All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Rafał Miłecki" <zajec5@gmail.com>
To: Felix Fietkau <nbd@nbd.name>, Andrew Lunn <andrew@lunn.ch>
Cc: Arnd Bergmann <arnd@arndb.de>,
	Alexander Lobakin <alexandr.lobakin@intel.com>,
	Network Development <netdev@vger.kernel.org>,
	linux-arm-kernel <linux-arm-kernel@lists.infradead.org>,
	Russell King <linux@armlinux.org.uk>,
	"openwrt-devel@lists.openwrt.org"
	<openwrt-devel@lists.openwrt.org>,
	Florian Fainelli <f.fainelli@gmail.com>
Subject: Re: Optimizing kernel compilation / alignments for network performance
Date: Fri, 6 May 2022 09:47:41 +0200	[thread overview]
Message-ID: <04fa6560-e6f4-005f-cddb-7bc9b4859ba2@gmail.com> (raw)
In-Reply-To: <2a338e8e-3288-859c-d2e8-26c5712d3d06@nbd.name>

On 5.05.2022 18:46, Felix Fietkau wrote:
> 
> On 05.05.22 18:04, Andrew Lunn wrote:
>>> you'll see that most used functions are:
>>> v7_dma_inv_range
>>> __irqentry_text_end
>>> l2c210_inv_range
>>> v7_dma_clean_range
>>> bcma_host_soc_read32
>>> __netif_receive_skb_core
>>> arch_cpu_idle
>>> l2c210_clean_range
>>> fib_table_lookup
>>
>> There is a lot of cache management functions here. Might sound odd,
>> but have you tried disabling SMP? These cache functions need to
>> operate across all CPUs, and the communication between CPUs can slow
>> them down. If there is only one CPU, these cache functions get simpler
>> and faster.
>>
>> It just depends on your workload. If you have 1 CPU loaded to 100% and
>> the other 3 idle, you might see an improvement. If you actually need
>> more than one CPU, it will probably be worse.
>>
>> I've also found that some Ethernet drivers invalidate or flush too
>> much. If you are sending a 64 byte TCP ACK, all you need to flush is
>> 64 bytes, not the full 1500 MTU. If you receive a TCP ACK, and then
>> recycle the buffer, all you need to invalidate is the size of the ACK,
>> so long as you can guarantee nothing has touched the memory above it.
>> But you need to be careful when implementing tricks like this, or you
>> can get subtle corruption bugs when you get it wrong.
> I just took a quick look at the driver. It allocates and maps rx buffers that can cover a packet size of BGMAC_RX_MAX_FRAME_SIZE = 9724.
> This seems rather excessive, especially since most people are going to use a MTU of 1500.
> My proposal would be to add support for making rx buffer size dependent on MTU, reallocating the ring on MTU changes.
> This should significantly reduce the time spent on flushing caches.

Oh, that's important too, it was changed by commit 8c7da63978f1 ("bgmac:
configure MTU and add support for frames beyond 8192 byte size"):
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=8c7da63978f1672eb4037bbca6e7eac73f908f03

It lowered NAT speed with bgmac by 60% (362 Mbps → 140 Mbps).

I do all my testing with
#define BGMAC_RX_MAX_FRAME_SIZE			1536

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

WARNING: multiple messages have this Message-ID (diff)
From: "Rafał Miłecki" <zajec5@gmail.com>
To: Felix Fietkau <nbd@nbd.name>, Andrew Lunn <andrew@lunn.ch>
Cc: Arnd Bergmann <arnd@arndb.de>,
	Alexander Lobakin <alexandr.lobakin@intel.com>,
	Network Development <netdev@vger.kernel.org>,
	linux-arm-kernel <linux-arm-kernel@lists.infradead.org>,
	Russell King <linux@armlinux.org.uk>,
	"openwrt-devel@lists.openwrt.org"
	<openwrt-devel@lists.openwrt.org>,
	Florian Fainelli <f.fainelli@gmail.com>
Subject: Re: Optimizing kernel compilation / alignments for network performance
Date: Fri, 6 May 2022 09:47:41 +0200	[thread overview]
Message-ID: <04fa6560-e6f4-005f-cddb-7bc9b4859ba2@gmail.com> (raw)
In-Reply-To: <2a338e8e-3288-859c-d2e8-26c5712d3d06@nbd.name>

On 5.05.2022 18:46, Felix Fietkau wrote:
> 
> On 05.05.22 18:04, Andrew Lunn wrote:
>>> you'll see that most used functions are:
>>> v7_dma_inv_range
>>> __irqentry_text_end
>>> l2c210_inv_range
>>> v7_dma_clean_range
>>> bcma_host_soc_read32
>>> __netif_receive_skb_core
>>> arch_cpu_idle
>>> l2c210_clean_range
>>> fib_table_lookup
>>
>> There is a lot of cache management functions here. Might sound odd,
>> but have you tried disabling SMP? These cache functions need to
>> operate across all CPUs, and the communication between CPUs can slow
>> them down. If there is only one CPU, these cache functions get simpler
>> and faster.
>>
>> It just depends on your workload. If you have 1 CPU loaded to 100% and
>> the other 3 idle, you might see an improvement. If you actually need
>> more than one CPU, it will probably be worse.
>>
>> I've also found that some Ethernet drivers invalidate or flush too
>> much. If you are sending a 64 byte TCP ACK, all you need to flush is
>> 64 bytes, not the full 1500 MTU. If you receive a TCP ACK, and then
>> recycle the buffer, all you need to invalidate is the size of the ACK,
>> so long as you can guarantee nothing has touched the memory above it.
>> But you need to be careful when implementing tricks like this, or you
>> can get subtle corruption bugs when you get it wrong.
> I just took a quick look at the driver. It allocates and maps rx buffers that can cover a packet size of BGMAC_RX_MAX_FRAME_SIZE = 9724.
> This seems rather excessive, especially since most people are going to use a MTU of 1500.
> My proposal would be to add support for making rx buffer size dependent on MTU, reallocating the ring on MTU changes.
> This should significantly reduce the time spent on flushing caches.

Oh, that's important too, it was changed by commit 8c7da63978f1 ("bgmac:
configure MTU and add support for frames beyond 8192 byte size"):
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=8c7da63978f1672eb4037bbca6e7eac73f908f03

It lowered NAT speed with bgmac by 60% (362 Mbps → 140 Mbps).

I do all my testing with
#define BGMAC_RX_MAX_FRAME_SIZE			1536

  reply	other threads:[~2022-05-06  7:48 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-27 12:04 Optimizing kernel compilation / alignments for network performance Rafał Miłecki
2022-04-27 12:04 ` Rafał Miłecki
2022-04-27 12:56 ` Alexander Lobakin
2022-04-27 12:56   ` Alexander Lobakin
2022-04-27 17:31   ` Rafał Miłecki
2022-04-27 17:31     ` Rafał Miłecki
2022-04-29 14:18     ` Rafał Miłecki
2022-04-29 14:18       ` Rafał Miłecki
2022-04-29 14:49     ` Arnd Bergmann
2022-04-29 14:49       ` Arnd Bergmann
2022-05-05 15:42       ` Rafał Miłecki
2022-05-05 15:42         ` Rafał Miłecki
2022-05-05 16:04         ` Andrew Lunn
2022-05-05 16:04           ` Andrew Lunn
2022-05-05 16:46           ` Felix Fietkau
2022-05-05 16:46             ` Felix Fietkau
2022-05-06  7:47             ` Rafał Miłecki [this message]
2022-05-06  7:47               ` Rafał Miłecki
2022-05-06 12:42               ` Andrew Lunn
2022-05-06 12:42                 ` Andrew Lunn
2022-05-10 10:29                 ` Rafał Miłecki
2022-05-10 10:29                   ` Rafał Miłecki
2022-05-10 14:09                   ` Dave Taht
2022-05-10 14:09                     ` Dave Taht
2022-05-10 19:15                     ` Dave Taht
2022-05-10 19:15                       ` Dave Taht
2022-05-06  7:44           ` Rafał Miłecki
2022-05-06  7:44             ` Rafał Miłecki
2022-05-06  8:45             ` Arnd Bergmann
2022-05-06  8:45               ` Arnd Bergmann
2022-05-06  8:55               ` Rafał Miłecki
2022-05-06  8:55                 ` Rafał Miłecki
2022-05-06  9:44                 ` Arnd Bergmann
2022-05-06  9:44                   ` Arnd Bergmann
2022-05-10 12:51                   ` Rafał Miłecki
2022-05-10 12:51                     ` Rafał Miłecki
2022-05-10 13:19                     ` Arnd Bergmann
2022-05-10 13:19                       ` Arnd Bergmann
2022-05-10 11:23               ` Rafał Miłecki
2022-05-10 11:23                 ` Rafał Miłecki
2022-05-10 13:18                 ` Arnd Bergmann
2022-05-10 13:18                   ` Arnd Bergmann
2022-05-08  9:53             ` Rafał Miłecki
2022-05-08  9:53               ` Rafał Miłecki

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=04fa6560-e6f4-005f-cddb-7bc9b4859ba2@gmail.com \
    --to=zajec5@gmail.com \
    --cc=alexandr.lobakin@intel.com \
    --cc=andrew@lunn.ch \
    --cc=arnd@arndb.de \
    --cc=f.fainelli@gmail.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux@armlinux.org.uk \
    --cc=nbd@nbd.name \
    --cc=netdev@vger.kernel.org \
    --cc=openwrt-devel@lists.openwrt.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.