| Commit message (Collapse) | Author | Age | Files | Lines |
| |
|
| |
|
| |
|
| |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Using workqueues frees us from having to manage the lifecycle
of three dedicated threads. Discovery (alt server checks) and
sending keepalive packets is now done using work on the
power efficient system queue. Sending and receiving happens
via dedicated work queues with higher priority.
blk-mq has also been around for quite a while in the kernel,
so switching to it doesn't hurt backwards compatibility.
As the code is now refactored to work more as blk-mq is designed,
backwards compatibility even improved while at the same time
freeing us from an arsenal of macros that were required to make
the blk-mq port look and feel like the old implementation.
For example, the code now compiles on CentOS 7 with kernel 3.10
without requiring special macros to detect the heavily modified
RedHat kernel with all its backported features.
A few other design limitations have been rectified along the way,
e.g. switching to another server now doesn't internally disconnect
from the current one first, which theoretically could lead to a
non-working setup, if the new server isn't reachable and then -
because of some transient network error - switching back also
fails. As the discover-thread was torn down from the disconnect
call, the connection would also not repair itself eventually.
we now establish the new connection in parallel to the old one,
and only if that succeeds do we replace the old one with it,
similar to how the automatic alt-server switch already does it.
|
| |
|
| |
|
| |
|
|
|
|
|
|
|
| |
This spams scary red errors to dmesg when really an unreachable alt
server isn't that much of a deal during normal operation. Change the
log level to debug instead.
Might even consider not printing anything at all.
|
| |
|
| |
|
| |
|
| |
|
| |
|
| |
|
|
|
|
|
|
|
|
| |
- Remove the ugly timeout hack that apparently isn't required after all.
- Set a few socket options that appear to make sense in out use case (no
linger, only one SYN retry, NODELAY).
- Adapt socket timeout in panic mode, in case we're on a very bad
connection.
|
|
|
|
|
|
|
| |
Similar logic already exists in the fuse client:
Count how many times in a row a server was fastest when
measuring RTTs, and lower the switching threshold
more the higher the count gets.
|
|
|
|
|
|
|
|
| |
Convert dnbd3_host_t to struct sockaddr immediately when
adding alt servers, so we don't have to convert it every time
we establish a connection. Additionally we can now use %pISpc
in printf-like functions instead of having if/else constructs
whenever we want to print an address.
|
| |
|
| |
|
| |
|
|
|
|
|
|
|
|
|
|
| |
Formerly, the request that was about to be received was looked up in
the receive queue without removing it, then the request payload was
received from the socket while the lock was not being held, and finally,
the lock was required again and the request removed from the queue.
This is dangrous as another thread can concurrently take the request
from the queue while the receive thread reads the payload from the
socket, leading to a double-free by calling blk_mq_end_request twice.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Previously disconnect was protected against concurrent calls, but connect
wasn't. It was easy to crash the kernel when calling connect and
disconnect IOCTLs in a tight loop concurrently.
A global lock was introduced to make sure only one caller can change the
connection state at a time. dev->connection_lock needs to be aquired
when calling dnbd3_net_connect or _disconnect.
This atomic_t based locking mechanism should be turned into a mutex in a
next step, relying on mutex_trylock for cases where we don't have the
cmpxchg-schedule() loop.
Along the way it was noticed that the send/receive timeouts don't apply
to kernel_connect, which might have been the case in older 3.x kernel
versions. A crude workaround using nonblocking connect has been
introduced to emulate this, but a clean solution for this is welcomed.
Also, devices are now properly closed on module unload.
|
|
|
|
|
|
|
| |
This patch replaces the __VA_OPT__ varadic macro for the C preprocessor
with a builtin GCC extension for optional varadic arguments. Based on
this change, the dnbd3 Linux kernel module can be also built with GCC
7.5 on a fresh Ubuntu 18.04 with Linux kernel version 4.19.x.
|
|
|
|
|
|
| |
This patch adds the feature to manually switch the dnbd3-server to a
specified server. The switching is implemented by the use of the ioctl
call SWITCH.
|
|
|
|
|
|
|
|
|
|
| |
The ioctl OPEN call for DNBD3 devices exposed by the dnbd3 Linux kernel
module, is extended with a fixed array of dnbd3 hosts. The fixed array
allows the dnbd3-client to submit host information (IP address and port)
of multiple dnbd3-servers. This information is used to probe all
submitted dnbd3-servers and add them to the alternative dnbd3-server
list. If at least one dnbd3-server is not reachable, the OPEN ioctl call
will abort with an error code.
|
|
|
|
|
|
|
|
|
|
| |
This change restructures the source code directories, separates shared
form non-shared application code and adds CMake dependencies. These
dependencies allow the tracking of changes and trigger a rebuild of
those build targets where changed files are involved.
WARNING: Note that the support of the DNBD3_SERVER_AFL build option is
not supported yet. Thus, the option should be never turned on.
|
|
|
|
|
|
|
|
|
| |
This patch implements the old time structures to support Linux kernels
prior to version 5.1.x.
WARNING: This change to the deprecated time structures does not solve
the Y2038 issue. Thus, the dnbd3 Linux kernel module can only run under
Linux kernels prior to version 5.1.x until the end of year 2037.
|
|
|
|
|
|
|
|
|
|
| |
This patch replaces the deprecated kernel_setsockopt() function with the
socket generic function sock_setsockopt() to set the send and receive
timeout for all used sockets in the kernel module. The timeout data type
is choosen according to the available kernel version, so that the dnbd3
kernel module supports the new y2038-problem-solving socket options.
With both changes, the kernel module runs on Linux kernel 5.4 LTS and
later (including Linux kernel 5.9).
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
This change converts all debug messages to support the Linux kernel's
dynamic debug feature. Debug messages can be enabled or disabled by
the debug feature if the
- kernel module is built in debug mode (EXTRA_CFLAGS=-g -DDEBUG)
- Linux kernel supports dynamic debug (CONFIG_DYNAMIC_DEBUG is set)
This patch removes outdated kernel compatibility macros (used for Linux
kernels in version 4.x) and cleans up the kernel module's code.
|
|
|
|
|
|
|
|
|
|
|
| |
This converts the dnbd3 kernel module driver to use the blk-mq
infrastructure, which allows the dnbd3 kernel module driver to be
compatible with Linux kernels in version 5.x or later. The conversion of
the implementation uses one hardware queue to preserve the existing
send/receive and load-balancing logic, but can be scaled up in the
future. In addition to that, time measurements in the implementation are
converted to ktime based accessors to replace the use of deprecated time
interfaces.
|
| |
|
| |
|
| |
|
|
|
|
| |
Version check for pre or post 4.11
|
| |
|
| |
|
|
|
|
| |
https://github.com/torvalds/linux/commit/aebf526b53aea164508730427597d45f3e06b376
|
|
|
|
|
|
|
| |
AF_INET luckily was "2" on all platforms checked, so no problems
there with interoperation, but AF_INET6 is different between
Linux, BSD, Windows and possibly others, so map back and forth
between AF_INET/AF_INET6 and HOST_IP4/HOST_IP6 to fix this.
|
| |
|
|
|
|
|
|
|
|
|
|
| |
- Disable panic timeout that reports errors to block layer by default
- Get rid of "is_server" used by old proxy mode, introduce
"honor_server_alts" that just controls whether we use alts provided by
the server
- Allow switching servers when we only have 3 RTT measurements
- If using alts provided by server, don't ignore those that come from
other servers than the initial one
|
| |
|
| |
|
| |
|
|
|
|
| |
It's a bad idea.
|
| |
|
|
|
|
|
| |
[KERNEL] Remove server mode support as it's not needed anymore
[KERNEL] Some more sanity checks and debug messages
|