Opened 18 months ago

Last modified 16 months ago

#15501 new bug

Fix unknown symbols/addresses in perf output

Reported by: last_g Owned by:
Priority: normal Milestone: Research needed
Component: Compiler (CodeGen) Version: 8.5
Keywords: perf, symbols, elf, linux Cc: bgamari, simonmar
Operating System: Linux Architecture: Unknown/Multiple
Type of failure: Debugging information is incorrect Test Case:
Blocked By: Blocking:
Related Tickets: Differential Rev(s): D4713
Wiki Page:

Description (last modified by bgamari)

After will be merged some addresses in perf output won't be mapped to the symbols. This needs investigation and fix.

A draft idea about the root cause:

The issue comes from the current perf symbolization algorithm.

The basic logic is (kind of) simple:

# Take all the @function symbols and put into a sorted list;
# the next steps are a hack to support handwritten assembly
# Take all the NOTYPE symbols with the size equals to 0 and put into the same ordered list;
# Run the symbols__fixup_end procedure which sets a symbol end address to be the beginning of the next symbol for every 0 sized symbol;
# If the last symbol is zero sized: set its size to be ~4k.
(The actual logic is more complicated because it also involves sections&map groups)

In GHC compiled binaries there are no @function symbols and most internal symbols are NOTYPE and 0 sized so we are ending up in the hack's code.

This logic effectively means that every address in our code space is attributed to some internal symbol (correct or not). Adding @function symbols with size directive stops this from happening. As the first guess, those addresses can come from _con_info entries which we don't mark as @function but in that case, there should be no unknown addresses in D4730 but we have some there too.

Change History (2)

comment:1 Changed 17 months ago by bgamari

Description: modified (diff)

comment:2 Changed 16 months ago by Simon Marlow <marlowsd@…>

In c23f057f/ghc:

Mark code related symbols as @function not @object

This diff is a part of the bigger project which goal is to improve
common profiling tools support (perf) for GHC binaries.

A similar job was already done and reverted in the past:


`Perf` and similar tools build in memory symbol table from the .symtab
section of the ELF file to display human-readable function names instead
of the addresses in the output. `Perf` uses only two types of symbols:
`@function` and `@notype` but GHC is not capable to produce any
`@function` symbols so the `perf` output is pretty useless (All the
haskell symbols that you can see in `perf` now are `@notype` internal
symbols extracted by mistake/hack).

The changes:
 * mark code related symbols as @function
 * small hack to mark InfoTable symbols as code if TABLES_NEXT_TO_CODE is true

 * The perf symbolization support is not complete after this patch but
   I'm working on the second patch.
 * Constructor symbols are not supported. To fix that we can issue extra
   local symbols which mark code sections as code and will be only used
   for debug.

Test Plan:
any additional ideas?

Perf output on stock ghc 8.4.1:
     9.78%  FibbSlow  FibbSlow            [.] ckY_info
     9.59%  FibbSlow  FibbSlow            [.] cjqd_info
     7.17%  FibbSlow  FibbSlow            [.] c3sg_info
     6.62%  FibbSlow  FibbSlow            [.] c1X_info
     5.32%  FibbSlow  FibbSlow            [.] cjsX_info
     4.18%  FibbSlow  FibbSlow            [.] s3rN_info
     3.82%  FibbSlow  FibbSlow            [.] c2m_info
     3.68%  FibbSlow  FibbSlow            [.] cjlJ_info
     3.26%  FibbSlow  FibbSlow            [.] c3sb_info
     3.19%  FibbSlow  FibbSlow            [.] cjPQ_info
     3.05%  FibbSlow  FibbSlow            [.] cjQd_info
     2.97%  FibbSlow  FibbSlow            [.] cjAB_info
     2.78%  FibbSlow  FibbSlow            [.] cjzP_info
     2.40%  FibbSlow  FibbSlow            [.] cjOS_info
     2.38%  FibbSlow  FibbSlow            [.] s3rK_info
     2.27%  FibbSlow  FibbSlow            [.] cjq0_info
     2.18%  FibbSlow  FibbSlow            [.] cKQ_info
     2.13%  FibbSlow  FibbSlow            [.] cjSl_info
     1.99%  FibbSlow  FibbSlow            [.] s3rL_info
     1.98%  FibbSlow  FibbSlow            [.] c2cC_info
     1.80%  FibbSlow  FibbSlow            [.] s3rO_info
     1.37%  FibbSlow  FibbSlow            [.] c2f2_info

Perf output on patched ghc:
     7.97%  FibbSlow  FibbSlow            [.] c3rM_info
     6.75%  FibbSlow  FibbSlow            [.] 0x000000000032cfa8
     6.63%  FibbSlow  FibbSlow            [.] cifA_info
     4.98%  FibbSlow  FibbSlow            [.] integerzmgmp_GHCziIntegerziType_eqIntegerzh_info
     4.55%  FibbSlow  FibbSlow            [.] chXn_info
     4.52%  FibbSlow  FibbSlow            [.] c3rH_info
     4.45%  FibbSlow  FibbSlow            [.] chZB_info
     4.04%  FibbSlow  FibbSlow            [.] Main_fibbzuslow_info
     4.03%  FibbSlow  FibbSlow            [.] stg_ap_0_fast
     3.76%  FibbSlow  FibbSlow            [.] chXA_info
     3.67%  FibbSlow  FibbSlow            [.] cifu_info
     3.25%  FibbSlow  FibbSlow            [.] ci4r_info
     2.64%  FibbSlow  FibbSlow            [.] s3rf_info
     2.42%  FibbSlow  FibbSlow            [.] s3rg_info
     2.39%  FibbSlow  FibbSlow            [.] integerzmgmp_GHCziIntegerziType_eqInteger_info
     2.25%  FibbSlow  FibbSlow            [.] integerzmgmp_GHCziIntegerziType_minusInteger_info
     2.17%  FibbSlow  FibbSlow            [.] ghczmprim_GHCziClasses_zeze_info
     2.09%  FibbSlow  FibbSlow            [.] cicc_info
     2.03%  FibbSlow  FibbSlow            [.] 0x0000000000331e15
     2.02%  FibbSlow  FibbSlow            [.] s3ri_info
     1.91%  FibbSlow  FibbSlow            [.] 0x0000000000331bb8
     1.89%  FibbSlow  FibbSlow            [.] ci4N_info

Reviewers: simonmar, niteria, bgamari, goldfire

Reviewed By: simonmar, bgamari

Subscribers: lelf, rwbarton, thomie, carter

GHC Trac Issues: #15501

Differential Revision:
Note: See TracTickets for help on using tickets.