刚看到网友发了AV-Comparatives 2010年8月性能测试结果，下载了原版文档，查看了一下，发现误解的人还真是不少。
建议各位看清楚测试是什么（红色字体文字），然后再回帖吧。文档较多，不费事翻译了。放在帖子里面，感兴趣的可
自己翻译或找在线翻译。
＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝ 华丽分割线 ＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝
Anti-Virus Comparative
Performance test (Suite Products)
Impact of Security Suites on System Performance
Language: English
July 2010
Last Revision: 23rd August 2010
www.av-comparatives.org
Table of Contents
1. Introduction 3
2. Tested products 3
3. Test methods 4
4. Side notes and comments 5
5. Test results 7
6. Summarized results 15
7. Certification levels reached in this test 16
8. Copyright and Disclaimer
Introduction
We want to make clear that the results in this report are intended to give only an indication of the
impact on system performance (mainly by the real-time/on-access components) of the various Securi-
ty suites in these specific tests. Users are encouraged to try out the software on their own PC’s and
form an opinion based on their own observations.
This test contains fewer tested products than usual as it is an additional test in which vendors agreed
to take part. The performance test including all the 20 Anti-Virus products (not suites) will be
done/released later this year.
Tested products
The following products, were evaluated (with default settings) in this test:
avast! Internet Security 5.0 Kaspersky Internet Security 2011
AVG Internet Security 9.0 Kingsoft Internet Security 2010
BitDefender Internet Security 2010 Norman Security Suite Pro 8
eScan Internet Security Suite 10 Panda Internet Security 2011
ESET Smart Security 4.2 PC Tools Internet Security 2011
F-Secure Internet Security 2011 Symantec Norton Internet Security 2011
G DATA Internet Security 2011 Trend Micro Internet Security Pro 2010
Please note that the results in this report apply only to the products/versions listed above and should
not be assumed comparable to (e.g.) the versions provided by the above listed vendors as part of a
product suite. Also, keep in mind that different vendors offer different (and differing quantities of)
features in their products.
The following activities/tests were performed under Windows XP and Windows 7:
File copying
Archiving / Unarchiving
Encoding / Transcoding
Installing / Uninstalling applications
Launching applications
Downloading files
Worldbench Testing Suite (XP)
‐ 3 ‐
Test methods
The tests were performed on an Intel Core 2 Duo E8300 machine with 2GB of RAM and SATAII hard
disks. The performance tests were first done on a clean Windows XP Professional SP3 system (English)
and then with the installed Internet Security software (with default settings). This report contains
also results based on Windows 7 Professional.
The hard disk was defragmented before starting the various tests, and care was taken to minimize
other factors that could influence the measurements and/or comparability of the systems (network,
temperature, etc.). Optimizing processes/fingerprinting used by the products were also considered –
this means that the results represent the impact on a system which has already been used by the user
for a while. The tests were repeated several times (with and without fingerprinting) in order to get
mean values and filter out measurement errors. After each run the workstation was defragmented and
rebooted.
We simulated various file operations that a computer user would execute: copying1 different types of
clean files from one place to another, archiving and unarchiving files, encoding and transcoding2
audio and video files, converting DVD-Files to IPOD format, downloading files from Internet, launch-
ing applications, etc.
We also used a third-party industry recognized performance testing suite (Worldbench 6) to measure
the system impact during real-world product usage.
Readers are invited to evaluate the various products themselves, to see how they impact on their sys-
tems (such as software conflicts and/or user preferences, as well as different system configurations
that may lead to varying results).
We did not test boot-times on purpose. Security products need to load on systems at an early stage to
provide security from the very beginning – this load has some impact on the time needed for a system
to start up. Measuring boot times accurately is challenging. The most significant issue is to define
exactly when the system is fully started, as many operating environments may continue to perform
start-up activities for some time after the system appears responsive to the user. It is also important
to consider when the protection provided by the security solution being tested is fully active, as this
could be a useful measure of boot completion as far as the security solution is concerned. To test this
is almost impossible. Some vendors let the user choose if he wants a safe or fast start. We recommend
to use the safe start, the user will only loose a few seconds but get more security. Furthermore, some
security products are loading their services very late (even minutes later) at boot (users may notice
that after some time that the system loaded, the system gets very slow for some moments), so the
system looks like loading very fast, but it just loads its services later and makes the system also inse-
cure/vulnerable. As we do not want to support such activities, and considering that in most cases a
workstation is powered on only once a day, we decided to do not measure boot times.
1 We used 2GB data of various file categories (pictures, movies, music, various MS Office 2003 and 2007 docu-
ments, PDF files, applications/executables, operating system files, archives, etc.).
2 Converting MP3 files to WAV, MP3 to WMA, AVI to MPG and MPG to AVI, as well as IPOD format
‐ 4 ‐
Side notes and comments
The on-access/real-time scanner component of Anti-Virus software runs as a background process to
check all files that are accessed, in order to protect the system continuously against malware threats.
For example, on-access scanners scan files as soon as they are accessed, while (e.g.) behaviour-
blockers add a different layer of protection and monitor what the file does when it is already execut-
ed/running. The services and processes that run in the background to do these tasks also require and
use system resources. Suite products have usually a higher impact on system performance than Anti-
Virus-only products, as more services/features are included and running in the background.
Security products need to be active deep in the system in order to protect it and (e.g.) to scan pro-
cesses and so on that are already active during the system start-up, to identify rootkits and other
malware. Those procedures add some extra time and thus a delay in system boot/start up.
If a product takes up too many system resources, users get annoyed and may either disable or unin-
stall some essential protective features (and considerably compromise the security of their system) or
may switch to security software that is less resource-hungry. Therefore, it is important not only that
Anti-Virus software provides high detection rates and good protection against malware, but also that
it does not degrade system performance or trouble users.
While this report looks at how much impact various Internet Security products have on system perfor-
mance, it is not always just the security software which is the main factor responsible for a slow sys-
tem. Other factors also play a role, and if users follow some simple rules, system performance can be
improved noticeably. The next sections address some of the other factors that may play a part.
A few common problems observed on some user PCs:
- Old hardware: If a PC already runs at a snail’s pace because it has ten-year-old hardware, us-
ing modern (Anti-Virus) software may make it unusable.
o If possible, buy a new PC that at least meets the minimum recommended requirements of
the software you want to use.
o Adding more RAM does not hurt. If you use Windows XP or Windows 7, you should use a
minimum of 2GB of RAM. If you use Vista switch to Windows 7.
o Make sure you have only ONE Anti-Virus program with real-time protection. If your new PC
came with a trial Anti-Virus program, remove this before installing a different AV program.
- Clean up the content of your hard disk:
o If your hard disk is almost full, your system performance will suffer accordingly. Leave at
least 20% of your disk space free and move your movies and other infrequently accessed
files to another (external) disk.
o Uninstall unneeded software. Often, the slowdown that users notice after installing an
Anti-Virus product is due to other software on the PC running in the background (that is,
due to software conflicts or heavy file access by other programs, each access requiring an-
ti-virus scanning).
o Remove unneeded entries/shortcuts from the Autostart/start-up folder in the program
menu
‐ 5 ‐
o if your PC is already messed up by residual files and registry entries left over by hundreds
of applications you installed and uninstalled after trying them out over the past years, re-
install a clean operating system and install only software you really need (fewer software
installations, fewer potential vulnerabilities and conflicts, and so on) and use e.g. an im-
age/backup tool in order to ensure that you do not have to reinstall everything manually
in future.
- Defragment your hard disks regularly! A fragmented hard disk can have a very big impact on
system performance as well as considerably increasing the time needed to boot up the system.
- Keep all your software up-to-date: Using an Anti-Virus version from 2008 does not protect you
as well as the newer version would, even though you may still be able to update the signatures.
Visit http://update.microsoft.com regularly and keep your operating system up-to-date by installing the
recommended patches. Any software can have vulnerabilities and bugs, so keep all the software
installed on your PC up-to-date: this will not only protect you against many exploits and vulnera-
bilities, but also give you any other application improvements that have been introduced.
- Fingerprinting/Optimization: most Anti-Virus products use various technologies to decrease
their impact on system performance. Fingerprinting is such a technology, where already scanned
files do not get rescanned again for a while (or more rarely) or are whitelisted. This increases the
speed considerably (esp. after some time the PC was used), but also adds some little potential
risk, as not all files are scanned anymore. It is up to the user to decide what to prefer. We sug-
gest to perform regularly a full-system scan (to be sure that all files are at least currently found as
clean and to further optimize the fingerprinting).
- Be patient: a delay of a few additional seconds due to Anti-Virus is not necessarily a big deal.
However, if even with the suggestions above your PC still needs a considerably longer time to
boot up, for instance, after you have installed the Anti-Virus you should consider trying out an-
other Anti-Virus product. (If you only notice a slow-down after using the Anti-Virus for a long
time, there are probably other factors behind the slowdown.). Do not reduce your security by dis-
abling essential protection features, just in the hope of gaining a slightly faster PC.
‐ 6 ‐
Test results
These specific test results show the impact on system performance that Internet Security products
have, compared to the other tested Internet Security products. The reported data just give an indica-
tion and are not necessarily applicable in all circumstances, as too many factors can play an addition-
al part. As we noticed that delivering percentages gets easily misinterpreted by users (as well as mis-
used by marketing departments of AV vendors), we grouped the results in four categories, as the im-
pact within those categories can be considered almost equal, also considering error measurements.
The categories were defined by the testers, based on what would be felt/noticed from user’s perspec-
tive (e.g. “slow” means that the user would notice and label the added slowdown as too high, also
compared to the impact of other security products).
File copying
Some Anti-Virus products do not scan all kind of files by design/default (based on their file
extensions), or use fingerprinting technologies, which may skip already scanned files in order to
increase the speed (see comments on page 6).
We copied a set of different file types which are widespread at home and office workstations from one
physical hard disk to another physical hard disk.
+0% to +25% very fast
+25% to +50% fast
+50% to +100% mediocre
over +100% slow
Windows XP Windows 7
On subsequent runs On subsequent runs
On first run (with fingerprinting, On first run (with fingerprinting,
if available) if available)
Avast fast very fast very fast very fast
AVG fast very fast fast very fast
Bitdefender fast fast mediocre fast
eScan mediocre fast mediocre fast
ESET fast very fast fast fast
F-Secure mediocre very fast fast very fast
G DATA slow very fast mediocre fast
Kaspersky mediocre fast fast very fast
Kingsoft fast very fast fast fast
Norman fast very fast mediocre mediocre
Panda fast very fast mediocre fast
PC Tools fast very fast fast very fast
Symantec fast very fast fast fast
Trend Micro mediocre mediocre mediocre mediocre
‐ 7 ‐
Archiving and unarchiving
Archives are commonly used for file storage, and the impact of Anti-Virus software on the time taken
to create new archives or to unarchive files from existing archives may be of interest for most users.
We archived a set of different file types which are widespread at home and office workstations form
one physical hard disk to another physical hard disk and unzipped them after this again on a third
physical hard disk.
The results below already consider the fingerprinting/optimization technologies of the Anti-Virus
products, as most users usually make archives of files they have on their disk.
+0% to +20% very fast
+20% to +40% fast
+40% to +80% mediocre
over +80% slow
Windows XP Windows 7
Avast very fast very fast
AVG very fast very fast
Bitdefender very fast very fast
eScan very fast very fast
ESET very fast very fast
F-Secure fast very fast
G DATA very fast very fast
Kaspersky fast very fast
Kingsoft very fast very fast
Norman very fast very fast
Panda very fast very fast
PC Tools fast very fast
Symantec fast very fast
Trend Micro fast very fast
‐ 8 ‐
Encoding/transcoding
Music files are often stored and converted on home systems, and converting such files takes system
resources. Due that, many home users may be interested to know if their Anti-Virus products imposes
a slowdown while converting multimedia files from one format to another.
We encoded and transcoded some multimedia files with FFmpeg, and for the IPOD conversion we used
HandBrakeCLI. The impact during FFmpeg and IPOD converting was almost the same.
+0 to +15% very fast
+15 to +30% fast
+30 to +50% mediocre
over +50% slow
Windows XP Windows 7
Avast very fast very fast
AVG very fast very fast
Bitdefender very fast very fast
eScan very fast very fast
ESET very fast very fast
F-Secure very fast very fast
G DATA very fast very fast
Kaspersky very fast very fast
Kingsoft very fast very fast
Norman very fast very fast
Panda very fast very fast
PC Tools very fast very fast
Symantec very fast very fast
Trend Micro very fast very fast
All tested Internet Security products added less than 15% slowdown (very fast) to the process and
would add almost unnoticeable impact while encoding/transcoding normal multimedia files.
‐ 9 ‐
Installing/uninstalling applications
We installed several programs (like Visual C++, .NET Framework, etc.) with MSI installers, and then
uninstalled them and measured how long it took. We did not consider fingerprinting, because usually
an application is only installed once.
+0% to +25% very fast
+25% to +50% fast
+50% to +100% mediocre
over +100% slow
Windows XP Windows 7
Avast very fast very fast
AVG very fast very fast
Bitdefender mediocre very fast
eScan very fast very fast
ESET fast very fast
F-Secure very fast very fast
G DATA mediocre very fast
Kaspersky fast very fast
Kingsoft fast very fast
Norman very fast very fast
Panda very fast very fast
PC Tools fast very fast
Symantec fast very fast
Trend Micro very fast very fast
‐ 10 ‐
Office document files and PDF files are very common. We opened some large document files in Mi-
crosoft Office (and closed it) and some large PDF files in Adobe Acrobat Reader (and closed it). Before
each opening, the workstation was rebooted. The time taken for the viewer or editor application to
open and a document to be displayed was measured.
Although we list the results for the first opening and the subsequent openings, we consider the sub-
sequent openings more important, as normally this operation is done several times by users, and op-
timization features of the Anti-Virus products take place, minimizing their impact on the systems.
+0% to +50% very fast
+50% to +100% fast
+100% to +200% mediocre
over +200% slow
Results Windows XP
Open Word Open PDF
On first run On subsequent runs On first run On subsequent runs
(with fingerprinting, (with fingerprinting,
if available) if available)
Avast mediocre mediocre mediocre fast
AVG mediocre fast mediocre very fast
Bitdefender mediocre fast fast very fast
eScan mediocre fast mediocre mediocre
ESET fast very fast mediocre very fast
F-Secure mediocre very fast fast very fast
G DATA mediocre fast slow mediocre
Kaspersky mediocre fast mediocre fast
Kingsoft very fast very fast very fast very fast
Norman mediocre very fast fast fast
Panda very fast very fast fast very fast
PC Tools slow slow slow slow
Symantec fast very fast fast very fast
Trend Micro slow slow slow slow
Some optimization features may not take place in some products (or not reduce enough the impact),
as documents and PDF files are common infection targets and therefore are anyway scanned when
opened.
‐ 11 ‐
Results Windows 7
+0% to +50% very fast
+50% to +100% fast
+100% to +200% mediocre
over +200% slow
Open Word Open PDF
On first run On subsequent runs On first run On subsequent runs
(with fingerprinting, (with fingerprinting,
if available) if available)
Avast very fast very fast very fast very fast
AVG very fast very fast very fast very fast
Bitdefender very fast very fast fast very fast
eScan fast very fast very fast very fast
ESET very fast very fast very fast very fast
F-Secure very fast very fast fast very fast
G DATA mediocre very fast fast fast
Kaspersky mediocre fast mediocre fast
Kingsoft very fast very fast very fast very fast
PC Tools fast fast fast fast
Norman mediocre fast mediocre fast
Panda very fast very fast very fast very fast
Symantec very fast very fast very fast very fast
Trend Micro fast fast mediocre mediocre
‐ 12 ‐
Downloading files from the Internet
Files are commonly downloaded from the internet. To avoid external influences, we used an in-house
Apache web server (wget) connected with 1GB LAN and measured the download time. We tested using
large files/archives.
+0% to +25% very fast
+25% to +50% fast
+50% to +100% mediocre
over +100% slow
Windows XP Windows 7
Avast fast fast
AVG mediocre very fast
Bitdefender fast fast
eScan very fast very fast
ESET mediocre mediocre
F-Secure mediocre fast
G DATA slow slow
Kaspersky mediocre mediocre
Kingsoft very fast very fast
Norman very fast very fast
Panda very fast very fast
PC Tools very fast very fast
Symantec very fast very fast
Trend Micro mediocre fast
‐ 13 ‐
In order to provide an industry-recognized performance test, we used the WorldBench testing suite of
PCWorld. WorldBench6 is a leading application-based real-world performance benchmark.
Popular applications are each a component of the final WorldBench score. The WorldBench score
(higher is better) is compared against a baseline4 system. Below you can see the reached Worldbench
scores.
WB score
without AV 115
Panda 104
eScan 103
ESET 103
F‐Secure 103
Kingsoft 102
Symantec 101
Avast 100
G DATA 98
Kaspersky 97
AVG 96
Norman 95
PC Tools 94
BitDefender 91
Trend Micro 90
The WorldBench testing Suite consists of the following ten tests, simulating real-world usage: Adobe
Photoshop CS2, Autodesk 3ds Max 8.0 SP3 (DirectX), Autodesk 3ds Max 8.0 SP3 (Rendering), Mozilla
Firefox 2, Microsoft Office 2003 with SP1, Microsoft Windows Media Encoder 9.0, Multitasking: Mozilla
Firefox and Windows Media Encoder, Nero 7 Ultra Edition, Roxio VideoWave Movie Creator 1.5 and
WinZip 10.0.
The WorldBench Test under Windows 7 has not been included in this report due compatibility issues.
3 For more information, see http://www.worldbench.com or http://en.wikipedia.org/wiki/WorldBench
4 The Worldbench baseline system (score 100) is an Intel Core 2 Duo E6600, with 2GB RAM. The AV-Comparatives
baseline system is an Intel Core 2 Duo E8300, with 2GB of RAM.
‐ 14 ‐
Below you can see a graph showing the time needed (in seconds) by the various suite products in the
various WorldBench6 tests (lower bars are better) under Windows XP SP3. As it can be seen, in most
cases there is not much difference between the products, except in few cases, where the difference on
system impact is higher (and can be clearly seen).
Summarized results
Users should weight the various subtests according to their needs. We applied a scoring system in
order to sum up the various results.
‐ 15 ‐
Certification levels reached in this test
We provide a 4-level ranking system: Tested, STANDARD, ADVANCED and ADVANCED+. All products
were quite good, and reached at least the STANDARD level.
The following certification levels are for the results reached in this performance test report. Please
note that the performance test only tells you how much impact a security suite may have on a system
compared to other security suites; it does not tell you anything about the effectiveness of the protec-
tion a product provides.
CERTIFICATION LEVELS PRODUCTS5
Panda
Kingsoft
Norman
Symantec
eScan
ESET
Avast
F-Secure
AVG
BitDefender
PC Tools
Kaspersky
G DATA
Trend Micro
The above awards have been given based on our assessment of the overall impact results with default
settings under Windows XP.
5 We suggest to consider products with same the award to be as good as the other products with same award.
‐ 16 ‐
Copyright and Disclaimer
This publication is Copyright © 2010 by AV-Comparatives e.V. ®. Any use of the results, etc. in whole
or in part, is ONLY permitted if the explicit written agreement of the management board of AV-
Comparatives e.V. is given prior to any publication. AV-Comparatives e.V. and its testers cannot be
held liable for any damage or loss, which might occur as a result of, or in connection with, the use of
the information provided in this paper. We take every possible care to ensure the correctness of the
basic data, but no representative of AV-Comparatives e.V. can he held liable for the accuracy of the
test results. We do not give any guarantee of the correctness, completeness, or suitability for a spe-
cific purpose of any of the information/content provided at any given time. No one else involved in
creating, producing or delivering test results shall be liable for any indirect, special or consequential
damage, or loss of profits, arising out of, or related to, the use or inability to use, the services pro-
vided by the website, test documents or any related data. AV-Comparatives e.V. is a Non-Profit Organ-
ization.
AV-Comparatives e.V. (August 2010)
‐ 17 ‐
|
[复制链接]
发表于 2010-8-24 18:48:59
楼主
直接把pdf复制了
