Rather than sending an interrupt on every buffer, we only send an interrupt
when we're about to wait for the Guest to send us a new one. The console
input and network input still send interrupts manually, but the block device,
network and console output queues can simply rely on this logic to send
interrupts to the Guest at the right time.
The patch is cluttered by moving trigger_irq() higher in the code.
In practice, two factors make this optimization less interesting:
(1) we often only get one input at a time, even for networking,
(2) triggering an interrupt rapidly tends to get coalesced anyway.
Before: Secs RxIRQS TxIRQs
1G TCP Guest->Host: 3.72 32784 32771
1M normal pings: 99 1000004 995541
100,000 1k pings (-l 120): 5 49510 49058
After:
1G TCP Guest->Host: 3.69 32809 32769
1M normal pings: 99 1000004 996196
100,000 1k pings (-l 120): 5 52435 52361
(Note the interrupt count on 100k pings goes *up*: see next patch).
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Currently lguest has three threads: the main Launcher thread, a Waker
thread, and a thread for the block device (because synchronous block
was simply too painful to bear).
The Waker selects() on all the input file descriptors (eg. stdin, net
devices, pipe to the block thread) and when one becomes readable it calls
into the kernel to kick the Launcher thread out into userspace, which
repeats the poll, services the device(s), and then tells the kernel to
release the Waker before re-entering the kernel to run the Guest.
Also, to make a slightly-decent network transmit routine, the Launcher
would suppress further network interrupts while it set a timer: that
signal handler would write to a pipe, which would rouse the Waker
which would prod the Launcher out of the kernel to check the network
device again.
Now we can convert all our virtqueues to separate threads: each one has
a separate eventfd for when the Guest pokes the device, and can trigger
interrupts in the Guest directly.
The linecount shows how much this simplifies, but to really bring it
home, here's an strace analysis of single Guest->Host ping before:
* Guest sends packet, notifies xmit vq, return control to Launcher
* Launcher clears notification flag on xmit ring
* Launcher writes packet to TUN device
writev(4, [{"\0\0\0\0\0\0\0\0\0\0", 10}, {"\366\r\224`\2058\272m\224vf\274\10\0E\0\0T\0\0@\0@\1\265"..., 98}], 2) = 108
* Launcher sets up interrupt for Guest (xmit ring is empty)
write(10, "\2\0\0\0\3\0\0\0", 8) = 0
* Launcher sets up timer for interrupt mitigation
setitimer(ITIMER_REAL, {it_interval={0, 0}, it_value={0, 505}}, NULL) = 0
* Launcher re-runs guest
pread64(10, 0xbfa5f4d4, 4, 0) ...
* Waker notices reply packet in tun device (it was in select)
select(12, [0 3 4 6 11], NULL, NULL, NULL) = 1 (in [4])
* Waker kicks Launcher out of guest:
pwrite64(10, "\3\0\0\0\1\0\0\0", 8, 0) = 0
* Launcher returns from running guest:
... = -1 EAGAIN (Resource temporarily unavailable)
* Launcher looks at input fds:
select(7, [0 3 4 6], NULL, NULL, {0, 0}) = 1 (in [4], left {0, 0})
* Launcher reads pong from tun device:
readv(4, [{"\0\0\0\0\0\0\0\0\0\0", 10}, {"\272m\224vf\274\366\r\224`\2058\10\0E\0\0T\364\26\0\0@"..., 1518}], 2) = 108
* Launcher injects guest notification:
write(10, "\2\0\0\0\2\0\0\0", 8) = 0
* Launcher rechecks fds:
select(7, [0 3 4 6], NULL, NULL, {0, 0}) = 0 (Timeout)
* Launcher clears Waker:
pwrite64(10, "\3\0\0\0\0\0\0\0", 8, 0) = 0
* Launcher reruns Guest:
pread64(10, 0xbfa5f4d4, 4, 0) = ? ERESTARTSYS (To be restarted)
* Signal comes in, uses pipe to wake up Launcher:
--- SIGALRM (Alarm clock) @ 0 (0) ---
write(8, "\0", 1) = 1
sigreturn() = ? (mask now [])
* Waker sees write on pipe:
select(12, [0 3 4 6 11], NULL, NULL, NULL) = 1 (in [6])
* Waker kicks Launcher out of Guest:
pwrite64(10, "\3\0\0\0\1\0\0\0", 8, 0) = 0
* Launcher exits from kernel:
pread64(10, 0xbfa5f4d4, 4, 0) = -1 EAGAIN (Resource temporarily unavailable)
* Launcher looks to see what fd woke it:
select(7, [0 3 4 6], NULL, NULL, {0, 0}) = 1 (in [6], left {0, 0})
* Launcher reads timeout fd, sets notification flag on xmit ring
read(6, "\0", 32) = 1
* Launcher rechecks fds:
select(7, [0 3 4 6], NULL, NULL, {0, 0}) = 0 (Timeout)
* Launcher clears Waker:
pwrite64(10, "\3\0\0\0\0\0\0\0", 8, 0) = 0
* Launcher resumes Guest:
pread64(10, "\0p\0\4", 4, 0) ....
strace analysis of single Guest->Host ping after:
* Guest sends packet, notifies xmit vq, creates event on eventfd.
* Network xmit thread wakes from read on eventfd:
read(7, "\1\0\0\0\0\0\0\0", 8) = 8
* Network xmit thread writes packet to TUN device
writev(4, [{"\0\0\0\0\0\0\0\0\0\0", 10}, {"J\217\232FI\37j\27\375\276\0\304\10\0E\0\0T\0\0@\0@\1\265"..., 98}], 2) = 108
* Network recv thread wakes up from read on tunfd:
readv(4, [{"\0\0\0\0\0\0\0\0\0\0", 10}, {"j\27\375\276\0\304J\217\232FI\37\10\0E\0\0TiO\0\0@\1\214"..., 1518}], 2) = 108
* Network recv thread sets up interrupt for the Guest
write(6, "\2\0\0\0\2\0\0\0", 8) = 0
* Network recv thread goes back to reading tunfd
13:39:42.460285 readv(4, <unfinished ...>
* Network xmit thread sets up interrupt for Guest (xmit ring is empty)
write(6, "\2\0\0\0\3\0\0\0", 8) = 0
* Network xmit thread goes back to reading from eventfd
read(7, <unfinished ...>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
The "len" field in the used ring for virtio indicates the number of
bytes *written* to the buffer. This means the guest doesn't have to
zero the buffers in advance as it always knows the used length.
Erroneously, the console and network example code puts the length
*read* into that field. The guest ignores it, but it's wrong.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
2088761152 (lguest: notify on empty) introduced
lguest support for the VIRTIO_F_NOTIFY_ON_EMPTY flag, but in fact it turned on
interrupts all the time.
Because we always process one buffer at a time, the inflight count is always 0
when call trigger_irq and so we always ignore VRING_AVAIL_F_NO_INTERRUPT from
the Guest.
It should be looking to see if there are more buffers in the Guest's queue:
if it's empty, then we force an interrupt.
This makes little difference, since we usually have an empty queue; but
that's the subject of another patch.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Since the Launcher process runs the Guest, it doesn't have to be very
serious about its barriers: the Guest isn't running while we are (Guest
is UP).
Before we change to use threads to service devices, we need to fix this.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
We hand the /dev/lguest fd everywhere; it's far neater to just make it
a global (it already is, in fact, hidden in the waker_fds struct).
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
We can't trust the values in the device descriptor table once the
guest has booted, so keep local copies. They could set them to
strange values then cause us to segv (they're 8 bit values, so they
can't make our pointers go too wild).
This becomes more important with the following patches which read them.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Impact: barrier correctness in example launcher
I doubt either lguest user will complain about performance.
Reported-by: Christoph Hellwig <hch@infradead.org>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
This patch moves the initial guest page table creation code to the host,
so the launcher keeps working with PAE enabled configs.
Signed-off-by: Matias Zabaljauregui <zabaljauregui@gmail.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
This doesn't really matter, since lguest is i386 only at the moment,
but we could actually choose a different value. (lguest doesn't have
a guarenteed ABI).
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
The Documentation/i386 and Documentation/x86_64 directories and their
contents have been moved into Documentation/x86. Fix references to
those files accordingly.
Signed-off-by: Uwe Hermann <uwe@hermann-uwe.de>
Signed-off-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This shows up when trying to bridge:
tap0: received packet with own address as source address
As Max Krasnyansky points out, there's no reason to give the guest the
same mac address as the TUN device.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Max Krasnyansky <maxk@qualcomm.com>
lguest uses a Waker process to break it out of the kernel (ie.
actually running the guest) when file descriptor needs attention.
Changing this from a process to a thread somewhat simplifies things:
it can directly access the fd_set of things to watch. More
importantly, it means that the Waker can see Guest memory correctly,
so /dev/vring file descriptors will work as anticipated (the
alternative is to actually mmap MAP_SHARED, but you can't do that with
/dev/zero).
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Since the correct timeout value varies, use a heuristic which adjusts
the timeout depending on how many packets we've seen. This gives
slightly worse results, but doesn't need tweaking when GSO is
introduced.
500 usec 19.1887 xmit 561141 recv 1 timeout 559657
Dynamic (278) 20.1974 xmit 214510 recv 5 timeout 214491 usec 278
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
virtio_ring has the ability to suppress notifications. This prevents
a guest exit for every packet, but we need to set a timer on packet
receipt to re-check if there were any remaining packets.
Here are the times for 1G TCP Guest->Host with different timeout
settings (it matters because the TCP window doesn't grow big enough to
fill the entire buffer):
Timeout value Seconds Xmit/Recv/Timeout
None (before) 25.3784 xmit 7750233 recv 1
2500 usec 62.5119 xmit 207020 recv 2 timeout 207020
1000 usec 34.5379 xmit 207003 recv 2 timeout 207003
750 usec 29.2305 xmit 207002 recv 1 timeout 207002
500 usec 19.1887 xmit 561141 recv 1 timeout 559657
250 usec 20.0465 xmit 214128 recv 2 timeout 214110
100 usec 19.2583 xmit 561621 recv 1 timeout 560153
(Note that these values are sensitive to the GSO patches which come
later, and probably other traffic-related variables, so take with a
large grain of salt).
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
To simplify the transition to when we publish indices in the ring
(and make shuffling my patch queue easier), wrap them in a lg_last_avail()
macro.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
This is a simple patch to add support for the virtio "hardware random
generator" to lguest. It gets about 1.2 MB/sec reading from /dev/hwrng
in the guest.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
If you've got a nice DHCP configuration which maps MAC
addresses to specific IP addresses, then you're going to
want to start your guest with one of those MAC addresses.
Also, in Fedora, we have persistent network interface naming
based on the MAC address, so with randomly assigned
addresses you're soon going to hit eth13. Who knows what
will happen then!
Allow assigning a MAC address to the network interface with
e.g.
--tunnet=bridge:eth0:00:FF:95:6B:DA:3D
or:
--tunnet=192.168.121.1:00:FF:95:6B:DA:3D
which is pretty unintelligable, but ...
(includes Rusty's minor rework)
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Rusty Russell
Matias Zabaljauregui
Uwe Hermann
Mark McLoughlin