From 6c386e720e2b96c22f128d50552a1fe6a4a24b4d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Motiejus=20Jak=C5=A1tys?= Date: Wed, 23 Feb 2022 10:45:05 +0200 Subject: [PATCH] update README --- README.md | 216 +++++++++++++++++++++++++++--------------------------- 1 file changed, 107 insertions(+), 109 deletions(-) diff --git a/README.md b/README.md index 12073f8..6ac700d 100644 --- a/README.md +++ b/README.md @@ -10,7 +10,7 @@ Turbonss is optimized for reading. If the data changes in any way, the whole file will need to be regenerated (and tooling only supports only full generation). It was created, and best suited, for environments that have a central user & group database which then needs to be distributed to many -servers/services. +servers/services, and the data does not change very often (e.g. hourly). To understand more about name service switch, start with [`nsswitch.conf(5)`][nsswitch]. @@ -42,15 +42,15 @@ struct passwd { Turbonss, among others, implements this call, and takes the following steps to resolve a username to a `struct passwd*`: -- Open the DB (using `mmap`) and interpret it's first 40 bytes as a `struct +- Open the DB (using `mmap`) and interpret it's first 64 bytes as a `*struct Header`. The header stores offsets to the sections of the file. This needs to - be done once, when the NSS library is loaded (or on the first call). + be done once, when the NSS library is loaded. - Hash the username using a perfect hash function. Perfect hash function returns a number `n ∈ [0,N-1]`, where N is the total number of users. -- Jump to the `n`'th location in the `idx_name2user` section (by pointer - arithmetic), which contains the index `i` to the user's information. -- Jump to the location `i` of section `Users` (again, using pointer arithmetic) - which stores the full user information. +- Jump to the `n`'th location in the `idx_name2user` section, which contains + the index `i` to the user's information. +- Jump to the location `i` of section `Users`, which stores the full user + information. - Decode the user information (which is all in a continuous memory block) and return it to the caller. @@ -58,10 +58,9 @@ In total, that's one hash for the username (~150ns), two pointer jumps within the group file (to sections `idx_name2user` and `Users`), and, now that the user record is found, `memcpy` for each field. -The turbonss DB file is be `mmap`-ed, making it simple to implement pointer -arithmetic and jumping across the file. This also reduces memory usage, -especially across multiple concurrent invocations of the `id` command. The -consumed heap space for each separate turbonss instance will be minimal. +The turbonss DB file is be `mmap`-ed, making it simple to jump across the file +using pointer arithmetic. This also reduces memory usage, as the mmap'ed +regions are shared. Turbonss reads do not consume any heap space. Tight packing places some constraints on the underlying data: @@ -105,9 +104,12 @@ A known implementation runs id(1) at ~250 rps sequentially on ~20k users and To better reason about the trade-offs, it is useful to understand how `id(1)` is implemented, in rough terms: -- lookup user by name. -- get all additional gids (an array attached to a member). -- for each additional gid, get the group information (`struct group*`). +- lookup user by name ([`getpwent_r(3)`][getpwent_r]). +- get all gids for the user ([`getgrouplist(3)`][getgrouplist]). Note: it is + actually using `initgroups_dyn`, accepts a uid, and is very poorly + documented. +- for each additional gid, get the `struct group*` + ([`getgrgid_r(3)`][getgrgid_r]). Assuming a member is in ~100 groups on average, that's 1M group lookups per second. We need to convert gid to a group index, and group index to a group @@ -115,40 +117,13 @@ gid/name quickly. Caveat: `struct group` contains an array of pointers to names of group members (`char **gr_mem`). However, `id` does not use that information, resulting in -read amplification. Therefore, if `argv[0] == "id"`, our implementation of -`getgrid(3)` returns the `struct group*` without the members. This speeds up -`id` by about 10x on a known NSS implementation. +read amplification, sometimes by 10-100x. Therefore, if `argv[0] == "id"`, our +implementation of [`getgrid_r(3)`][getgrid] returns the `struct group*` without +the members. This speeds up `id` by about 10x on a known NSS implementation. -Relatedly, because `getgrid(3)` does not need the group members, the group -members are stored in a different DB sectoin, making the `Groups` section -smaller, thus more CPU-cache-friendly in the hot path. - -Indices -------- - -Now that we've sketched the implementation of `id(3)`, it's clearer to -understand which operations need to be fast; in order of importance: - -1. lookup gid -> group info (this is on hot path in id) without members. -2. lookup username -> user's groups. -3. lookup uid -> user. -4. lookup groupname -> group. -5. lookup username -> user. - -These indices can use perfect hashing like [bdz from cmph][cmph]: a perfect -hash hashes a list of bytes to a sequential list of integers. Perfect hashing -algorithms require some space, and take some time to calculate ("hashing -duration"). I've tested BDZ, which hashes [][]u8 to a sequential list of -integers (not preserving order) and CHM, preserves order. BDZ accepts an -optional argument `3 <= b <= 10`. - -* BDZ algorithm requires (b=3, 900KB, b=7, 338KB, b=10, 306KB) for 1M values. -* Latency to resolve 1M keys: (170ms, 180ms, 230ms, respectively). -* Packed vs non-packed latency differences are not meaningful. - -CHM retains order, however, 1M keys weigh 8MB. 10k keys are ~20x larger with -CHM than with BDZ, eliminating the benefit of preserved ordering: we can just -have a separate index. +Relatedly, because [`getgrid_r(3)`][getgrid] does not need the group members, +the group members are stored in a different DB section, reducing the `Groups` +section and making more of it fit the CPU caches. Turbonss header --------------- @@ -160,7 +135,7 @@ OFFSET TYPE NAME DESCRIPTION 0 [4]u8 magic always 0xf09fa4b7 4 u8 version now `0` 5 u16 bom 0x1234 - u8 num_shells max value: 63. Padding is strange on little endian. + u8 num_shells max value: 63. 8 u32 num_users number of passwd entries 12 u32 num_groups number of group entries 16 u32 offset_bdz_uid2user @@ -180,10 +155,11 @@ created at. Turbonss files cannot be moved across different-endianness computers. If that happens, turbonss will refuse to read the file. Offsets are indices to further sections of the file, with zero being the first -block (pointing to the `magic` field). As all blobs are 64-byte aligned, the -offsets are always pointing to the beginning of an 64-byte "block". Therefore, -all `offset_*` values could be `u26`. As `u32` is easier to visualize with xxd, -and the header block fits to 64 bytes anyway, we are keeping them as u32 now. +block (pointing to the `magic` field). As all sections are aligned to 64 bytes, +the offsets are always pointing to the beginning of an 64-byte "block". +Therefore, all `offset_*` values could be `u26`. As `u32` is easier to +visualize with xxd, and the header block fits to 64 bytes anyway, we are +keeping them as u32 now. Sections whose lengths can be calculated do not have a corresponding `offset_*` header field. For example, `bdz_gid2group` comes immediately after the header, @@ -193,13 +169,13 @@ and `idx_groupname2group` comes after `idx_gid2group`, whose offset is `num_shells` would fit to u6; however, we would need 2 bits of padding (all other fields are byte-aligned). If we instead do `u2` followed by `u6`, the byte would look very unusual on a little-endian architecture. Therefore we will -just refuse loading the file if the number of shells exceeds 63. +just reject the DB if the number of shells exceeds 63. Primitive types --------------- -`User` and `Group` entries are sorted by name, ordered by their unicode -codepoints. They are byte-aligned (8bits). All `User` and `Group` entries are +`User` and `Group` entries are sorted by the order they were received in the input +file. All entries are aligned to 8 bytes. All `User` and `Group` entries are referred by their byte offset in the `Users` and `Groups` section relative to the beginning of the section. @@ -214,61 +190,59 @@ const Group = struct { groupname []u8; } -const User = struct { +pub const PackedUser = packed struct { uid: u32, gid: u32, - // pointer to a separate structure that contains a list of gids - additional_gids_offset: u29, - // shell is a different story, documented elsewhere. shell_here: bool, shell_len_or_idx: u6, home_len: u6, name_is_a_suffix: bool, name_len: u5, - gecos_len: u8, - // a variable-sized array that will be stored immediately after this - // struct. + gecos_len: u10, + padding: u3, + // pseudocode: variable-sized array that will be stored immediately after + // this struct. stringdata []u8; } ``` `stringdata` contains a few string entries: - home. -- name. +- name (optional). - gecos. - shell (optional). -First byte of the home is stored right after the `gecos_len` field, and it's +First byte of home is stored right after the `gecos_len` field, and it's length is `home_len`. The same logic applies to all the `stringdata` fields: there is a way to calculate their relative position from the length of the fields before them. -Additionally, two optimizations for special fields are made: +Additionally, there are two "easy" optimizations: - shells are often shared across different users, see the "Shells" section. -- name is frequently a suffix of the home. For example, `/home/motiejus` - and `motiejus`. In which case storing both name and home strings is - wasteful. For that cases, name has two options: - 1. `name_is_a_suffix=true`: name is a suffix of the home dir. In that - case, the name starts at the `home_len - name_len`'th - byte of the home, and ends at the same place as the home. - 2. `name_is_a_suffix=false`: name is stored separately. In that case, - it begins one byte after home, and it's length is - `name_len`. +- `name` is frequently a suffix of `home`. For example, `/home/motiejus` and + `motiejus`. In this case storing both name and home is wasteful. Therefore + name has two options: + 1. `name_is_a_suffix=true`: name is a suffix of the home dir. Then `name` + starts at the `home_len - name_len`'th byte of `home`, and ends at the same + place as `home`. + 2. `name_is_a_suffix=false`: name begins one byte after home, and it's length + is `name_len`. Shells ------ -Normally there is a limited number of shells even in the huge user databases. A -few examples: `/bin/bash`, `/usr/bin/nologin`, `/bin/zsh` among others. -Therefore, "shells" have an optimization: they can be pointed by in the -external list, or reside among the user's data. +Normally there is a limited number of separate shells even in huge user +databases. A few examples: `/bin/bash`, `/usr/bin/nologin`, `/bin/zsh` among +others. Therefore, "shells" have an optimization: they can be pointed by in the +external list, or, if they are unique to the user, reside among the user's +data. 63 most popular shells (i.e. referred to by at least two User entries) are stored externally in "Shells" area. The less popular ones are stored with userdata. -There are two "Shells" areas: the index and the blob. The index is a list of -structs which point to a location in the "blob" area: +Shells section consists of two sub-sections: the index and the blob. The index +is a list of structs which point to a location in the "blob" area: ``` const ShellIndex = struct { @@ -277,29 +251,24 @@ const ShellIndex = struct { }; ``` -In the user's struct the `shell_here=true` bit signifies that the shell is -stored with userdata. `false` means it is stored in the `Shells` section. If -the shell is stored "here", it is the first element in `stringdata`, and it's -length is `shell_len_or_idx`. If it is stored externally, the latter variable -points to it's index in the ShellIndex area. - -Shells in the external storage are sorted by their weight, which is -`length*frequency`. +In the user's struct `shell_here=true` signifies that the shell is stored with +userdata, and it's length is `shell_len_or_idx`. `shell_here=false` means it is +stored in the `Shells` section, and it's index is `shell_len_or_idx`. Variable-length integers (varints) ---------------------------------- Varint is an efficiently encoded integer (packed for small values). Same as [protocol buffer varints][varint], except the largest possible value is `u64`. -They compress integers well. +They compress integers well. Varints are stored for group memberships. Group memberships ----------------- There are two group memberships at play: -1. given a username, resolve user's group gids (for `initgroups(3)`). -2. given a group (gid/name), resolve the members' names (e.g. `getgrgid`). +1. Given a username, resolve user's group gids (for `initgroups(3)`). +2. Given a group (gid/name), resolve the members' names (e.g. `getgrgid`). When user's groups are resolved in (1), the additional userdata is not requested (there is no way to return it). Therefore, it is reasonable to store @@ -309,23 +278,26 @@ username. When group's memberships are resolved in (2), the same call also requires other group information: gid and group name. Therefore it makes sense to store a pointer to the group members in the group information itself. However, the -memberships are not *always* necessary (see remarks about `id(1)` in this -document), therefore the memberships will be stored separately, outside of the -groups section. +memberships are not *always* necessary (see remarks about `id(1)`), therefore +the memberships will be stored separately, outside of the groups section. -`groupmembers` and `additional_gids` store group and user memberships -respectively: for each group, a list of pointers (offsets) to User records, and -for each user — a list of pointers to Group records. These fields are always -used in their entirety — not necessitating random access, thus suitable for -tight packing. +`Groupmembers` and `Username2gids` store group and user memberships +respectively. Membership IDs are used in their entirety — not necessitating +random access, thus suitable for tight packing and varint encoding. -An entry of `groupmembers` and `additional_gids` looks like this piece of + +- For each group — a list of pointers (offsets) to User records, because + `getgr*_r` returns an array of pointers to membernames. +- For each user — a list of gids, because `initgroups_dyn` (and friends) + returns an array of gids. + +An entry of `Groupmembers` and `Username2gids` looks like this piece of pseudo-code: ``` const PackedList = struct { - length: varint, - members: [length]varint, + Length: varint, + Members: [Length]varint, } const Groupmembers = PackedList; const Username2gids = PackedList; @@ -333,17 +305,40 @@ const Username2gids = PackedList; A packed list is a list of varints. -Section `Username2gidsIndex` stores an index from `hash(username)` to `offset` -in Username2gids. +Indices +------- -Complete file structure ------------------------ +Now that we've sketched the implementation of `id(3)`, it's clearer to +understand which operations need to be fast; in order of importance: + +1. lookup gid -> group info (this is on hot path in id) without members. +2. lookup username -> user's groups. +3. lookup uid -> user. +4. lookup groupname -> group. +5. lookup username -> user. `idx_*` sections are of type `[]PackedIntArray(u29)` and are pointing to the respective `Groups` and `Users` entries (from the beginning of the respective -section). Since User and Group records are 8-byte aligned, 3 bits can be saved -from every element. However, since the header easily fits to 64 bytes, we are -storing plain `u32` for easier inspection. +section). Since User and Group records are 8-byte aligned, 3 bits are saved for +every element. + +These indices can use perfect hashing like [bdz from cmph][cmph]: a perfect +hash hashes a list of bytes to a sequential list of integers. Perfect hashing +algorithms require some space, and take some time to calculate ("hashing +duration"). I've tested BDZ, which hashes [][]u8 to a sequential list of +integers (not preserving order) and CHM, preserves order. BDZ accepts an +optional argument `3 <= b <= 10`. + +* BDZ algorithm requires (b=3, 900KB, b=7, 338KB, b=10, 306KB) for 1M values. +* Latency to resolve 1M keys: (170ms, 180ms, 230ms, respectively). +* Packed vs non-packed latency differences are not meaningful. + +CHM retains order, however, 1M keys weigh 8MB. 10k keys are ~20x larger with +CHM than with BDZ, eliminating the benefit of preserved ordering: we can just +have a separate index. + +Complete file structure +----------------------- Each section is padded to 64 bytes. @@ -374,3 +369,6 @@ STATUS SECTION SIZE DESCRIPTION [data-oriented-design]: https://media.handmade-seattle.com/practical-data-oriented-design/ [getpwnam_r]: https://linux.die.net/man/3/getpwnam_r [varint]: https://developers.google.com/protocol-buffers/docs/encoding#varints +[getpwent_r]: https://www.man7.org/linux/man-pages/man3/getpwent_r.3.html +[getgrouplist]: https://www.man7.org/linux/man-pages/man3/getgrouplist.3.html +[getgrid_r]: https://www.man7.org/linux/man-pages/man3/getgrid_r.3.html