我重建了一个服务器，特别是媒体服务器，基于Debian 12稳定（内核6.1）。
- 中央处理器:i7-6700K（不超频）
- 内存：16GB DDR4（双通道）
- 网卡：2 个 2.5Gbit（绑定平衡-tlb) (最大传输单元bond0：4096。但我的网络家庭有经典的MTU）
- 图形处理器：PHY T400（4GB 版本）
- 贮存: 3固态硬盘
这些 SSD 的配置如下：
- 固态硬盘1：每部电影 1TB（xfs）（调度程序：没有任何）
- 固态硬盘2：250GB 用于操作系统（125GB操作系统，125GB 用于交换）（外部4）（调度程序：没有任何）
Disk /dev/sdb: 232,89 GiB, 250059350016 bytes, 488397168 sectors
Disk model: Samsung SSD 860
Units: sectors of 1 * 512 = 512 bytes
Sector size (logical/physical): 512 bytes / 512 bytes
I/O size (minimum/optimal): 512 bytes / 512 bytes
Disklabel type: dos
Disk identifier: 0xcfa6d02d
Device Boot Start End Sectors Size Id Type
/dev/sdb1 * 2048 244140031 244137984 116,4G 83 Linux
/dev/sdb2 244140032 488280063 244140032 116,4G 82 Linux swap / Solaris
dumpe2fs 1.47.0 (5-Feb-2023)
Filesystem volume name: root
Last mounted on: /
Filesystem UUID: 927a3648-60d1-4537-af56-0d87ff5a6e0b
Filesystem magic number: 0xEF53
Filesystem revision #: 1 (dynamic)
Filesystem features: has_journal ext_attr resize_inode dir_index fast_commit filetype needs_recovery extent 64bit flex_bg sparse_super large_file huge_file dir_nlink extra_isize metadata_csum
Filesystem flags: signed_directory_hash
Default mount options: user_xattr acl
Filesystem state: clean
Errors behavior: Continue
Filesystem OS type: Linux
Inode count: 7634944
Block count: 30517248
Reserved block count: 305172
Overhead clusters: 625720
Free blocks: 28139695
Free inodes: 7541676
First block: 0
Block size: 4096
Fragment size: 4096
Group descriptor size: 64
Reserved GDT blocks: 1024
Blocks per group: 32768
Fragments per group: 32768
Inodes per group: 8192
Inode blocks per group: 512
Flex block group size: 16
Filesystem created: Tue Oct 17 02:41:54 2023
Last mount time: Thu Oct 19 19:21:21 2023
Last write time: Thu Oct 19 19:21:21 2023
Mount count: 25
Maximum mount count: -1
Last checked: Wed Oct 18 03:33:16 2023
Check interval: 0 (<none>)
Lifetime writes: 90 GB
Reserved blocks uid: 0 (user root)
Reserved blocks gid: 0 (group root)
First inode: 11
Inode size: 256
Required extra isize: 32
Desired extra isize: 32
Journal inode: 8
Default directory hash: half_md4
Directory Hash Seed: 5f52b9e5-cf5a-438c-9e90-0c2d91207ea7
Journal backup: inode blocks
Checksum type: crc32c
Checksum: 0x2f208f9b
Journal features: journal_incompat_revoke journal_64bit journal_checksum_v3 FEATURE_I5
Total journal size: 512M
Total journal blocks: 131072
Max transaction length: 130816
Fast commit length: 256
Journal sequence: 0x0000796d
Journal start: 1
Journal checksum type: crc32c
Journal checksum: 0x0a6d11a2
- 固态硬盘3：500GB 用于“常规”缓存（转码、通过 fscache 进行网络挂载点缓存等）。 (外部4）（调度程序：没有任何）
Disk /dev/sdc: 465,76 GiB, 500107862016 bytes, 976773168 sectors
Disk model: CT500MX500SSD1
Units: sectors of 1 * 512 = 512 bytes
Sector size (logical/physical): 512 bytes / 4096 bytes
I/O size (minimum/optimal): 4096 bytes / 4096 bytes
dumpe2fs 1.47.0 (5-Feb-2023)
Filesystem volume name: <none>
Last mounted on: /cache
Filesystem UUID: 070d06bd-6a01-4457-b20f-cf699f412168
Filesystem magic number: 0xEF53
Filesystem revision #: 1 (dynamic)
Filesystem features: has_journal ext_attr resize_inode dir_index fast_commit filetype needs_recovery extent 64bit flex_bg sparse_super large_file huge_file dir_nlink extra_isize metadata_csum
Filesystem flags: signed_directory_hash
Default mount options: user_xattr acl
Filesystem state: clean
Errors behavior: Continue
Filesystem OS type: Linux
Inode count: 30531584
Block count: 122096646
Reserved block count: 0
Overhead clusters: 2201430
Free blocks: 119895208
Free inodes: 30531569
First block: 0
Block size: 4096
Fragment size: 4096
Group descriptor size: 64
Reserved GDT blocks: 1024
Blocks per group: 32768
Fragments per group: 32768
Inodes per group: 8192
Inode blocks per group: 512
Flex block group size: 16
Filesystem created: Wed Oct 18 19:01:18 2023
Last mount time: Thu Oct 19 19:21:22 2023
Last write time: Thu Oct 19 19:21:22 2023
Mount count: 16
Maximum mount count: -1
Last checked: Wed Oct 18 19:01:18 2023
Check interval: 0 (<none>)
Lifetime writes: 48 GB
Reserved blocks uid: 0 (user root)
Reserved blocks gid: 0 (group root)
First inode: 11
Inode size: 256
Required extra isize: 32
Desired extra isize: 32
Journal inode: 8
Default directory hash: half_md4
Directory Hash Seed: cbad2af6-a244-4e66-b27c-3e8dea9f8f2f
Journal backup: inode blocks
Checksum type: crc32c
Checksum: 0x47fb58ba
Journal features: journal_incompat_revoke journal_64bit journal_checksum_v3 FEATURE_I5
Total journal size: 1040M
Total journal blocks: 266240
Max transaction length: 262144
Fast commit length: 4096
Journal sequence: 0x00000384
Journal start: 0
Journal checksum type: crc32c
Journal checksum: 0xae89c35f
使用的软件：丛（和硬件转码/编码）和服务（DLNA 软件）
我选择 xfs 作为电影的文件系统，因为将托管大文件（众所周知，xfs 在这种类型的文件上执行），对于所有其他 SSD，我选择 ext4，也用于缓存。我的选择正确吗？小前提：不要查看与备份计划、有关文件系统的数据安全等相关的服务器/存储，因为该服务器仅充当“通道”...让我更好地解释...也就是说，它必须在转码、文件访问速度（通过 cifs/fscache）以及与文件共享介质相关的所有内容方面尽最大努力，因此即使某些内容被损坏，我也不会丢失任何东西......我不知道我是否'我明白了。因此，我寻找优化/设置来尽可能加快速度，包括吞吐量。我发布了一些配置。根据更专家的意见，我应该更改/添加一些内容吗？抛开这些配置不谈，我是否也应该更改操作系统中的某些内容？我只运行了 rsyslogd，省略了我主要使用的上述软件。
幼虫
GRUB_CMDLINE_LINUX_DEFAULT="quiet mitigations=off nopti net.ifnames=0 biosdevname=0 intel_idle.max_cstate=1 i915.enable_psr=0 i915.enable_dc=0 zswap.enabled=1 zswap.compressor=lzo nowatchdog nosgx"
系统配置文件
kernel.sysrq=0
vm.swappiness=1
vm.vfs_cache_pressure=60
fs.suid_dumpable=0
kernel.core_pattern=|/bin/false
net.ipv6.conf.all.disable_ipv6=1
net.ipv6.conf.default.disable_ipv6=1
net.ipv6.conf.lo.disable_ipv6=1
net.ipv4.tcp_keepalive_time = 60
net.ipv4.tcp_keepalive_intvl = 10
net.ipv4.tcp_keepalive_probes = 3
net.ipv4.tcp_fastopen=3
net.ipv4.tcp_tw_reuse=1
net.ipv4.tcp_fin_timeout=5
net.ipv4.tcp_sack=1
net.core.default_qdisc=cake
net.ipv4.tcp_congestion_control=bbr