent iflib conversion, but at least this should go into stable branches.

Apr 3 2017, 7:02 PM
rstone created D10255: Fix a double free in ixgbe_rxeof().
Apr 3 2017, 7:00 PM

Mar 22 2017

rstone abandoned D9465: Remove unnecessary ifdef soup from struct tcpcb.

Obsoleted by gleb's User/Kernel KPI fixes

Mar 22 2017, 6:00 PM

Feb 23 2017

rstone added a reviewer for D9485: Make LACP behavior more closely conform to the standard: rstone.
Feb 23 2017, 5:34 PM

Feb 18 2017

rstone added inline comments to D9519: Don't zero out srtt after excess retransmits.
Feb 18 2017, 12:46 AM

Feb 17 2017

rstone added inline comments to D9658: Remove the arbitrary limit on DTrace buffers.
Feb 17 2017, 10:55 PM

Feb 16 2017

rstone committed rS313824: Revert r313814 and r313816.
Revert r313814 and r313816
Feb 16 2017, 9:18 PM
rstone committed rS313816: Fix a typo in my previous commit.
Fix a typo in my previous commit
Feb 16 2017, 8:06 PM
rstone committed rS313814: Check for preemption after lowering a thread's priority.
Check for preemption after lowering a thread's priority
Feb 16 2017, 7:41 PM
rstone closed D9518: Check for preemption after lowering a thread's priority by committing rS313814: Check for preemption after lowering a thread's priority.
Feb 16 2017, 7:41 PM

Feb 15 2017

rstone added a comment to D9465: Remove unnecessary ifdef soup from struct tcpcb.

I realize the issue there is exposure of a type definition to userland, but a related question is - what exactly is the userland-ABI property we are trying to maintain here? Are we just trying to keep this struct the same size and layout under all kernel configuration option selections and feature evolutions for a given machine type? Or are we also trying to keep it the same size and layout across different machine types (or at the very least a single pair of relevant machine types)? For example, is the #ifdef_LP64 really necessary in the TCPPCAP section?

Feb 15 2017, 12:49 AM

Feb 11 2017

rstone committed rS313646: Don't zero out srtt after excess retransmits.
Don't zero out srtt after excess retransmits
Feb 11 2017, 5:05 PM
rstone closed D9519: Don't zero out srtt after excess retransmits by committing rS313646: Don't zero out srtt after excess retransmits.
Feb 11 2017, 5:05 PM
rstone updated the diff for D9519: Don't zero out srtt after excess retransmits.
  • fixup! Don't zero out srtt after excess retransmits
Feb 11 2017, 4:50 PM

Feb 9 2017

rstone retitled D9519: Don't zero out srtt after excess retransmits from to Don't zero out srtt after excess retransmits.
Feb 9 2017, 6:18 PM
rstone added a comment to D9518: Check for preemption after lowering a thread's priority.
Feb 9 2017, 5:57 PM
rstone added a comment to D9518: Check for preemption after lowering a thread's priority.

See this ML post for a detailed description of the problem:
https://lists.freebsd.org/pipermail/freebsd-current/2013-January/039261.html

Feb 9 2017, 5:55 PM
rstone retitled D9518: Check for preemption after lowering a thread's priority from to Check for preemption after lowering a thread's priority.
Feb 9 2017, 5:53 PM