search for: corking

...as I need more time to investigate why Unix sockets appeared to degrade with this patch. But as TCP sockets (over loopback to localhost) and TLS sessions (regardless of underlying Unix or TCP) both showed improvements, this looks like a worthwhile series. Eric Blake (2): server: Add support for corking server: Cork around grouped transmission send()s server/internal.h | 3 +++ server/connections.c | 27 +++++++++++++++++++++++ server/crypto.c | 19 ++++++++++++++++ server/protocol.c | 52 ++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 101 insertions(+) -- 2.20.1

As mentioned in the previous patch, sending small packets as soon as possible leads to network packet overhead. Grouping related writes under corking appears to help everything but unencrypted Unix plain sockets. I tested with appropriate combinations from: $ nbdkit {-p 10810,-U -} \ {--tls=require --tls-verify-peer --tls-psk=./keys.psk,} memory size=64m \ --run './aio-parallel-load{-tls,} {$unixsocket,nbd://localhost:10810}' with...

...n->send() more than once. Now that we've disabled Nagle's algorithm, this implies that we try harder to send the small header immediately, rather than batching it with the rest of the payload, which causes more overhead in the amount of actual network traffic. For interfaces that support corking (gnutls, or Linux TCP sockets), we can give a hint that the separate send() calls should be batched into a single network packet where practical. This patch just wires up support; the next one will actually use it and provide performance measurements. Signed-off-by: Eric Blake <eblake@redhat.c...

...blindly implemented the tls code as: if (SEND_MORE) { cork send } else { send uncork } because it showed improvements for my test case of aio-parallel-load from libnbd. But that test sticks to 64k I/O requests. But with further investigation, I've learned that even though gnutls corking works great for smaller NBD_CMD_READ replies, it can actually pessimize behavior for larger requests (such as a client sending lots of 2M read requests). This is because gnutls loses time both to realloc()s to copy the entire packet into memory, as well as CPU time spent encrypting the entire paylo...

...ly noticeable, but with TLS this really shows. > > Booting a VM via qemu-nbd on localhost (with tls) takes more than > 2 minutes on my system. tcpdump shows frequent wait periods, where no > packets get sent for a 40ms period. Thank you for this analysis. > > Add explicit (un)corking when processing (and responding to) requests. > "TCP_CORK, &zero" after earlier "CORK, &one" will flush pending data. > > VM Boot time: > main: no tls: 23s, with tls: 2m45s > patched: no tls: 14s, with tls: 15s > > VM Boot time, qemu-nbd via n...

I did chmod -R 777 /var/lib/dovecot and it worked. I just need to figure out what the correct setting are. Thanks everyone //Ger ----------------original message----------------- From:Ger Hooton Scoil Chro? ?osa Blarney [ghooton at scins.ie ] To:Robert Moskowitz [rgm at htt-consult.com ], chaouche yacine [yacinechaouche at yahoo.com ], dovecot at dovecot.org Date:Tue, 21 Mar 2017 14:05:17

Hi everyone Has anybody ever come across this, I want it to join automatically the recording files for me but it creates the wav files as I expect but it doesn't join them sadly, so eg: ls 1250623104.10-in.wav 1250628672.23-in.wav 1250630411.30-in.wav 1250623104.10-out.wav 1250628672.23-out.wav 1250630411.30-out.wav Here is my queues.conf snippet [testQ]

dovecot-v1.0-alpha build failed for Solaris 11 (OpenSolaris Nevada). The problematic line is in socket.c line 228. The fix should be to change SOL_TCP to IPPROTO_TCP found in netinet/in.h. This change should work universally on all platforms. Gary

I am trying to move from IAX2 to SIP for voipbuster, moving at the same time to sip1.voipbuster.com. When I try calling out, I see that there is SIP exchange, and in many cases also RTP data being exchanged. Hover in a very large number of attempts the connection is not established. Half of the time there is no RTP, the rest of the time there *is* RTP data flowing in two ways, but no ringtone is

On Mon, 5 Jul 2021 at 07:15, Hooton, Gerard <g.hooton at ucc.ie> wrote: > > Hi All, > I am having problems with a kickstart install of CentOS 8 > When I try to do a completely automated install using PXE/UEFI it get to the point where it reads the kickstart config file. > Then I see the following message > "kickstart install Started cancel waiting for multipath

>From the log: Jul 11 13:12:42 mproxy dovecot: imap-login: Login: user=<hildeb>, method=PLAIN, rip=141.42.206.36, lip=141.42.206.11, mpid=27254, TLS, session=<TGwoO1o3id+NKs4k> Jul 11 13:12:44 mproxy dovecot: imap(hildeb)<TGwoO1o3id+NKs4k>: Panic: file imap-client.c: line 854 (client_check_command_hangs): assertion failed: ((io_loop_find_fd_conditions(current_ioloop,

Hello all, I am using Samba version 3.2.5 configured for Windows Domain login. It was working fine until I moved over to ldapsam. Now when I login to the XP client I don't see the logon drive (X: in my case) Any debug tips? //Ger -- Gerard Hooton Systems Administrator Blarney Boy's National School, Blarney. Co. Cork

The following is a message to be sent to the President of the United States of America. Although we may not be able to do a great deal from where we are, but for the people of America just knowing we care and feel their sadness will help. Please put your name on the following list and send it to all you know and who care. If you are the 100th name and every 100th there on could you please also

Hi everybody I have a logic question that is confusing me. ifTime(00:00-12:00|*|*|*) { Playback(welcome-morning); } else { ifTime(12:00-18:00|*|*|*) { Playback(welcome-afternoon); } else { Playback(welcome-evening); }

Hi All, I cannot get the sieve_before to work. I have dovecot & sieve installed on Debian 7 as follows /etc/dovecot/conf.d/90-sieve.conf : plugin { # The path to the user's main active script. If ManageSieve is used, this the # location of the symbolic link controlled by ManageSieve. sieve = ~/.dovecot.sieve # The default Sieve script when the user has none. This is a path to a

This time around, the numbers are indeed looking better than in v1; and I like the interface better. Eric Blake (2): server: Prefer send() over write() server: Group related transmission send()s server/internal.h | 7 +++- server/connections.c | 51 +++++++++++++++++++++++++--- server/crypto.c | 11 ++++--

...2023 at 02:41:20PM -0500, Eric Blake wrote: > On Fri, Mar 24, 2023 at 11:47:20AM +0100, Florian Westphal wrote: > > qemu-nbd doesn't set TCP_NODELAY on the tcp socket. Replying to myself, WHY aren't we setting TCP_NODELAY on the socket? > > And surprisingly, qemu IS using corking on the client side: > https://gitlab.com/qemu-project/qemu/-/blob/master/block/nbd.c#L525 > just not on the server side, before your patch. Corking matters more when TCP_NODELAY is enabled. The entire reason Nagle's algorithm exists (and is default on unless you enable TCP_NODELAY) is t...

...weeks :) Changes: - Fixed maildir syncing errors about wrong UIDs - Maildir was re-read all the time, even if we knew nothing had changed there - SSL/TLS connections used to have extra ~0.2s latencies because kernel was waiting for more data before sending it (at least with Linux). Fixed it by corking/uncorking before/after sending. I don't think the socket latencies are this bad normally though, I should probably look more into it if we're setting some socket flags badly (or does it happen specifically because we were using corking for the socket before SSL and kernel increased the time...

Hi All, I am having problems with a kickstart install of CentOS 8 When I try to do a completely automated install using PXE/UEFI it get to the point where it reads the kickstart config file. Then I see the following message "kickstart install Started cancel waiting for multipath siblings for nvme0n1" This is what I have in the kickstart file # Clear the Master Boot Record zerombr #

> As a streaming server, it's fairly crucial for icecast to > send out data with as low a delay as possible (many clients > don't care, but some do). That's why we use TCP_NODELAY - we > actually WANT to send out data as soon as we can. Nagle is inherently unsuited for streams. NODELAY was (imho) ment for connections for which Nagle isn't sufficient and CORK is not