[Tarantool-patches] [PATCH luajit 7/7] tools: introduce parsers for sysprof

Maxim Kokryashkin max.kokryashkin at gmail.com
Wed Sep 8 20:50:50 MSK 2021


Since the sysprof's binary output is not human-readable, so there is a
demand to create a parser. The parser, which this commit provides,
converts sysprof's event stream into the format that the flamegraph.pl
can process.

The sysprof parser machinery uses the same symtab module as memprof's
parser since the format is the same.

Part of tarantool/tarantool#781
---
 .gitignore                                    |   1 +
 .../misclib-sysprof-lapi.test.lua             |   2 +
 tools/CMakeLists.txt                          |  83 ++++++++
 tools/luajit-parse-sysprof.in                 |   6 +
 tools/sysprof.lua                             | 119 +++++++++++
 tools/sysprof/collapse.lua                    | 110 ++++++++++
 tools/sysprof/parse.lua                       | 188 ++++++++++++++++++
 7 files changed, 509 insertions(+)
 create mode 100644 tools/luajit-parse-sysprof.in
 create mode 100644 tools/sysprof.lua
 create mode 100755 tools/sysprof/collapse.lua
 create mode 100755 tools/sysprof/parse.lua

diff --git a/.gitignore b/.gitignore
index 2103a30f..099df060 100644
--- a/.gitignore
+++ b/.gitignore
@@ -19,4 +19,5 @@ cmake_uninstall.cmake
 compile_commands.json
 install_manifest.txt
 luajit-parse-memprof
+luajit-parse-sysprof
 luajit.pc
diff --git a/test/tarantool-tests/misclib-sysprof-lapi.test.lua b/test/tarantool-tests/misclib-sysprof-lapi.test.lua
index 17d83d1b..b9b3461f 100644
--- a/test/tarantool-tests/misclib-sysprof-lapi.test.lua
+++ b/test/tarantool-tests/misclib-sysprof-lapi.test.lua
@@ -8,6 +8,7 @@ jit.flush()
 
 local bufread = require "utils.bufread"
 local symtab = require "utils.symtab"
+local sysprof = require "sysprof.parse"
 
 local TMP_BINFILE = arg[0]:gsub(".+/([^/]+)%.test%.lua$", "%.%1.sysprofdata.tmp.bin")
 local BAD_PATH = arg[0]:gsub(".+/([^/]+)%.test%.lua$", "%1/sysprofdata.tmp.bin")
@@ -98,6 +99,7 @@ end
 
 local reader = bufread.new(TMP_BINFILE)
 symtab.parse(reader)
+sysprof.parse(reader)
 
 os.remove(TMP_BINFILE)
 
diff --git a/tools/CMakeLists.txt b/tools/CMakeLists.txt
index 61830e44..93a2f763 100644
--- a/tools/CMakeLists.txt
+++ b/tools/CMakeLists.txt
@@ -87,4 +87,87 @@ else()
   )
 endif()
 
+
+
+if(LUAJIT_DISABLE_SYSPROF)
+  message(STATUS "LuaJIT system profiler support is disabled")
+else()
+  # XXX: Can use genex here since the value need to be evaluated
+  # at the configuration phase. Fortunately, we know the exact
+  # path where LuaJIT binary is located.
+  set(LUAJIT_TOOLS_BIN ${LUAJIT_BINARY_DIR}/${LUAJIT_CLI_NAME})
+  set(LUAJIT_TOOLS_DIR ${CMAKE_CURRENT_SOURCE_DIR})
+  # XXX: Unfortunately, there is no convenient way to set
+  # particular permissions to the output file via CMake.
+  # Furthermore, I even failed to copy the given file to the same
+  # path to change its permissions. After looking at the docs, I
+  # realized that the valid solution would be too monstrous for
+  # such a simple task. As a result I've made the template itself
+  # executable, so the issue is resolved.
+  configure_file(luajit-parse-sysprof.in luajit-parse-sysprof @ONLY ESCAPE_QUOTES)
+
+
+  add_custom_target(tools-parse-sysprof EXCLUDE_FROM_ALL DEPENDS
+    luajit-parse-sysprof
+    sysprof/parse.lua
+    sysprof/collapse.lua
+    sysprof.lua
+    utils/bufread.lua
+    utils/symtab.lua
+  )
+  list(APPEND LUAJIT_TOOLS_DEPS tools-parse-sysprof)
+
+  install(FILES
+      ${CMAKE_CURRENT_SOURCE_DIR}/sysprof/parse.lua
+      ${CMAKE_CURRENT_SOURCE_DIR}/sysprof/collapse.lua
+    DESTINATION ${LUAJIT_DATAROOTDIR}/sysprof
+    PERMISSIONS
+      OWNER_READ OWNER_WRITE
+      GROUP_READ
+      WORLD_READ
+    COMPONENT tools-parse-sysprof
+  )
+  install(FILES
+      ${CMAKE_CURRENT_SOURCE_DIR}/utils/bufread.lua
+      ${CMAKE_CURRENT_SOURCE_DIR}/utils/symtab.lua
+    DESTINATION ${LUAJIT_DATAROOTDIR}/utils
+    PERMISSIONS
+      OWNER_READ OWNER_WRITE
+      GROUP_READ
+      WORLD_READ
+    COMPONENT tools-parse-sysprof
+  )
+  install(FILES
+      ${CMAKE_CURRENT_SOURCE_DIR}/sysprof.lua
+    DESTINATION ${LUAJIT_DATAROOTDIR}
+    PERMISSIONS
+      OWNER_READ OWNER_WRITE
+      GROUP_READ
+      WORLD_READ
+    COMPONENT tools-parse-sysprof
+  )
+  install(CODE
+    # XXX: The auxiliary script needs to be configured for to be
+    # used in repository directly. Furthermore, it needs to be
+    # reconfigured prior to its installation. The temporary
+    # <configure_file> output is stored to the project build
+    # directory and removed later after being installed. This
+    # script will have gone as a result of the issue:
+    # https://github.com/tarantool/tarantool/issues/5688.
+    "
+      set(LUAJIT_TOOLS_BIN ${CMAKE_INSTALL_PREFIX}/bin/${LUAJIT_CLI_NAME})
+      set(LUAJIT_TOOLS_DIR ${CMAKE_INSTALL_PREFIX}/${LUAJIT_DATAROOTDIR})
+      configure_file(${CMAKE_CURRENT_SOURCE_DIR}/luajit-parse-sysprof.in
+        ${PROJECT_BINARY_DIR}/luajit-parse-sysprof @ONLY ESCAPE_QUOTES)
+      file(INSTALL ${PROJECT_BINARY_DIR}/luajit-parse-sysprof
+        DESTINATION ${CMAKE_INSTALL_PREFIX}/bin
+        USE_SOURCE_PERMISSIONS
+      )
+      file(REMOVE ${PROJECT_BINARY_DIR}/luajit-parse-sysprof)
+    "
+    COMPONENT tools-parse-sysprof
+  )
+endif()
+
 add_custom_target(LuaJIT-tools DEPENDS ${LUAJIT_TOOLS_DEPS})
+
diff --git a/tools/luajit-parse-sysprof.in b/tools/luajit-parse-sysprof.in
new file mode 100644
index 00000000..2be25eb3
--- /dev/null
+++ b/tools/luajit-parse-sysprof.in
@@ -0,0 +1,6 @@
+#!/bin/bash
+#
+# Launcher for sysprof parser.
+
+LUA_PATH="@LUAJIT_TOOLS_DIR@/?.lua;;" \
+  @LUAJIT_TOOLS_BIN@ @LUAJIT_TOOLS_DIR@/sysprof.lua $@
diff --git a/tools/sysprof.lua b/tools/sysprof.lua
new file mode 100644
index 00000000..e6d8cc34
--- /dev/null
+++ b/tools/sysprof.lua
@@ -0,0 +1,119 @@
+local bufread = require "utils.bufread"
+local sysprof = require "sysprof.parse"
+local symtab = require "utils.symtab"
+local misc = require "sysprof.collapse"
+
+local stdout, stderr = io.stdout, io.stderr
+local match, gmatch = string.match, string.gmatch
+
+local split_by_vmstate = false
+
+-- Program options.
+local opt_map = {}
+
+function opt_map.help()
+  stdout:write [[
+luajit-parse-sysprof - parser of the profile collected
+                       with LuaJIT's sysprof.
+
+SYNOPSIS
+
+luajit-parse-sysprof [options] sysprof.bin
+
+Supported options are:
+
+  --help                            Show this help and exit
+  --split                           Split callchains by vmstate
+]]
+  os.exit(0)
+end
+
+function opt_map.split()
+  split_by_vmstate = true
+end
+
+-- Print error and exit with error status.
+local function opterror(...)
+  stderr:write("luajit-parse-sysprof.lua: ERROR: ", ...)
+  stderr:write("\n")
+  os.exit(1)
+end
+
+-- Parse single option.
+local function parseopt(opt, args)
+  local opt_current = #opt == 1 and "-"..opt or "--"..opt
+  local f = opt_map[opt]
+  if not f then
+    opterror("unrecognized option `", opt_current, "'. Try `--help'.\n")
+  end
+  f(args)
+end
+
+-- Parse arguments.
+local function parseargs(args)
+  -- Process all option arguments.
+  args.argn = 1
+  repeat
+    local a = args[args.argn]
+    if not a then
+      break
+    end
+    local lopt, opt = match(a, "^%-(%-?)(.+)")
+    if not opt then
+      break
+    end
+    args.argn = args.argn + 1
+    if lopt == "" then
+      -- Loop through short options.
+      for o in gmatch(opt, ".") do
+        parseopt(o, args)
+      end
+    else
+      -- Long option.
+      parseopt(opt, args)
+    end
+  until false
+
+  -- Check for proper number of arguments.
+  local nargs = #args - args.argn + 1
+  if nargs ~= 1 then
+    opt_map.help()
+  end
+
+  -- Translate a single input file.
+  -- TODO: Handle multiple files?
+  return args[args.argn]
+end
+
+local function traverse_calltree(node, prefix)
+  if node.is_leaf then
+    print(prefix..' '..node.count)
+  end
+
+  local sep_prefix = #prefix == 0 and prefix or prefix..';'
+
+  for name,child in pairs(node.children) do
+    traverse_calltree(child, sep_prefix..name)
+  end
+end
+
+local function dump(inputfile)
+  local reader = bufread.new(inputfile)
+
+  local symbols = symtab.parse(reader)
+
+  local events = sysprof.parse(reader)
+  local calltree = misc.collapse(events, symbols, split_by_vmstate)
+
+  traverse_calltree(calltree, '')
+
+  os.exit(0)
+end
+
+-- FIXME: this script should be application-independent.
+local args = {...}
+if #args == 1 and args[1] == "sysprof" then
+  return dump
+else
+  dump(parseargs(args))
+end
diff --git a/tools/sysprof/collapse.lua b/tools/sysprof/collapse.lua
new file mode 100755
index 00000000..2d684c95
--- /dev/null
+++ b/tools/sysprof/collapse.lua
@@ -0,0 +1,110 @@
+local parse = require "sysprof.parse"
+local vmdef = require "jit.vmdef"
+local symtab = require "utils.symtab"
+
+local VMST_NAMES = {
+  [parse.VMST.INTERP] = "VMST_INTERP",
+  [parse.VMST.LFUNC]  = "VMST_LFUNC",
+  [parse.VMST.FFUNC]  = "VMST_FFUNC",
+  [parse.VMST.CFUNC]  = "VMST_CFUNC",
+  [parse.VMST.GC]     = "VMST_GC",
+  [parse.VMST.EXIT]   = "VMST_EXIT",
+  [parse.VMST.RECORD] = "VMST_RECORD",
+  [parse.VMST.OPT]    = "VMST_OPT",
+  [parse.VMST.ASM]    = "VMST_ASM",
+  [parse.VMST.TRACE]  = "VMST_TRACE",
+}
+
+local M = {}
+
+local function new_node(name, is_leaf)
+  return {
+    name = name,
+    count = 0,
+    is_leaf = is_leaf,
+    children = {}
+  }
+end
+
+-- insert new child into a node (or increase counter in existing one)
+local function insert(name, node, is_leaf)
+  if node.children[name] == nil then
+    node.children[name] = new_node(name, is_leaf)
+  end
+
+  local child = node.children[name]
+  child.count = child.count + 1
+
+  return child
+end
+
+local function insert_lua_callchain(chain, lua, symbols)
+  for _,fr in pairs(lua.callchain) do
+    local name_lua
+
+    if fr.type == parse.FRAME.FFUNC then
+      name_lua = vmdef.ffnames[fr.ffid]
+    else
+      name_lua = symtab.demangle(symbols, {
+        addr = fr.addr,
+        line = fr.line
+      })
+      if lua.trace.id ~= nil and lua.trace.addr == fr.addr and
+          lua.trace.line == fr.line then
+        name_lua = 'TRACE_'..tostring(lua.trace.id)..'_'..name_lua
+      end
+    end
+
+    table.insert(chain, { name = name_lua })
+  end
+end
+
+-- merge lua and host callchains into one callchain representing
+-- transfer of control
+local function merge(event, symbols, sep_vmst)
+  local cc = {}
+  local lua_inserted = false
+
+  for _,h_fr in pairs(event.host.callchain) do
+    local name_host = symtab.demangle(symbols, { addr = h_fr.addr })
+
+    -- We assume that usually the transfer of control
+    -- looks like:
+    --    HOST -> LUA -> HOST
+    -- so for now, lua callchain starts from lua_pcall() call
+    if name_host == 'lua_pcall' then
+      insert_lua_callchain(cc, event.lua, symbols)
+      lua_inserted = true
+    end
+
+    table.insert(cc, { name = name_host })
+  end
+
+  if lua_inserted == false then
+    insert_lua_callchain(cc, event.lua, symbols)
+  end
+
+  if sep_vmst == true then
+    table.insert(cc, { name = VMST_NAMES[event.lua.vmstate] })
+  end
+
+  return cc
+end
+
+-- Collapse all the events into call tree
+function M.collapse(events, symbols, sep_vmst)
+  local root = new_node('root', false)
+
+  for _,ev in pairs(events) do
+    local callchain = merge(ev, symbols, sep_vmst)
+    local curr_node = root
+    for i=#callchain,1,-1 do
+      curr_node = insert(callchain[i].name, curr_node, false)
+    end
+    insert('', curr_node, true)
+  end
+
+  return root
+end
+
+return M
diff --git a/tools/sysprof/parse.lua b/tools/sysprof/parse.lua
new file mode 100755
index 00000000..766b0c99
--- /dev/null
+++ b/tools/sysprof/parse.lua
@@ -0,0 +1,188 @@
+-- Parser of LuaJIT's sysprof binary stream.
+-- The format spec can be found in <src/lj_sysprof.h>.
+
+local string_format = string.format
+
+local LJP_MAGIC = "ljp"
+local LJP_CURRENT_VERSION = 1
+
+local M = {}
+
+M.VMST = {
+  INTERP = 0,
+  LFUNC  = 1,
+  FFUNC  = 2,
+  CFUNC  = 3,
+  GC     = 4,
+  EXIT   = 5,
+  RECORD = 6,
+  OPT    = 7,
+  ASM    = 8,
+  TRACE  = 9,
+}
+
+
+M.FRAME = {
+  LFUNC  = 1,
+  CFUNC  = 2,
+  FFUNC  = 3,
+  BOTTOM = 0x80
+}
+
+local STREAM_END = 0x80
+
+local function new_event()
+  return {
+    lua = {
+      vmstate = 0,
+      callchain = {},
+      trace = {
+        id = nil,
+        addr = 0,
+        line = 0
+      }
+    },
+    host = {
+      callchain = {}
+    }
+  }
+end
+
+local function parse_lfunc(reader, event)
+  local addr = reader:read_uleb128()
+  local line = reader:read_uleb128()
+  table.insert(event.lua.callchain, {
+    type = M.FRAME.LFUNC,
+    addr = addr,
+    line = line
+  })
+end
+
+local function parse_ffunc(reader, event)
+  local ffid = reader:read_uleb128()
+  table.insert(event.lua.callchain, {
+    type = M.FRAME.FFUNC,
+    ffid = ffid,
+  })
+end
+
+local function parse_cfunc(reader, event)
+  local addr = reader:read_uleb128()
+  table.insert(event.lua.callchain, {
+    type = M.FRAME.CFUNC,
+    addr = addr
+  })
+end
+
+local frame_parsers = {
+  [M.FRAME.LFUNC] = parse_lfunc,
+  [M.FRAME.FFUNC] = parse_ffunc,
+  [M.FRAME.CFUNC] = parse_cfunc
+}
+
+local function parse_lua_callchain(reader, event)
+  while true do
+    local frame_header = reader:read_octet()
+    if frame_header == M.FRAME.BOTTOM then
+      break
+    end
+    frame_parsers[frame_header](reader, event)
+  end
+end
+
+--~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~--
+
+local function parse_host_callchain(reader, event)
+  local addr = reader:read_uleb128()
+
+  while addr ~= 0 do
+    table.insert(event.host.callchain, {
+      addr = addr
+    })
+    addr = reader:read_uleb128()
+  end
+end
+
+--~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~--
+
+local function parse_trace_callchain(reader, event)
+  event.lua.trace.id   = reader:read_uleb128()
+  event.lua.trace.addr = reader:read_uleb128()
+  event.lua.trace.line = reader:read_uleb128()
+end
+
+--~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~--
+
+local function parse_host_only(reader, event)
+  parse_host_callchain(reader, event)
+end
+
+local function parse_lua_host(reader, event)
+  parse_lua_callchain(reader, event)
+  parse_host_callchain(reader, event)
+end
+
+local function parse_trace(reader, event)
+  parse_trace_callchain(reader, event)
+  -- parse_lua_callchain(reader, event)
+end
+
+local event_parsers = {
+  [M.VMST.INTERP] = parse_host_only,
+  [M.VMST.LFUNC]  = parse_lua_host,
+  [M.VMST.FFUNC]  = parse_lua_host,
+  [M.VMST.CFUNC]  = parse_lua_host,
+  [M.VMST.GC]     = parse_host_only,
+  [M.VMST.EXIT]   = parse_host_only,
+  [M.VMST.RECORD] = parse_host_only,
+  [M.VMST.OPT]    = parse_host_only,
+  [M.VMST.ASM]    = parse_host_only,
+  [M.VMST.TRACE]  = parse_trace
+}
+
+local function parse_event(reader, events)
+  local event = new_event()
+
+  local vmstate = reader:read_octet()
+  if vmstate == STREAM_END then
+    -- TODO: samples & overruns
+    return false
+  end
+
+  assert(0 <= vmstate and vmstate <= 9, "Vmstate "..vmstate.." is not valid")
+  event.lua.vmstate = vmstate
+
+  event_parsers[vmstate](reader, event)
+
+  table.insert(events, event)
+  return true
+end
+
+function M.parse(reader)
+  local events = {}
+
+  local magic = reader:read_octets(3)
+  local version = reader:read_octets(1)
+  -- Dummy-consume reserved bytes.
+  local _ = reader:read_octets(3)
+
+  if magic ~= LJP_MAGIC then
+    error("Bad LJP format prologue: "..magic)
+  end
+
+  if string.byte(version) ~= LJP_CURRENT_VERSION then
+    error(string_format(
+      "LJP format version mismatch: the tool expects %d, but your data is %d",
+      LJP_CURRENT_VERSION,
+      string.byte(version)
+    ))
+  end
+
+  while parse_event(reader, events) do
+    -- Empty body.
+  end
+
+  return events
+end
+
+return M
-- 
2.33.0



More information about the Tarantool-patches mailing list