git@vger.kernel.org list mirror (unofficial, one of many)
 help / color / Atom feed
From: Ben Peart <peartben@gmail.com>
To: Stefan Beller <sbeller@google.com>, Ben Peart <Ben.Peart@microsoft.com>
Cc: git <git@vger.kernel.org>, Junio C Hamano <gitster@pobox.com>
Subject: Re: [PATCH v1] read-cache: speed up index load through parallelization
Date: Thu, 23 Aug 2018 15:44:58 -0400
Message-ID: <12b29bbf-4565-fe0e-97d4-19da2b4ddf5e@gmail.com> (raw)
In-Reply-To: <CAGZ79kbXfPPvcQ1rnUdiOqWs5wC2qccGCnf8DvCVnp8QV126MA@mail.gmail.com>



On 8/23/2018 1:31 PM, Stefan Beller wrote:
> On Thu, Aug 23, 2018 at 8:45 AM Ben Peart <Ben.Peart@microsoft.com> wrote:
>>
>> This patch helps address the CPU cost of loading the index by creating
>> multiple threads to divide the work of loading and converting the cache
>> entries across all available CPU cores.
>>
>> It accomplishes this by having the primary thread loop across the index file
>> tracking the offset and (for V4 indexes) expanding the name. It creates a
>> thread to process each block of entries as it comes to them. Once the
>> threads are complete and the cache entries are loaded, the rest of the
>> extensions can be loaded and processed normally on the primary thread.
>>
>> Performance impact:
>>
>> read cache .git/index times on a synthetic repo with:
>>
>> 100,000 entries
>> FALSE       TRUE        Savings     %Savings
>> 0.014798767 0.009580433 0.005218333 35.26%
>>
>> 1,000,000 entries
>> FALSE       TRUE        Savings     %Savings
>> 0.240896533 0.1751243   0.065772233 27.30%
>>
>> read cache .git/index times on an actual repo with:
>>
>> ~3M entries
>> FALSE       TRUE        Savings     %Savings
>> 0.59898098  0.4513169   0.14766408  24.65%
>>
>> Signed-off-by: Ben Peart <Ben.Peart@microsoft.com>
>> ---
>>
>> Notes:
>>      Base Ref: master
>>      Web-Diff: https://github.com/benpeart/git/commit/67a700419b
>>      Checkout: git fetch https://github.com/benpeart/git read-index-multithread-v1 && git checkout 67a700419b
>>
>>   Documentation/config.txt |   8 ++
>>   config.c                 |  13 +++
>>   config.h                 |   1 +
>>   read-cache.c             | 218 ++++++++++++++++++++++++++++++++++-----
>>   4 files changed, 216 insertions(+), 24 deletions(-)
>>
>> diff --git a/Documentation/config.txt b/Documentation/config.txt
>> index 1c42364988..3344685cc4 100644
>> --- a/Documentation/config.txt
>> +++ b/Documentation/config.txt
>> @@ -899,6 +899,14 @@ relatively high IO latencies.  When enabled, Git will do the
>>   index comparison to the filesystem data in parallel, allowing
>>   overlapping IO's.  Defaults to true.
>>
>> +core.fastIndex::
>> +       Enable parallel index loading
>> ++
>> +This can speed up operations like 'git diff' and 'git status' especially
>> +when the index is very large.  When enabled, Git will do the index
>> +loading from the on disk format to the in-memory format in parallel.
>> +Defaults to true.
> 
> "fast" is a non-descriptive word as we try to be fast in any operation?
> Maybe core.parallelIndexReading as that just describes what it
> turns on/off, without second guessing its effects?
> (Are there still computers with just a single CPU, where this would not
> make it faster? ;-))
> 

How about core.parallelReadIndex?  Slightly shorter and matches the 
function names better.

> 
>> +int git_config_get_fast_index(void)
>> +{
>> +       int val;
>> +
>> +       if (!git_config_get_maybe_bool("core.fastindex", &val))
>> +               return val;
>> +
>> +       if (getenv("GIT_FASTINDEX_TEST"))
>> +               return 1;
> 
> We look at this env value just before calling this function,
> can be write it to only look at the evn variable once?
> 

Sure, I didn't like the fact that it was called twice but didn't get 
around to cleaning it up.

>> +++ b/config.h
>> @@ -250,6 +250,7 @@ extern int git_config_get_untracked_cache(void);
>>   extern int git_config_get_split_index(void);
>>   extern int git_config_get_max_percent_split_change(void);
>>   extern int git_config_get_fsmonitor(void);
>> +extern int git_config_get_fast_index(void);
> 
> Oh. nd/no-extern did not cover config.h
> 
> 
>>
>> +#ifndef min
>> +#define min(a,b) (((a) < (b)) ? (a) : (b))
>> +#endif
> 
> We do not have a minimum function in the tree,
> except for xdiff/xmacros.h:29: XDL_MIN.
> I wonder what the rationale is for not having a MIN()
> definition, I think we discussed that on the list a couple
> times but the rationale escaped me.
> 
> If we introduce a min/max macro, can we put it somewhere
> more prominent? (I would find it useful elsewhere)
>

I'll avoid that particular rabbit hole and just remove the min macro 
definition.  ;-)

>> +/*
>> +* Mostly randomly chosen maximum thread counts: we
>> +* cap the parallelism to online_cpus() threads, and we want
>> +* to have at least 7500 cache entries per thread for it to
>> +* be worth starting a thread.
>> +*/
>> +#define THREAD_COST            (7500)
> 
> This reads very similar to preload-index.c THREAD_COST
> 
>> +       /* loop through index entries starting a thread for every thread_nr entries */
>> +       consumed = thread = 0;
>> +       for (i = 0; ; i++) {
>> +               struct ondisk_cache_entry *ondisk;
>> +               const char *name;
>> +               unsigned int flags;
>> +
>> +               /* we've reached the begining of a block of cache entries, kick off a thread to process them */
> 
> beginning
> 

Thanks

> Thanks,
> Stefan
> 

  reply index

Thread overview: 199+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-08-23 15:41 Ben Peart
2018-08-23 17:31 ` Stefan Beller
2018-08-23 19:44   ` Ben Peart [this message]
2018-08-24 18:40   ` Duy Nguyen
2018-08-28 14:53     ` Ben Peart
2018-08-23 18:06 ` Junio C Hamano
2018-08-23 20:33   ` Ben Peart
2018-08-24 15:37     ` Duy Nguyen
2018-08-24 15:57       ` Duy Nguyen
2018-08-24 17:28         ` Ben Peart
2018-08-25  6:44         ` [PATCH] read-cache.c: optimize reading index format v4 Nguyễn Thái Ngọc Duy
2018-08-27 19:36           ` Junio C Hamano
2018-08-28 19:25             ` Duy Nguyen
2018-08-28 23:54               ` Ben Peart
2018-08-29 17:14               ` Junio C Hamano
2018-09-04 16:08             ` Duy Nguyen
2018-09-02 13:19           ` [PATCH v2 0/1] " Nguyễn Thái Ngọc Duy
2018-09-02 13:19             ` [PATCH v2 1/1] read-cache.c: " Nguyễn Thái Ngọc Duy
2018-09-04 18:58               ` Junio C Hamano
2018-09-04 19:31               ` Junio C Hamano
2018-08-24 18:20       ` [PATCH v1] read-cache: speed up index load through parallelization Duy Nguyen
2018-08-24 18:40         ` Ben Peart
2018-08-24 19:00           ` Duy Nguyen
2018-08-24 19:57             ` Ben Peart
2018-08-29 15:25 ` [PATCH v2 0/3] " Ben Peart
2018-08-29 15:25   ` [PATCH v2 1/3] " Ben Peart
2018-08-29 17:14     ` Junio C Hamano
2018-08-29 21:35       ` Ben Peart
2018-09-03 19:16     ` Duy Nguyen
2018-08-29 15:25   ` [PATCH v2 2/3] read-cache: load cache extensions on worker thread Ben Peart
2018-08-29 17:12     ` Junio C Hamano
2018-08-29 21:42       ` Ben Peart
2018-08-29 22:19         ` Junio C Hamano
2018-09-03 19:21     ` Duy Nguyen
2018-09-03 19:27       ` Duy Nguyen
2018-08-29 15:25   ` [PATCH v2 3/3] read-cache: micro-optimize expand_name_field() to speed up V4 index parsing Ben Peart
2018-09-06 21:03 ` [PATCH v3 0/4] read-cache: speed up index load through parallelization Ben Peart
2018-09-06 21:03   ` [PATCH v3 1/4] read-cache: optimize expand_name_field() to speed up V4 index parsing Ben Peart
2018-09-06 21:03   ` [PATCH v3 2/4] eoie: add End of Index Entry (EOIE) extension Ben Peart
2018-09-07 17:55     ` Junio C Hamano
2018-09-07 20:23       ` Ben Peart
2018-09-08  6:29         ` Martin Ågren
2018-09-08 14:03           ` Ben Peart
2018-09-08 17:08             ` Martin Ågren
2018-09-06 21:03   ` [PATCH v3 3/4] read-cache: load cache extensions on a worker thread Ben Peart
2018-09-07 21:10     ` Junio C Hamano
2018-09-08 14:56       ` Ben Peart
2018-09-06 21:03   ` [PATCH v3 4/4] read-cache: speed up index load through parallelization Ben Peart
2018-09-07  4:16     ` Torsten Bögershausen
2018-09-07 13:43       ` Ben Peart
2018-09-07 17:21   ` [PATCH v3 0/4] " Junio C Hamano
2018-09-07 18:31     ` Ben Peart
2018-09-08 13:18     ` Duy Nguyen
2018-09-11 23:26 ` [PATCH v4 0/5] " Ben Peart
2018-09-11 23:26   ` [PATCH v4 1/5] eoie: add End of Index Entry (EOIE) extension Ben Peart
2018-09-11 23:26   ` [PATCH v4 2/5] read-cache: load cache extensions on a worker thread Ben Peart
2018-09-11 23:26   ` [PATCH v4 3/5] read-cache: speed up index load through parallelization Ben Peart
2018-09-11 23:26   ` [PATCH v4 4/5] read-cache.c: optimize reading index format v4 Ben Peart
2018-09-11 23:26   ` [PATCH v4 5/5] read-cache: clean up casting and byte decoding Ben Peart
2018-09-12 14:34   ` [PATCH v4 0/5] read-cache: speed up index load through parallelization Ben Peart
2018-09-12 16:18 ` [PATCH v5 " Ben Peart
2018-09-12 16:18   ` [PATCH v5 1/5] eoie: add End of Index Entry (EOIE) extension Ben Peart
2018-09-13 22:44     ` Junio C Hamano
2018-09-15 10:02     ` Duy Nguyen
2018-09-17 14:54       ` Ben Peart
2018-09-17 16:05         ` Duy Nguyen
2018-09-17 17:31           ` Junio C Hamano
2018-09-17 17:38             ` Duy Nguyen
2018-09-17 19:08               ` Junio C Hamano
2018-09-12 16:18   ` [PATCH v5 2/5] read-cache: load cache extensions on a worker thread Ben Peart
2018-09-15 10:22     ` Duy Nguyen
2018-09-15 10:24       ` Duy Nguyen
2018-09-17 16:38         ` Ben Peart
2018-09-15 16:23       ` Duy Nguyen
2018-09-17 17:19         ` Junio C Hamano
2018-09-17 16:26       ` Ben Peart
2018-09-17 16:45         ` Duy Nguyen
2018-09-17 21:32       ` Junio C Hamano
2018-09-12 16:18   ` [PATCH v5 3/5] read-cache: load cache entries on worker threads Ben Peart
2018-09-15 10:31     ` Duy Nguyen
2018-09-17 17:25       ` Ben Peart
2018-09-15 11:07     ` Duy Nguyen
2018-09-15 11:09       ` Duy Nguyen
2018-09-17 18:52         ` Ben Peart
2018-09-15 11:29     ` Duy Nguyen
2018-09-12 16:18   ` [PATCH v5 4/5] read-cache.c: optimize reading index format v4 Ben Peart
2018-09-12 16:18   ` [PATCH v5 5/5] read-cache: clean up casting and byte decoding Ben Peart
2018-09-26 19:54 ` [PATCH v6 0/7] speed up index load through parallelization Ben Peart
2018-09-26 19:54   ` [PATCH v6 1/7] read-cache.c: optimize reading index format v4 Ben Peart
2018-09-26 19:54   ` [PATCH v6 2/7] read-cache: clean up casting and byte decoding Ben Peart
2018-09-26 19:54   ` [PATCH v6 3/7] eoie: add End of Index Entry (EOIE) extension Ben Peart
2018-09-28  0:19     ` SZEDER Gábor
2018-09-28 18:38       ` Ben Peart
2018-09-29  0:51     ` SZEDER Gábor
2018-09-29  5:45     ` Duy Nguyen
2018-09-29 18:24       ` Junio C Hamano
2018-09-26 19:54   ` [PATCH v6 4/7] config: add new index.threads config setting Ben Peart
2018-09-28  0:26     ` SZEDER Gábor
2018-09-28 13:39       ` Ben Peart
2018-09-28 17:07         ` Junio C Hamano
2018-09-28 19:41           ` Ben Peart
2018-09-28 20:30             ` Ramsay Jones
2018-09-28 22:15               ` Junio C Hamano
2018-10-01 13:17                 ` Ben Peart
2018-10-01 15:06                   ` SZEDER Gábor
2018-09-26 19:54   ` [PATCH v6 5/7] read-cache: load cache extensions on a worker thread Ben Peart
2018-09-26 19:54   ` [PATCH v6 6/7] ieot: add Index Entry Offset Table (IEOT) extension Ben Peart
2018-09-26 19:54   ` [PATCH v6 7/7] read-cache: load cache entries on worker threads Ben Peart
2018-09-26 22:06   ` [PATCH v6 0/7] speed up index load through parallelization Junio C Hamano
2018-09-27 17:13   ` Duy Nguyen
2018-10-01 13:45 ` [PATCH v7 " Ben Peart
2018-10-01 13:45   ` [PATCH v7 1/7] read-cache.c: optimize reading index format v4 Ben Peart
2018-10-01 13:45   ` [PATCH v7 2/7] read-cache: clean up casting and byte decoding Ben Peart
2018-10-01 15:10     ` Duy Nguyen
2018-10-01 13:45   ` [PATCH v7 3/7] eoie: add End of Index Entry (EOIE) extension Ben Peart
2018-10-01 15:17     ` SZEDER Gábor
2018-10-02 14:34       ` Ben Peart
2018-10-01 15:30     ` Duy Nguyen
2018-10-02 15:13       ` Ben Peart
2018-10-01 13:45   ` [PATCH v7 4/7] config: add new index.threads config setting Ben Peart
2018-10-01 13:45   ` [PATCH v7 5/7] read-cache: load cache extensions on a worker thread Ben Peart
2018-10-01 15:50     ` Duy Nguyen
2018-10-02 15:00       ` Ben Peart
2018-10-01 13:45   ` [PATCH v7 6/7] ieot: add Index Entry Offset Table (IEOT) extension Ben Peart
2018-10-01 16:27     ` Duy Nguyen
2018-10-02 16:34       ` Ben Peart
2018-10-02 17:02         ` Duy Nguyen
2018-10-01 13:45   ` [PATCH v7 7/7] read-cache: load cache entries on worker threads Ben Peart
2018-10-01 17:09     ` Duy Nguyen
2018-10-02 19:09       ` Ben Peart
2018-10-10 15:59 ` [PATCH v8 0/7] speed up index load through parallelization Ben Peart
2018-10-10 15:59   ` [PATCH v8 1/7] read-cache.c: optimize reading index format v4 Ben Peart
2018-10-10 15:59   ` [PATCH v8 2/7] read-cache: clean up casting and byte decoding Ben Peart
2018-10-10 15:59   ` [PATCH v8 3/7] eoie: add End of Index Entry (EOIE) extension Ben Peart
2018-10-10 15:59   ` [PATCH v8 4/7] config: add new index.threads config setting Ben Peart
2018-10-10 15:59   ` [PATCH v8 5/7] read-cache: load cache extensions on a worker thread Ben Peart
2018-10-10 15:59   ` [PATCH v8 6/7] ieot: add Index Entry Offset Table (IEOT) extension Ben Peart
2018-10-10 15:59   ` [PATCH v8 7/7] read-cache: load cache entries on worker threads Ben Peart
2018-10-19 16:11     ` Jeff King
2018-10-22  2:14       ` Junio C Hamano
2018-10-22 14:40         ` Ben Peart
2018-10-12  3:18   ` [PATCH v8 0/7] speed up index load through parallelization Junio C Hamano
2018-10-14 12:28   ` Duy Nguyen
2018-10-15 17:33     ` Ben Peart
2018-11-13  0:38   ` [PATCH 0/3] Avoid confusing messages from new index extensions (Re: [PATCH v8 0/7] speed up index load through parallelization) Jonathan Nieder
2018-11-13  0:39     ` [PATCH 1/3] eoie: default to not writing EOIE section Jonathan Nieder
2018-11-13  1:05       ` Junio C Hamano
2018-11-13 15:14         ` Ben Peart
2018-11-13 18:25           ` Jonathan Nieder
2018-11-14  1:36             ` Junio C Hamano
2018-11-15  0:19               ` Jonathan Nieder
2018-11-13  0:39     ` [PATCH 2/3] ieot: default to not writing IEOT section Jonathan Nieder
2018-11-13  0:58       ` Jonathan Tan
2018-11-13  1:09       ` Junio C Hamano
2018-11-13  1:12         ` Jonathan Nieder
2018-11-13 15:37           ` Duy Nguyen
2018-11-13 18:09         ` Jonathan Nieder
2018-11-13 15:22       ` Ben Peart
2018-11-13 18:18         ` Jonathan Nieder
2018-11-13 19:15           ` Ben Peart
2018-11-13 21:08             ` Jonathan Nieder
2018-11-14 18:09               ` Ben Peart
2018-11-15  0:05                 ` Jonathan Nieder
2018-11-14  3:05         ` Junio C Hamano
2018-11-20  6:09           ` [PATCH v2 0/5] Avoid confusing messages from new index extensions Jonathan Nieder
2018-11-20  6:11             ` [PATCH 1/5] eoie: default to not writing EOIE section Jonathan Nieder
2018-11-20 13:06               ` Ben Peart
2018-11-20 13:21                 ` SZEDER Gábor
2018-11-21 16:46                   ` Jeff King
2018-11-22  0:47                     ` Junio C Hamano
2018-11-20 15:01               ` Ben Peart
2018-11-20  6:12             ` [PATCH 2/5] ieot: default to not writing IEOT section Jonathan Nieder
2018-11-20 13:07               ` Ben Peart
2018-11-26 19:59                 ` Stefan Beller
2018-11-26 21:47                   ` Ben Peart
2018-11-26 22:02                     ` Stefan Beller
2018-11-27  0:50                   ` Junio C Hamano
2018-11-20  6:12             ` [PATCH 3/5] index: do not warn about unrecognized extensions Jonathan Nieder
2018-11-20  6:14             ` [PATCH 4/5] index: make index.threads=true enable ieot and eoie Jonathan Nieder
2018-11-20 13:24               ` Ben Peart
2018-11-20  6:15             ` [PATCH 5/5] index: offer advice for unknown index extensions Jonathan Nieder
2018-11-20  9:26               ` Ævar Arnfjörð Bjarmason
2018-11-20 13:30                 ` Ben Peart
2018-11-21  0:22                   ` Junio C Hamano
2018-11-21  0:39                     ` Jonathan Nieder
2018-11-21  0:44                       ` Jonathan Nieder
2018-11-21  5:01                       ` Junio C Hamano
2018-11-21  5:04                         ` Jonathan Nieder
2018-11-21  5:15                         ` Junio C Hamano
2018-11-21  5:31                           ` Junio C Hamano
2018-11-21  1:03                     ` Jonathan Nieder
2018-11-21  4:23                       ` Junio C Hamano
2018-11-21  4:57                         ` Jonathan Nieder
2018-11-21  9:30                       ` Ævar Arnfjörð Bjarmason
2018-11-13  0:40     ` [PATCH 3/3] index: do not warn about unrecognized extensions Jonathan Nieder
2018-11-13  1:10       ` Junio C Hamano
2018-11-13 15:25       ` Ben Peart
2018-11-14  3:24       ` Junio C Hamano
2018-11-14 18:19         ` Ben Peart

Reply instructions:

You may reply publically to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=12b29bbf-4565-fe0e-97d4-19da2b4ddf5e@gmail.com \
    --to=peartben@gmail.com \
    --cc=Ben.Peart@microsoft.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=sbeller@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

git@vger.kernel.org list mirror (unofficial, one of many)

Archives are clonable:
	git clone --mirror https://public-inbox.org/git
	git clone --mirror http://ou63pmih66umazou.onion/git
	git clone --mirror http://czquwvybam4bgbro.onion/git
	git clone --mirror http://hjrcffqmbrq6wope.onion/git

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.version-control.git
	nntp://ou63pmih66umazou.onion/inbox.comp.version-control.git
	nntp://czquwvybam4bgbro.onion/inbox.comp.version-control.git
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.version-control.git
	nntp://news.gmane.org/gmane.comp.version-control.git

 note: .onion URLs require Tor: https://www.torproject.org/
       or Tor2web: https://www.tor2web.org/

AGPL code for this site: git clone https://public-inbox.org/ public-inbox