Version: | 1 as of 2016-11-08 |
---|
XRay is a function call tracing system which combines compiler-inserted instrumentation points and a runtime library that can dynamically enable and disable the instrumentation.
More high level information about XRay can be found in the XRay whitepaper.
This document describes how to use XRay as implemented in LLVM.
XRay consists of three main parts:
Compiler-inserted instrumentation points.
A runtime library for enabling/disabling tracing at runtime.
A suite of tools for analysing the traces.
NOTE: As of February 27, 2017 , XRay is only available for the following architectures running Linux: x86_64, arm7 (no thumb), aarch64, powerpc64le, mips, mipsel, mips64, mips64el.
The compiler-inserted instrumentation points come in the form of nop-sleds in the final generated binary, and an ELF section named xray_instr_map which contains entries pointing to these instrumentation points. The runtime library relies on being able to access the entries of the xray_instr_map, and overwrite the instrumentation points at runtime.
You can use XRay in a couple of ways:
The rest of this section covers these main ways and later on how to customise what XRay does in an XRay-instrumented binary.
The easiest way of getting XRay instrumentation for your application is by enabling the -fxray-instrument flag in your clang invocation.
For example:
clang -fxray-instrument ..
By default, functions that have at least 200 instructions will get XRay instrumentation points. You can tweak that number through the -fxray-instruction-threshold= flag:
clang -fxray-instrument -fxray-instruction-threshold=1 ..
You can also specifically instrument functions in your binary to either always or never be instrumented using source-level attributes. You can do it using the GCC-style attributes or C++11-style attributes.
[[clang::xray_always_intrument]] void always_instrumented();
[[clang::xray_never_instrument]] void never_instrumented();
void alt_always_instrumented() __attribute__((xray_always_intrument));
void alt_never_instrumented() __attribute__((xray_never_instrument));
When linking a binary, you can either manually link in the XRay Runtime Library or use clang to link it in automatically with the -fxray-instrument flag. Alternatively, you can statically link-in the XRay runtime library from compiler-rt – those archive files will take the name of libclang_rt.xray-{arch} where {arch} is the mnemonic supported by clang (x86_64, arm7, etc.).
If you’re using LLVM IR directly, you can add the function-instrument string attribute to your functions, to get the similar effect that the C/C++/Objective-C source-level attributes would get:
define i32 @always_instrument() uwtable "function-instrument"="xray-always" {
; ...
}
define i32 @never_instrument() uwtable "function-instrument"="xray-never" {
; ...
}
You can also set the xray-instruction-threshold attribute and provide a numeric string value for how many instructions should be in the function before it gets instrumented.
define i32 @maybe_instrument() uwtable "xray-instruction-threshold"="2" {
; ...
}
The XRay Runtime Library is part of the compiler-rt project, which implements the runtime components that perform the patching and unpatching of inserted instrumentation points. When you use clang to link your binaries and the -fxray-instrument flag, it will automatically link in the XRay runtime.
The default implementation of the XRay runtime will enable XRay instrumentation before main starts, which works for applications that have a short lifetime. This implementation also records all function entry and exit events which may result in a lot of records in the resulting trace.
Also by default the filename of the XRay trace is xray-log.XXXXXX where the XXXXXX part is randomly generated.
These options can be controlled through the XRAY_OPTIONS environment variable, where we list down the options and their defaults below.
Option | Type | Default | Description |
---|---|---|---|
patch_premain | bool | false | Whether to patch instrumentation points before main. |
xray_naive_log | bool | true | Whether to install the naive log implementation. |
xray_logfile_base | const char* | xray-log. | Filename base for the XRay logfile. |
xray_fdr_log | bool | false | Whether to install the Flight Data Recorder (FDR) mode. |
If you choose to not use the default logging implementation that comes with the XRay runtime and/or control when/how the XRay instrumentation runs, you may use the XRay APIs directly for doing so. To do this, you’ll need to include the xray_interface.h from the compiler-rt xray directory. The important API functions we list below:
There are some requirements on the logging handler to be installed for the thread-safety of operations to be performed by the XRay runtime library:
XRay supports a logging mode which allows the application to only capture a fixed amount of memory’s worth of events. Flight Data Recorder (FDR) mode works very much like a plane’s “black box” which keeps recording data to memory in a fixed-size circular queue of buffers, and have the data available programmatically until the buffers are finalized and flushed. To use FDR mode on your application, you may set the xray_fdr_log option to true in the XRAY_OPTIONS environment variable (while also optionally setting the xray_naive_log to false).
When FDR mode is on, it will keep writing and recycling memory buffers until the logging implementation is finalized – at which point it can be flushed and re-initialised later. To do this programmatically, we follow the workflow provided below:
// Patch the sleds, if we haven't yet.
auto patch_status = __xray_patch();
// Maybe handle the patch_status errors.
// When we want to flush the log, we need to finalize it first, to give
// threads a chance to return buffers to the queue.
auto finalize_status = __xray_log_finalize();
if (finalize_status != XRAY_LOG_FINALIZED) {
// maybe retry, or bail out.
}
// At this point, we are sure that the log is finalized, so we may try
// flushing the log.
auto flush_status = __xray_log_flushLog();
if (flush_status != XRAY_LOG_FLUSHED) {
// maybe retry, or bail out.
}
The default settings for the FDR mode implementation will create logs named similarly to the naive log implementation, but will have a different log format. All the trace analysis tools (and the trace reading library) will support all versions of the FDR mode format as we add more functionality and record types in the future.
NOTE: We do not however promise perpetual support for when we update the log versions we support going forward. Deprecation of the formats will be announced and discussed on the developers mailing list.
XRay allows for replacing the default FDR mode logging implementation using the following API:
We currently have the beginnings of a trace analysis tool in LLVM, which can be found in the tools/llvm-xray directory. The llvm-xray tool currently supports the following subcommands:
These subcommands use various library components found as part of the XRay libraries, distributed with the LLVM distribution. These are:
There are a number of ongoing efforts for expanding the toolset building around the XRay instrumentation system.
We have more subcommands and modes that we’re thinking of developing, in the following forms:
We’re looking forward to contributions to port XRay to more architectures and operating systems.