From 472a0e82a52a3d5d841e1dfad6b13e26082a5750 Mon Sep 17 00:00:00 2001
From: Ludovic Courtès <ludo@gnu.org>
Date: Sat, 13 Nov 2021 21:47:15 +0100
Subject: daemon: Do not deduplicate files smaller than 8 KiB.

Files smaller than 8 KiB typically represent ~70% of the entries in
/gnu/store/.links but only contribute to ~4% of the space savings
afforded by deduplication.

Not considering these files for deduplication speeds up file insertion
in the store and, more importantly, leaves 'removeUnusedLinks' with
fewer entries to traverse, thereby speeding it up proportionally.

Partly fixes <https://issues.guix.gnu.org/24937>.

* config-daemon.ac: Remove symlink hard link check and CAN_LINK_SYMLINK
definition.
* guix/store/deduplication.scm (%deduplication-minimum-size): New
variable.
(deduplicate)[loop]: Do not recurse when FILE's size is below
%DEDUPLICATION-MINIMUM-SIZE.
(dump-port): New procedure.
(dump-file/deduplicate)[hash]: Turn into...
[dump-and-compute-hash]: ... this thunk.
Call 'deduplicate' only when SIZE is greater than
%DEDUPLICATION-MINIMUM-SIZE; otherwise call 'dump-port'.
* nix/libstore/gc.cc (LocalStore::removeUnusedLinks): Drop files where
st.st_size < deduplicationMinSize.
* nix/libstore/local-store.hh (deduplicationMinSize): New declaration.
* nix/libstore/optimise-store.cc (deduplicationMinSize): New variable.
(LocalStore::optimisePath_): Return when PATH is a symlink or smaller
than 'deduplicationMinSize'.
* tests/derivations.scm ("identical files are deduplicated"): Produce
files bigger than %DEDUPLICATION-MINIMUM-SIZE.
* tests/nar.scm ("restore-file-set with directories (signed, valid)"):
Likewise.
* tests/store-deduplication.scm ("deduplicate, below %deduplication-minimum-size"):
New test.
("deduplicate", "deduplicate, ENOSPC"): Produce files bigger than
%DEDUPLICATION-MINIMUM-SIZE.
* tests/store.scm ("substitute, deduplication"): Likewise.
---
 tests/derivations.scm | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

(limited to 'tests/derivations.scm')

diff --git a/tests/derivations.scm b/tests/derivations.scm
index cd165d1be6..0775719ea3 100644
--- a/tests/derivations.scm
+++ b/tests/derivations.scm
@@ -1,5 +1,5 @@
 ;;; GNU Guix --- Functional package management for GNU
-;;; Copyright © 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020 Ludovic Courtès <ludo@gnu.org>
+;;; Copyright © 2012-2021 Ludovic Courtès <ludo@gnu.org>
 ;;;
 ;;; This file is part of GNU Guix.
 ;;;
@@ -170,11 +170,15 @@ (define prefix-len (string-length dir))
         #f))))
 
 (test-assert "identical files are deduplicated"
-  (let* ((build1  (add-text-to-store %store "one.sh"
-                                     "echo hello, world > \"$out\"\n"
+  ;; Note: DATA must be longer than %DEDUPLICATION-MINIMUM-SIZE.
+  (let* ((data    (make-string 9000 #\a))
+         (build1  (add-text-to-store %store "one.sh"
+                                     (string-append "echo -n " data
+                                                    " > \"$out\"\n")
                                      '()))
          (build2  (add-text-to-store %store "two.sh"
-                                     "# Hey!\necho hello, world > \"$out\"\n"
+                                     (string-append "# Hey!\necho -n "
+                                                    data " > \"$out\"\n")
                                      '()))
          (drv1    (derivation %store "foo"
                               %bash `(,build1)
@@ -187,7 +191,7 @@ (define prefix-len (string-length dir))
                (file2 (derivation->output-path drv2)))
            (and (valid-path? %store file1) (valid-path? %store file2)
                 (string=? (call-with-input-file file1 get-string-all)
-                          "hello, world\n")
+                          data)
                 (= (stat:ino (lstat file1))
                    (stat:ino (lstat file2))))))))
 
-- 
cgit v1.2.3