| Age | Commit message (Collapse) | Author |
|---|
|
|
|
9P2000.L is silent as to how readdir RPCs interact with directory mutation. The
most performant option is for Treaddir with offset=0 to restart iteration,
avoiding needing to walk+open+clunk a new directory fid between invocations of
getdents64(2), and the VFS2 gofer client assumes this is the case. Make this
actually true for the runsc fsgofer.
Fixes #3344, #3345, #3355
PiperOrigin-RevId: 324090384
|
|
|
|
... when it is possible.
The guitar gVisorKernel*Workflow-s runs test with the local execution_method.
In this case, blaze runs test cases locally without sandboxes. This means
that all tests run in the same network namespace. We have a few tests which
use hard-coded network ports and they can fail if one of these port will be
used by someone else or by another test cases.
PiperOrigin-RevId: 323137254
|
|
|
|
Implement WalkGetAttr() to reuse the stat that is already
needed for Walk(). In addition, cache file QID, so it
doesn't need to stat the file to compute it.
open(2) time improved by 10%:
Baseline: 6780 ns
Change: 6083 ns
Also fixed file type which was not being set in all places.
PiperOrigin-RevId: 323102560
|
|
|
|
Open tries to reuse the control file to save syscalls and
file descriptors when opening a file. However, when the
control file was opened using O_PATH (e.g. no file permission
to open readonly), Open() would not check for it.
PiperOrigin-RevId: 322821729
|
|
|
|
This change fixes a few things:
- creating sockets using mknod(2) is supported via vfs2
- fsgofer can create regular files via mknod(2)
- mode = 0 for mknod(2) will be interpreted as regular file in vfs2 as well
Updates #2923
PiperOrigin-RevId: 320074267
|
|
|
|
The previous format skipped many important structs that
are pointers, especially for cgroups. Change to print
as json, removing parts of the spec that are not relevant.
Also removed debug message from gofer that can be very
noisy when directories are large.
PiperOrigin-RevId: 316713267
|
|
|
|
PiperOrigin-RevId: 313663382
|
|
|
|
|
|
|
|
PiperOrigin-RevId: 305344989
|
|
|
|
Note that these are only implemented for tmpfs, and other impls will still
return EOPNOTSUPP.
PiperOrigin-RevId: 293899385
|
|
|
|
|
|
|
|
Go 1.14 has a workaround for a Linux 5.2-5.4 bug which requires mlock'ing the g
stack to prevent register corruption. We need to allow this syscall until it is
removed from Go.
PiperOrigin-RevId: 293212935
|
|
|
|
PiperOrigin-RevId: 291745021
|
|
|
|
There was a very bare get/setxattr in the InodeOperations interface. Add
context.Context to both, size to getxattr, and flags to setxattr.
Note that extended attributes are passed around as strings in this
implementation, so size is automatically encoded into the value. Size is
added in getxattr so that implementations can return ERANGE if a value is larger
than can fit in the user-allocated buffer. This prevents us from unnecessarily
passing around an arbitrarily large xattr when the user buffer is actually too
small.
Don't use the existing xattrwalk and xattrcreate messages and define our
own, mainly for the sake of simplicity.
Extended attributes will be implemented in future commits.
PiperOrigin-RevId: 290121300
|
|
|
|
* Rename syncutil to sync.
* Add aliases to sync types.
* Replace existing usage of standard library sync package.
This will make it easier to swap out synchronization primitives. For example,
this will allow us to use primitives from github.com/sasha-s/go-deadlock to
check for lock ordering violations.
Updates #1472
PiperOrigin-RevId: 289033387
|
|
|
|
PiperOrigin-RevId: 285012278
|
|
|
|
Refer to golang mallocgc(), each time of allocating an object > 32 KB,
a gc will be triggered.
When we do readdir, sentry always passes 65535, which leads to a malloc
of 65535 * sizeof(p9.Direnta) > 32 KB.
Considering we already use slice append, let's avoid defining the
capability for this slide.
Command for test:
Before this change:
(container)$ time tree linux-5.3.1 > /dev/null
real 0m54.272s
user 0m2.010s
sys 0m1.740s
(CPU usage of Gofer: ~30 cores)
(host)$ perf top -p <pid-of-gofer>
42.57% runsc [.] runtime.gcDrain
23.41% runsc [.] runtime.(*lfstack).pop
9.74% runsc [.] runtime.greyobject
8.06% runsc [.] runtime.(*lfstack).push
4.33% runsc [.] runtime.scanobject
1.69% runsc [.] runtime.findObject
1.12% runsc [.] runtime.findrunnable
0.69% runsc [.] runtime.runqgrab
...
(host)$ mkdir test && cd test
(host)$ for i in `seq 1 65536`; do mkdir $i; done
(container)$ time ls test/ > /dev/null
real 2m10.934s
user 0m0.280s
sys 0m4.260s
(CPU usage of Gofer: ~1 core)
After this change:
(container)$ time tree linux-5.3.1 > /dev/null
real 0m22.465s
user 0m1.270s
sys 0m1.310s
(CPU usage of Gofer: ~1 core)
$ perf top -p <pid-of-gofer>
20.57% runsc [.] runtime.gcDrain
7.15% runsc [.] runtime.(*lfstack).pop
4.11% runsc [.] runtime.scanobject
3.78% runsc [.] runtime.greyobject
2.78% runsc [.] runtime.(*lfstack).push
...
(host)$ mkdir test && cd test
(host)$ for i in `seq 1 65536`; do mkdir $i; done
(container)$ time ls test/ > /dev/null
real 0m13.338s
user 0m0.190s
sys 0m3.980s
(CPU usage of Gofer: ~0.8 core)
Fixes #898
Signed-off-by: Jianfeng Tan <henry.tjf@antfin.com>
|
|
|
|
This is required to implement O_TRUNC correctly on filesystems backed by
gofers.
9P2000.L: "lopen prepares fid for file I/O. flags contains Linux open(2) flags
bits, e.g. O_RDONLY, O_RDWR, O_WRONLY."
open(2): "The argument flags must include one of the following access modes:
O_RDONLY, O_WRONLY, or O_RDWR. ... In addition, zero or more file creation
flags and file status flags can be bitwise-or'd in flags."
The reference 9P2000.L implementation also appears to expect arbitrary flags,
not just access modes, in Tlopen.flags:
https://github.com/chaos/diod/blob/master/diod/ops.c#L703
PiperOrigin-RevId: 278972683
|
|
|
|
newfstatat() syscall is not supported on arm64, so we resort
to use the fstatat() syscall.
Signed-off-by: Haibo Xu <haibo.xu@arm.com>
Change-Id: I9e89d46c5ec9ae07db201c9da5b6dda9bfd2eaf0
|
|
|
|
Since the syscall.Stat_t.Nlink is defined as different types on
amd64 and arm64(uint64 and uint32 respectively), we need to cast
them to a unified uint64 type in gVisor code.
Signed-off-by: Haibo Xu <haibo.xu@arm.com>
Change-Id: I7542b99b195c708f3fc49b1cbe6adebdd2f6e96b
|
|
|
|
This change fixes several issues with the fsgofer host UDS support. Notably, it
adds support for SOCK_SEQPACKET and SOCK_DGRAM sockets [1]. It also fixes
unsafe use of unet.Socket, which could cause a panic if Socket.FD is called
when err != nil, and calls to Socket.FD with nothing to prevent the garbage
collector from destroying and closing the socket.
A set of tests is added to exercise host UDS access. This required extracting
most of the syscall test runner into a library that can be used by custom
tests.
Updates #235
Updates #1003
[1] N.B. SOCK_DGRAM sockets are likely not particularly useful, as a server can
only reply to a client that binds first. We don't allow bind, so these are
unlikely to be used.
PiperOrigin-RevId: 275558502
|
|
|
|
fsgofer.attachPoint.Attach has a bunch of funky special logic to create a RW
file or connect a socket rather than creating a standard control file like
localFile.Walk.
This is unecessary and error-prone, as the attach point still has to go through
Open or Connect which will properly convert the control file to something
usable. As such, switch the logic to be equivalent to a simple Walk.
Updates #235
PiperOrigin-RevId: 274827872
|
|
|
|
rt_sigreturn is required for signal handling (e.g., SIGSEGV for nil-pointer
dereference). Before this, nil-pointer dereferences cause a syscall violation
instead of a panic.
PiperOrigin-RevId: 274028767
|
|
|
|
Updates #235
PiperOrigin-RevId: 271475319
|
|
|
|
PiperOrigin-RevId: 271235134
|
