From b7e6a4162207785c66a1de6f4530499925b762b6 Mon Sep 17 00:00:00 2001 From: Emily Shaffer Date: Wed, 21 Jul 2021 18:27:06 -0700 Subject: tr2: make process info collection platform-generic To pave the way for non-Windows platforms to define trace2_collect_process_info(), reorganize the stub-or-definition schema to something which doesn't directly reference Windows. Platforms which want to collect parent process information in the future should: 1. Add an implementation to compat/ (e.g. compat/somearch/procinfo.c) 2. Add that object to COMPAT_OBJS to config.mak.uname (e.g. COMPAT_OBJS += compat/somearch/procinfo.o) 3. Define HAVE_PLATFORM_PROCINFO in config.mak.uname In the Windows case, this definition lives in compat/win32/trace2_win32_process_info.c, which is already conditionally added to COMPAT_OBJS; so let's add HAVE_PLATFORM_PROCINFO to hint to the build that compat/stub/procinfo.c should not be used. Signed-off-by: Emily Shaffer Helped-by: Jonathan Nieder Signed-off-by: Junio C Hamano --- compat/stub/procinfo.c | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 compat/stub/procinfo.c (limited to 'compat') diff --git a/compat/stub/procinfo.c b/compat/stub/procinfo.c new file mode 100644 index 0000000000..12c0a23c9e --- /dev/null +++ b/compat/stub/procinfo.c @@ -0,0 +1,11 @@ +#include "git-compat-util.h" + +#include "trace2.h" + +/* + * Stub. See sample implementations in compat/linux/procinfo.c and + * compat/win32/trace2_win32_process_info.c. + */ +void trace2_collect_process_info(enum trace2_process_info_reason reason) +{ +} -- cgit v1.2.3 From 2f732bf15e6dc9c2caf210784f180c6c059c570a Mon Sep 17 00:00:00 2001 From: Emily Shaffer Date: Wed, 21 Jul 2021 18:27:07 -0700 Subject: tr2: log parent process name It can be useful to tell who invoked Git - was it invoked manually by a user via CLI or script? By an IDE? In some cases - like 'repo' tool - we can influence the source code and set the GIT_TRACE2_PARENT_SID environment variable from the caller process. In 'repo''s case, that parent SID is manipulated to include the string "repo", which means we can positively identify when Git was invoked by 'repo' tool. However, identifying parents that way requires both that we know which tools invoke Git and that we have the ability to modify the source code of those tools. It cannot scale to keep up with the various IDEs and wrappers which use Git, most of which we don't know about. Learning which tools and wrappers invoke Git, and how, would give us insight to decide where to improve Git's usability and performance. Unfortunately, there's no cross-platform reliable way to gather the name of the parent process. If procfs is present, we can use that; otherwise we will need to discover the name another way. However, the process ID should be sufficient to look up the process name on most platforms, so that code may be shareable. Git for Windows gathers similar information and logs it as a "data_json" event. However, since "data_json" has a variable format, it is difficult to parse effectively in some languages; instead, let's pursue a dedicated "cmd_ancestry" event to record information about the ancestry of the current process and a consistent, parseable way. Git for Windows also gathers information about more than one generation of parent. In Linux further ancestry info can be gathered with procfs, but it's unwieldy to do so. In the interest of later moving Git for Windows ancestry logging to the 'cmd_ancestry' event, and in the interest of later adding more ancestry to the Linux implementation - or of adding this functionality to other platforms which have an easier time walking the process tree - let's make 'cmd_ancestry' accept an array of parentage. Signed-off-by: Emily Shaffer Signed-off-by: Junio C Hamano --- compat/linux/procinfo.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 55 insertions(+) create mode 100644 compat/linux/procinfo.c (limited to 'compat') diff --git a/compat/linux/procinfo.c b/compat/linux/procinfo.c new file mode 100644 index 0000000000..578fed4cd3 --- /dev/null +++ b/compat/linux/procinfo.c @@ -0,0 +1,55 @@ +#include "cache.h" + +#include "strbuf.h" +#include "strvec.h" +#include "trace2.h" + +static void get_ancestry_names(struct strvec *names) +{ + /* + * NEEDSWORK: We could gather the entire pstree into an array to match + * functionality with compat/win32/trace2_win32_process_info.c. + * To do so, we may want to examine /proc//stat. For now, just + * gather the immediate parent name which is readily accessible from + * /proc/$(getppid())/comm. + */ + struct strbuf procfs_path = STRBUF_INIT; + struct strbuf name = STRBUF_INIT; + + /* try to use procfs if it's present. */ + strbuf_addf(&procfs_path, "/proc/%d/comm", getppid()); + if (strbuf_read_file(&name, procfs_path.buf, 0)) { + strbuf_release(&procfs_path); + strbuf_trim_trailing_newline(&name); + strvec_push(names, strbuf_detach(&name, NULL)); + } + + return; + /* NEEDSWORK: add non-procfs-linux implementations here */ +} + +void trace2_collect_process_info(enum trace2_process_info_reason reason) +{ + if (!trace2_is_enabled()) + return; + + /* someday we may want to write something extra here, but not today */ + if (reason == TRACE2_PROCESS_INFO_EXIT) + return; + + if (reason == TRACE2_PROCESS_INFO_STARTUP) { + /* + * NEEDSWORK: we could do the entire ptree in an array instead, + * see compat/win32/trace2_win32_process_info.c. + */ + struct strvec names = STRVEC_INIT; + + get_ancestry_names(&names); + + if (names.nr) + trace2_cmd_ancestry(names.v); + strvec_clear(&names); + } + + return; +} -- cgit v1.2.3