kaleb@THYME.JPL.NASA.GOV (Kaleb Keithley) (08/31/90)
Well, as Chris Peterson pointed out, there were some major discrepancies
in the timings I made using different versions of malloc; so I re-ran my
tests, and GNU is indeed faster.
I built three servers: Server 1 using SunOS 4.1 malloc, Server 2 using
GNU emacs malloc, and Server 3 using GNUs' alpha release malloc. All
servers and mallocs were built using -O3 -pg, with the exception of Suns'
malloc which I don't have control over. After building the servers, I
started the server from the command line, ran the x11perf benchmark, and
gprof'd the gmon.out file. x11perf took about one hour, 45 minutes to run
to completion (-all option.) Attached are the relevant sections from the
gprof and the x11perfcomp output.
BTW, the test was run on a Sun SS1 with CG3, and 8MB RAM.
In summary, use of GNUs' emacs malloc() and free() saved 65 seconds and
150 seconds respectively, or just under three minutes out of the test run;
Around 3.5% if my math is correct. So, is it worth it? I'd say on a
slower machine, it probably is, it almost isn't worth it on the SPARC.
On a faster machine, I'd guess it definitely isn't worth it unless you
have an exceptionally poor implementation of malloc.
malloc gprofs:
SunOS malloc:
0.00 0.00 1/6649310 _dbm_open [550]
0.00 0.00 1/6649310 __default_domain [767]
0.00 0.00 1/6649310 _load_dom_binding [591]
0.00 0.00 2/6649310 __findbuf [628]
0.00 0.00 2/6649310 _on_exit [757]
0.00 0.00 2/6649310 _clntudp_bufcreate [621]
0.00 0.00 3/6649310 _calloc [737]
0.00 0.00 28/6649310 _v2domatch [475]
0.00 0.00 28/6649310 _xdr_bytes [607]
0.00 0.00 140/6649310 _makenode [626]
0.17 0.10 13889/6649310 _Xrealloc [162]
0.22 0.13 17715/6649310 _realloc [171]
80.61 49.79 6617498/6649310 _Xalloc [57]
[63] 2.4 81.00 50.03 6649310 _malloc [63]
43.41 0.00 5745550/5745550 _demote [118]
3.28 2.94 903760/6954542 _delete [111]
0.36 0.03 81/81 _morecore [338]
------------------------------------------------------------------------
GNU alpha malloc:
224678 _malloc [75]
0.00 0.00 1/7779831 _dbm_open [567]
0.00 0.00 1/7779831 __default_domain [749]
0.00 0.00 1/7779831 _load_dom_binding [591]
0.00 0.00 2/7779831 __findbuf [479]
0.00 0.00 2/7779831 _on_exit [743]
0.00 0.00 2/7779831 _clntudp_bufcreate [604]
0.00 0.00 3/7779831 _calloc [721]
0.00 0.00 28/7779831 _v2domatch [510]
0.00 0.00 28/7779831 _xdr_bytes [627]
0.00 0.00 140/7779831 _makenode [608]
0.17 0.01 13893/7779831 _Xrealloc [175]
4.22 0.28 348143/7779831 _realloc [187]
90.00 5.95 7417587/7779831 _Xalloc [67]
[75] 1.8 94.40 6.24 7779831+224678 _malloc [75]
0.30 5.44 8937/8937 _morecore [223]
0.01 0.49 849/10780 ___default_morecore [219]
0.00 0.00 1/1 _initialize [638]
224678 _malloc [75]
------------------------------------------------------------------------
GNU emacs malloc:
0.00 0.00 1/8155300 _dbm_open [577]
0.00 0.00 1/8155300 __default_domain [762]
0.00 0.00 1/8155300 _load_dom_binding [631]
0.00 0.00 2/8155300 __findbuf [622]
0.00 0.00 2/8155300 _on_exit [757]
0.00 0.00 2/8155300 _clntudp_bufcreate [632]
0.00 0.00 3/8155300 _calloc [737]
0.00 0.00 28/8155300 _v2domatch [462]
0.00 0.00 28/8155300 _xdr_bytes [652]
0.00 0.00 140/8155300 _makenode [627]
0.11 0.00 13893/8155300 _Xrealloc [204]
2.22 0.02 271829/8155300 _realloc [221]
64.22 0.48 7869370/8155300 _Xalloc [85]
[96] 1.3 66.56 0.49 8155300 _malloc [96]
0.03 0.46 727/727 _morecore [323]
------------------------------------------------------------------------
free gprofs:
SunOS free:
0.00 0.00 2/6954557 _fclose [548]
0.00 0.00 28/6954557 _gethostbyname [404]
0.00 0.00 28/6954557 _xdr_bytes [607]
0.00 0.00 70/6954557 _freenode [637]
0.00 0.00 81/6954557 _morecore [338]
0.16 0.29 17715/6954557 _realloc [171]
2.74 5.06 306612/6954557 _shrink [205]
59.15 109.34 6630021/6954557 _Xfree [47]
[46] 3.2 62.05 114.69 6954557 _free [46]
54.47 19.51 6954557/6954557 _insert [95]
21.47 19.24 5907584/6954542 _delete [111]
------------------------------------------------------------------------
GNU alpha free:
0.00 0.00 2/7786430 _fclose [748]
0.00 0.00 28/7786430 _gethostbyname [427]
0.00 0.00 28/7786430 _xdr_bytes [627]
0.00 0.00 70/7786430 _freenode [631]
3.48 0.46 356188/7786430 _realloc [187]
72.57 9.54 7430114/7786430 _Xfree [80]
[82] 1.6 76.05 10.00 7786430 _free [82]
9.41 0.00 8011082/13984534 .div [158]
0.01 0.58 992/10780 ___default_morecore [219]
------------------------------------------------------------------------
GNU emacs free:
0.00 0.00 2/8153854 _fclose [494]
0.00 0.00 28/8153854 _gethostbyname [421]
0.00 0.00 28/8153854 _xdr_bytes [652]
0.00 0.00 70/8153854 _freenode [682]
0.94 0.00 271829/8153854 _realloc [221]
27.19 0.00 7881897/8153854 _Xfree [131]
[135] 0.5 28.13 0.00 8153854 _free [135]
------------------------------------------------------------------------
and lastly x11perfcomp report:
1: Xsun.test
2: alpha.test
3: emacs.test
1 2 3 Operation
-------- -------- -------- ---------
102000.0 105000.0 106000.0 Dot
36800.0 37500.0 37400.0 1x1 rectangle
17200.0 17700.0 17700.0 10x10 rectangle
675.0 676.0 677.0 100x100 rectangle
30.0 30.0 30.1 500x500 rectangle
15400.0 16100.0 16100.0 1x1 stippled rectangle
3160.0 3180.0 3180.0 10x10 stippled rectangle
220.0 220.0 220.0 100x100 stippled rectangle
16.2 16.3 16.2 500x500 stippled rectangle
18500.0 19000.0 19500.0 1x1 opaque stippled rectangle
4800.0 4830.0 4820.0 10x10 opaque stippled rectangle
340.0 337.0 340.0 100x100 opaque stippled rectangle
24.5 24.6 24.6 500x500 opaque stippled rectangle
26000.0 28700.0 28400.0 1x1 4x4 tiled rectangle
14300.0 14700.0 14700.0 10x10 4x4 tiled rectangle
654.0 654.0 656.0 100x100 4x4 tiled rectangle
29.8 29.8 29.8 500x500 4x4 tiled rectangle
16800.0 17400.0 17500.0 1x1 161x145 tiled rectangle
6470.0 6550.0 6550.0 10x10 161x145 tiled rectangle
243.0 243.0 242.0 100x100 161x145 tiled rectangle
11.3 11.3 11.3 500x500 161x145 tiled rectangle
33200.0 36700.0 35400.0 1-pixel line segment
26500.0 28700.0 28300.0 10-pixel line segment
12000.0 12500.0 12400.0 100-pixel line segment
3530.0 3570.0 3560.0 500-pixel line segment
8110.0 8550.0 8540.0 100-pixel line segment (1 kid)
6080.0 6640.0 6630.0 100-pixel line segment (2 kids)
5230.0 5550.0 5540.0 100-pixel line segment (3 kids)
17000.0 18200.0 18100.0 10-pixel dashed segment
5140.0 5240.0 5240.0 100-pixel dashed segment
4670.0 4750.0 4750.0 100-pixel double-dashed segment
39900.0 40900.0 39400.0 1-pixel line
31400.0 31500.0 31000.0 10-pixel line
12900.0 12900.0 12800.0 100-pixel line
3610.0 3610.0 3610.0 500-pixel line
18500.0 19600.0 19500.0 10-pixel dashed line
5260.0 5350.0 5350.0 100-pixel dashed line
4770.0 4840.0 4840.0 100-pixel double-dashed line
1950.0 1860.0 1930.0 10x1 wide line
551.0 485.0 548.0 100x10 wide line
95.4 85.5 94.9 500x50 wide line
242.0 224.0 240.0 100x10 wide dashed line
212.0 202.0 211.0 100x10 wide double-dashed line
14400.0 14500.0 12600.0 1-pixel circle
10500.0 10500.0 9130.0 10-pixel circle
4090.0 4090.0 3860.0 100-pixel circle
1150.0 1150.0 1130.0 500-pixel circle
309.0 273.0 310.0 100-pixel dashed circle
219.0 189.0 219.0 100-pixel double-dashed circle
223.0 225.0 236.0 10-pixel wide circle
51.0 54.2 55.8 100-pixel wide circle
10.8 11.2 11.5 500-pixel wide circle
14.4 15.2 15.3 100-pixel wide dashed circle
11.9 11.3 12.3 100-pixel wide double-dashed circle
5750.0 5850.0 5610.0 10-pixel partial circle
2180.0 2170.0 2150.0 100-pixel partial circle
92400.0 94100.0 93800.0 1-pixel solid circle
7360.0 7660.0 7450.0 10-pixel solid circle
597.0 599.0 599.0 100-pixel solid circle
35.3 35.3 35.4 500-pixel solid circle
2810.0 2880.0 2900.0 10-pixel fill chord partial circle
597.0 605.0 603.0 100-pixel fill chord partial circle
2920.0 3020.0 2960.0 10-pixel fill slice partial circle
590.0 607.0 602.0 100-pixel fill slice partial circle
9380.0 9480.0 8810.0 10-pixel ellipse
3560.0 3560.0 3480.0 100-pixel ellipse
953.0 952.0 946.0 500-pixel ellipse
373.0 330.0 374.0 100-pixel dashed ellipse
265.0 229.0 264.0 100-pixel double-dashed ellipse
102.0 106.0 108.0 10-pixel wide ellipse
17.2 17.3 17.6 100-pixel wide ellipse
3.8 3.8 3.8 500-pixel wide ellipse
6.3 6.4 6.4 100-pixel wide dashed ellipse
3.9 3.9 3.9 100-pixel wide double-dashed ellipse
5170.0 5240.0 5040.0 10-pixel partial ellipse
2370.0 2380.0 2340.0 100-pixel partial ellipse
7880.0 8200.0 7870.0 10-pixel filled ellipse
977.0 983.0 980.0 100-pixel filled ellipse
67.4 67.5 67.5 500-pixel filled ellipse
2920.0 2990.0 3010.0 10-pixel fill chord partial ellipse
1000.0 1020.0 1020.0 100-pixel fill chord ellipse
3050.0 3150.0 3080.0 10-pixel fill slice partial ellipse
1000.0 1020.0 990.0 100-pixel fill slice ellipse
3930.0 3780.0 3860.0 Fill 1-pixel/side triangle
2340.0 2130.0 2320.0 Fill 10-pixel/side triangle
292.0 263.0 293.0 Fill 100-pixel/side triangle
2780.0 2550.0 2770.0 Fill 10x10 trapezoid
348.0 321.0 350.0 Fill 100x100 trapezoid
940.0 968.0 966.0 Fill 10x10 stippled trapezoid
20.7 20.0 20.3 Fill 100x100 stippled trapezoid
965.0 1010.0 996.0 Fill 10x10 opaque stippled trapezoid
21.7 22.1 22.1 Fill 100x100 opaque stippled trapezoid
855.0 946.0 888.0 Fill 10x10 tiled trapezoid
17.3 18.5 17.8 Fill 100x100 tiled trapezoid
1410.0 1330.0 1450.0 Fill 10-pixel/side complex polygon
213.0 189.0 214.0 Fill 100-pixel/side complex polygons
24200.0 24200.0 24000.0 Char in 80-char line (6x13)
33200.0 33300.0 33400.0 Char in 80-char line (TR 10)
11600.0 11700.0 11700.0 Char in 30-char line (TR 24)
23700.0 23900.0 23800.0 Char in 20/40/20 line (6x13, TR 10)
43900.0 47700.0 47800.0 Char in 80-char image line (6x13)
22000.0 22000.0 22000.0 Char in 80-char image line (TR 10)
6990.0 7020.0 7040.0 Char in 30-char image line (TR 24)
3900.0 3840.0 4020.0 Scroll 10x10 pixels
394.0 393.0 394.0 Scroll 100x100 pixels
19.0 19.0 19.0 Scroll 500x500 pixels
3700.0 3600.0 3800.0 Copy 10x10 from window to window
347.0 346.0 348.0 Copy 100x100 from window to window
16.7 16.8 16.9 Copy 500x500 from window to window
3980.0 3800.0 4010.0 Copy 10x10 from pixmap to window
423.0 420.0 423.0 Copy 100x100 from pixmap to window
20.0 20.0 20.0 Copy 500x500 from pixmap to window
3850.0 3830.0 3990.0 Copy 10x10 from window to pixmap
345.0 345.0 346.0 Copy 100x100 from window to pixmap
16.6 16.6 16.6 Copy 500x500 from window to pixmap
4450.0 4440.0 4700.0 Copy 10x10 from pixmap to pixmap
468.0 467.0 469.0 Copy 100x100 from pixmap to pixmap
22.0 22.0 22.0 Copy 500x500 from pixmap to pixmap
3490.0 3340.0 3560.0 Copy 10x10 1-bit deep plane
417.0 416.0 419.0 Copy 100x100 1-bit deep plane
22.9 22.9 22.9 Copy 500x500 1-bit deep plane
2210.0 2200.0 2300.0 PutImage 10x10 square
79.8 80.2 79.0 PutImage 100x100 square
3.5 3.6 3.6 PutImage 500x500 square
354.0 364.0 367.0 GetImage 10x10 square
97.3 94.5 96.5 GetImage 100x100 square
5.1 5.2 5.1 GetImage 500x500 square
29900.0 41000.0 37100.0 X protocol NoOperation
439.0 454.0 452.0 GetAtomName
434.0 448.0 441.0 GetProperty
4540.0 4900.0 4680.0 Change graphics context
1160.0 3060.0 3540.0 Create and map subwindows (4 kids)
1010.0 1080.0 1220.0 Create and map subwindows (16 kids)
1030.0 1090.0 1230.0 Create and map subwindows (25 kids)
1020.0 1090.0 1210.0 Create and map subwindows (50 kids)
1010.0 1080.0 1200.0 Create and map subwindows (75 kids)
1000.0 1070.0 1180.0 Create and map subwindows (100 kids)
960.0 1030.0 1120.0 Create and map subwindows (200 kids)
2250.0 2230.0 2520.0 Create unmapped window (4 kids)
2240.0 2430.0 2550.0 Create unmapped window (16 kids)
2260.0 2430.0 2540.0 Create unmapped window (25 kids)
2260.0 2450.0 2520.0 Create unmapped window (50 kids)
2240.0 2490.0 2560.0 Create unmapped window (75 kids)
2260.0 2500.0 2540.0 Create unmapped window (100 kids)
2260.0 2510.0 2530.0 Create unmapped window (200 kids)
1170.0 1290.0 1560.0 Map window via parent (4 kids)
1700.0 1820.0 2170.0 Map window via parent (16 kids)
1800.0 1940.0 2310.0 Map window via parent (25 kids)
1850.0 1960.0 2320.0 Map window via parent (50 kids)
1870.0 1970.0 2320.0 Map window via parent (75 kids)
1890.0 1980.0 2360.0 Map window via parent (100 kids)
1910.0 2000.0 2370.0 Map window via parent (200 kids)
5310.0 5840.0 6120.0 Unmap window via parent (4 kids)
12400.0 12800.0 13300.0 Unmap window via parent (16 kids)
14200.0 15200.0 15500.0 Unmap window via parent (25 kids)
17400.0 17800.0 17900.0 Unmap window via parent (50 kids)
18500.0 18300.0 19000.0 Unmap window via parent (75 kids)
19200.0 19000.0 19600.0 Unmap window via parent (100 kids)
20300.0 19900.0 20500.0 Unmap window via parent (200 kids)
1310.0 2580.0 3020.0 Destroy window via parent (4 kids)
3310.0 4140.0 4890.0 Destroy window via parent (16 kids)
3780.0 4450.0 5270.0 Destroy window via parent (25 kids)
4200.0 4770.0 5620.0 Destroy window via parent (50 kids)
4320.0 4890.0 5770.0 Destroy window via parent (75 kids)
4430.0 4970.0 5840.0 Destroy window via parent (100 kids)
4490.0 5070.0 5940.0 Destroy window via parent (200 kids)
487.0 588.0 709.0 Hide/expose window via popup (4 kids)
864.0 1000.0 1190.0 Hide/expose window via popup (16 kids)
953.0 1090.0 1300.0 Hide/expose window via popup (25 kids)
978.0 1120.0 1330.0 Hide/expose window via popup (50 kids)
1020.0 1150.0 1360.0 Hide/expose window via popup (75 kids)
1050.0 1160.0 1380.0 Hide/expose window via popup (100 kids)
1080.0 1190.0 1400.0 Hide/expose window via popup (200 kids)
460.0 546.0 611.0 Move window (4 kids)
355.0 398.0 456.0 Move window (16 kids)
321.0 348.0 391.0 Move window (25 kids)
244.0 253.0 292.0 Move window (50 kids)
203.0 213.0 230.0 Move window (75 kids)
178.0 180.0 190.0 Move window (100 kids)
110.0 115.0 111.0 Move window (200 kids)
4720.0 5230.0 5010.0 Moved unmapped window (4 kids)
4780.0 5220.0 4980.0 Moved unmapped window (16 kids)
4730.0 5200.0 4960.0 Moved unmapped window (25 kids)
4750.0 5160.0 4910.0 Moved unmapped window (50 kids)
4740.0 5160.0 4910.0 Moved unmapped window (75 kids)
4720.0 5120.0 4890.0 Moved unmapped window (100 kids)
4660.0 5080.0 4830.0 Moved unmapped window (200 kids)
1340.0 1620.0 1840.0 Move window via parent (4 kids)
2780.0 3280.0 3660.0 Move window via parent (16 kids)
3220.0 3750.0 4160.0 Move window via parent (25 kids)
3700.0 4290.0 4730.0 Move window via parent (50 kids)
3850.0 4510.0 4930.0 Move window via parent (75 kids)
3970.0 4520.0 5020.0 Move window via parent (100 kids)
4160.0 4710.0 5180.0 Move window via parent (200 kids)
423.0 512.0 572.0 Resize window (4 kids)
359.0 413.0 453.0 Resize window (16 kids)
329.0 361.0 410.0 Resize window (25 kids)
263.0 275.0 320.0 Resize window (50 kids)
227.0 239.0 261.0 Resize window (75 kids)
202.0 205.0 221.0 Resize window (100 kids)
132.0 137.0 136.0 Resize window (200 kids)
4770.0 5390.0 5050.0 Resize unmapped window (4 kids)
4870.0 5370.0 5000.0 Resize unmapped window (16 kids)
4810.0 5300.0 5030.0 Resize unmapped window (25 kids)
4840.0 5290.0 5010.0 Resize unmapped window (50 kids)
4810.0 5290.0 4980.0 Resize unmapped window (75 kids)
4800.0 5270.0 4980.0 Resize unmapped window (100 kids)
4770.0 5210.0 4930.0 Resize unmapped window (200 kids)
184.0 223.0 264.0 Circulate window (4 kids)
128.0 155.0 181.0 Circulate window (16 kids)
125.0 145.0 171.0 Circulate window (25 kids)
115.0 136.0 159.0 Circulate window (50 kids)
109.0 133.0 150.0 Circulate window (75 kids)
105.0 128.0 142.0 Circulate window (100 kids)
92.9 107.0 117.0 Circulate window (200 kids)
15200.0 18000.0 15200.0 Circulate Unmapped window (4 kids)
13800.0 15800.0 13900.0 Circulate Unmapped window (16 kids)
11000.0 14600.0 12700.0 Circulate Unmapped window (25 kids)
10200.0 11400.0 10500.0 Circulate Unmapped window (50 kids)
8940.0 9710.0 8060.0 Circulate Unmapped window (75 kids)
7860.0 8360.0 5970.0 Circulate Unmapped window (100 kids)
5140.0 4780.0 3130.0 Circulate Unmapped window (200 kids)