https://bugzilla.novell.com/show_bug.cgi?id=478477
User squan@web.de added comment
https://bugzilla.novell.com/show_bug.cgi?id=478477#c2
--- Comment #2 from Stefan Quandt 2009-02-24 14:53:01 MST ---
To check wether it is a proble in a software layer between kernel and
application (kget) I used konqueror as client for copying a large file onto
said NAS. Result: Smooth and almost silent write access.
Next I checked with the KDE3 version of kget. Result: Frightening drive noise.
Next I checked with an older combination of CIFS/kget on from a SUSE-11.0
machine. Result: Same noise.
Next I attached kget with strace.
Result of roughly 30s:
- about 4000 writev() calls on file descriptor 8
- about 15000 read() calls on the same fd
- about two thirds of the read attempt have the result EAGAIN (Resource
temporarily unavailable)
So I think for this one the kget developers have to be addressed.
Since the problem is already present in KDE3 I wonder wether I am the first one
directly writing on a samba share with kget.
Here a short excerpt of the strace log:
clock_gettime(CLOCK_MONOTONIC, {703, 8962380}) = 0
read(8, "\7\3,\240 \272\n\0t\0\0\0+\0\300\6\0\0\0\0\250\1\315\0\213\1\33\0\20
\0\3"..., 4096) = 64
read(8, 0x80d49b4, 4096) = -1 EAGAIN (Resource temporarily
unavailable)
select(9, [8], [8], NULL, NULL) = 1 (out [8])
writev(8, [{"&\3\2\0t\0\0\0", 8}], 1) = 8
select(9, [8], [], NULL, NULL) = 1 (in [8])
read(8, "\1\1-\240\0\0\0\0t\0\0\0\321\316`\1\250\1\315\0\250\1\315\0\20
\0\0\320\254.\n", 4096) = 32
read(8, 0x80d49b4, 4096) = -1 EAGAIN (Resource temporarily
unavailable)
select(9, [8], [8], NULL, NULL) = 1 (out [8])
writev(8, [{"(\3\4\0t\0\0\0+\0\300\6\250\1\315\0", 16}], 1) = 16
select(9, [8], [], NULL, NULL) = 1 (in [8])
read(8,
"\1\1.\240\0\0\0\0\0\0\0\0\213\1\33\0\2\0\0\0\20\0\0\0\320\254.\n\0\0\0\0",
4096) = 32
read(8, 0x80d49b4, 4096) = -1 EAGAIN (Resource temporarily
unavailable)
select(9, [8], [8], NULL, NULL) = 1 (out [8])
writev(8,
[{"\2\3\4\0+\0\300\6\0@\0\0\7\0\300\6(\3\4\0t\0\0\0+\0\300\6\250\1\315\0",
32}], 1) = 32
select(9, [8], [], NULL, NULL) = 1 (in [8])
read(8,
"\1\0010\240\0\0\0\0\0\0\0\0\213\1\33\0\2\0\0\0\20\0\0\0\320\254.\n\0\0\0\0",
4096) = 32
read(8, 0x80d49b4, 4096) = -1 EAGAIN (Resource temporarily
unavailable)
clock_gettime(CLOCK_MONOTONIC, {703, 10478221}) = 0
select(9, [8], [8], NULL, NULL) = 1 (out [8])
writev(8, [{"(\3\4\0t\0\0\0+\0\300\6\252\1`\2", 16}], 1) = 16
select(9, [8], [], NULL, NULL) = 1 (in [8])
read(8,
"\1\0011\240\0\0\0\0\0\0\0\0\215\1\256\1\2\0\0\0\20\0\0\0\320\254.\n\0\0\0\0",
4096) = 32
read(8, 0x80d49b4, 4096) = -1 EAGAIN (Resource temporarily
unavailable)
read(8, 0x80d49b4, 4096) = -1 EAGAIN (Resource temporarily
unavailable)
clock_gettime(CLOCK_MONOTONIC, {703, 10938337}) = 0
read(8, 0x80d49b4, 4096) = -1 EAGAIN (Resource temporarily
unavailable)
poll([{fd=3, events=POLLIN}, {fd=9, events=POLLIN}, {fd=8, events=POLLIN},
{fd=5, events=POLLIN}, {fd=12, events=POLLIN}, {fd=15, events=POLLIN}, {fd=22,
events=POLLIN}], 7, 0) = 0 (Timeout)
clock_gettime(CLOCK_MONOTONIC, {703, 11102045}) = 0
read(8, 0x80d49b4, 4096) = -1 EAGAIN (Resource temporarily
unavailable)
clock_gettime(CLOCK_MONOTONIC, {703, 12145478}) = 0
select(9, [8], [8], NULL, NULL) = 1 (out [8])
writev(8,
[{"7\3\4\0\36\21\300\6A\v\300\6\0\0\0\0007\3\4\0\37\21\300\6A\v\300\6\0\0\0\0"...,
3060}], 1) = 3060
read(8, 0x80d49b4, 4096) = -1 EAGAIN (Resource temporarily
unavailable)
poll([{fd=3, events=POLLIN}, {fd=9, events=POLLIN}, {fd=8, events=POLLIN},
{fd=5, events=POLLIN}, {fd=12, events=POLLIN}, {fd=15, events=POLLIN}, {fd=22,
events=POLLIN}], 7, 408) = 1 ([{fd=8, revents=POLLIN}])
--
Configure bugmail: https://bugzilla.novell.com/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are on the CC list for the bug.
