Re: Any TCP VTW users?
On Thu, Sep 15, 2022 at 04:33:09PM +0900, Ryota Ozaki wrote: > Hi, > > Are there any users of TCP Vestigial Time-Wait (VTW)? > The feature is disabled by default and we need to explicitly > enable via sysctl to use it. > > I just want to know if we should still maintain it. Have you read the original discussion at https://mail-index.netbsd.org/tech-net/2011/04/08/msg002566.html ? I believe the rationale for this feature is still valid, and I think it is unfortuanate it was never enabled by default, and thus seems to have rotted. Thor
Re: Any TCP VTW users?
On Fri, Sep 16, 2022 at 10:33:31AM +0900, Ryota Ozaki wrote: > > Thank you for the report! > > Just curious. Does it improve performance? (or reduce CPU/memory usage?) The Coyote Point loadbalancers couldn't survive our load testing (which was modeled on traces of real world workloads) without it. But Coyote Point was bought by Fortinet and I believe the NetBSD-based firmware is long gone. Coyote Point did much more with the fat pointer stuff, but I don't think any of it even got into the internal tree before they were purchased and basically shut down. A lot of it was actually aimed at connection placement to improve concurrency within the stack - it is not surprising that if you are looking at only a small fragment of it, it makes that much _harder_. Thor
Re: Any TCP VTW users?
On Fri, Sep 16, 2022 at 10:21 AM Simon Burge wrote: > > Ryota Ozaki wrote: > > > Hi, > > > > Are there any users of TCP Vestigial Time-Wait (VTW)? > > The feature is disabled by default and we need to explicitly > > enable via sysctl to use it. > > > > I just want to know if we should still maintain it. > > I wouldn't be unhappy if it just disappeared. It's totally > undocumented, and will also cause a panic on archs with larger cache > line size because it does some really funky incorrect math that I > stared at for a while then gave up on. > > erlite# sysctl -w net.inet.tcp.vtw.enable=1 > 15293.7939168] panic: kernel diagnostic assertion "n <= FATP_MAX / 2" failed: > file "../../../../netinet/tcp_vtw.c", line 218 Oh, that's bad... Thank you for telling me. ozaki-r
Re: Any TCP VTW users?
On Fri, Sep 16, 2022 at 2:03 AM Brad Spencer wrote: > > Ryota Ozaki writes: > > > Hi, > > > > Are there any users of TCP Vestigial Time-Wait (VTW)? > > The feature is disabled by default and we need to explicitly > > enable via sysctl to use it. > > > > I just want to know if we should still maintain it. > > > > ozaki-r > > > I do use it on one system, but it is not likely to be critical to > anything. The system in question creates a whole ton of short lived > connections and I think I was trying to get them to expire quicker then > normal. Thank you for the report! Just curious. Does it improve performance? (or reduce CPU/memory usage?) ozaki-r
Re: Any TCP VTW users?
Ryota Ozaki wrote: > Hi, > > Are there any users of TCP Vestigial Time-Wait (VTW)? > The feature is disabled by default and we need to explicitly > enable via sysctl to use it. > > I just want to know if we should still maintain it. I wouldn't be unhappy if it just disappeared. It's totally undocumented, and will also cause a panic on archs with larger cache line size because it does some really funky incorrect math that I stared at for a while then gave up on. erlite# sysctl -w net.inet.tcp.vtw.enable=1 15293.7939168] panic: kernel diagnostic assertion "n <= FATP_MAX / 2" failed: file "../../../../netinet/tcp_vtw.c", line 218 Cheers, Simon.
Re: Any TCP VTW users?
On Thu, Sep 15, 2022 at 9:33 PM Andy Ruhl wrote: > > On Thu, Sep 15, 2022 at 12:34 AM Ryota Ozaki wrote: > > > > Hi, > > > > Are there any users of TCP Vestigial Time-Wait (VTW)? > > The feature is disabled by default and we need to explicitly > > enable via sysctl to use it. > > > > I just want to know if we should still maintain it. > > > > ozaki-r > > I wasn't even aware of it. I read the comments in > sys/netinet/tcp_vtw.c. Seems useful for systems that handle a lot of > sockets. Pretty neat. > > Is there some reason why this is obsolete or something? > > Andy When we do mp-ification of TCP, VTW requires extra efforts; the code looks not mp-ification friendly. If nobody uses the feature, we can defer mp-ification of it or completely ignore it. So I asked the question. ozaki-r
Re: Any TCP VTW users?
Ryota Ozaki writes: > Hi, > > Are there any users of TCP Vestigial Time-Wait (VTW)? > The feature is disabled by default and we need to explicitly > enable via sysctl to use it. > > I just want to know if we should still maintain it. > > ozaki-r I do use it on one system, but it is not likely to be critical to anything. The system in question creates a whole ton of short lived connections and I think I was trying to get them to expire quicker then normal. -- Brad Spencer - b...@anduin.eldar.org - KC8VKS - http://anduin.eldar.org
Re: Any TCP VTW users?
On Thu, Sep 15, 2022 at 12:34 AM Ryota Ozaki wrote: > > Hi, > > Are there any users of TCP Vestigial Time-Wait (VTW)? > The feature is disabled by default and we need to explicitly > enable via sysctl to use it. > > I just want to know if we should still maintain it. > > ozaki-r I wasn't even aware of it. I read the comments in sys/netinet/tcp_vtw.c. Seems useful for systems that handle a lot of sockets. Pretty neat. Is there some reason why this is obsolete or something? Andy