aboutsummaryrefslogtreecommitdiffstats
path: root/erts
AgeCommit message (Collapse)Author
2012-03-22Update dtrace for changes in R15Björn-Egil Dahlberg
2012-03-22Add DTrace support for OS X, Solaris, and Linux (via SystemTap), 4/4Scott Lystig Fritchie
Add probes to (mostly) the efile_drv.c driver and other file I/O-related source files.
2012-03-22Add DTrace support for OS X, Solaris, and Linux (via SystemTap), 3/4Scott Lystig Fritchie
Add probes to the virtual machine, except (mostly) the efile_drv.c driver and other file I/O-related source files.
2012-03-22Add DTrace support for OS X, Solaris, and Linux (via SystemTap), 1/4Scott Lystig Fritchie
Since it's been quite a while since I've written C code, *and* I haven't done any significant hacking on the VM itself in years, it's quite likely that I haven't done things in 100% proper style. Or my co-collaborators Dustin Sallings (CouchBase) or Michal Ptaszek (Erlang Solutions). My intent for this patch is to start discussion and review of DTrace support for consideration for the R15 release. For additional background on the motivation for this work, please see the slides for the presentation at the Erlang User Conference 2011 in Stockholm: https://www.erlang-factory.com/upload/presentations/462/euc2011-draft2.pdf Changes relative to dtrace-review2 branch: * Fix errors in OTP test suite 'kernel' file_SUITE * Fix errors in OTP test suite 'kernel' prim_file_SUITE * Fix bad pointer bug in efile_drv.c flush_write() * Move the DTrace material from the top of `README.md` into a new file, `README.dtrace.md` Changes since last push to GitHub (relative to commit 5828a4fb28, which was the former `dtrace-review1` branch): * Rebased onto 14 Nov 2011's "master" branch * Recent changes to the async task queuing mechanism means that the async worker queue length is not available. A bogus value of -1 is hard-coded until there's a good way to peek into the new queue structure and find the queue length. * Small fixes based on review comments by Mikael Pettersson, Andrew Thompson, and Andreas Schultz. Add autoconf support: use "./configure --enable-dtrace" on all supported platforms: * OS X Snow Leopard or later * Solaris 10 or OpenSolaris * Linux, via SystemTap's DTrace compatibility packages * FreeBSD 9.0RC1. FreeBSD 8 and earlier do not have support for USDT, DTrace's User-land Statically Defined Tracing. See the file `erts/emulator/beam/erlang_dtrace.d` for the definition of all DTrace probes in the virtual machine so far. Example D scripts can be found in `lib/dtrace/examples`. Note that if you see the error message `{name of probe} does not match any probes`, then there is no Erlang VM process + DTrace probes running. To fix, start a DTrace-enabled VM or remove `-q` from the `dtrace` command line. The `lib/dtrace` directory contains a small code-only OTP application that contains code that allows Erlang code to trigger a DTrace probe. Dynamic creation & deletion of DTrace probes is not currently supported, so the `dtrace:p()` function is hacked to allow a variable number of arguments (up to four integers and up to four strings) to be used. See the comments at the top of `lib/dtrace/src/dtrace.c` for more detail. One feature that may be controversial is the notion I've introduced of a special process dictionary key that can be used by Erlang code to tag I/O operations for an application-specific purpose. Right now, that tag's name is `dtrace_utag`. The dictionary keys used by `sys` and other modules start with a dollar sign. Perhaps there is some convention (but not a dollar sign?) that this tag should use? The purpose of the process dictionary key is to allow the tag to be included in trace messages, e.g. for file I/O, without changing the API of the `file.erl` module's functions. For example, here's a use of the tag when calling the `file:rename/2` function: (bar@sbb2)1> put(dtrace_utag, "GGOOOAAALL!!!!!"). undefined (bar@sbb2)2> dtrace:init(). ok %% Now start both the `user-probe.d` and `efile_drv.d` D scripts %% found in the `lib/dtrace/examples` directory. (bar@sbb2)3> dtrace:p(7, 8, 9, "one", "four"). true %% The output from the `user-probe.d` script: <0.40.0> GGOOOAAALL!!!!! 7 8 9 0 'one' 'four' '' '' (bar@sbb2)4> file:rename("old-name", "new-name"). {error,enoent} %% The output from the `efile_drv.d` script: async I/O pool port #Port<0.59> queue len 1 async I/O pool port #Port<0.59> queue len 0 efile_drv enter tag={1,110} user tag GGOOOAAALL!!!!! | RENAME (12) | args: old-name new-name , 0 0 (port #Port<0.59>) async I/O worker tag={1,110} | RENAME (12) | efile_drv-int_entry async I/O worker tag={1,110} | RENAME (12) | efile_drv-int_return efile_drv return tag={1,110} user tag GGOOOAAALL!!!!! | RENAME (12) | errno 2 I'm not exactly happy with this choice of tagging, namely using `put(dtrace_utag, Tag::list())`. But this is an experiment, so we'll see how it goes. I can't imagine changing the API for all file.erl functions in order pass the tag explicitly. Some modules have some extensive (ab)use of the C preprocessor to reduce the amount of #ifdefs that clutter the code. In several places, I have not #ifdef'ed automatic variables because of clutter. For the same reason, there are a handful of cases where I added DTrace-related members to a struct definition without an #ifdef. I feel that the result is easier to read than earlier drafts where I did use many more `https://github.com/slfritchie/otp/tree/dtrace-experiment+michal2` if you're curious.) I expect there may be some debate about whether the bloat of the affected structs is worthwhile. I erred on adding stuff to structs, especially in the efile_drv.c driver, not having a full grasp on what was thread-safe and what was not ... so I erred on the side of caution. The efile_drv.c has a work-around for a crazy GCC optimization bug. Thank goodness for Google, I dunno how I would've found a work-around for this silly thing. Many thanks to Trond Norbye for writing clearly about the problem in a membase Git repo commit message. /* * A note on probe naming: if "__" appears in a provider probe * definition, then two things happen during compilation: * * 1. The "__" will turn into a hypen, "-", for the probe name. * 2. The "__" will turn into a single underscore, "_", for the * macro names and function definitions that the compiler and * C developers will see. * * We'll try to use the following naming convention. We're a bit * limited because, as a USDT probe, we can only specify the 4th part * of the probe name, e.g. erlang*:::mumble. The 2nd part of the * probe name is always going to be "beam" or "beam.smp", and the 3rd * part of the probe name will always be the name of the function * that's calling the probe. * * So, all probes will be have names defined in this file using the * convention category__name or category__sub_category__name. This * will translate to probe names of category-name or * category-sub_category-name. * * Each of "category", "sub_category", and "name" may have underscores * but may not have hyphens. */ Add tentative support for sequential tracing sending, queueing, and receiving a message. I don't believe I've fully covered all the major places where it would be useful to have the sequential trace token info in a probe -- guidance from the OTP team would be helpful, if there's time to do that kind of review. Add global variable `erts_this_node_sysname`.
2012-03-22Merge branch 'raimo/close-ports-on-halt/OTP-9985' into maintRaimo Niskanen
* raimo/close-ports-on-halt/OTP-9985: erts: Basic test of erlang:halt/0..2 erts: Document erlang:halt/2 and update erlang:halt/0,1 erts: Implement erlang:halt/2 stdlib: Stop working around erlang:halt not flushing erts: Make erlang:halt/0,1 close ports and flush async threads erts: Remove forgotten and unused function erl_exit0 erts: Implement erl_halt erts: Remove unused ntbuild.erl
2012-03-21erts: Basic test of erlang:halt/0..2Raimo Niskanen
2012-03-21erts: Document erlang:halt/2 and update erlang:halt/0,1Raimo Niskanen
2012-03-21erts: Implement erlang:halt/2Raimo Niskanen
2012-03-21erts: Make erlang:halt/0,1 close ports and flush async threadsRaimo Niskanen
2012-03-21erts: Remove forgotten and unused function erl_exit0Raimo Niskanen
2012-03-21erts: Implement erl_haltRaimo Niskanen
2012-03-20Merge branch 'sverk/cpu-topology-crash' into maintSverker Eriksson
* sverk/cpu-topology-crash: erts: Fix memory corruption when reading topology info OTP-10004
2012-03-20Merge branch 'dc/dch-fix-win32-escript' into maintGustav Simonsson
* dc/dch-fix-win32-escript: add escript win32 alternative invocation (thanks Pierre Rouleau) OTP-9997
2012-03-20Merge branch 'sverk/zlib_port_leak' into maintSverker Eriksson
* sverk/zlib_port_leak: Fix port leaks in zlib OTP-9981
2012-03-20Merge branch 'ps/inet6-less-build-fix' into maintGustav Simonsson
* ps/inet6-less-build-fix: Add missing HAVE_IN6 && AF_INET6 ifdef OTP-9996
2012-03-20Merge branch 'lukas/kernel/sendfile_fixes' into maintLukas Larsson
* lukas/kernel/sendfile_fixes: Fix reselecting bug on OS X Fix bug when sending long files using select Fix ifdef to check if we are on OS X Add test case for sending multiple small files on same connection Fix memory leak when sendfile process crashes Extend timeout for windows Skip sendfile suite if solaris 8
2012-03-20Fix reselecting bug on OS XLukas Larsson
Since stop_select is called at an arbitrary point in the future it would sometime not be alled before the tcp driver started selecting on the fd. So now ERL_DRV_USE_NO_CALLBACK is used so that the stop_select call is never made. This seems to only have happened OS X.
2012-03-20Fix bug when sending long files using selectLukas Larsson
The return value from efile_sendfile was not consistent inbetween platforms. The API should now be working as it was intended. OTP-9994
2012-03-20Fix ifdef to check if we are on OS XLukas Larsson
2012-03-20Fix memory leak when sendfile process crashesLukas Larsson
We use the fact that file_flush is called when there is data in the driver queue when a port is closed to ensure that all data is cleaned up as it should. OTP-9993
2012-03-20erts: Remove unused ntbuild.erlRaimo Niskanen
2012-03-20Merge branch 'bjorn/kernel/erts_debug_size-fix/OTP-9991' into maintBjörn Gustavsson
* bjorn/kernel/erts_debug_size-fix/OTP-9991: Improve erts_debug_SUITE Fix calculation of fun size in erts_debug:size/1
2012-03-20Improve erts_debug_SUITEBjörn Gustavsson
Test erts_debug:size/1 too. Also test funs and shared terms.
2012-03-19Merge branch 'ph/fix-enfile/OTP-9990' into maintBjörn-Egil Dahlberg
* ph/fix-enfile/OTP-9990: Update preloaded prim_inet.beam gen_tcp: Use correct specs for accept and listen prim_inet: Catch system_limit in open_port Fix returned error from gen_tcp:accept/1,2 when running out of ports
2012-03-16Update preloaded prim_inet.beamBjörn-Egil Dahlberg
2012-03-16prim_inet: Catch system_limit in open_portBjörn-Egil Dahlberg
Will catch system_limit and return error tuple instead. An uncaught exception would be an incorrect behaviour. This problem would occur for gen_tcp:listen/1,2 for example.
2012-03-15erts: Fix memory corruption when reading topology infoSverker Eriksson
If the number of processors actually found while reading sysfs is lower than the configured value, we realloc() the cpuinfo array to the smaller size, but we then iterate it using the original configured size, thus corrupting memory beyond the allocated block.
2012-03-15Fix port leaks in zlibSverker Eriksson
zip,unzip,gzip,gunzip,compress and uncompress did not close the port when given invalid data argument. Fixed by putting close in "try-after". A closed port could in same cases get stuck in limbo due to data in io-queue. Fixed by adding a flush callback.
2012-03-15Merge branch 'rickard/barriers/OTP-9922' into maintRickard Green
* rickard/barriers/OTP-9922: Remove newly introduced excessive barrier in erts_thr_progress_later() Fix implementation with ddrb barriers
2012-03-14erts: Do not rebuild all emulator when preloaded changesRaimo Niskanen
2012-03-13Merge branch 'sverk/cpu-topology-crash' into maintSverker Eriksson
* sverk/cpu-topology-crash: erts: Fix crash on Linux if /sys/devices/system/node is not readable OTP-9978
2012-03-12Remove newly introduced excessive barrier in erts_thr_progress_later()Rickard Green
2012-03-12Fix implementation with ddrb barriersRickard Green
2012-03-09Merge branch 'egil/redocument-scheduler_wall_time/OTP-9858' into maintBjörn-Egil Dahlberg
* egil/redocument-scheduler_wall_time/OTP-9858: doc: Enhance wording and remove typos doc: Move examples and notes into tag-lists doc: Rewording of scheduler_wall_time doc: Change variable name to 'A' to reflect Active doc: Rewording of scheduler busy Update scheduler_wall_time documentation
2012-03-09Merge branch 'lukas/system/ssh_undef_function' into maintLukas Larsson
* lukas/system/ssh_undef_function: Add filter for ssh undefined function calls
2012-03-09erts: Fix crash on Linux if /sys/devices/system/node is not readableSverker Eriksson
Fallback on using /sys/devices/system/cpu to get cpu topology, as is already done when node directory doesn't exist.
2012-03-08doc: Enhance wording and remove typosBjörn-Egil Dahlberg
2012-03-08doc: Move examples and notes into tag-listsBjörn-Egil Dahlberg
2012-03-08doc: Rewording of scheduler_wall_timeBjörn-Egil Dahlberg
2012-03-08doc: Change variable name to 'A' to reflect ActiveBjörn-Egil Dahlberg
2012-03-07doc: Rewording of scheduler busyBjörn-Egil Dahlberg
2012-03-07Update scheduler_wall_time documentationBjörn-Egil Dahlberg
* Add example on calculating scheduler utilization
2012-03-05erts: Fix gdb command etp-ets-tabledumpSverker Eriksson
2012-02-29Merge branch 'rickard/barriers/OTP-9922' into maintRickard Green
* rickard/barriers/OTP-9922: Fix implementation with ddrb barriers
2012-02-21Fix implementation with ddrb barriersRickard Green
2012-02-21Add missing HAVE_IN6 && AF_INET6 ifdefPeer Stritzinger
This prevents building for operating systems that do not yet have IPv6 compatible socket API. Error can be reproduced by (cross)building for a os that doesn't have these headers. This will abort with a error about incomplete type 'struct in6_addr'. All other uses of IPv6 API in inet_drv.c are conditionalized like in the patch.
2012-02-21erts: Fail binary_to_term if bignum arity is too largeSverker Eriksson
2012-02-21erts: Fix bignum-bug in ETS with compressed optionSverker Eriksson
A large 64-bit immediate number will be stored as SMALL_BIG_EXT by ETS compressed format. When uncompressing, the SMALL_BIG_EXT was first decoded as as bignum (by bytes_to_big) and then turned into a small (by big_norm). This works for normal "binary_to_term" as decoded_size() over-estimates the needed heap size. But for ETS no over-estimation is done as the real term size is known and stored in DbTerm. Fixed by preventing bytes_to_big() from writing bignum digit when the number is seen to fit in an immediate.
2012-02-20Merge branch 'rickard/barriers/OTP-9922' into maintRickard Green
* rickard/barriers/OTP-9922: Reduce thread progress read operations in handle_aux_work() Misc memory barrier fixes
2012-02-19Reduce thread progress read operations in handle_aux_work()Rickard Green