search for: sendmmsg

On NetBSD 6.99.28-CURRENT, nsd 3.2.16 works fine, however nsd 4.0.0 is spinning chewing CPU. The logs show: Nov 28 23:07:00 xxx nsd[466]: sendmmsg failed: Resource temporarily unavailable ktruss shows it getting EAGAIN from sendmmsg(2) over and over again. According to the man page: [EAGAIN|EWOULDBLOCK] The socket is marked non-blocking and the requested operation would block. Sounds li...

Guus Sliepen, on Wed 02 Dec 2015 13:53:37 +0100, wrote: > I guess in the future, we want to put a "cork" on the output until all > packets from a single recvmmsg() have been received, so that we can do > sendmmsg() on the resulting outgoing packets. Yes. > > More is yet to come: I'll have a look at extending the tun/tap interface > > to send/receive several packets at a time, and then also using sendmmsg > > will again improve performance. > > Last time I checked, the send/rec...

...ne that processes each individual packet, to reduce the level of indentation and make the functions a bit more readable. Then I'll merge it :) I guess in the future, we want to put a "cork" on the output until all packets from a single recvmmsg() have been received, so that we can do sendmmsg() on the resulting outgoing packets. > More is yet to come: I'll have a look at extending the tun/tap interface > to send/receive several packets at a time, and then also using sendmmsg > will again improve performance. Last time I checked, the send/recvmmsg() functionality is actual...

..., I saw the non-ciphered bandwidth achieved over direct ethernet improve from 680Mbps to 800Mbps (or conversely, reduce the CPU usage for the same bandwidth). More is yet to come: I'll have a look at extending the tun/tap interface to send/receive several packets at a time, and then also using sendmmsg will again improve performance. Samuel --- configure.ac.original 2015-10-02 17:06:31.250034677 +0200 +++ configure.ac 2015-10-02 17:06:54.147546590 +0200 @@ -187,7 +187,7 @@ dnl Checks for library functions. AC_TYPE_SIGNAL -AC_CHECK_FUNCS([asprintf daemon fchmod flock ftime fork get_current_d...

...er will send more */ #define MSG_WAITFORONE 0x10000 /* recvmmsg(): block until 1+ packets avail */ #define MSG_SENDPAGE_NOPOLICY 0x10000 /* sendpage() internal : do no apply policy */ -#define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */ #define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */ #define MSG_EOF MSG_FIN #define MSG_NO_SHARED_FRAGS 0x80000 /* sendpage() internal : page frags are not shared */ @@ -341,8 +340,7 @@ struct ucred { /* Flags to be cleared on entry by sendmsg and sendmmsg syscalls */ #define MSG_INTERNAL_SENDMSG_FLAGS \ - (M...

...> > _______________________________________________ > linux-um mailing list > linux-um at lists.infradead.org > http://lists.infradead.org/mailman/listinfo/linux-um > I have looked at using virtio semantics in UML in the past around the point when I wanted to make the recvmmsg/sendmmsg vector drivers common in UML and QEMU. It is certainly possible, I went for the native approach at the end though. -- Anton R. Ivanov https://www.kot-begemot.co.uk/

...y want the stock drivers > > that are part of the kernel now (like virtio-net etc.) but rather > > something that integrates with wifi (probably building on hwsim). > I have looked at using virtio semantics in UML in the past around the > point when I wanted to make the recvmmsg/sendmmsg vector drivers common > in UML and QEMU. It is certainly possible, > > I went for the native approach at the end though. Hmm. I'm not sure what you mean by either :-) Is there any commonality between the vector drivers? I can't see how that'd work without a bus abstraction...

...t; surprising for any contributor. It is a bit unfortunate, but now we're stuck with it. > My earlier patch was really against 1.1pre11. My latest patch was a > port of it to the git master, thinking it was the latest code... No problem. Now you know for when you're working on the sendmmsg() part :) -- Met vriendelijke groet / with kind regards, Guus Sliepen <guus at tinc-vpn.org> -------------- next part -------------- A non-text attachment was scrubbed... Name: signature.asc Type: application/pgp-signature Size: 819 bytes Desc: Digital signature URL: <http://www.tin...

On Thu, Dec 10, 2015 at 10:15:19AM +0100, Samuel Thibault wrote: > I did get a bit more than a hundred packets in the queue at 800Mbps. But > we can reduce to 64, yes. I wouldn't recommend using a static buffer, > since we'd want to go threaded at some point. Allocating an array on the > stack is very cheap anyway. I assumed that one would only get more than 1 packet at a

On Mon, Jan 5, 2015 at 7:10 AM, Lance Fredrickson <lancethepants at gmail.com> wrote: > Just wanted to pop in and say I think 1.1pre11 is a really good release. > I have a couple nodes behind a work firewall (sonicwall) over which I have > no control. Previously nodes always fell back to TCP, and the connection > was unusable. Now it always connects over UDP and works like it

Hi, While my main interest is mostly in UML right now [1] I've CC'ed the qemu and virtualization lists because something similar might actually apply to other types of virtualization. I'm thinking about adding virt-io support to UML, but the tricky part is that while I want to use the virt-io basics (because it's a nice interface from the 'inside'), I don't actually

Hi, While my main interest is mostly in UML right now [1] I've CC'ed the qemu and virtualization lists because something similar might actually apply to other types of virtualization. I'm thinking about adding virt-io support to UML, but the tricky part is that while I want to use the virt-io basics (because it's a nice interface from the 'inside'), I don't actually

...bandwidth achieved over direct > ethernet improve from 680Mbps to 800Mbps (or conversely, reduce the CPU > usage for the same bandwidth). > > More is yet to come: I'll have a look at extending the tun/tap interface > to send/receive several packets at a time, and then also using sendmmsg > will again improve performance. > > Samuel > > --- configure.ac.original 2015-10-02 17:06:31.250034677 +0200 > +++ configure.ac 2015-10-02 17:06:54.147546590 +0200 > @@ -187,7 +187,7 @@ > > dnl Checks for library functions. > AC_TYPE_SIGNAL > -AC_CH...

...44018) = 0 socket(PF_INET, SOCK_DGRAM|SOCK_NONBLOCK, IPPROTO_IP) = 3 connect(3, {sa_family=AF_INET, sin_port=htons(53), sin_addr=inet_addr("127.0.0.1")}, 16) = 0 gettimeofday({1383869704, 698589}, NULL) = 0 poll([{fd=3, events=POLLOUT}], 1, 0) = 1 ([{fd=3, revents=POLLOUT}]) sendmmsg(3, {{{msg_name(0)=NULL, msg_iov(1)=[{"\250\317\1\0\0\1\0\0\0\0\0\0\6mirror\6aarnet\3edu\2a"..., 38}], msg_controllen=0, msg_flags=0}, 38}, {{msg_name(0)=NULL, msg_iov(1)=[{"d\273\1\0\0\1\0\0\0\0\0\0\6mirror\6aarnet\3edu\2a"..., 38}], msg_controllen=0, msg_flags=0}, 38}}, 2, MSG_...

...osleep SYSCALL FOUND: fanotify_init SYSCALL FOUND: lremovexattr SYSCALL FOUND: read SYSCALL FOUND: fadvise64_64 SYSCALL FOUND: sched_setparam SYSCALL FOUND: swapon SYSCALL FOUND: io_getevents SYSCALL FOUND: olduname SYSCALL FOUND: link SYSCALL FOUND: recv SYSCALL FOUND: timer_gettime SYSCALL FOUND: sendmmsg SYSCALL FOUND: ulimit SYSCALL FOUND: truncate64 SYSCALL FOUND: timerfd_create SYSCALL FOUND: gettid SYSCALL FOUND: set_tid_address SYSCALL FOUND: setregid SYSCALL FOUND: inotify_rm_watch SYSCALL FOUND: mq_unlink SYSCALL FOUND: oldfstat SYSCALL FOUND: lchown SYSCALL FOUND: request_key SYSCALL FOUND:...

On Tue, Aug 20, 2013 at 07:44:39AM +0200, leroy christophe wrote: > > > Find attached two patches I have in order to build klibc 2.0.2 > against kernel 3.8.13 > We had to introduce those patches when going from kernel 3.6 to kernel 3.7 > Hope it helps. > those patches are wrong and again very brittle. just use the way it is described in `make help': A) cd ~/src/linux