22.1. Comparisons

23.1. Comparisons

The Samba server uses TCP to talk to the client. Thus if you are trying to see if it performs well you should really compare it to @@ -111,17 +111,17 @@ CLASS="SECT1" >

22.2. Oplocks

23.2. Oplocks

22.2.1. Overview

23.2.1. Overview

Oplocks are the way that SMB clients get permission from a server to locally cache file operations. If a server grants an oplock @@ -155,9 +155,9 @@ CLASS="SECT2" >

22.2.2. Level2 Oplocks

23.2.2. Level2 Oplocks

With Samba 2.0.5 a new capability - level2 (read only) oplocks is supported (although the option is off by default - see the smb.conf @@ -179,9 +179,9 @@ CLASS="SECT2" >

22.2.3. Old 'fake oplocks' option - deprecated

23.2.3. Old 'fake oplocks' option - deprecated

Samba can also fake oplocks, by granting a oplock whenever a client asks for one. This is controlled using the smb.conf option "fake @@ -200,9 +200,9 @@ CLASS="SECT1" >

22.3. Socket options

23.3. Socket options

There are a number of socket options that can greatly affect the performance of a TCP based server like Samba.

22.4. Read size

23.4. Read size

The option "read size" affects the overlap of disk reads/writes with network reads/writes. If the amount of data being transferred in @@ -254,9 +254,9 @@ CLASS="SECT1" >

22.5. Max xmit

23.5. Max xmit

At startup the client and server negotiate a "maximum transmit" size, which limits the size of nearly all SMB commands. You can set the @@ -277,9 +277,9 @@ CLASS="SECT1" >

22.6. Locking

23.6. Locking

By default Samba does not implement strict locking on each read/write call (although it did in previous versions). If you enable strict @@ -294,9 +294,9 @@ CLASS="SECT1" >

22.7. Share modes

23.7. Share modes

Some people find that opening files is very slow. This is often because of the "share modes" code needed to fully implement the dos @@ -324,9 +324,9 @@ CLASS="SECT1" >

22.8. Log level

23.8. Log level

If you set the log level (also known as "debug level") higher than 2 then you may suffer a large drop in performance. This is because the @@ -338,9 +338,9 @@ CLASS="SECT1" >

22.9. Wide lines

23.9. Wide lines

The "wide links" option is now enabled by default, but if you disable it (for better security) then you may suffer a performance hit in @@ -352,9 +352,9 @@ CLASS="SECT1" >

22.10. Read raw

23.10. Read raw

The "read raw" operation is designed to be an optimised, low-latency file read operation. A server may choose to not support it, @@ -374,9 +374,9 @@ CLASS="SECT1" >

22.11. Write raw

23.11. Write raw

The "write raw" operation is designed to be an optimised, low-latency file write operation. A server may choose to not support it, @@ -391,9 +391,9 @@ CLASS="SECT1" >

22.12. Read prediction

23.12. Read prediction

Samba can do read prediction on some of the SMB commands. Read prediction means that Samba reads some extra data on the last file it @@ -417,9 +417,9 @@ CLASS="SECT1" >

22.13. Memory mapping

23.13. Memory mapping

Samba supports reading files via memory mapping them. One some machines this can give a large boost to performance, on others it @@ -438,9 +438,9 @@ CLASS="SECT1" >

22.14. Slow Clients

23.14. Slow Clients

One person has reported that setting the protocol to COREPLUS rather than LANMAN2 gave a dramatic speed improvement (from 10k/s to 150k/s).

22.15. Slow Logins

23.15. Slow Logins

Slow logins are almost always due to the password checking time. Using the lowest practical "password level" will improve things a lot. You @@ -468,9 +468,9 @@ CLASS="SECT1" >

22.16. Client tuning

23.16. Client tuning

Often a speed problem can be traced to the client. The client (for example Windows for Workgroups) can often be tuned for better TCP @@ -572,9 +572,9 @@ CLASS="SECT1" >

22.17. My Results

23.17. My Results

Some people want to see real numbers in a document like this, so here they are. I have a 486sx33 client running WfWg 3.11 with the 3.11b @@ -631,7 +631,7 @@ WIDTH="33%" ALIGN="right" VALIGN="top" >Next Up