2023-05-14 21:29:03

by Abhijeet Rastogi

[permalink] [raw]
Subject: [PATCH v2] ipvs: increase ip_vs_conn_tab_bits range for 64BIT

Current range [8, 20] is set purely due to historical reasons
because at the time, ~1M (2^20) was considered sufficient.
With this change, 27 is the upper limit for 64-bit, 20 otherwise.

Previous change regarding this limit is here.

Link: https://lore.kernel.org/all/86eabeb9dd62aebf1e2533926fdd13fed48bab1f.1631289960.git.aclaudi@redhat.com/T/#u

Signed-off-by: Abhijeet Rastogi <[email protected]>
---
The conversation for this started at:

https://www.spinics.net/lists/netfilter/msg60995.html

The upper limit for algo is any bit size less than 32, so this
change will allow us to set bit size > 20. Today, it is common to have
RAM available to handle greater than 2^20 connections per-host.

Distros like RHEL already allow setting limits higher than 20.
---
Changes in v2:
- Lower the ranges, 27 for 64bit, 20 otherwise
- Link to v1: https://lore.kernel.org/r/[email protected]
---
net/netfilter/ipvs/Kconfig | 26 +++++++++++++-------------
net/netfilter/ipvs/ip_vs_conn.c | 4 ++--
2 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index 271da8447b29..aac5d6bd82e6 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -44,7 +44,8 @@ config IP_VS_DEBUG

config IP_VS_TAB_BITS
int "IPVS connection table size (the Nth power of 2)"
- range 8 20
+ range 8 20 if !64BIT
+ range 8 27 if 64BIT
default 12
help
The IPVS connection hash table uses the chaining scheme to handle
@@ -52,18 +53,17 @@ config IP_VS_TAB_BITS
reduce conflicts when there are hundreds of thousands of connections
in the hash table.

- Note the table size must be power of 2. The table size will be the
- value of 2 to the your input number power. The number to choose is
- from 8 to 20, the default number is 12, which means the table size
- is 4096. Don't input the number too small, otherwise you will lose
- performance on it. You can adapt the table size yourself, according
- to your virtual server application. It is good to set the table size
- not far less than the number of connections per second multiplying
- average lasting time of connection in the table. For example, your
- virtual server gets 200 connections per second, the connection lasts
- for 200 seconds in average in the connection table, the table size
- should be not far less than 200x200, it is good to set the table
- size 32768 (2**15).
+ Note the table size must be power of 2. The table size will be the value
+ of 2 to the your input number power. The number to choose is from 8 to 27
+ for 64BIT(20 otherwise), the default number is 12, which means the table
+ size is 4096. Don't input the number too small, otherwise you will lose
+ performance on it. You can adapt the table size yourself, according to
+ your virtual server application. It is good to set the table size not far
+ less than the number of connections per second multiplying average lasting
+ time of connection in the table. For example, your virtual server gets
+ 200 connections per second, the connection lasts for 200 seconds in
+ average in the connection table, the table size should be not far less
+ than 200x200, it is good to set the table size 32768 (2**15).

Another note that each connection occupies 128 bytes effectively and
each hash entry uses 8 bytes, so you can estimate how much memory is
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 13534e02346c..e1b9b52909a5 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1484,8 +1484,8 @@ int __init ip_vs_conn_init(void)
int idx;

/* Compute size and mask */
- if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 20) {
- pr_info("conn_tab_bits not in [8, 20]. Using default value\n");
+ if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 27) {
+ pr_info("conn_tab_bits not in [8, 27]. Using default value\n");
ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS;
}
ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;

---
base-commit: 09a9639e56c01c7a00d6c0ca63f4c7c41abe075d
change-id: 20230412-increase_ipvs_conn_tab_bits-4322c90da216

Best regards,
--
Abhijeet Rastogi <[email protected]>



2023-05-15 15:40:06

by Julian Anastasov

[permalink] [raw]
Subject: Re: [PATCH v2] ipvs: increase ip_vs_conn_tab_bits range for 64BIT


Hello,

On Sun, 14 May 2023, Abhijeet Rastogi wrote:

> Current range [8, 20] is set purely due to historical reasons
> because at the time, ~1M (2^20) was considered sufficient.
> With this change, 27 is the upper limit for 64-bit, 20 otherwise.
>
> Previous change regarding this limit is here.
>
> Link: https://lore.kernel.org/all/86eabeb9dd62aebf1e2533926fdd13fed48bab1f.1631289960.git.aclaudi@redhat.com/T/#u
>
> Signed-off-by: Abhijeet Rastogi <[email protected]>
> ---
> The conversation for this started at:
>
> https://www.spinics.net/lists/netfilter/msg60995.html
>
> The upper limit for algo is any bit size less than 32, so this
> change will allow us to set bit size > 20. Today, it is common to have
> RAM available to handle greater than 2^20 connections per-host.
>
> Distros like RHEL already allow setting limits higher than 20.
> ---
> Changes in v2:
> - Lower the ranges, 27 for 64bit, 20 otherwise
> - Link to v1: https://lore.kernel.org/r/[email protected]
> ---
> net/netfilter/ipvs/Kconfig | 26 +++++++++++++-------------
> net/netfilter/ipvs/ip_vs_conn.c | 4 ++--
> 2 files changed, 15 insertions(+), 15 deletions(-)
>
> diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
> index 271da8447b29..aac5d6bd82e6 100644
> --- a/net/netfilter/ipvs/Kconfig
> +++ b/net/netfilter/ipvs/Kconfig
> @@ -44,7 +44,8 @@ config IP_VS_DEBUG
>
> config IP_VS_TAB_BITS
> int "IPVS connection table size (the Nth power of 2)"
> - range 8 20
> + range 8 20 if !64BIT
> + range 8 27 if 64BIT
> default 12
> help
> The IPVS connection hash table uses the chaining scheme to handle
> @@ -52,18 +53,17 @@ config IP_VS_TAB_BITS
> reduce conflicts when there are hundreds of thousands of connections
> in the hash table.
>
> - Note the table size must be power of 2. The table size will be the
> - value of 2 to the your input number power. The number to choose is
> - from 8 to 20, the default number is 12, which means the table size
> - is 4096. Don't input the number too small, otherwise you will lose
> - performance on it. You can adapt the table size yourself, according
> - to your virtual server application. It is good to set the table size
> - not far less than the number of connections per second multiplying
> - average lasting time of connection in the table. For example, your
> - virtual server gets 200 connections per second, the connection lasts
> - for 200 seconds in average in the connection table, the table size
> - should be not far less than 200x200, it is good to set the table
> - size 32768 (2**15).
> + Note the table size must be power of 2. The table size will be the value
> + of 2 to the your input number power. The number to choose is from 8 to 27
> + for 64BIT(20 otherwise), the default number is 12, which means the table
> + size is 4096. Don't input the number too small, otherwise you will lose
> + performance on it. You can adapt the table size yourself, according to
> + your virtual server application. It is good to set the table size not far
> + less than the number of connections per second multiplying average lasting
> + time of connection in the table. For example, your virtual server gets
> + 200 connections per second, the connection lasts for 200 seconds in
> + average in the connection table, the table size should be not far less
> + than 200x200, it is good to set the table size 32768 (2**15).

Can you keep the previous line width of the above help
because on standard 80-width window the help now gets truncated in
make menuconfig.

After that I'll send a patch on top of yours to limit the
rows depending on the memory.

> Another note that each connection occupies 128 bytes effectively and
> each hash entry uses 8 bytes, so you can estimate how much memory is
> diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
> index 13534e02346c..e1b9b52909a5 100644
> --- a/net/netfilter/ipvs/ip_vs_conn.c
> +++ b/net/netfilter/ipvs/ip_vs_conn.c
> @@ -1484,8 +1484,8 @@ int __init ip_vs_conn_init(void)
> int idx;
>
> /* Compute size and mask */
> - if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 20) {
> - pr_info("conn_tab_bits not in [8, 20]. Using default value\n");
> + if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 27) {
> + pr_info("conn_tab_bits not in [8, 27]. Using default value\n");
> ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS;
> }
> ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;
>
> ---

Regards

--
Julian Anastasov <[email protected]>


2023-05-16 02:04:55

by Abhijeet Rastogi

[permalink] [raw]
Subject: Re: [PATCH v2] ipvs: increase ip_vs_conn_tab_bits range for 64BIT

Hi Julian Anastasov,

>Can you keep the previous line width of the above help
because on standard 80-width window the help now gets truncated in
make menuconfig.

Refer this screenshot: https://i.imgur.com/9LgttpC.png

Sorry for the confusion, I was already expecting this comment. The
patch had a few words added, hence it feels like many lines have
changed. However, no line actually exceeds 80 width.

Longest line is still 80-width max. Do you prefer I reduce it to a
lower number like 70?

Thanks,
Abhijeet


On Mon, May 15, 2023 at 8:18 AM Julian Anastasov <[email protected]> wrote:
>
>
> Hello,
>
> On Sun, 14 May 2023, Abhijeet Rastogi wrote:
>
> > Current range [8, 20] is set purely due to historical reasons
> > because at the time, ~1M (2^20) was considered sufficient.
> > With this change, 27 is the upper limit for 64-bit, 20 otherwise.
> >
> > Previous change regarding this limit is here.
> >
> > Link: https://lore.kernel.org/all/86eabeb9dd62aebf1e2533926fdd13fed48bab1f.1631289960.git.aclaudi@redhat.com/T/#u
> >
> > Signed-off-by: Abhijeet Rastogi <[email protected]>
> > ---
> > The conversation for this started at:
> >
> > https://www.spinics.net/lists/netfilter/msg60995.html
> >
> > The upper limit for algo is any bit size less than 32, so this
> > change will allow us to set bit size > 20. Today, it is common to have
> > RAM available to handle greater than 2^20 connections per-host.
> >
> > Distros like RHEL already allow setting limits higher than 20.
> > ---
> > Changes in v2:
> > - Lower the ranges, 27 for 64bit, 20 otherwise
> > - Link to v1: https://lore.kernel.org/r/[email protected]
> > ---
> > net/netfilter/ipvs/Kconfig | 26 +++++++++++++-------------
> > net/netfilter/ipvs/ip_vs_conn.c | 4 ++--
> > 2 files changed, 15 insertions(+), 15 deletions(-)
> >
> > diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
> > index 271da8447b29..aac5d6bd82e6 100644
> > --- a/net/netfilter/ipvs/Kconfig
> > +++ b/net/netfilter/ipvs/Kconfig
> > @@ -44,7 +44,8 @@ config IP_VS_DEBUG
> >
> > config IP_VS_TAB_BITS
> > int "IPVS connection table size (the Nth power of 2)"
> > - range 8 20
> > + range 8 20 if !64BIT
> > + range 8 27 if 64BIT
> > default 12
> > help
> > The IPVS connection hash table uses the chaining scheme to handle
> > @@ -52,18 +53,17 @@ config IP_VS_TAB_BITS
> > reduce conflicts when there are hundreds of thousands of connections
> > in the hash table.
> >
> > - Note the table size must be power of 2. The table size will be the
> > - value of 2 to the your input number power. The number to choose is
> > - from 8 to 20, the default number is 12, which means the table size
> > - is 4096. Don't input the number too small, otherwise you will lose
> > - performance on it. You can adapt the table size yourself, according
> > - to your virtual server application. It is good to set the table size
> > - not far less than the number of connections per second multiplying
> > - average lasting time of connection in the table. For example, your
> > - virtual server gets 200 connections per second, the connection lasts
> > - for 200 seconds in average in the connection table, the table size
> > - should be not far less than 200x200, it is good to set the table
> > - size 32768 (2**15).
> > + Note the table size must be power of 2. The table size will be the value
> > + of 2 to the your input number power. The number to choose is from 8 to 27
> > + for 64BIT(20 otherwise), the default number is 12, which means the table
> > + size is 4096. Don't input the number too small, otherwise you will lose
> > + performance on it. You can adapt the table size yourself, according to
> > + your virtual server application. It is good to set the table size not far
> > + less than the number of connections per second multiplying average lasting
> > + time of connection in the table. For example, your virtual server gets
> > + 200 connections per second, the connection lasts for 200 seconds in
> > + average in the connection table, the table size should be not far less
> > + than 200x200, it is good to set the table size 32768 (2**15).
>
> Can you keep the previous line width of the above help
> because on standard 80-width window the help now gets truncated in
> make menuconfig.
>
> After that I'll send a patch on top of yours to limit the
> rows depending on the memory.
>
> > Another note that each connection occupies 128 bytes effectively and
> > each hash entry uses 8 bytes, so you can estimate how much memory is
> > diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
> > index 13534e02346c..e1b9b52909a5 100644
> > --- a/net/netfilter/ipvs/ip_vs_conn.c
> > +++ b/net/netfilter/ipvs/ip_vs_conn.c
> > @@ -1484,8 +1484,8 @@ int __init ip_vs_conn_init(void)
> > int idx;
> >
> > /* Compute size and mask */
> > - if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 20) {
> > - pr_info("conn_tab_bits not in [8, 20]. Using default value\n");
> > + if (ip_vs_conn_tab_bits < 8 || ip_vs_conn_tab_bits > 27) {
> > + pr_info("conn_tab_bits not in [8, 27]. Using default value\n");
> > ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS;
> > }
> > ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits;
> >
> > ---
>
> Regards
>
> --
> Julian Anastasov <[email protected]>
>


--
Cheers,
Abhijeet (https://abhi.host)

2023-05-16 05:49:23

by Julian Anastasov

[permalink] [raw]
Subject: Re: [PATCH v2] ipvs: increase ip_vs_conn_tab_bits range for 64BIT


Hello,

On Mon, 15 May 2023, Abhijeet Rastogi wrote:

> Hi Julian Anastasov,
>
> >Can you keep the previous line width of the above help
> because on standard 80-width window the help now gets truncated in
> make menuconfig.
>
> Refer this screenshot: https://i.imgur.com/9LgttpC.png
>
> Sorry for the confusion, I was already expecting this comment. The
> patch had a few words added, hence it feels like many lines have
> changed. However, no line actually exceeds 80 width.
>
> Longest line is still 80-width max. Do you prefer I reduce it to a
> lower number like 70?

I'm checking in menuconfig where the help text is displayed.
The word "lasting" is visible up to "last". So, 3 columns are not
visible. In editor, this line is 84, may be up to 80 should be good.
You are using editor that represents Tabs as 4 spaces, that is why
it looks like it fits in 80. Open Kconfig in less. But in editor/less
does not matter because menuconfig simply ignores the leading spaces
in Kconfig and considers the text length which should be no more
than 70.

Regards

--
Julian Anastasov <[email protected]>


2023-05-17 03:48:16

by Abhijeet Rastogi

[permalink] [raw]
Subject: Re: [PATCH v2] ipvs: increase ip_vs_conn_tab_bits range for 64BIT

@Julian, Thank you for the clarification. I've sent v3 and I truly
appreciate your patience with this.

On Mon, May 15, 2023 at 10:35 PM Julian Anastasov <[email protected]> wrote:
>
>
> Hello,
>
> On Mon, 15 May 2023, Abhijeet Rastogi wrote:
>
> > Hi Julian Anastasov,
> >
> > >Can you keep the previous line width of the above help
> > because on standard 80-width window the help now gets truncated in
> > make menuconfig.
> >
> > Refer this screenshot: https://i.imgur.com/9LgttpC.png
> >
> > Sorry for the confusion, I was already expecting this comment. The
> > patch had a few words added, hence it feels like many lines have
> > changed. However, no line actually exceeds 80 width.
> >
> > Longest line is still 80-width max. Do you prefer I reduce it to a
> > lower number like 70?
>
> I'm checking in menuconfig where the help text is displayed.
> The word "lasting" is visible up to "last". So, 3 columns are not
> visible. In editor, this line is 84, may be up to 80 should be good.
> You are using editor that represents Tabs as 4 spaces, that is why
> it looks like it fits in 80. Open Kconfig in less. But in editor/less
> does not matter because menuconfig simply ignores the leading spaces
> in Kconfig and considers the text length which should be no more
> than 70.
>
> Regards
>
> --
> Julian Anastasov <[email protected]>
>


--
Cheers,
Abhijeet (https://abhi.host)