similar to: [nbdkit PATCH v2 0/4] enable parallel nbd forwarding

I'm still working on the interleaving (and Rich reminded me on IRC that we still don't have THREAD_MODEL_PARALLEL working anywhere yet, anyways). Since nbdkit doesn't really have a parallel plugin yet, my testing on that front will have to use qemu-nbd as the original server, as well as qemu-io as the driver (qemu-io's aio_read and aio_write commands can be used to trigger

Now that we properly clean up 'trans' in the reader thread, we must not dereference 'trans' from the write thread at any point after trans has been added to the list unless we have grabbed it back off the list ourselves, or we risk an occasional use-after-free or even double free that valgrind can detect. Reported-by: Richard W.M. Jones <rjones@redhat.com> Fixes:

I'm hoping to implement .extents for the nbd plugin; this is a prerequisite. I'm not sure about patch 3 - if we like it, I'll squash it to 2, if we don't, I think we are okay just dropping it. I'm also wondering if we have to worry about malicious plugins that don't populate the entire .pread buffer in an effort to get nbdkit to expose portions of the heap; my patch 7 loses

I ran some local testing on my Fedora 29 system via: $ ./nbdkit memory 1m $ for i in `seq 10`; do ./nbdkit -U - --filter=stats nbd \ statsappend=true statsfile=$file hostname=localhost port=10809 \ --run '~/libnbd/examples/threaded-reads-and-writes $unixsocket' done Pre-patch, the runs averaged 1.266s, 1.30E+08 bits/s Post-patch, the runs averaged 1.154s, 1.42E+08

Patch 1 played with an early draft of Rich's Fedora 30 libnbd package: https://bugzilla.redhat.com/show_bug.cgi?id=1713767#c17 Note that comment 21 provides a newer package 0.1.1-1 with a different API; and that libnbd has more unreleased API changes in the pipeline (whether that will be called 0.2 or 0.1.2); so we'll have to tweak things based on what is actually available in distros.

Updated based on other changes that have happened in the meantime: - rely more on cleanup.h (throughout) - split structured read for easier review (patch 2 and 3 were combined in v1) - rely on nbdkit not leaking a server's partial answer (patch 3) - add tests (patch 5) - other bug fixes I found while testing it - drop EOVERFLOW patch for now; it will be separate once upstream NBD protocol

libnbd-0.1.2-1 is now available in Fedora 29/30 updates-testing, although it was not compiled against libxml2 so it lacks uri support (I ended up testing patch 4 with a self-built libnbd). Diffs since v1 - rebase to master, bump from libnbd 0.1 to 0.1.2, add URI support, better timing results Still not done - patch 5 needs associated tests Eric Blake (5): nbd: Check for libnbd nbd:

libnbd-0.1.4-1 is now available in Fedora 29/30 updates testing. Diffs since v2 - rebase to master, bump from libnbd 0.1.2 to 0.1.3+, add tests to TLS usage which flushed out the need to turn relative pathnames into absolute, doc tweaks Now that the testsuite covers TLS and libnbd has been fixed to provide the things I found lacking when developing v2, I'm leaning towards pushing this on

In preparation for allowing interleaved response, refactor the nbd forwarder so that writes are still done from the thread handling the original request from the client, but all reads are done by a dedicated reader thread. Control between the two flags is gated by a mutex for storing the transaction information, coupled with a pipe for the reader thread to send the final status back to the

With some crufty sed scripts we can generate functions that map from NBD protocol flags (eg. NBD_CMD_READ) to strings ("NBD_CMD_READ"). This works on GNU sed and with FreeBSD, also with GNU sed's --posix option, so I guess the sed code is POSIX-compatible. Rich.

Time to enhance the nbd plugin to request structured replies from the server. For now, deal only with structured reads. The server can now return sparse reads, even though we need nbdkit version 3 before we can in turn return sparse reads back to the client. In general, we have to assume the server is malicious, and so we must sanity check that it sends replies we expect. Thus, we have a choice

This one introduces a warning (error because I'm using -Werror): libtool: compile: gcc -DHAVE_CONFIG_H -I. -I../.. -I../../include -I../../src -Wall -Werror -g -O2 -MT nbdkit_nbd_plugin_la-nbd.lo -MD -MP -MF .deps/nbdkit_nbd_plugin_la-nbd.Tpo -c nbd.c -fPIC -DPIC -o .libs/nbdkit_nbd_plugin_la-nbd.o nbd.c: In function ‘nbd_reply’: nbd.c:306:19: error: ‘trans.cookie’ may be used uninitialized

Tested via: term1$ qemu-nbd -k $PWD/sock -t -f raw -x foo junk --trace=nbd_\* term2$ ./nbdkit -f -v -e bar nbd socket=$PWD/sock export=foo term3$ qemu-io -t none -f raw nbd://localhost:10809/bar --trace=nbd_\* and checking the traces to see that 'w 0 1' vs. 'w -f 0 1' was able to influence whether the FUA flag showed up at the server in term1. Still to go: figure out how to

I got annoyed by qemu-nbd's default of only allowing a single connection; combine that with nbdkit's nbd plugin, and even 'qemu-nbd --list' of nbdkit counts as the single connection and immediately hangs up. If we introduce a shared mode, then 'qemu-nbd --list' can connect as many times as it wants without killing the original qemu-nbd wrapped by nbdkit. But this in turn

This is about the simplest implementation of NBD Structured Replies (SR) that we can do right now. It accepts NBD_OPT_STRUCTURED_REPLIES when negotiated by the client, but only sends back the simplest possible SR when required to by NBD_CMD_READ. The rest of the time it will send back simple replies as before. We do not modify the plugin API so plugins are unable to send complex SRs. Also we

Hi Eric, There's a memory leak in the nbd client. The message (below) is not very useful because somehow debuginfo is missing in the plugin. However it's easily reproducible by doing: make check-valgrind TESTS=test-nbd I tried the attached patch to fix what I thought was the bug, but sadly the fix doesn't work for me :-( So I guess something else is going on, but it does look as

ThreadSanitizer [1] pointed out that in the nbd plugin, nbd_close() can attempt close() in the main thread while the worker thread is still attempting to start a read(). Normally, if the read() loses the race, it will get a harmless EBADF that exits the worker thread (which is what we want, as we are closing the connection anyway); but if another connection happens to start in that window, we

I'm not observing any noticeable performance differences, but I'm liking the diffstat. I can't push this patch until we release a new libnbd version with the _notify API addition, but am posting it now for playing with things. Eric Blake (2): nbd: Move transaction info from heap to stack nbd: Use nbdkit aio_*_notify variants plugins/nbd/nbd.c | 217

When we first used libnbd (nbdkit 1.14), it was brand new, so we left in the ability to build a limited nbd plugin without the use of libnbd for comparison. But now that libnbd has had more time under its belt, and we have learned that our nbd-standalone code is not getting much testing, it's time to follow through with our plan to finish off the old code, and now build the nbd plugin only

Accepting only Unix sockets can be a bit limiting; let's be more flexible. Eric Blake (2): nbd: Refactor Unix socket connection nbd: Support TCP socket plugins/nbd/nbdkit-nbd-plugin.pod | 36 ++++-- plugins/nbd/nbd.c | 175 ++++++++++++++++++++++-------- TODO | 3 - 3 files changed, 161 insertions(+), 53 deletions(-) -- 2.20.1