On Thu, Jan 13, 2022 at 09:06:50PM +0100, Michael Tuexen wrote:
M> > I'm talking about statistics that I recently committed to CURRENT only:
M> >
M> > # netstat -sp tcp | grep TIME-WAIT
M> >3 times connection in TIME-WAIT responded with ACK
M> >0 times connection in TIME-WAIT was a
On Thu, Jan 13, 2022 at 09:11:09PM +0100, Michael Tuexen wrote:
M> > On Thu, Jan 13, 2022 at 10:30:10AM -0800, Gleb Smirnoff wrote:
M> > T> Sorry, the stats I was talking about are present in CURRENT only:
M> > T>
M> > T> netstat -sp tcp | grep TIME-WAIT
M> > T> 3 times connection in TIME-
Gleb Smirnoff wrote:
> On Thu, Jan 13, 2022 at 10:30:10AM -0800, Gleb Smirnoff wrote:
> T> Sorry, the stats I was talking about are present in CURRENT only:
Yeah, sorry, I saw your other post about that after posting mine.
> Sorry, I actually can't merge it to stable, as it changes size of tcps
On Thu, Jan 13, 2022 at 10:30:10AM -0800, Gleb Smirnoff wrote:
T> Sorry, the stats I was talking about are present in CURRENT only:
T>
T> netstat -sp tcp | grep TIME-WAIT
T> 3 times connection in TIME-WAIT responded with ACK
T> 0 times connection in TIME-WAIT was actively recycled
On Thu, Jan 13, 2022 at 06:25:06PM +, Jamie Landeg-Jones wrote:
J> > modern HTTP server can be lowered 3 times more. Feel free to lower
J> > net.inet.tcp.msl and do your own measurements with
J> > 'netstat -sp tcp | grep TIME-WAIT'. I'd be glad to see your results.
J>
J> Without changi
Gleb Smirnoff wrote:
> modern HTTP server can be lowered 3 times more. Feel free to lower
> net.inet.tcp.msl and do your own measurements with
> 'netstat -sp tcp | grep TIME-WAIT'. I'd be glad to see your results.
Without changing net.inet.tcp.msl I get:
| 18:18 (46.0°C 1100) (2) "/tmp
On Wed, Jan 12, 2022 at 11:16:09PM -0800, Chris wrote:
C> > * Who told that 2*MSL (60 seconds) is adequate time to keep TIME-WAIT?
C> > In 71d2d5adfe1 I added some stats on usage of tcptw and experimented a
bit
C> > with lowering net.inet.tcp.msl. It appeared that lowering it down three
C> >
On Wed, Jan 12, 2022 at 05:01:51PM -0500, George Neville-Neil wrote:
G> > * Who told that 2*MSL (60 seconds) is adequate time to keep TIME-WAIT?
G> > In 71d2d5adfe1 I added some stats on usage of tcptw and experimented a
bit
G> > with lowering net.inet.tcp.msl. It appeared that lowering it dow
On 2022-01-12 10:48, Gleb Smirnoff wrote:
Hi!
Thanks for the informative writeup, Gleb!
Untrimmed, sorry...
[crossposted to current@, but let's keep discussion at net@]
I have already touched the topic with rrs@, jtl@, tuexen@, rscheff@ and
Igor Sysoev (author of nginx). Now posting for wid
Removed current@ given your comment below.
On 12 Jan 2022, at 13:48, Gleb Smirnoff wrote:
> Hi!
>
> [crossposted to current@, but let's keep discussion at net@]
>
> I have already touched the topic with rrs@, jtl@, tuexen@, rscheff@ and
> Igor Sysoev (author of nginx). Now posting for wider di
On Wed, Jan 12, 2022 at 10:48:59AM -0800, Gleb Smirnoff wrote:
T> * Many of HTTP connections were made by older browsers, which were not able
T> to use persistent HTTP connections. Those browsers that could, would
T> recycle connections more often, then today. Default timeouts in Apache
T>
Hi!
[crossposted to current@, but let's keep discussion at net@]
I have already touched the topic with rrs@, jtl@, tuexen@, rscheff@ and
Igor Sysoev (author of nginx). Now posting for wider discussion.
TLDR: struct tcptw shall be decomissioned
Longer version covers three topics: why does tcp
12 matches
Mail list logo
