- User Since
- Jan 18 2019, 4:52 AM (228 w, 2 d)
Apr 25 2023
Apr 16 2023
Mar 31 2023
Mar 4 2023
@kp , just out of curiosity. How many packets per second did you get in your test after this patch?
Sep 13 2022
Sep 9 2022
Sep 8 2022
Sep 6 2022
Thanks. I will submit this patch in a separate review where we can discuss the details.
My main objection is that it is bad to extend 'struct protosw' for only one consumer ( ng_kocket(4) ).
Jul 21 2022
@rew, do you have any plans to continue this work? If not, I'd like to take over.
Jun 23 2022
Feb 23 2022
Feb 21 2022
Looks good to me.
Feb 19 2022
I'm concerned about two things:
Feb 17 2022
I have this problem in STABLE-13 with disk image located on NFS share.
Feb 16 2022
Feb 15 2022
@vmaffione , do you have any objections?
Feb 14 2022
Feb 13 2022
Feb 9 2022
Feb 8 2022
Feb 7 2022
Feb 6 2022
Feb 5 2022
Dec 22 2021
Dec 16 2021
Dec 15 2021
Nov 9 2021
I don't understand what the alignment does in this case.
Does it fix a bug or is it an optimization?
What part of the code requires this alignment, is it the TCP/IP stack?
Because not only ng_eiface(4) can inject Ethernet packets into the network stack.
Nov 8 2021
The polynomial 0x8005 is CRC-16-IBM or CRC-16-ANSI.
Oct 21 2021
This is done in FreeBSD 13.
I am also against the use of generic messages.
Sep 13 2021
Aug 12 2021
I looked at other nodes that implement the ng_newhook_t method. They already use M_NOWAIT, so I think this patch is good.
Aug 10 2021
The load simply allows this bug to manifest itself. Under load, the node's queue already contains the item's, so if a message item is sent at that moment (ngtstl shutdown), it will also go to the queue and will be processed by ngthread(). Without load, the queue is mostly empty, the message item will be delivered/processed by the thread of the calling process directly: ngctl -> syscall (sandto(2)) -> ngc_send (ng_socket(4)) -> ng_eiface(4) without entering to the EPOCH section. Therefore, the bug does not manifest itself.
JFYI, the same situation. If you call "ngctl shutdown ngeth0:" under load:
I think the problem is somewhat broader. Any message item can be added to the node's queue under load or if the queue is blocked. This message item will be processed by ngthread() in the EPOCH section. There are many places in the code of the nodes that perform actions prohibited in the EPOCH section.
Jul 22 2021
Overall, this patch looks good to me.
Jul 7 2021
Jun 15 2021
Jun 5 2021
- Move ethernet packet length check to vxlan_input().
Jun 4 2021
Jun 3 2021
I prefer having sound loaded as a module in fact, but until we have module autoloading by PCI ID this should be available in GENERIC.
May 18 2021
Apr 28 2021
The capsicum support should look something like this:
Have you tested this code with CAPSICUM enabled?
Apr 7 2021
As I mentioned previously, the other thing to consider when using kvmclock in the current patch is the need for a system call for clock_gettime(), gettimeofday(), etc.
@me_freebsd_mathieu.digital, what a CPU model was used for testing?
Mar 30 2021
Mar 28 2021
Mar 27 2021
Mar 11 2021
I have no objections.
Mar 2 2021
Mar 1 2021
Feb 20 2021
I'm not an English expert, so you may be right.
Technically, I have no questions, I think this patch can be committed.
Feb 18 2021
Did you mean D28559?
Feb 15 2021
I have no competence in this area. Maybe you wanted to add @fsu to the reviewers? He was working on improving ext2/3/4 support.
Feb 5 2021
Jan 13 2021
Lutz, do you have any plans for the upcoming changes?
I also thought about getting rid of ng_bridge from NG_NODE_FORCE_WRITER. Since rcv_data is always called in the NET_EPOCH context, I think we can do it like @kp did it for if_bridge(4) (see D24250).
Dec 18 2020
I don't really like how ng_etner(4) is implemented as a whole. But I think this patch is correct and should be committed.
Dec 17 2020
Dec 6 2020
@grehan do you have any objections?